188results about How to "Extract comprehensive" patented technology

The invention discloses a medical visual question-answering method and system based on multi-task modeling, and the method comprises the steps: carrying out the feature extraction of a to-be-analyzed medical image through a visual encoder, obtaining an image feature, inputting a preliminary question instruction and historical question-answering data into a dialogue large model to generate a question instruction, and obtaining a text feature through a text encoder; carrying out feature fusion on the obtained text features and image features, and carrying out self-attention image importance weighting processing and image-text alignment to obtain image-text fusion representation; and inputting a multi-target output projection layer, carrying out multi-task prediction, outputting question answers, image categories and important region masks, inputting the question answers and the image categories into a dialogue large model, and finally generating diagnosis opinions with detailed description in combination with dialogue context and multi-round interaction data and in combination with the important region masks. According to the invention, the interaction experience and the performance of the question and answer system are improved, and more accurate medical diagnosis in multi-modal complex information is facilitated.

The invention discloses a multi-modal document structured processing and knowledge extraction method based on a large language model. The method comprises the following steps: S1, receiving an input multi-modal document; s2, performing preprocessing on the text data in the multi-mode document; s3, performing feature extraction on non-text data in the multi-mode document; s4, performing multi-modal data fusion on the preprocessed text data and the non-text data after feature extraction; s5, performing deep semantic analysis on the fused multi-modal data through a pre-trained improved BERT model, wherein the deep semantic analysis comprises key entity recognition, relation extraction and event detection; s6, based on a deep semantic analysis result, automatically constructing a knowledge graph by using the extracted information; and S7, outputting the data of the knowledge graph in a format for analysis or application. According to the method and the system, structured processing and knowledge extraction of unstructured and multi-modal documents are realized.

The invention belongs to the technical field of equipment fault diagnosis, and discloses a variable working condition bearing fault diagnosis method based on a domain adversarial hybrid graph convolutional network. According to the specific technical scheme, the method comprises the specific steps that firstly, a convolutional neural network is used for conducting feature extraction on input data, obtained features serve as nodes, secondly, an adjacent matrix is obtained through a graph generation layer, an association graph is constructed according to the input matrix, and thirdly, the association graph is obtained. Inputting the constructed graph into a multi-receptive-field mixed graph convolutional network to extract structural information, capturing local structural information and global structural information of the graph from the perspective of the graph convolutional network and graph sampling and aggregation by using the multi-receptive-field mixed graph convolutional network, and finally, extracting the structural information of the graph from the perspective of the multi-receptive-field mixed graph convolutional network. And fault classification is carried out on the obtained features through a transfer learning method, so that the fault diagnosis capability of the model on a target domain is improved, and the expression capability, the generalization performance and the robustness of the model are remarkably improved.

The invention provides an LED spectrum fingerprint open set identification method based on Transform and support vector data description and related equipment. The method comprises the following steps: collecting an optical signal emitted by at least one LED device, converting the optical signal into spectral data, and dividing the spectral data into a training set and a test set; inputting the training set into a preset feature extraction network to carry out network training so as to learn and obtain a spectral feature vector; wherein the feature extraction network comprises a Transform branch, a CNN (Convolutional Neural Network) branch and a feature interaction module; based on the spectral feature vectors of the training set, constructing a hypersphere model by using an SVDD algorithm, and optimizing parameters of the hypersphere model to obtain an optimal hypersphere model; and inputting test samples in a test set into the trained feature extraction network to obtain corresponding spectral feature vectors, and inputting the spectral feature vectors of the test samples into the optimal hypersphere model for classification.

The invention provides a distribution network automation equipment group fault diagnosis system and method, and relates to the technical field of power distribution networks, and the method comprises the following steps: carrying out the feature extraction of fault data through employing fractional order Boltzmann-Shannon interaction entropy; the rational activation function is combined with an extreme learning machine algorithm, a rational extreme learning machine is constructed, and faults are diagnosed; the non-smooth optimization problem of the rational extreme learning machine is solved by adopting a novel umbrella-exponent optimization algorithm; according to the method, the fractional order Boltzmann-Shannon interaction entropy is adopted to carry out feature extraction on the fault data, the data does not need to be decomposed or transformed, and the complexity of the data is directly measured, so that the defect that hidden fault features cannot be effectively extracted by a traditional time-domain and frequency-domain feature extraction method is overcome; the parameter-free measurement can be accurately estimated in a calculation-efficient mode, fractional order information is further considered, and the dynamic change of a fractional order time sequence can be measured.

