27 results about "Port security" patented technology

The invention relates to a port water area ship navigation risk distribution calculation and visualization method and device based on AIS and GIS data fusion, and the method comprises the following steps: 110, obtaining ship AIS data, and carrying out the preprocessing of the ship AIS data, thereby obtaining the preprocessed ship AIS data, and the preprocessing comprises the standardization, feature extraction and abnormal point detection; step 120, carrying out port water area grid construction, and carrying out grid mapping and legality screening on the preprocessed ship AIS data; step 130, performing port water area static risk assessment, port water area dynamic risk assessment and port water area propagation risk assessment on the port water area, and performing port water area comprehensive risk assessment on the basis to obtain an assessment result; and step 140, drawing a port water area risk thermodynamic diagram based on the evaluation result to realize risk distribution visualization. According to the invention, efficient and scientific decision support can be provided for port safety management.

The invention relates to the technical field of artificial intelligence, in particular to an intelligent risk hidden danger prediction method for port safety. The intelligent risk hidden danger prediction method for port safety comprises the steps of collecting heterogeneous data of a plurality of data sources from a port, and performing time and space marking on the heterogeneous data; performing feature extraction including time features and space features on the heterogeneous data, and constructing a dynamic space-time knowledge graph based on the extracted features; and inputting the dynamic space-time knowledge graph into a graph neural network to obtain a node feature vector of each node based on space-time knowledge graph topology, and performing risk and hidden danger prediction based on the node feature vectors. In this way, the dynamic space-time knowledge graph constructed based on the time information and the space information of heterogeneous data is combined with the knowledge association of the graph neural network, so that the effective intelligent prediction of the harbor security risk hidden danger can be carried out.

The invention provides a linkage control method and system for multiple optoelectronic devices. The method comprises the steps that a monitoring area of the optoelectronic devices is divided into a plurality of monitoring sub-areas; acquiring position information of the monitored object; listing the photoelectric devices, containing the position information of the monitored object, in the monitoring area as selectable photoelectric devices; turning the selectable photoelectric equipment to the monitored object, and displaying the monitored object at a monitoring end of the selectable photoelectric equipment; performing parameter calibration on the monitoring area of the photoelectric equipment by using a reference object, and storing a calibration result of the monitoring area in a calibration database; and carrying out parameter calibration on the monitoring sub-region of the photoelectric equipment by using a reference object, and storing a calibration result of the monitoring sub-region in the calibration database. The technical scheme of the invention can be widely applied to the fields of maritime supervision, port security and protection and the like.

The invention discloses a switch port security management method, device and equipment and a storage medium, and relates to the technical field of network management, and the switch port security management method comprises the steps: obtaining port operation data and traffic data of a switch; generating a security policy of the port according to the port operation data and the traffic data; after the security policy is executed, carrying out real-time state monitoring on the port of the switch and determining an abnormal event; and executing a safety response operation according to the type and the severity level of the abnormal event. According to the invention, the security management accuracy of the switch port can be improved.

The invention discloses a port storage tank risk prediction method and system based on machine learning, and the method comprises the steps: obtaining the storage tank data and regional data of a preset port, carrying out the logistics transportation analysis and energy density simulation according to the regional data, carrying out the statistics of historical risk factors of a risk region based on the simulation energy density fluctuation range, and obtaining a risk prediction result; and constructing a criticality matrix according to the historical risk factors and the logistics grid point locations, performing risk assessment on the risk region by using the criticality matrix, inputting a risk assessment result and risk factor items of the storage tank data into a random forest for training, and obtaining a storage tank risk prediction model. And outputting a risk prediction result of the storage area according to the storage tank risk prediction model. According to the method, risk prediction is carried out by utilizing logistics grid division, risk area irregular splitting, energy density simulation and quality detection data of the storage tank, a multi-dimensional decision basis is provided for safe operation of a port, and meanwhile, the method has relatively good interpretability.

