159 results about "Space Network" patented technology

The invention discloses an internet constellation dynamic routing optimization method and system, and the method comprises the steps: setting orbit plane parameters and satellite parameters, and carrying out the modeling of an orbit and a constellation; performing link visualization and time-varying graph generation according to ephemeris data and the constructed constellation model; defining a related space, a network and a function based on a deep reinforcement learning algorithm; and based on an MADDPG framework, introducing a multi-agent collaborative decision-making mechanism, and outputting action selection and execution results after collaborative optimization. The system comprises a model construction module, an embedding module, a reinforcement learning design module and a collaborative optimization module. By using the method, the dynamic change of the low-orbit satellite network can be effectively dealt with, satellite resources are fully utilized, and efficient and reliable communication is realized. The method can be widely applied to the field of wireless communication.

The invention relates to a computer vision technology, in particular to an event camera target detection method based on Euclidean-hyperbolic motion perception, which comprises the following steps: down-sampling original event data, constructing an event graph by using the down-sampled data, and inputting the event graph into a double-space network for target detection; performing local perception feature extraction on the event graph by using a graph convolutional network based on a B-spline kernel function, and projecting the extracted features to a hyperbolic space; extracting global event dependency features from the local sensing features mapped to the hyperbolic space through a learnable curvature hyperbolic graph convolutional network; and decoding the global event dependency feature and inputting the decoded global event dependency feature into a sensing head, and outputting a target detection result by the sensing head. The method solves the problems of noise suppression, topological mapping and hierarchical expression in event data, has good application prospects and popularization value, and is particularly suitable for real-time target sensing tasks in complex dynamic environments such as automatic driving and robot navigation.

The invention relates to the technical field of medical image processing, in particular to a nuclear magnetic image brain tumor detection method and system, and the method comprises the steps: obtaining an initial nuclear magnetic brain tumor image, taking a dual-convolution cross-stage division network as a backbone network, taking a partial visual state space network as a feature enhancement network, lightening a YOLOv8 model, and improving the performance at the same time; in the YOLOv8 model with improved performance, the constructed re-parameterized dynamic selectable large-kernel convolutional network is used as a multi-scale feature interaction network in the neck structure, and the performance of the YOLOv8 model is further improved by using re-parameterization, so that the improved YOLOv8 model is obtained; performing iterative optimization training on the improved YOLOv8 model by using the initial image data set to obtain a nuclear magnetic image brain tumor detection model; and inputting the initial image data set into a nuclear magnetic image brain tumor detection model for detection, and outputting a nuclear magnetic brain tumor detection result. According to the invention, the accuracy and efficiency of brain tumor detection can be improved.

The invention provides a surface deformation monitoring and classifying method based on InSAR and deep learning, which comprises the following steps: (1) collecting multi-scene time sequence SAR images and DEM data of a monitoring area, (2) carrying out registration, interference and DEM difference on the multi-scene time sequence SAR images, (3) selecting PS pixels by using amplitude deviation and a coherence coefficient threshold value, (4) linking the PS pixels to construct a spatial network, and (5) classifying the spatial network. (6) recovering deformation information of PS monitoring points; (7) performing primary classification on registered SAR images by using a random forest; (8) performing secondary classification on the SAR images by using primary classification samples and a ViT network; and (9) performing classification, statistics and cause analysis on deformation based on a multi-classification result. According to the method, the classification precision of the SAR image classification method is improved, and the InSAR deformation can be effectively classified and analyzed by using the land classification result.

The invention discloses a software upgrading control method and device supporting multiple platforms and an automobile. The method comprises the steps that a terminal periodically and automatically detects whether available systems or application programs are updated or not; when an available system or application program is detected to be updated, intelligently selecting a corresponding idle time and a spatial network mode to download an update package according to the network condition of the terminal and a preset user update downloading setting; when the update package is downloaded, automatically detecting and analyzing the use condition of the terminal, and judging whether the terminal is in an idle state or not; the specific platform type and the upgrading strategy of the terminal are analyzed, and an upgrading scheme of the terminal is automatically generated; and when detecting that the terminal is in an idle state, automatically installing and updating in a silent manner according to the generated upgrading scheme. The invention provides the method and the system capable of automatically detecting, downloading, installing and updating, and simultaneously supports a plurality of upgrading modes, so that the use experience of a user and the safety of equipment are improved, and convenience is provided for the use of the user.

The invention discloses a streaming telemetry data plane forwarding method and device, and belongs to the technical field of communication. According to the method disclosed by the invention, stream telemetering is realized by processing the header of a service message through multi-level cache, and satellite nodes and paths in a spatial network are measured and monitored in a high-fineness manner; according to the method, the proportional sampling of the stream telemetering is realized through the stream classification list, so that the resource overhead of the stream telemetering is saved, and the occurrence of network congestion possibly caused by the stream telemetering is reduced; the end-to-end sending of the telemetering message is realized by pre-configuring the telemetering message output interface, and the telemetering message uploading process is simplified. Based on the streaming telemetry data plane forwarding method, the streaming telemetry data plane forwarding device comprises a service message processing subsystem which is used for service message analysis, processing and stream classification; the telemetering message processing subsystem is used for constructing and uploading a telemetering message; and the message forwarding subsystem is used for forwarding the service message and the telemetering message.