The invention provides an automatic software testing method and system based on a visual attention mechanism, and relates to the technical field of automatic testing, and the method comprises the steps: obtaining an initial interface of to-be-tested software, carrying out the preprocessing, inputting an enhanced interface image into an interface detection model, and recognizing control information through the analysis of the enhanced interface image; inputting the control information into a pre-trained attention mechanism model, generating semantic association and context information between controls based on the control information, determining an execution sequence and execution parameters of test actions, sequentially simulating manual test actions, and performing test operation on the controls according to the execution parameters; interface feedback information of the to-be-tested software is obtained, text content in the interface feedback information is extracted based on a character recognition algorithm, semantics corresponding to the text content are determined in combination with a pre-constructed semantic understanding model and compared with a preset expected result, and a test conclusion corresponding to the test operation is generated.

The invention belongs to the technical field of coal rock carbon content detection, and particularly discloses a coal rock carbon content detection method and system based on a multi-feature image spectrum technology, and the method comprises the steps: constructing a typical coal rock type and a feature spectrum and texture feature database corresponding to the typical coal rock type; performing text labeling on the image category of each pixel point in the spectral image of the mixed sample; taking the data in the database as source domain data, taking the hyperspectral data of the to-be-tested coal rock sample as target domain data, and realizing coal rock classification of the to-be-tested coal rock sample in the target domain through transfer learning; for the identified coal sample, identifying whether each pixel point on the spectral image of the coal sample contains carbon or not; and for the pixel points with the carbon content, the carbon content of each pixel point on the coal sample spectral image is obtained by utilizing the trained carbon content prediction model, so that rapid and accurate detection of the carbon content of the coal rock is ensured.

The invention discloses a real-time auricle identification and auricular point positioning method and system for multi-task feature sharing. An auricle identification and auricular point positioning combined model used in the method comprises an encoder and a decoder. The encoder includes a backbone network and a neck network. The decoder comprises a plurality of detection heads. A plurality of detection heads receive outputs of different layers of the neck network. The detection head comprises a target regression branch, a target classification branch and a feature point regression branch which are parallel. A plurality of detection heads share output features of the same encoder, and parallel target regression branches, target classification branches and feature point regression branches in the detection heads are respectively used for calculating loss functions of different tasks; therefore, auricle identification, frame selection and auricular point feature point marking tasks can be efficiently completed; on the basis, high-frame-rate real-time prediction is realized in the field of auricular point positioning for the first time, and the limitation of the prior art is broken through.

The invention discloses a global feature-based solid wood texture identification and classification method and system, and the system comprises a picture collection unit, a preprocessing unit, a filtering unit and a classification model unit, and is characterized in that a plurality of solid wood composite floor pictures are collected and preprocessed to obtain preprocessed floor pictures; the collected images are classified according to straight lines and patterns, a global feature method is used for conducting floor surface texture feature vector extraction on the preprocessed floor images, feature dimension reduction operation is conducted according to an overall data set in combination with a nonlinear method, and filtering images in different scale directions are obtained; the extracted feature vectors are substituted into a support vector machine model for classification training, meanwhile, optimal hyper-parameters of the support vector machine are obtained through a grid search algorithm in the training process, and the trained model is stored; and the to-be-classified solid wood composite floor pictures are classified through the trained model. According to the method, the influence caused by color difference possibly existing on the wood surface can be overcome, and the operation cost is reduced.

The invention discloses an unmanned aerial vehicle image transmission signal modulation mode identification system and method based on multi-modal fusion. The method comprises the following steps: (S100) collecting and preprocessing unmanned aerial vehicle communication signal data; (S200) converting the one-dimensional time-domain signal into a two-dimensional Gramer angle field graph and estimating a two-dimensional time-frequency graph of the image transmission signal; (S300) carrying out feature merging; (S400) generating a training set and a test set; (S500) constructing a VGG-ResNet hybrid architecture deep learning network and carrying out training; and (S600) identifying the image transmission signal modulation mode of the unmanned aerial vehicle to be identified. The method disclosed by the invention is based on a multi-modal fusion technology and shows remarkable advantages, and data features of different modals can be comprehensively utilized by fusing the one-dimensional time domain signal and the two-dimensional time frequency graph information to realize more comprehensive description of data.