The invention discloses a radar-sonar-video fusion association method and system based on cross-modal semantic mapping. The method comprises the steps that modal specific feature vectors are extracted from three heterogeneous sensors including a radar sensor, a sonar sensor and an optical video sensor respectively; constructing a three-branch deep metric learning network, and mapping the heterogeneous features to a unified d-dimensional semantic embedding space; a tripartite graph model is constructed, and semantic similarity and kinematics consistency constraints are comprehensively considered for edge weights; an improved Kuhn-Munkres algorithm is applied to solve the global optimal matching of the tripartite graph; and outputting a fusion target state and matching confidence evaluation. Cross-physical-domain invariant feature representation is automatically extracted through deep metric learning, three-mode global optimal association is achieved in combination with a graph optimization algorithm, the technical problem that cross-physical-domain data fusion is difficult to process through a traditional method is solved, and the method has high accuracy, strong generalization ability and real-time performance in application scenes such as ocean monitoring and port security and protection and is suitable for being used in the field of ocean monitoring and port security and protection. And an effective technical scheme is provided for multi-sensor heterogeneous data fusion.

The invention relates to the technical field of port safety management, in particular to a port loading and unloading production dynamic closed process operation system based on deep learning and an image recognition algorithm, which comprises a port machinery surrounding environment monitoring safety management and control system, a port mobile machinery anti-fatigue driving system and an intelligent scheduling system, the harbor machinery surrounding environment monitoring safety management and control system comprises an electronic fence, an environment information acquisition camera, an edge computing terminal, a display device and an electronic alarm. The anti-fatigue driving system comprises a state monitoring camera, a behavior recognition module and a reminding module. The intelligent scheduling system comprises a cargo identification camera, an edge calculation chip, a cargo identification sensor, a PLC controller, a transportation device and an industrial robot. Through the system, through deep fusion of deep learning and an image recognition algorithm, the safety and management efficiency of port machinery night operation and the reliability and efficiency of anti-intrusion control are improved.

Access point network equipment has communication ports that allow communications with other network components. Communications cables coupled to ports can be easily removed and replaced with unauthorized devices that have access to the network creating a security breach. Covers placed over the authorized cable connectors can create a physical barrier preventing unauthorized connections to the access point network equipment. When an authorized cable is removed from a port, a link down event can be detected by tamper detection by tamper detection software running on the access point network equipment. When a link down events is detected the tamper detection software can perform various possible security actions to protect the network.

The application discloses a port safety monitoring edge computing task unloading scheduling method based on deep learning, relates to the technical field of port safety monitoring, and comprises the following steps: performing deep learning inference on a port safety monitoring video to extract abnormal behavior semantic features, quantifying a task processing process to extract task data scale features, and respectively constructing semantic risk potential energy values and load scale potential energy values based on the abnormal behavior semantic features and the task data scale features; constructing a potential energy confrontation domain based on the direction difference of the semantic risk potential energy values and the load scale potential energy values in a unified reference space, and judging whether the abnormal behavior semantic features and the task data scale features conflict according to the potential energy confrontation domain. The application solves the problem that the scheduling emphasis direction cannot be adjusted based on the semantic risk and the task scale conflict intensity, and realizes the effects of high-risk task priority response and dynamic optimization of a scheduling strategy.

This invention discloses a safety early warning method and system based on port monitoring data analysis, relating to the field of port safety monitoring technology. The method identifies human figures and mobile work equipment in the land-based work area from port monitoring videos and maps them onto a land-based work area plan. Simultaneously, it acquires data on ship entry and exit and cargo loading / unloading in the port's water-based work area, determining the tonnage and cargo volume of each berthed ship to form a ship / cargo parameter group. The land-based work area plans corresponding to ship / cargo parameter groups with a similarity greater than or equal to preset values ​​are integrated and categorized, and the performance characteristics of the human figure and mobile equipment mapping points are analyzed to derive characteristic parameters. These characteristic parameters are then mapped back to the land-based work area plan to form a plan template for analyzing real-time port monitoring data and issuing safety early warnings based on the analysis results. The above technical solution of this invention achieves port safety early warning and improves the safety of port operations.

