940results about How to "Easy to classify" patented technology

The invention relates to the technical field of sensor detection, and discloses a detection method and device based on a multi-mode gas sensor, and the method comprises the following steps: carrying out blending processing on a metal oxide semiconductor and a conductive material to obtain a bimodal nano composite material, and creating a multi-mode gas detection module, the preprocessed multi-mode signal data is acquired and obtained; acquiring and analyzing data of the temperature sensor and the humidity sensor to obtain environmental factor compensation parameters; performing adaptive calibration processing on the preprocessed multi-modal signal data according to the environmental factor compensation parameters to obtain calibrated multi-modal signal data; constructing a multi-input neural network model based on the calibrated multi-modal signal data, and training to obtain a gas recognition model; multi-mode signals collected and calibrated in real time are analyzed and judged based on the gas recognition model, gas type and concentration information is obtained, and high-precision and high-reliability gas detection is achieved.

The invention relates to the technical field of wire harness intelligent evaluation, in particular to a wire harness connection performance intelligent test method and system. The method comprises the following steps: collecting wire harness test data generated by a wire harness test device and a wire harness sensor in real time through an edge computing node; performing electrical performance detection extraction and mechanical performance detection extraction according to the wire harness test data to respectively obtain wire harness electrical performance detection data and wire harness mechanical performance detection data; performing electrical performance deep evaluation according to the wire harness electrical performance detection data to obtain wire harness electrical performance evaluation data, and performing mechanical performance deep evaluation on the wire harness mechanical performance detection data to obtain wire harness mechanical performance evaluation data; and performing environment pressure cross reference according to the wire harness electrical performance evaluation data and the wire harness mechanical performance evaluation data to obtain wire harness connection performance test evaluation data. According to the method, the accuracy of wire harness performance evaluation is improved, and reliable performance data can be obtained in different application fields.

The invention relates to the technical field of defect detection, in particular to an improved YOLOv8 high-voltage transmission line defect detection algorithm. Obtaining a plurality of shot high-voltage transmission line images to construct a high-voltage transmission line defect detection data set; inputting the defect detection data set of the high-voltage transmission line into the improved YOLOv8 network model for training; performing defect detection on the high-voltage transmission line to be detected by using the trained improved YOLOv8 network model; according to the improved YOLOv8 network model, a main network adopts a Mamba-Block module to carry out feature extraction on a high-voltage transmission line image, and a dynamic weight selection mechanism is introduced to carry out weight distribution on a fused feature map; and the neck network adopts a focused diffusion pyramid network structure to fuse the extracted features. The improved model provided by the invention can effectively improve the detection capability of small defects, and meets the requirements of high-voltage transmission line detection tasks.

The invention, which relates to the technical field of the cloud security system, discloses a monitoring method for a cloud security system comprising a data acquisition and preprocessing system, a threat detection and identification system, a behavior analysis and association analysis system, a risk assessment and early warning system, a response strategy making and execution system, and a monitoring report and log management system. The data acquisition and preprocessing system is used for acquiring network traffic, system logs and user behavior data in real time, and the threat detection and recognition system is used for performing threat detection and recognition on the preprocessed data. The data analysis and machine learning technology extracts significant features related to threats from a large amount of monitoring data, and the features can help a machine learning model better understand and classify potential threats, so that the accuracy and efficiency of threat detection are improved, the system automatically learns and updates threat features, and the threat detection efficiency is improved. And rapid identification and response to novel threats are realized.

The invention provides a modal information constraint-based multi-modal remote sensing image ground object classification method, which comprises the following steps of: firstly, adaptively learning a fusion weight of modal sharing and modal difference characteristics by adopting an MDF decoder, and adaptively controlling the contribution of modal sharing and modal proprietary information from a multi-scale angle so as to reserve the modal proprietary information; then, an MSIE decoder is adopted to guide modal difference features and multi-modal features to carry out a multi-modal auxiliary classification task so as to enhance optical and SAR proprietary information beneficial to classification; therefore, compared with other multi-mode remote sensing image ground feature classification methods, the method is higher in recognition precision, can effectively relieve the ground feature recognition performance bottleneck in a complex scene, and provides effective support for multi-mode remote sensing image interpretation.