The invention discloses a petroleum pipe microscopic fracture morphology identification method, system and device and a medium, and belongs to the technical field of failure analysis image process.The method comprises the steps that a deep learning classification network with a residual module is constructed and trained, and a deep learning classification network loaded with a network connection weight matrix is obtained; and finally, the deep learning classification network is utilized to efficiently and accurately identify the to-be-tested object region image. According to the method, massive data sets can be quickly processed and analyzed by using the high-speed processing capability of a modern computer, so that the efficiency is greatly improved. Compared with a traditional method, the automatic fracture classification method can reduce subjective interference of people and enhance reliability and consistency of results. And meanwhile, the identification method is simple, engineering application integration is facilitated, and good practicability and expansibility are achieved.

The invention discloses a medical image segmentation method based on multi-axis attention, and the method comprises the steps: obtaining a medical image, and carrying out the preprocessing of the medical image, so as to obtain a preprocessed medical image; and inputting the preprocessed medical image into a pre-trained medical image segmentation model based on multi-axis attention to obtain a final focus segmentation prediction result. According to the method, the technical problem that in an existing U-Net medical image segmentation method, due to the fact that a U-Net model lacks enough attention to a region of interest for some complex structures and small targets, excessive segmentation or information loss exists can be solved, and jumping connection in the U-Net model directly splices low-level features and high-level features. The technical problems of information redundancy and over-fitting, the technical problem of limited expressive power of a CBAM attention mechanism improvement model, and the technical problem of model over-fitting caused by excessive superposition of calculation units when CBAM is introduced into a data set with few samples and non-uniform data distribution are solved.

The invention provides a multi-edge collaborative anomaly detection system and method based on a double-flow parallel neural network, and the scheme employs a multi-edge collaborative task unloading method, can effectively improve the network anomaly detection efficiency of the Internet of Things, improves the defects when a single-edge gateway faces a large number of task processing requests, and improves the utilization rate of an overall edge system. Meanwhile, by adopting an anomaly detection model based on a double-flow parallel network, while the deep meaning and the context relationship of the traffic are extracted, a traffic data structure and a feature visual representation form can be effectively concerned, and a data anomaly mode can be visually described, so that the features of the abnormal traffic can be more comprehensively extracted and analyzed, and accurate detection is realized.

The invention discloses a fault identification method and system after a high-proportion distributed power supply is connected to a power distribution network, computer equipment and a storage medium. The method comprises the following steps: acquiring fault data of the high-proportion distributed power supply connected to power distribution networks with different topological structures; extracting fault features; constructing a fault identification model based on a convolutional neural network; integrating a channel attention mechanism into a fault identification model based on a convolutional neural network; training a fault identification model integrated with a channel attention mechanism; testing the trained fault identification model; and after the test is completed, identifying a fault after the high-proportion distributed power supply is connected to the power distribution network. According to the method, the identification model integrated with the channel attention mechanism can be trained through the fault data so as to improve the fault identification accuracy.

The present invention provides a variational mode decomposition optimization method based on a time-frequency correlation coefficient joint factor, comprising: S1, initializing the K value, setting K=2; S2, performing VMD decomposition on the signal to obtain K IMF components; S3, calculating the time domain correlation coefficient ρ between each IMF component and the original signal K,i and frequency domain correlation coefficient #imgabs0#Calculate the time-frequency correlation coefficient joint factor δ K,i ; S4, let K = K + 1, perform VMD decomposition again, and obtain K + 1 IMF components; S5, calculate the time domain correlation coefficient ρ between each IMF component and the original signal K+1,j and frequency domain correlation coefficient #imgabs1#Calculate the time-frequency correlation coefficient joint factor δ K+1,j ; S6, calculate the time-frequency correlation coefficient joint factor difference β between each IMF component when K takes different values ​​and the same decomposition number K,r ; S7, when β K,r ≤θ(θ=0.05), it is considered as an effective factor, otherwise it is considered as an invalid factor; S8, when K=m, the number of continuous effective factors reaches the maximum value, that is, when K=m+1, the number of continuous effective factors is less than K=m, it is considered that the decomposition is optimal, and K=m is finally selected as the optimal value. The present invention is simple to operate, the correlation feature extraction is comprehensive and reliable, and is less affected by the factors of the signal itself.