The application discloses a switch port security management method and device, equipment and a storage medium, and relates to the technical field of network management. The switch port security management method comprises the following steps: obtaining port operation data and traffic data of a switch; generating a security policy of a port according to the port operation data and the traffic data; performing real-time state monitoring on the port of the switch and determining an abnormal event after the security policy is executed; and performing a security response operation according to the type and severity level of the abnormal event. The application can improve the accuracy of switch port security management.

The invention relates to the technical field of artificial intelligence, in particular to an intelligent evaluation method for a harbor potential safety hazard treatment effect, and the method comprises the steps: constructing a harbor safety knowledge graph based on harbor static data and harbor potential safety hazard treatment dynamic data; performing text analysis based on semantic understanding of a port potential safety hazard treatment scheme and treatment records, and converting the text into a structured action sequence; creating a copy of the port safety knowledge graph, and mapping the structured action sequence to the copy of the port safety knowledge graph to obtain a simulation evaluation initial state graph; performing simulation deduction on the simulation evaluation initial state diagram by using Monte Carlo tree search to obtain probability distribution of a deduction result; and determining an evaluation score of the harbor potential safety hazard treatment effect based on each deduction result included in the probability distribution of the deduction results and the probability score thereof. Therefore, the accuracy of the evaluation score is improved.

This invention discloses a comprehensive prevention method for hazardous chemical safety accidents in ports based on WGT (Warranty-Gross Theory), relating to the field of port safety technology. It collects risk influencing factors for different types of hazardous chemical safety accidents occurring in different ports; classifies these risk influencing factors using WSR theory; further filters and grades them using GRA (Gross Response Analysis); calculates the probability of occurrence of risk influencing factors for different types of hazardous chemical safety accidents in ports; and couples the selected risk influencing factors using TSS (Treatise on Risk-Gross Theory) to calculate the probability of occurrence of risk influencing factors for different types of hazardous chemical safety accidents in ports under a three-dimensional risk scenario; then identifies the risk influencing factor index corresponding to the maximum probability of coupled risk for each port in different types of hazardous chemical safety accidents; and formulates comprehensive preventive measures to avoid and reduce the risk of the same type of accident occurring in ports, preventing the same type of accident from recurring in other ports.

The invention relates to the technical field of port safety management, in particular to a ship navigation risk alarm information intelligent identification method and system. According to the method, when entities and relationships are extracted, iterative updating of a graph attention network of directional entity perception is performed on an initial node feature matrix, and a final high-order node feature matrix is obtained; inputting the final high-order node feature matrix into a classifier, and performing entity recognition and relationship classification; in an iterative updating link, a brand-new final high-order node feature matrix is output, and each row in the matrix is a depth feature which is rich in global context information and directional entity perception and customized for entity recognition and relationship classification. And the depth feature is directly input into a subsequent classifier to finish a final extraction task, so that the extraction precision and robustness of the complex alarm statement are remarkably improved.

The present application provides a kind of breakwater wave force real-time calculation method and system, it is related to port safety monitoring technical field.The method is by wave monitoring sensor array and structural response monitoring sensor network synchronous acquisition wave parameter and structural response data;Based on wave parameter and initial wave force calculation model, obtain initial wave force value;Utilize structural response data through structural mechanics model conversion and numerical difference analysis, obtain error signal;Combined with error signal and environmental state monitoring data, using reinforcement learning algorithm dynamically adjusts model parameter;Finally, based on the model parameter of optimization, recalculate to obtain real-time wave force value.The present application realizes the dynamic correction and self-adaptive optimization of wave force calculation, effectively improves the accuracy and real-time of breakwater safety monitoring.