The invention belongs to the technical field of motor fault diagnosis, and particularly relates to an asynchronous induction motor fault intelligent detection method based on a multi-modal time sequence. The method comprises the following steps: acquiring various signals of a motor, including three-phase current, vibration, equipment sound, environment sound and the like, and constructing a multi-modal data set; thirdly, constructing a Transform network classified by a single time sequence, and on the basis of the Transform network, connecting a plurality of the networks in parallel to obtain a lumped Transform network; and then, features of different modal data are dynamically integrated by using a self-attention mechanism, and accurate recognition of a motor fault is realized. In a network training process, a hyper-parameter of the lumped Transform network is optimized by adopting a chaos WOA algorithm; finally, different types of faults of the asynchronous motor can be accurately detected and judged, the situation that different fault features of the motor cannot be accurately represented by a single time sequence is avoided, and the accuracy and reliability of fault detection of the asynchronous motor are guaranteed.

The invention provides a data classification method, device and equipment and a computer storage medium, and the method relates to the technical field of computers, and is used for improving the efficiency and accuracy of data classification and improving the flexibility of data classification. The method comprises the following steps: acquiring data features corresponding to to-be-classified data; obtaining a corresponding query condition based on the data feature, and obtaining at least one target classification rule matched with the to-be-classified data from a preset classification rule set based on the query condition; inputting the to-be-classified data and at least one target classification rule into a trained label generation model, and generating at least one data classification label corresponding to the to-be-classified data based on description information included in the at least one target classification rule and the data features corresponding to the to-be-classified data; wherein each data classification label represents one data type; and based on the at least one data classification tag, determining a target classification result corresponding to the to-be-classified data.

The invention provides a forestry pest monitoring method and system based on machine learning, and the method comprises the steps: carrying out the principal component analysis of a forestry pest image, obtaining a plurality of recognition indexes of the pest of a target forestry region, determining an effective feature vector when the image recognition of the forestry pest is carried out according to all recognition indexes, and carrying out the recognition of the effective feature vector. Determining a first-level correlation feature of the pest image in the target forestry region through the effective feature vector; extracting a plurality of environmental influence factors from the monitoring image, and determining secondary correlation features of the pest image in the target forestry area according to all the environmental influence factors; carrying out interactive fusion on the first-level correlation features and the second-level correlation features to obtain multi-level distribution features for carrying out image recognition on the diseases and insect pests; and identifying the current pest and disease distribution of the target forestry area based on the multi-level distribution characteristics through a pest and disease identification model. By adopting the scheme of the application, diversified monitoring of the forestry diseases and insect pests can be realized under a complex background, so that the false detection rate of the forestry diseases and insect pests is reduced.

The invention relates to the technical field of pigment image processing, and particularly discloses a pigment hyperspectral image classification method, a storage medium and computer equipment. The pigment hyperspectral image classification method comprises the following steps: acquiring a hyperspectral image of a simulated painting through a hyperspectral camera, firstly extracting low-level detail information by using a spectrum-space attention module, and then extracting deep semantic features in combination with ViT; the multi-scale features are then effectively fused for classification. According to the method, detail and global information in the hyperspectral image can be more comprehensively captured, so that the analysis and classification capability of complex hyperspectral data is improved, the pigment detection accuracy is improved, lossless and reliable technical support is provided for scientific repair and value protection of ancient calligraphy and painting, and the method is suitable for popularization and application. And a technical foundation is laid for intelligent development of cultural relic protection.

The invention discloses a PET waste plastic intelligent sorting method and system based on multi-feature fusion, and the method comprises the following steps: collecting an RGB-HSI original data set of PET waste plastic, carrying out the dimension reduction processing of the HSI data set based on a genetic algorithm to generate MSI data, and forming a feature fusion data set with RGB data; constructing a feature fusion network based on a YOLACT model, and training by adopting a feature fusion data set; the feature fusion network comprises an RGB branch, an MSI branch and a fusion prediction module, RGB is used for extracting features of RGB data, the MSI branch is used for extracting features of MSI data, and the fusion prediction module is used for combining output of the RGB branch and output of the MSI branch to make comprehensive prediction; and installing the trained feature fusion network to an industrial personal computer to realize intelligent sorting of the PET waste plastics. Compared with a traditional recognition algorithm, the method can improve the recognition precision.