The invention provides a knowledge distillation passive domain unsupervised domain self-adaptive method, which realizes classification of a target domain without using source domain data by designing a teacher-student model and a competition mechanism. Firstly, a teacher network composed of a feature extractor, a classifier and a rotation classifier is constructed, source domain data is used for training, classifier parameters are fixed, a source model is finely adjusted through a self-supervised rotation sampling method, and a pseudo label of target domain data is generated through a clustering method. And then designing a student network composed of a feature extractor and a classifier, generating a pseudo tag only by using target domain data, and optimizing the discrimination and diversity of the tag by maximizing mutual information loss. And finally, screening the pseudo labels of the teacher-student network by using a competition module, and extracting the pseudo labels with higher confidence to update the student network, thereby completing knowledge migration. According to the method, source domain data is not needed, data storage and transmission cost is reduced, privacy and data security are improved, and unsupervised classification learning on unlabeled target domain data is supported.

The invention discloses a ship target detection method based on an attention-enhanced feature pyramid network, and belongs to the technical field of remote sensing image processing. The method comprises the following steps: constructing an attention enhancement module; building an attention enhancement feature pyramid network based on an attention enhancement module and a corresponding ship target detection model; then ship target detection task training is carried out on the ship target detection model; and finally, performing ship target detection on a to-be-detected remote sensing image by using the trained ship target detection model. According to the method, the attention mechanism is fully utilized to capture global semantic information association more fully, fusion features have more complete multi-scale feature information, the model can extract data features more comprehensively on a remote sensing image ship target detection task, the image content is understood, and the target detection efficiency is improved. The method can achieve the accurate recognition and positioning of the ship target in a complex ocean background, and facilitates the improvement of the accuracy and robustness of remote sensing image ship target detection.

The invention relates to the technical field of remote sensing image processing, in particular to a local climate region classification method based on multi-source data fusion, which comprises the following steps of: constructing a multi-source feature extraction and fusion network which comprises two self-attention calculation branches and a cross attention fusion module; the two self-attention calculation branches respectively comprise a series of self-attention modules which are used for carrying out different-level feature extraction on multispectral remote sensing image features and SAR remote sensing image features respectively; the cross attention fusion module receives different levels of different-source data features extracted by the two self-attention calculation branches and carries out fusion on the different levels of different-source data features; building a local climate region classification model based on the multi-source feature extraction and fusion network, and performing training and testing; and classifying the multi-source remote sensing image based on the local climate region classification model to obtain a local climate region classification result. According to the method, the semantic association among the multi-source data can be more accurately captured, so that the urban microclimate characteristics can be more accurately reflected.

The invention provides a water environment index change trend prediction and model establishment method and device, and a medium, and the model establishment method comprises the following steps: obtaining historical index data of a target water environment and driving influence factor data of the historical index data, and enabling the historical index data and the driving influence factor data to be used for establishing a training data set; hyper-parameters of the water environment index change trend prediction model are determined by adopting an automatic optimization algorithm, and the key hyper-parameters comprise a learning rate, the size of a convolution kernel and the number of neurons; the training data set is used for training a water environment index change trend prediction model, and a basic network model of the water environment index change trend prediction model is a combination of a convolutional neural network, a long and short term memory neural network and a self-attention mechanism. The method is based on the CNN-LSTM-Attention neural network model and adopts the automatic optimization algorithm to adjust the hyper-parameters, so that the parameter setting optimality in the model training process is ensured, higher adaptability and stability are obtained, and a more reliable water environment index change trend prediction result can be provided.

The invention discloses a method for extracting micro-plastics in soil of a refuse landfill. The method comprises the following steps: pretreating a refuse landfill soil sample to obtain sample soil; the sample soil and an extracting agent are fully mixed and oscillated and then stand for layering, first supernate is obtained, the extracting agent is added at least twice, the types of the extracting agent added each time are different, and the extracting agent added each time is one of saturated sodium chloride, saturated sodium bromide and saturated sodium iodide; the first supernate is extracted and fully mixed with a digesting agent, the mixture is shaken and then stands for layering again, second supernate is obtained, and the digesting agent is at least one of 30% hydrogen peroxide, a Fenton reagent, pepsin and trypsin; and filtering the second supernatant to obtain the micro-plastic. Therefore, the extraction method provided by the embodiment of the invention has multiple technical effects of high efficiency, deep digestion, accurate filtration, wide applicability, environmental friendliness and the like.

