216 results about "Network identification" patented technology

The invention discloses a chromatographic data optimization processing method for a liquid chromatograph, and relates to the technical field, and the method comprises the following steps: collecting an original signal flow, carrying out preliminary peak detection, and generating an original peak list; extracting modal exclusive characteristics of each chromatographic peak; converting the modal exclusive features into a unified multi-dimensional semantic feature vector; calculating a time interval weight, and calculating a semantic relevancy weight based on the multi-dimensional semantic feature vector; correcting the time interval weight, generating a network edge weight, and constructing a peak correlation topology network by taking the multi-dimensional semantic feature vector as a node; identifying node clusters connected with high edge weights, and aggregating the node clusters into candidate compound entities; tracking a node signal intensity change track, and adding a conflict mark; conflict resolution arbitration is carried out on the candidate compound entities with the added conflict marks, dominant detector evidence is output, and an analysis report is generated. According to the method, the problems of poor data collaboration of multiple detectors, inaccurate peak identification and association and isolated data processing flow are effectively solved.

The invention provides a sheep abnormal behavior real-time monitoring method and system based on the Internet of Things, and relates to the technical field of abnormal monitoring, and the method comprises the steps: obtaining multi-source data information of sheep, including a position coordinate sequence, motion sensor data, a gait rhythm sequence, a colony house environment parameter sequence and a group topological relation; the influence of environmental constraints on group movement is quantified by constructing a group behavior field intensity model; based on an individual physiological energy consumption backstepping mechanism, an energy metabolism imbalance index is identified by using a deep residual network; through Granger causal relationship and conditional independence analysis, behavior causal separation of true and false anomalies is realized; and performing cross-cycle abnormal evolution path prediction in combination with historical behavior data, and generating a graded early warning conclusion. According to the invention, the false anomaly and the real health anomaly caused by environmental factors can be effectively distinguished, and the monitoring accuracy and the early warning timeliness are remarkably improved.

The invention discloses a provincial and regional power transmission network cooperative control method, system and device and a medium, and relates to the technical field of power transmission, comprising the steps of monitoring a network in real time, identifying fault nodes and analyzing propagation, evaluating an influence range and resource availability, optimizing standby resource scheduling, and generating a calling priority in combination with load balancing. Cross-level permission allocation is adjusted through load difference analysis, a standby path is analyzed to determine a convergence acceleration sequence, real-time flow and sequence are combined, flow is reallocated to balance loads, resource scheduling parameters are dynamically adjusted, a resource calling and path switching sequence is iteratively optimized, and historical data feedback is utilized to realize resource scheduling. And generating a final resource allocation and path switching scheme. According to the method, a provincial and regional power transmission network cooperative control closed loop is constructed, the fault recovery speed, the resource utilization efficiency and the system toughness are improved, and the problems of response lag, resource waste and insufficient adaptability of a traditional method are effectively solved.

The invention discloses a building full life cycle management method and system based on AI and BIM, and particularly relates to the technical field of building information, and the method comprises the steps of component information access and semantic standardization, spatio-temporal data collection and registration and multi-objective optimization, version monitoring and difference influence evaluation and influence management and control. Component attributes are automatically extracted through natural language processing, and precise mapping between the BIM model and field sensing and detection data is achieved; the graph neural network and the long and short term memory network are combined to identify collision risk and performance deviation, and a multi-target optimal solution optimization scheme is generated through an evolutionary algorithm; a graph neural network is utilized to extract difference sub-graphs, and change influence scores are quantified in three dimensions of progress, cost and safety, so that a basis is provided for auditing and backspacing; people, machines, materials and early warning are dispatched based on the change influence score, and the risk management and control and resource utilization efficiency in building full life cycle management is improved.

Identification and resolution of anomalies over a network include obtaining at least a set of media characteristics associated with media data transmitted from a first entity to a second entity over the network and contextual information associated with at least one of the first entity or the second entity. A first operational score associated with the first entity is determined based on the obtained set of media characteristics and the obtained contextual information. The first operational score is indicative of operating conditions associated with the first entity for the transmission of the media data over the network. Based on a comparison of the first operational score with a threshold, a set of anomalies associated with the first entity is identified. A set of operations to resolve the set of anomalies is determined. The first entity is controlled to execute the determined set of operations on the media data.