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 discloses a multi-modal network traffic classification method based on deep learning. The method comprises the following steps: data preprocessing; establishing a traffic classification network; training a traffic classification network; a traffic classification network is tested. According to the method, the traffic features are extracted from different angles by inputting the two modalities of the original bytes and the length sequences, so that the performance of the classifier is improved, and the problem that single-modal feature extraction is insufficient is solved. According to the method, the features of the original bytes of the traffic are extracted by using the Transform of the improved attention mechanism, meanwhile, the features of the data packet length sequence are extracted by using the bidirectional LSTM, and then the two extracted features are fused to generate a new more comprehensive feature representation, so that the accuracy of network traffic classification is improved. According to the method, on the design of the loss function, the final classification result is measured, and the classification performance of the learning features of each part is considered, so that the optimal classification performance of each part is obtained, and the overall classification accuracy is finally improved.

The invention relates to a guiding type improved neural network ankle joint fracture classification method, system and device, and belongs to the field of computer-aided medical image processing.The classification method comprises the steps that S1, database images are collected and enhanced; s2, training a segmentation network model by using the segmentation data marked with the fibula region; s3, inputting the fracture type classification data into the trained segmentation network model, predicting a fibula area, and taking a prediction result as guidance to act on the improved neural network classification model; s4, inputting the fracture type classification data into the improved neural network classification model guided by the prediction result for training; and S5, verifying a classification result by using a test set, and evaluating the model by using a statistical index. The ankle joint fracture type can be judged, the method has the advantages of being high in diagnosis accuracy, high in speed and the like, and the problem that a traditional deep learning method is prone to being interfered by other information in images in the medical field to make misjudgment is effectively solved.

The invention relates to a pathological image morphological subtype classification method based on an optimal transmission prototype network, and belongs to the technical field of medical image processing. The method comprises the steps of constructing a pathological image data set, performing preliminary grouping by using an unsupervised clustering method, and performing cooperation with a pathologist to optimize the data set; preprocessing the image through a data enhancement strategy; performing feature extraction on the enhanced image through a pre-training model; the method comprises the following steps of: constructing and training an OT-ProtoNet model; setting a prototype, determining dimensions and quantity, realizing a category specific prototype based on a soft distribution mechanism, calculating similarity based on an OT distance, setting training parameters and selecting an optimization algorithm to train a model, and ensuring that the model effectively learns key features in data; and carrying out image morphological subtype classification on the basis of an OT-ProtoNet model. According to the pathological image morphological subtype classification method, the pre-training features can be fully utilized, the classification accuracy can be improved, and interpretability can be kept.

The invention discloses a cleaning base station for cleaning equipment and a cleaning system with the cleaning base station, and the cleaning base station comprises a base station base which is provided with a cleaning tank and a filtering tank, the filtering tank is communicated with the cleaning tank, and a filtering structure is formed on the bottom wall of the filtering tank; and the drying and collecting assembly is arranged on the base station base and used for drying and collecting the solid dirt in the filter tank. According to the cleaning base station, sewage and solid dirt can be well separated through the filtering structure, the solid dirt in the filtering groove can be dried and collected through the drying and collecting assembly, and the cleanliness of the drying and collecting assembly and the filtering groove can be improved.

The invention discloses a client information management method and system based on real estate transaction, relates to the technical field of client information management, and solves the technical problem that client information management cannot be evaluated according to a real-time product demand trend, so that client types cannot be distinguished according to different demand trend stages in the prior art. Specifically, a demand trend evaluation unit evaluates the demand trend of a real-time sales product, collects demand trend information, substitutes the demand trend information into a formula to obtain a demand trend evaluation coefficient in a real-time circulation stage, and deduces that the current circulation stage is in a purchaser market or a supplier market according to coefficient comparison; a customer stage analysis unit performs customer stage analysis according to the real-time circulation stage, obtains the speed-to-time ratio information of a supplier and the speed-to-time ratio information of a purchaser, deduces whether a current customer is a customer in a knowing stage or a customer in an intention stage according to information comparison, and correspondingly sends the customer to a customer information management platform; the label classification setting unit performs label classification setting on clients.