The invention discloses a cellular base station network traffic prediction method based on Mama and a graph neural network, which belongs to the field of deep learning and base station traffic prediction, and comprises a linear embedded layer module, an encoder module, a double-view graph neural network module, a decoder module and an output layer module. The method specifically comprises the following steps: (1) coding base station flow data by a linear embedded layer module to obtain coding information of the base station flow data; (2) the encoder module extracts time characteristics of the base station flow data; (3) extracting spatial features of the base station flow data by a double-view image neural network module; (4) the decoder module fuses the time characteristics and the space characteristics of the base station flow data; and (5) an output layer module calculates and obtains a prediction result of the base station flow data according to the fusion result of the time features and the space features. According to the method, accurate long-term prediction of the network flow of the cellular base station is realized under the condition of fully considering the space-time correlation of the flow of the base station.

The invention discloses a power generation equipment maintenance knowledge question-answering system and method based on a multi-modal large model. The system comprises an equipment question-answering robot module, a data lake module, a large data model module and the like. A data lake knowledge base is constructed; receiving user demand questions for semantic analysis and classification, and determining data types in the demand questions; according to the data type, selecting an appropriate trained RAG large model to carry out comprehensive processing and reasoning, and generating a question answer; and presenting the question answer to the user as a reply. According to the invention, data intercommunication between equipment knowledge questions and answers and maintenance questions and answers is realized through the data sharing module, so that the accuracy of fault diagnosis and the maintenance efficiency are improved; the application of the multi-modal large model and the data management module provides powerful data support for equipment maintenance; and through the real-time monitoring function of the fault alarm module, the equipment fault can be found in time, the downtime is reduced, and the production efficiency is improved.

The invention provides a power distribution cabinet arc discharge defect detection method, and belongs to the technical field of power distribution cabinet arc discharge defect detection, and the method comprises the steps: building an electric field intensity dense matrix through analyzing historical data and a simulation model, and carrying out the Fourier transform to obtain a frequency domain feature set; and a multi-branch hybrid neural network model is trained by comparing feature differences of normal and defect samples. And performing the same data processing and feature extraction on the power distribution cabinet to be tested, inputting an obtained difference feature set into the trained model, and predicting a possible arc discharge position. According to the method, the technical advantages of modern signal processing and machine learning are fully utilized, simulation analysis and experimental testing are combined, rich feature information contained in electric field data is deeply excavated, accurate identification and quantitative evaluation of arc discharge defects are achieved through deep analysis of the electric field data in the power distribution cabinet, and the accuracy and the reliability of the arc discharge defects are improved. The problems of low detection precision and high cost in the prior art are solved.

The invention relates to the field of three-dimensional point cloud semantic segmentation, and particularly discloses a three-dimensional point cloud semantic segmentation method and system based on a graph neural network and a window attention mechanism, and a storage medium. The point cloud features are changed into three groups of rgb-xyz-xyz information from two groups of rgb-xyz information, so that the subsequent extraction of local geometric information is facilitated; the combination of the graph neural network and the kernel point convolution can extract richer, more real and more effective local information window attention mechanism to extract local context information, and then the local context information is combined with local geometric information extracted by the graph neural network, so that the accuracy of semantic segmentation is remarkably improved.

The invention discloses a hyperspectral image change detection method based on multi-scale convolution sparse coding, and the method comprises the steps: inputting a dual-time-phase hyperspectral image into a deep interpretable network guided by the multi-scale convolution sparse coding, extracting multi-scale spatial spectrum features, reducing feature redundancy at the same time, and enhancing the interpretability of deep multi-scale feature extraction; putting forward a change-sensitive teacher-student self-distillation learning normal form, aligning dual-temporal features and difference features, and performing two-stage training on the network in combination with supervised learning; and extracting multi-scale features in the dual-temporal hyperspectral image by using the trained depth interpretable network, combining the multi-scale features with the dual-temporal hyperspectral image to obtain a difference feature map, and sending the difference feature map into a classifier to obtain a final change detection result. According to the method, the interpretability of the multi-scale feature extraction process in the deep neural network is improved, the dependence on labeled data is reduced, meanwhile, the sensitivity of a network model to changes is enhanced, and the generalization performance and the change detection precision of the model are improved.