An apparatus and / or a method for providing dual connectivity (DC) in an electronic device which may include multiple SIMs. An electronic device may include: a first SIM comprising first subscriber identity information; a second SIM comprising second subscriber identify information; a wireless communication circuit; and at least one processor operatively connected to the first SIM, the second SIM, and the communication circuit, wherein the at least one processor: connects to a first MCG network or a first SCG network, based on the first subscriber identity information when data communication using the first subscriber identity information is configured; identifies a state of communication with the first MCG network; restricts addition of a second SCG network, based on the second subscriber identity information when the state of communication with the first MCG network is a connected state; and allows addition of the second SCG network, based on the second subscriber identity information when the state of communication with the first MCG network is in an idle state. Other embodiments may be also possible.

The invention relates to a grassland obstacle visual detection and identification method for a mowing robot, and belongs to the technical field of image identification. According to the method, firstly, a traditional neural network is used for carrying out obstacle recognition and elimination on a grassland image during mowing operation to obtain a preliminary screening image, and then the possibility that different sub-regions in the preliminary screening image contain unobvious obstacles is represented in a multi-dimensional mode based on image texture differences, edge trend differences and color distribution differences between the unobvious obstacles and a grassland background. Therefore, the parameters of the lightweight neural network are adaptively and accurately adjusted, so that the adjusted network is prevented from losing weak and sparse characteristic signals of an unobvious obstacle when facing a preliminary screening image possibly containing the unobvious obstacle, and the unobvious obstacle recognition with both recognition efficiency and recognition accuracy is realized. Finally, when the grassland obstacles in the mowing operation are recognized through the lightweight neural network, the obstacle recognition accuracy is remarkably improved.

The invention discloses a dynamic network access control system under a zero-trust architecture, which relates to the technical field of network security, and comprises a multi-dimensional trust evaluation module, a self-adaptive micro-segmentation engine, a strategy decision execution module and a risk perception feedback module, the multi-dimensional trust evaluation module calculates a comprehensive trust score based on five-dimensional features of identity, equipment, network, application and data; the self-adaptive micro-segmentation engine dynamically generates network micro-segments based on a graph diffusion algorithm; the strategy decision execution module adopts deep reinforcement learning to generate an access decision; the risk perception feedback module identifies abnormity based on the LSTM network and adjusts trust parameters through closed-loop feedback, the four modules are deeply coupled and cooperated, refined dynamic access control is realized, the occurrence rate of security events is reduced by more than 85%, and an innovative solution is provided for enterprise network security.

The present application relates to the technical field of irrigation control automation, in particular to a kind of irrigation area flow full node measurement method based on remote sensing interpretation and Internet of Things fusion, in the present application, through remote sensing interpretation plot pixel determination gray scale difference and reconstruct boundary connected structure, combined with multi-scale residual network identifies low reflection water area, effectively improve the identification precision of water area in complex background, make the boundary of identified area have closed integrity, through combining plot center and actual node coordinate error analysis, realize the spatial binding of node and canal section, optimize the spatial fragmentation and response delay problem caused by traditional segmented irrigation information acquisition mode, through the structural association between disturbance information by graph neural network, extract water pressure response consistent path combination, improve the ability of connectivity identification, water pressure evolution capture, path closed loop mining and scheduling node identification in distributed irrigation system.

An example operation may include one or more of storing a hash of a service set identifier (SSID) of a wireless network via an apparatus, receiving a probe request message transmitted from a network device, wherein the probe request message comprises a hash value, determining that the hash value within the probe request is a valid SSID based on the hash of the SSID of the wireless network stored in the storage device, and controlling the network interface to transmit a probe response with a plain text name of the SSID to the network device in response to the determination.