The invention discloses a cleaning base station for cleaning equipment and a cleaning system with the cleaning base station, and the cleaning base station comprises a base station base which is provided with a cleaning tank and a filtering tank, the filtering tank is communicated with the cleaning tank, and a filtering structure is formed on the bottom wall of the filtering tank; the cleaning part is movably arranged in the cleaning tank; the drying and collecting assembly is arranged on the base station base and used for drying and collecting the solid dirt in the filter tank; in the first cleaning state, the cleaning piece is fixed relative to the base station base to clean the mopping piece; in the second cleaning state, the cleaning piece can move to clean the cleaning tank. According to the cleaning base station, by controlling the cleaning part to be switched between the first cleaning state and the second cleaning state, switching of the cleaning base station between the mopping part cleaning mode and the cleaning tank cleaning mode can be achieved, the filtering structure separates sewage and solid dirt, and the drying and collecting assembly dries and collects the solid dirt in the filtering tank; and the cleanliness of the drying and collecting assembly and the filter tank is improved.

The invention relates to the technical field of fault diagnosis, and discloses a fault diagnosis method and system applied to an automobile air conditioner compressor. The method comprises the following steps: firstly, introducing auxiliary noise to decompose a vibration signal, calculating a decomposition result by using a sample entropy method to obtain a sample entropy, and identifying and removing noise; secondly, variational mode decomposition is carried out on the vibration signals after noise elimination, an improved crayfish optimization algorithm is used for optimizing a decomposition scale and a penalty factor in the variational mode decomposition process, and a final IMF component signal set is obtained; mapping the final IMF component signal set to polar coordinates through a symmetric polar coordinate transformation method to form a fault diagnosis image set; and finally, training to obtain a convolutional neural network fault diagnosis model, identifying a fault diagnosis image set, and outputting a fault diagnosis result of the automobile air conditioner compressor. The vibration signal of the automobile air conditioner compressor is processed and analyzed, the purpose of fault diagnosis is achieved, and the method is objective and accurate.

The invention discloses a small sample target detection method and device based on hybrid experts, and belongs to the technical field of target detection, and the method comprises the steps: employing a repeated up-sampling and data enhancement mode to carry out the enhancement of a new-class small sample image; constructing a small sample target detection model based on the hybrid experts, wherein the small sample target detection model comprises a shared shallow feature network, a unique deep feature network of each hybrid expert, a feature fusion network and a target detection network corresponding to each hybrid expert; and performing parameter optimization on the small sample target detection model based on the hybrid experts by using the basic category image and the new category enhanced image, and learning knowledge of different depths by using the hybrid experts and skillfully combining features of different depths, thereby improving the detection performance of the model on a small sample target detection task. And meanwhile, the combination of up-sampling and data enhancement is proposed, so that the overfitting problem caused by the up-sampling process is effectively alleviated, the diversity of small sample data is enhanced, and the robustness of the model is improved.

The invention discloses a hyperspectral image and LiDAR data collaborative classification method based on double-branch Swin Transformer, and the method comprises the steps: S1, employing 3D-2D mixed convolution to extract the shallow space-spectrum information of a hyperspectral image after principal component analysis and dimension reduction according to the characteristic of image and spectrum integration of the hyperspectral image; and S2, an improved Swin Transform network is adopted, a ResNet module is adopted in the network, and SSR (Spectral Segment Recombination) is introduced in the network, so that information loss in feature transmission is eliminated, and deep space-spectrum features of the hyperspectral image are further mined. S3, carrying out 2D-2D convolution on the LiDAR data of the other branch, and mining elevation information through an improved Swin Transform network; and S4, aiming at the hyperspectral and LiDAR double branches, improving a CAM (Cross Attention Module) into double-branch input, through hyperspectral and LiDAR feature interaction, by establishing a dynamic attention mechanism, effectively capturing associated information between two modals, and fusing the associated information into uniform feature representation. The network is tested on two public hyperspectral and LiDAR data sets, and shows good classification performance.

The invention discloses an urban rail transit abnormal passenger flow prediction method and system based on artificial intelligence, and relates to the field of passenger flow prediction. According to the method, the SVM machine learning model is trained and tested by adopting the classified historical abnormal passenger flow data of the station, the historical data of the natural influence factors and the historical data of the social influence factors, so that a relatively accurate classification model is provided for subsequent classification; secondly, collecting real-time data of different types of natural influence factors, real-time data of social influence factors and real-time passenger flow data of different rail transit stations in real time, and continuously updating the final SVM classification model so as to adapt to continuously changed behavioral habits and modes of people; the accuracy of subsequently classifying the predicted data is improved; indirect prediction is carried out on the passenger flow volume data through the predictable natural influence factor data and social influence factor data, and the prediction accuracy is improved.