The invention provides a cyclic enhanced vision-text cross-modal attention characterization method and a cyclic enhanced vision-text cross-modal attention characterization system. The invention aims to provide a vision-text cross-modal attention characterization method, and aims to enhance vision-text association and reduce feature difference between vision-text bimodals. Visual text fusion is researched in a unified manner through an iterative multi-stage vision-text fusion module, a mask reference-based central point supervision module and a cyclic enhancement decoder module. According to the method, the text information can be fully utilized, more comprehensive and more detailed text embedding is obtained, the context understanding of the image is enhanced, and the visual target most relevant to the text features is fused through circular enhancement. The method has a wide application prospect, can be applied to the fields of visual text fusion, remote sensing image processing and the like, and provides an effective solution for visual-text cross-modal feature representation.

The invention belongs to the technical field of wireless communication signal identification, and particularly discloses a double-branch automatic modulation identification method based on cross signal enhancement. The method comprises the following steps: firstly, acquiring a modulation signal, preprocessing the modulation signal, and converting the modulation signal from I / Q data into A / P data; then, building a modulation identification model; the modulation recognition model comprises a cross enhancement module, a channel feature fusion module, a time sequence context feature capture module and a classifier module; the cross enhancement module performs cross enhancement on I and Q channel data of the modulation signal and extracts I / Q features; the channel feature fusion module performs deep fusion on the I / Q features and the A / P features to obtain channel fusion enhanced features; a time sequence context feature capture module extracts time sequence context features from the channel fusion enhancement features, the time sequence context features are input into a classifier for classification, and modulation types are obtained; and finally, training and optimizing the modulation identification model, and using the optimized modulation identification model for identification of modulation signals. According to the method, the unbalance phenomenon between I / Q channels can be effectively reduced, and the recognition accuracy is improved.

The invention discloses application of a cannabidiol analogue CIAC001 in preparation of a medicine for treating Alzheimer's disease, and relates to the technical field of medicine. The application comprises the following steps: step 1, medicine extraction: extracting CIAC001, an NMDA receptor antagonist and a cholinesterase inhibitor according to a ratio of 1: 5: 5 into a medicine carrying needle cylinder; 2, medicine heating, wherein a heating assembly is started to conduct pulse heating on the medicine in the medicine carrying needle cylinder; 3, nursing the patient: heating and nursing the injection part of the patient by using a nursing assembly; 4, medicine injection: pushing a pushing head, puncturing a needle into the injection part of the patient, and injecting the medicine into the body of the patient; and 5, observing and treating side reactions: taking down the injection device after the drug reaction is complete, observing the side reaction condition of the patient, and starting a temperature regulator to cool the patient. The medicine activity can be effectively improved, side effects of the medicine on patients are reduced, and therefore the treatment effect of the medicine is enhanced.

The invention discloses a digital display meter identification method and system based on an E-Net model and a LeNet-5 network. The method comprises the following steps: applying a bottleneck convolution structure to an ENet network model, and carrying out digital region segmentation on a to-be-identified image based on the E-Net model; carrying out numeric character extraction on the segmented numeric region by utilizing a binarization method of an adaptive threshold; and carrying out denoising and tilt correction on the extracted characters, and carrying out character recognition by using an attention mechanism-based LeNet-5 network model to obtain a digital display meter recognition result. According to the scheme of the invention, high-precision identification of the reading of the digital electric meter in various complex environments is realized.

The invention relates to the technical field of deep learning and intelligent network connection, and discloses an intersection traffic flow detection method and system based on deep learning in an intelligent network connection vehicle. Preprocessing the frame image; the preprocessed image passes through a Backbone module integrated with an RFCBAMConv attention mechanism, and rich features in the image are extracted; carrying out classification and regression tasks on the extracted features through a DFMhead detection head, further determining a detected target category, estimating a bounding box position of the detected target category, and outputting a final detection result; sIWL is introduced into the loss calculation module to serve as a loss function, so that the detection capability of a small target is enhanced; by improving a traffic flow detection algorithm based on deep learning and applying the algorithm to the intelligent networked vehicle, the detection accuracy and stability of small targets and shielded targets are improved, so that the intelligent networked vehicle can re-plan a path in advance to avoid a congested road section when encountering long-distance intersection congestion in a planned path.