This invention discloses an artificial intelligence-based method for managing and controlling power grid water dispatch data, specifically relating to the field of power grid water dispatch data management technology. The method involves collecting multi-source heterogeneous water dispatch data and its metadata to construct a unified format dataset; generating a credibility score based on metadata and data features to form a credibility matrix; constructing a multi-dimensional quality assessment tensor and extracting the dominant factor subspace; inputting this tensor into a clustering perceptual neural network to identify abnormal data, outputting an abnormal dataset and abnormal labels; combining a large model enhanced by RAG retrieval with historical similar data to complete abnormal data repair; constructing a data quality improvement report using the difference vectors before and after repair and label information; and finally pushing the report to a data management platform and generating a traceable rectification work order. This method achieves automatic identification, intelligent repair, and feedback tracking of power grid water dispatch data, improving data credibility, governance efficiency, and security, and is suitable for data management needs in complex scenarios under new power systems.

The application discloses a point cloud analysis and reconstruction method and system based on a cloud CAD platform, belongs to the technical field of point cloud reconstruction, and is used for solving the technical problems that the existing point cloud data reconstruction mode depends on manual operation, is low in efficiency, poor in precision and consistency, and difficult to adapt to complex scenes and automation requirements. The method comprises the following steps: receiving a point cloud data file and determining a processing mode; determining a corresponding irregular sampling region according to the processing mode, and performing signed distance field prediction on the point cloud data file in the irregular sampling region to obtain unsigned distance field and gradient information; generating a sliding window, identifying local boundary information in the sliding window through a boundary prediction neural network, and performing splicing to obtain global boundary information; dividing a face region of the point cloud data file according to the global boundary information to obtain different types of faces; performing targeted fitting processing on each type of face, and solving a boundary representation relationship between the faces to reconstruct a CAD model.

This invention discloses a method for preparing and intelligently identifying microscopic stealth codes by integrating artificial intelligence and hyperspectral imaging, belonging to the field of anti-counterfeiting technology. The method comprises two parts: preparation and identification. During preparation, photochromic materials are doped into a substrate to form microscopic code points. A hyperspectral feature library is established, and a digital twin initial model containing partial differential equations is constructed, followed by pre-training of a physical information neural network. During identification, measured hyperspectral data of the code points to be tested are collected. Combined with environmental parameters and historical data, the expected state is predicted using the trained physical information neural network. The authenticity is determined by comparing the measured data with the expected state. This invention embeds physical laws into the identification process through a digital twin model and a physical information neural network, achieving proactive prediction of the evolution of the microscopic stealth code state, significantly improving the accuracy, robustness, and anti-counterfeiting capability of anti-counterfeiting identification.

This invention discloses a method for extracting the contours of point clouds on the surface of castings based on neural networks. The method comprises the following steps: S1: acquiring point cloud data of the casting surface; S2: preprocessing the point cloud data; S3: constructing a point cloud edge detection network based on a UNet++ neural network and training the network to obtain a trained point cloud edge detection network; the point cloud edge detection network includes an input layer, an encoder module, a feature extraction module, an attention module, a decoder module, and an output layer connected in sequence; S4: identifying the contours of various parts of the casting surface based on the trained point cloud edge detection network. This invention enhances the ability to capture detailed features of the target point cloud by constructing a point cloud edge detection network and extracting attention features of the center point features, while also exhibiting stronger robustness to sparse and noisy point clouds. Extracting the point cloud contours of parts on the casting surface using the point cloud edge detection network improves the accuracy of robots in identifying different shaped parts of the casting surface and provides better adaptability in complex industrial scenarios.