The invention discloses a vulnerability early warning method and device based on a low-code platform, equipment and a storage medium, and the method comprises the steps: querying a target service weight corresponding to a target service based on a first mapping relation; querying a target environment weight corresponding to the access mode of the target service based on the second mapping relationship; querying a target utilization difficulty weight based on the third mapping relationship; querying a target influence range weight corresponding to the influence range of the target vulnerability based on a fourth mapping relationship; on the basis of the fifth mapping relation, the weight of the target vulnerability is inquired; transmitting each weight to a risk value calculation script, wherein the risk value calculation script is used for calculating a risk value of the target vulnerability based on the received weight information; and determining a risk level corresponding to the target vulnerability according to a risk value returned by the risk value calculation script, and sending vulnerability early warning information when the risk level reaches a preset early warning risk level. According to the invention, the accuracy of vulnerability assessment can be improved and vulnerability early warning can be carried out.

The invention provides a soil layer classification method based on PSO-RF, and is suitable for the field of geotechnical engineering in-situ testing. The method comprises the steps of data acquisition and preprocessing, parameter dimension reduction, particle swarm optimization and model test and use, training and prediction are carried out based on data collected by a DCM pile, in the soil layer classification process, field data acquisition is faster and more convenient, and through random forest diversified decision-making tree construction, the classification efficiency is improved. Good classification performance can be kept under different project and different soil layer conditions, in addition, the particle swarm optimization algorithm is used for efficiently searching for an optimal parameter combination by simulating group behaviors, the accuracy of a classification model is improved, and the method has the advantages of being convenient to collect field data, high in generalization ability and accurate in classification result and has good application prospects. The device can be widely applied to the field of geotechnical engineering in-situ testing.

The invention relates to the field of discrete signal processing, in particular to a distribution line fault identification and positioning method based on DWT and BP algorithms. Comprising the following steps: S1, carrying hardware equipment on different phases of nodes of the same line in a distribution network line, and collecting and recording discrete data information of current, voltage and traveling waves in an overhead line; s2, constructing a network topological graph of a to-be-monitored line according to the hardware equipment mounting points, and performing noise reduction preprocessing on the original data by combining a particle swarm optimization algorithm and a DWT (Discrete Wavelet Transform) algorithm; and S3, performing polynomial fitting and cumulative curve fitting approximate processing on the data after noise reduction processing to obtain continuous curve data after fitting. According to the distribution line fault identification and positioning method based on the DWT algorithm and the BP algorithm, automatic identification and accurate positioning of distribution line faults are achieved by combining a signal processing technology and an intelligent classification algorithm, the accuracy and efficiency of fault detection are improved, and a powerful guarantee is provided for safe and stable operation of a power grid.

The utility model discloses a plasma cleaning machine material box which comprises a first mounting plate and a second mounting plate, the corresponding ends of the first mounting plate and the second mounting plate are jointly provided with a plurality of placing devices, and the upper portion and the lower portion of the left end of the first mounting plate and the upper portion and the lower portion of the right end of the second mounting plate are each provided with a supporting plate. And clamping devices are mounted at the ends, corresponding to each other in pairs, of the four supporting plates. According to the material box of the plasma cleaning machine, the material boxes on the containing device are clamped in the clamping grooves in the supporting frame through the clamping blocks at the lower ends of the material boxes, so that the material boxes are clamped between the first mounting plate and the second mounting plate, the multiple material boxes are arranged, different kinds of objects can be stored in a classified mode according to cleaning requirements, and the cleaning efficiency is improved. According to the device, the multiple articles can be cleaned at a time, meanwhile, after the articles are stored in a classified mode, follow-up classified arrangement of the articles is facilitated, and therefore the practicability of the device is improved.

The utility model relates to the technical field of file cabinets, in particular to a moisture-proof file cabinet for office file data management, which comprises a cabinet body, a cabinet door is movably connected to the left end of the cabinet body through hinges, four partition plates are fixedly connected to the inner wall of the cabinet body, and exhaust fans are fixedly connected to the lower ends of the three partition plates on the upper portion and the inner wall of the cabinet body. Four grooves are formed in the left inner wall and the right inner wall of the cabinet body respectively, storage boxes are movably connected to the upper ends of the four partition plates, and the left ends and the right ends of the four storage boxes are slidably connected with the grooves respectively. According to the moistureproof file cabinet for office file data management, through the arrangement of the storage box and the exhaust fan, the flexibility of storing and taking data and the controllability of humidity in the cabinet body are improved, the space is fully utilized, classification is facilitated, the object taking efficiency is improved, meanwhile, the situation that the storage requirement cannot be met is prevented, and the service life of the file cabinet is prolonged. And the archive data storage quality is influenced.