The invention relates to an unsupervised domain adaptive target detection method based on harmonious learning and sample mixing, and belongs to the technical field of computer vision and intelligent perception. The method aims at solving the problem of detection performance degradation caused by illumination, weather and scene differences among different domains, and is particularly suitable for low-illumination complex environments such as port night safety detection. The method comprises the following steps: S1, proposing an unsupervised domain adaptation detection task; s11, constructing a domain adaptation detection network HLMix based on harmonious learning and sample mixing; s12, designing a Harmony Measure (Harmony Measure) module; s13, designing a sample mixing module; s14, a feature enhancement module C3k2-CG is introduced; s15, a joint loss function is designed, wherein the joint loss function comprises supervised detection loss, unsupervised consistency loss and harmonious weighting loss; s2, establishing a data set for model evaluation; the method comprises the following steps: (S21) selecting an mAP (Mean Average Prediction) as an evaluation index; and S22, verifying the effectiveness of the model, and carrying out a contrast experiment on the method and various typical unsupervised domain adaptive detection methods. The method can significantly improve the detection precision and robustness of the model in a non-label target domain scene, especially has high adaptability in low-illumination complex environments such as night and foggy days, and can be widely applied to cross-domain target detection tasks in automatic driving and industrial scenes.

The application discloses a port safety dynamic evaluation system and method based on double-database cooperation, and particularly relates to the field of port safety dynamic evaluation edge data processing, and is used for solving the problems of logical shock and evaluation distortion caused by high-frequency fragmented attribute changes; through receiving fragmented basic data containing equipment account and operation record attribute changes, time sequence aggregation and semantic deduplication feature extraction are completed based on a port compliance guide label dictionary, a structured incremental update instruction set is generated, and the evaluation logic dependency tree in the labeled standard database is linked, a graph walking structure decay degree and a time sequence operation frequency domain distortion wave peak number are extracted, a graph node containing a decision coefficient is formed, a damaged logic subgraph is constructed, bidirectional consistency checking and conflict resolution coding are completed, an updated state evaluation node sequence is output and atomized and synchronized to the labeled standard database, and a local recalculation trigger signal and a professional semantic prompt word are generated.

Access point network equipment has communication ports that allow communications with other network components and a cloud based AP device management system having an Auto Configuration Service (ACS). Communications cables coupled to ports can be easily removed and replaced with unauthorized devices that have access to the network creating a security breach. When an authorized cable or plug is removed from a port, a link down event can be detected by tamper detection software running on the access point network equipment and the link down event information can be transmitted to the cloud / Map service. When a link down events is detected, the cloud / ACS transmits instructions to the access point network equipment to perform various possible security actions to protect the network.

This invention discloses a deep learning-based edge computing task offloading and scheduling method for port safety monitoring, relating to the field of port safety monitoring technology. The method includes the following steps: performing deep learning inference on port safety monitoring videos to extract semantic features of abnormal behavior; quantifying the task processing process to extract task data scale features; and constructing semantic risk potential values ​​and load scale potential values ​​based on the semantic features of abnormal behavior and the task data scale features, respectively; constructing a potential energy adversarial domain based on the directional difference between the semantic risk potential value and the load scale potential value in a unified reference space; and determining whether there is a conflict between the semantic features of abnormal behavior and the task data scale features based on the potential energy adversarial domain. This invention solves the problem of not being able to adjust the scheduling focus direction based on the intensity of the conflict between semantic risk and task scale, achieving the effect of prioritizing high-risk tasks and dynamically optimizing scheduling strategies.

The invention provides a port security and protection management method and system based on target detection and a large language model, and the method comprises the steps: obtaining real-time and historical video streams, carrying out the framing processing, generating a to-be-detected image and a historical training image, training a YOLOv5x network model through employing the marked historical image to construct a security and protection alarm event detection model, and carrying out the detection of the security and protection alarm event. The method comprises the following steps: acquiring a to-be-detected image, inputting the to-be-detected image into a model for target detection, outputting a target detection result for triggering alarm, screening out effective alarm data by using a DeepSeek VL large language model, converting the effective alarm data into a structured document, segmenting the document into a plurality of different semantic data blocks by using a DeepSeek R1 large language model, and performing target detection on the segmented semantic data blocks. The method comprises the following steps: firstly, extracting a data block, converting the data block into a semantic vector by utilizing an Embedding model, storing the semantic vector into a vector database, finally receiving a natural language query request of a user, vectorizing a query statement, retrieving the matched semantic vector from the vector database, generating a cue word based on a retrieval result in combination with the query request, and further generating a response report through a large language model. And port intelligent security alarm and disposal are completed.