The invention discloses a hydrogen energy heavy truck multi-target energy management method based on reinforcement learning, and relates to the technical field of hydrogen energy heavy truck energy management, the method constructs a neural network model of an MOSAC algorithm, through an environment interaction training model, Bayesian optimization and Pareto frontier constraint are introduced in the training process, and the energy management efficiency of the hydrogen energy heavy truck is improved. And after training, an NSGAII algorithm is used to obtain a Pareto optimal strategy set. During online application, a state vector is constructed according to real-time vehicle data, a driving condition is identified through adaptive modal decomposition and a time sequence convolutional network, a control strategy is matched or adjusted from a Pareto optimal strategy set according to the type of the condition, and the state vector is input into the strategy to obtain initial power distribution; and finally, performing correction according to the fuel cell power change rate constraint and the power cell SOC boundary limitation to obtain a final power distribution instruction. According to the method, self-adaptive optimization control of the hydrogen energy heavy truck under multiple targets is realized, and the economical efficiency, the dynamic property and the safety are effectively improved.

The invention discloses an unmanned aerial vehicle ad hoc network identification and multi-hop relay method and system based on dynamic optimization of an HCAR. According to the method, a dynamic network topology is constructed and maintained through periodic beacon interaction between nodes; after a target unmanned aerial vehicle identification signal is received, evaluating the direct link quality with a ground control center, and if the direct link quality is lower than a threshold value, starting a multi-hop relay; the optimal next-hop node and the communication channel are jointly selected according to the real-time topology and the channel state through the HCAR algorithm, and data are forwarded to a ground control center hop by hop. According to the invention, through the dynamic collaborative optimization of the routing and the channel, the transmission stability and the spectrum efficiency in a high-density scene are improved; link interruption rapid detection and self-healing capabilities are provided, and data transmission continuity is guaranteed; energy state monitoring and dynamic deployment are combined, and outdoor long-term reliable operation is supported.

The invention relates to the technical field of data processing, in particular to a pharmaceutical production whole-process quality tracing method and system applying a block chain technology, and the method comprises the steps: obtaining a liquid matrix composed of pixel values of a liquid region in an injection bottle; obtaining an effective test region in the liquid matrix by using a region growth method; processing the pixel value of the effective test area to obtain an enhanced matrix; training a recognition network to recognize impurity types in the enhancement matrix; acquiring an enhanced matrix in the production process, and identifying whether impurity types exist or not by using the trained identification network; and in response to the existence of the impurity type, prompting related personnel to perform quality inspection on the corresponding production process. The method has the effects of improving the drug detection accuracy and providing a reliable data basis for subsequent drug traceability.

This invention discloses a lightweight neural network identification method for high-speed dynamic impact signals. In the process of penetrating multi-layered hard targets, the presence of signal adhesion in the overload signals from multiple dynamic impacts makes identification exceptionally difficult. To address this problem, a lightweight network identification method based on an attention mechanism is proposed. First, time-frequency feature analysis is performed on the overload signal equivalent to that from multiple impact test benches, and continuous wavelet transform is used to extract the time-frequency features as input to the neural network. A lightweight network architecture based on an attention mechanism is designed, eliminating redundant layers and adding residual connection structures and a lightweight attention mechanism, thus ensuring recognition accuracy while significantly reducing parameters.

This application discloses a method and system for intelligent generation and quality control of medical documents, relating to the field of medical information technology. The disclosed method and system for intelligent generation and quality control of medical documents acquires multi-source medical data, constructs a medical semantic graph network, performs clinical logical reasoning, generates and verifies medical documents, and updates them based on feedback. It can automatically construct a patient-specific medical knowledge network, identify deep semantic relationships between clinical entities, generate logically rigorous professional descriptions, and improve the quality of medical documents and medical safety.

This invention relates to the field of air pollutant detection technology and discloses a method for detecting excessive emissions of air pollutants. The method includes: acquiring pollutant concentration data from multiple monitoring points in a target area to form a raw dataset; performing outlier detection and correction, removing sensor malfunction outliers to obtain a preprocessed dataset; extracting concentration change trend characteristics within a preset time window for each monitoring point to construct a spatiotemporal feature matrix; inputting the matrix into a pollutant diffusion model to calculate the transmission paths and intensities between monitoring points, generating a regional transmission network; identifying potential source areas of abnormal pollutant concentration fluctuations based on the network and marking them as candidate areas for verification; performing multi-scale concentration gradient analysis on the candidate areas to determine key monitoring areas; deploying mobile equipment in the key monitoring areas to collect high-precision component data; comparing this data with a standard emission source feature library, matching emission source types with similarity exceeding a threshold, determining whether emissions exceed standards, and generating a detection report.