The invention relates to a coal slime flotation froth three-dimensional model classification method based on a Pointnet network, and aims to solve the technical problem that the current two-dimensional froth image cannot process the states of three-dimensional froth space fluctuation and the like and the internal relationship of the space, and the technical scheme is as follows: expanding a data set; designing a foam characteristic network architecture; extracting a high-dimensional feature lambda 1 by using a point cloud feature extractor f theta; projecting the high-dimensional feature lambda 1 into a low-dimensional space by using a feature projection head # imgabs0 # to obtain a low-dimensional feature lambda 2 of the single-groove foam point cloud; splicing and fusing the single-groove foam point cloud features by using the feature fusion function yf to obtain an overall feature gamma; classifying the overall feature gamma through a multi-layer perceptron (MLP) and a Softmax function, and outputting a classification result; evaluating and analyzing. According to the method, the foam three-dimensional point cloud models of a plurality of flotation cells are used as input, the limitation of a single-cell data source is made up, the generalization ability and stability of the model are improved by using the flotation machine overall feature training network, and the performance of the model is optimized.

The invention relates to the technical field of information and data processing, and discloses an intelligent recommendation method and system for a bone fracture rehabilitation training plan based on traditional Chinese medicine, and the method comprises the steps: dividing image information according to labels, and obtaining skeleton data sets with different functions; taking the first position information and the second position information as a special information set; deleting the special data set from the skeleton data set to obtain a target data set; obtaining position information of the bones to be subjected to bone fracture rehabilitation training from the target data set, and selecting matched contents such as shadowboxing, eight-section brocade or five-poultry play from a pre-stored traditional Chinese medicine rehabilitation training database; deleting related actions of the second position information from an action data set corresponding to the content; guiding the trainee to perform bone fracture rehabilitation training through the visual terminal; the system comprises a first data set construction module, a second data set construction module and a target action output module. According to the bone fracture rehabilitation training system and method, biological feature recognition and personalized, precise and systematic bone fracture rehabilitation training are achieved.

The invention discloses a vehicle-mounted multi-target classification and detection method based on multi-teacher distillation and dynamic reasoning, and the method comprises the steps: collecting an image through a vehicle-mounted image collection device, taking the image as the input through a dynamic neural network, and outputting the classification and bounding box regression of multiple targets. The dynamic neural network is composed of a multi-teacher network and a student network. The multi-teacher network is composed of a plurality of teacher models; a dynamic weight distribution system based on an attention mechanism is introduced into the multi-teacher network, and different weights are distributed to each teacher model according to the characteristics of the current input scene; a confidence coefficient threshold value is set in a multi-teacher network, and regional knowledge possibly containing a target is only taught to a student network. The student network is composed of a strategy network and a detection network, and the detection network is a two-stage target detection network obtained by integrating a feature extraction network and a target positioning network; the strategy network adaptively extracts task features according to knowledge provided by the multi-teacher network; and the detection network dynamically selects a route according to the policy network decision vector.

The invention relates to the technical field of archive management, in particular to an intelligent archive management system based on RPA, and the system comprises a storage module which recognizes an invoice structure and carries out distributed storage; the frequency setting module collects first node performance data to determine an initial detection frequency; a third-class node analysis module detects whether the third-class storage nodes are abnormal or not, adjusts the initial detection frequency according to an abnormality judgment result, or generates a second-class storage node abnormality judgment instruction; the second-class node analysis module judges whether the second-class storage nodes are abnormal or not based on the node exception proportions of the third-class storage nodes or the change trend of the node exception proportions, so that a second-class node repair strategy is formulated according to the comparison result of the second-class exception number and the preset exception number, or a first-class storage node exception judgment instruction is generated; and the first-class node analysis module analyzes abnormal distribution of a plurality of abnormal second-class storage nodes so as to judge the abnormal degree and determine a first-class node repair strategy. According to the invention, the efficiency and safety of archive management are improved.