The invention provides a breakwater wave force real-time calculation method and system, and relates to the technical field of port safety monitoring. The method comprises the following steps: synchronously acquiring wave parameters and structural response data through a wave monitoring sensor array and a structural response monitoring sensor network; obtaining an initial wave force value based on the wave parameters and an initial wave force calculation model; utilizing the structural response data to obtain an error signal through structural mechanical model conversion and numerical difference analysis; dynamically adjusting model parameters by adopting a reinforcement learning algorithm in combination with error signals and environmental state monitoring data; and finally, recalculating based on the optimized model parameters to obtain a real-time wave force value. According to the method, dynamic correction and self-adaptive optimization of wave force calculation are realized, and the accuracy and real-time performance of breakwater safety monitoring are effectively improved.

This invention relates to the field of port safety management technology, and more particularly to an intelligent identification method and system for ship navigation risk alarm information. In extracting entities and relationships, this invention iteratively updates the initial node feature matrix using a directional entity-aware graph attention network to obtain a final high-order node feature matrix. This final high-order node feature matrix is ​​then input into a classifier for entity recognition and relationship classification. During the iterative update phase, the output is a completely new final high-order node feature matrix. Each row of this matrix is ​​a deep feature rich in global contextual information and directional entity awareness, tailored for entity recognition and relationship classification. These deep features are directly input into the subsequent classifier to complete the final extraction task, thereby significantly improving the extraction accuracy and robustness for complex alarm statements.

1. The name of the design product: network interface security lock. 2. The use of the design product: for protecting RJ45 network interface, preventing random copying of data. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: usage state diagram 1. 5. Other circumstances that need to be explained: the front of the network interface security lock is designed with a cover that can be buckled or opened as needed.

This invention relates to the field of port safety management technology, specifically to a port hazardous chemical storage end-to-end safety situation simulation and decision-making system based on digital twins. It includes: a digital twin end-to-end modeling unit; an end-to-end safety data acquisition unit; a safety situation simulation unit, which uses dynamic topology graph neural network technology to conduct chain risk simulation of the end-to-end safety situation of port hazardous chemical storage; and an intelligent decision generation and execution unit. This invention employs dynamic topology graph neural network technology to model nodes and configure attributes of physical facilities throughout the port hazardous chemical storage end-to-end. Through dynamic connection weight generation, risk message transmission, and iterative updates, it completes risk propagation path identification and spatiotemporal risk data mapping, achieving accurate dynamic risk simulation of the entire port hazardous chemical storage end-to-end. This solves the problem of the lack of dynamic topology end-to-end risk simulation capabilities in existing technologies and meets the needs of dynamic risk control throughout the end-to-end.

1. The name of the design product: the network port lock. 2. The use of the design product: used for network port security lock, network port plug. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: perspective view.

1. Name of the product in this design: Network Port Security Lock (RJ45). 2. Purpose of this design: A security lock for network port security protection. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a bottom view.

This invention relates to the fields of port safety management and artificial intelligence technology, specifically disclosing a method for diagnosing missing or incomplete port safety regulations based on an AI large-scale model. The method includes: constructing a safety regulations knowledge graph by hierarchically decomposing a standard regulations library; dividing the system into scenario units and identifying inherent risk points and priority indices; constructing a dual-channel comparative diagnostic model of regulations and scenarios; completing feature encoding to obtain feature vectors of the same dimension on both the regulations and scenarios sides; analyzing the similarity of feature vectors through a cross-attention mechanism; calling knowledge subgraphs of the knowledge graph to determine the type of difference and establish rectification priorities. This method solves the problems of rigid compliance benchmarks, detachment from practical application, difficulty in multimodal data fusion, ambiguous difference determination, and lack of clear rectification priorities in traditional port safety regulations diagnosis. It achieves dynamic adaptation of compliance benchmarks, diagnosis aligned with port practices, cross-modal data fusion and comparison, and clear priorities for both diagnosis and rectification, thus improving diagnostic accuracy and efficiency.