The application discloses a kind of self-supervised industrial defect detection methods based on frequency domain mask strategy, based on Vision Transformer Shared encoder is constructed, feature extraction is carried out to the industrial product surface image after masking and the industrial product surface spectrum diagram after masking, and spatial domain shared encoding feature and frequency domain shared encoding feature are obtained;Two independent encoder-decoder branches are constructed, including spatial domain branch and frequency domain branch, each branch is encoded by Transformer block as encoder, and is decoded by convolution layer as decoder, to obtain spatial domain and frequency domain reconstruction image;Based on pre-training shared encoder and encoder, reconnect detection network, build self-supervised industrial defect detection model, the encoder output of spatial domain branch and frequency domain branch is spliced, input detection network identifies flaw area, and uses labeled sample to fine-tune model;Industrial defect detection is carried out using the adjusted self-supervised industrial defect detection model.The application greatly reduces the labeling cost while improving the performance of industrial defect detection.

The application provides a mechanical state monitoring method based on an interpretable sparse optimization unfolding network, comprising the following steps: S100, performing mechanical state data monitoring test to obtain mechanical state signals; S200, constructing a sparse optimization model, and using sparse feature representation for the extracted mechanical state features; S300, using an alternating multiplier method to derive an iterative optimization solving algorithm of the sparse optimization model; S400, introducing learnable parameters to replace the parameters in the iterative optimization solving algorithm; S500, using an unfolding algorithm framework to construct an interpretable sparse optimization unfolding network; S600, using the interpretable sparse optimization unfolding network to identify the health state of a test machine; the application embeds a Q-adjusted wavelet transform into a sparse optimization model, and uses the multi-scale characteristics and wavelet dictionary structure for sparse feature representation, so that accurate capture of key state information can be realized in the feature extraction stage.

The present application relates to the technical field of stockpile collapse risk early warning, and discloses a coal mine stockpile intelligent monitoring stockpile collapse safety early warning method based on deep learning, wherein the coal mine stockpile intelligent monitoring stockpile collapse safety early warning method based on deep learning comprises: acquiring sound wave feedback signals of each height layer of a stockpile, performing frequency spectrum transformation and layered decoupling processing on the signals, and generating independent frequency spectrum features of each layer; inputting the independent frequency spectrum features of each layer into a blockage form classification neural network, identifying the blockage form types of each height layer, and generating a multilayer blockage state joint time sequence; performing causal analysis on the multilayer blockage state joint time sequence, identifying the interlayer causal relationship and implicit conduction variables, and generating an interlayer blockage conduction path diagram; based on the interlayer blockage conduction path diagram, when a change in the blockage state of a certain layer is detected, the cascading influence is calculated and a stockpile collapse risk early warning is output; the present application overcomes the limitation that the existing early warning system can only respond passively to the deterioration that has occurred and cannot predict the cascading risk.

The embodiment of the application provides a kind of based on AFDX data interaction system, method and electronic equipment, belong to communication technical field.The method the system includes successively connected interface analysis module, DMA transmission control module, AFDX protocol processing module, data cache module and MAC data processing module, MAC data processing module includes the MAC data processing unit of at least one network corresponding, AFDX protocol processing module uses AFDX protocol to the effective downstream data from DMA transmission control module carries out address group packet and obtains AFDX downstream data, data cache module according to the network identification indicated by AFDX downstream data sends AFDX downstream data to corresponding MAC data processing unit, MAC data processing unit is according to the target network protocol of corresponding to the AFDX downstream data received by it repackage, obtains target network downstream data, and then can be based on AFDX protocol realizes communication in other network, improves the data interaction efficiency between equipment.

The embodiment of the invention discloses an intelligent object recognition method and device, electronic equipment and a storage medium, and relates to the technical field of object recognition. The recognition accuracy can be improved. The method comprises the following steps: acquiring image data of a to-be-recognized object; wherein the image data comprises a color image and a multispectral image; respectively preprocessing the color image and the multispectral image; inputting the preprocessed color image and the preprocessed multispectral image into a double-feature extraction network of a preset object recognition model to respectively obtain morphological features of the object to be recognized and spectral response features of the object to be recognized; according to the morphological characteristics, the spectral response characteristics and an identification network of the object identification model, identifying category information of the to-be-identified object; wherein the recognition network is connected with the double-feature extraction network. The method is suitable for natural object recognition scenes.

The application belongs to the field of power station oil-water pipeline monitoring, and particularly relates to a liquid leakage metering detection method and system based on an event camera, which comprises continuously monitoring by using the event camera to obtain original event data; performing space-time filtering processing on the original event data to generate event image frames; inputting the event image frames into a pre-trained target detection neural network to identify whether there is a liquid leakage target in the image; if the liquid leakage target is detected, inputting the corresponding event image frame into an image segmentation network to obtain a pixel-level segmentation result of a liquid drop region; calculating a liquid drop contour area based on the segmentation result, converting the liquid drop contour area into a single leakage volume; and calculating a real-time leakage rate and a cumulative leakage amount. The application can detect the liquid drop leakage amount in real time without changing the liquid properties, takes the event stream of the event camera as the input, combines the image processing technology with the physical model, and realizes accurate estimation of the liquid leakage amount.

The application discloses a terminal equipment-based signed receipt information identification method and device, medium and equipment. The method comprises the following steps: obtaining a signed receipt image, identifying the current angle of the signed receipt image through an SVM network, and rotating the signed receipt to a standard angle according to the current angle; performing verification element detection on the signed receipt image by using a YOLO network, determining the bounding box position and category of the verification element, and identifying whether the bounding box position and category of each verification element in the signed receipt image match; if the bounding box position and category match, each verification element is cropped according to the bounding box position; the verification element is input into a text recognition model for text recognition; and if the text recognition result matches the signed receipt information recorded in advance, it is determined that the information identification of the signed receipt is completed. According to the technical scheme, main verification matching processing can be performed on the mobile equipment side, and in the case that the verification is unqualified, the mobile equipment needs to inform the business party of the unqualified verification element and the reason for the unqualification.

The application discloses a non-ideal observation radar PRI modulation identification method, comprising the following steps: presetting parameter ranges of different PRI modulation types; generating a plurality of PRI pulse sequences for each PRI modulation type; preprocessing the PRI pulse sequences generated for each PRI modulation type, generating GASF coded images and GADF coded images, and establishing an identification dataset; establishing a PRI modulation identification model, fusing features output by two convolutional neural networks of the PRI modulation identification model to obtain a network identification result; for a PRI pulse sequence corresponding to each sample, determining a continuity identification result of the PRI modulation type by calculating a continuity parameter of the PRI pulse sequence and based on a prior parameter interval; combining the network identification result and the continuity identification result, and if the continuity identification result contains the network identification result, taking the network identification result as a final identification result; and acquiring a PRI pulse sequence to be identified, determining a PRI modulation type by using the trained PRI modulation identification model and combining a calculation result of a continuity parameter of the PRI pulse sequence.

The invention discloses an adhesive quality detection method and equipment based on image recognition, and belongs to the technical field of adhesive quality detection. The detection method comprises the steps that a digital image of a target adhesive needing quality detection is acquired, a trained recognition network is acquired, the recognition network is configured to receive the digital image and generate category information of the digital image, and therefore quality detection of the target adhesive is completed; a feature capture module is arranged in the recognition network, the feature capture module comprises a mutation capture unit, a semantic capture unit and an adjacent fusion unit which are connected with one another, and the mutation capture unit and the semantic capture unit are each provided with a convolutional layer. The identification network can simultaneously capture local mutation defects and overall semantic distribution defects, and the accuracy and reliability of adhesive quality identification are greatly improved.