The invention discloses a distributed multi-level organization data space construction method and device based on a tree structure. The method comprises the following steps of: 1) constructing a data space node with autonomous management capability, which has independent operation capability and data autonomous characteristics and has native control right on data of a data space to which the data space node belongs; 2) deploying spatial network coordination nodes by using a spatial network coordination node device; 3) registering the data space node to a space network coordination node, and constructing a distributed space communication network; 4) constructing a multi-level data space tree topology based on the organization hierarchical relationship, and forming a tree structure multi-level organization data space; and 5) based on the management network of the tree structure, implementing a three-power discrete control mechanism of data control power, management power and use power, and supporting cross-domain data sharing. According to the method, data complex strip block management of huge complex organizations in the real world is mapped into a tree structure, control over the management right, the control right and the use right is achieved on the basis of the tree structure, and therefore efficient circulation and collaborative management of data among multi-level organizations are achieved.

The invention provides a segmented routing method and system for a low-orbit giant satellite base. The method comprises the following steps: S1, setting part of satellite nodes as preset satellite segment nodes; s2, enabling each satellite node in the satellite network to collect network parameters between adjacent satellite segment nodes; s3, enabling any satellite node to request spatial network data transmission from the routing calculation module through the application sensing module; s4, taking the routing calculation module as a head node of spatial network data transmission, and determining a data transmission path through a quadrant method; and S5, generating a path label stack, pressing the path label stack into a to-be-transmitted data packet header, and sending data to a next-hop satellite segment node. According to the segmented routing algorithm for the low-orbit giant satellite base, the satellite segment nodes are screened and calculated through a quadrant method, a basis is provided for selection of the satellite segment nodes, the data packets are forwarded by the appropriate satellite segment nodes, transmission delay and network congestion are reduced, and QoS guarantee of the data is ensured.

The invention is suitable for the field of communication interference monitoring, and provides a 5G millimeter wave equipment high-frequency interference monitoring method and system, and the method comprises the steps: collecting a target monitoring frequency band, dividing the target monitoring frequency band into a plurality of sub-frequency bands with the bandwidth of 20MHz, collecting the signal power spectrum density of each sub-frequency band, and calculating the signal power spectrum density of each sub-frequency band; extracting interference intensity, an interference range and a service volume parameter of a corresponding frequency band; constructing a priority ranking model and grading the interference of each sub-band; the spatial position of an interference source is positioned through multi-TRP cooperation; adjusting time slot allocation and power resources of the space-air-ground network according to an interference priority sorting result; based on an interference source positioning result and a resource allocation scheme, dynamically adjusting beam forming parameters of the phased-array antenna or switching a working frequency band; through multi-dimensional parameter acquisition and priority modeling, the influence of interference on different services is accurately quantified, so that interference processing better meets actual requirements; the space-air-ground cooperation and multi-TRP positioning technology provides a reliable basis for interference treatment.

The invention discloses a deep space network optimal transmission path calculation method, relates to the technical field of deep space network data transmission path selection, and is used for solving the problem of transmission path selection in a deep space network. The method comprises the following steps; data communication is realized, link delay, packet loss rate and environmental factors are monitored, and an optimal transmission path is selected based on a link quality score; an integrated learning and multi-agent reinforcement learning model is constructed, and the path optimization effect is enhanced; designing a completely decentralized independent learning algorithm to realize autonomous path selection; a multi-objective optimization model is adopted to dynamically balance energy consumption and performance, and an optimal path is selected; collaborative optimization among nodes is performed based on the graph neural network, and the resource utilization rate is improved. According to the method, the characteristics of the deep space environment are creatively combined, link monitoring is fused, efficient and reliable deep space network transmission path planning is realized, and the stability and the resource utilization rate of deep space communication are improved.

The invention provides a routing fast convergence method for next hop separation of a spatial network, and belongs to the technical field of communication. The method comprises the following steps: firstly, establishing a next hop group for a spatial network, distributing an array index for all possible next hop outbound interface combinations, and storing a next hop IP address and outbound interfaces in an array; and then the routing table entries are bound to the corresponding next hop groups, and a plurality of routing table entries pointing to the same next hop outbound interface share the same index. When the states of links, nodes and the like change, the routing table only needs to update the corresponding index or the next hop information corresponding to the index, and does not need to traverse each routing table item to modify the next hop and an outbound interface, so that rapid routing convergence is realized. According to the method, the routing storage resource consumption can be reduced, and the routing convergence rate is greatly improved.

The invention relates to the technical field of satellite-borne edge computing and simulation, and provides a satellite-borne edge computing task unloading semi-physical simulation system. Comprising a physical satellite-borne edge computing device, a software virtual satellite-borne edge computing device, a ground user device, a space environment simulator, a container and cloud management base, a resource data distribution module and a task unloading scheduling module. The physical satellite-borne edge computing device and the software virtual satellite-borne edge computing device jointly construct a cloud side end cooperative computing cluster, the ground user device is used for initiating a computing task request, the space environment simulator is used for simulating spatial network characteristics, and the container and the cloud management base are used for achieving all-node unified management and control. The resource data distribution module is used for issuing and subscribing node resources and environment information, and the task unloading scheduling module is used for executing a task unloading decision. The problems that in the prior art, on-orbit verification cost is high, a pure software simulation environment is distorted, algorithm credibility is insufficient, and a satellite-borne data set is scarce are solved.

A method for measuring disaster resilience of urban public services includes the following steps: constructing a residence-service-transportation space network under normal conditions; removing, through disaster simulation, failed road segments and function nodes to construct a damaged residence-service-transportation space network; calculating a per capita accessible public service of each residential node to represent network performance; calculating a change rate of the per capita accessible public service level before and after the disaster; and drawing a relation curve between the change rate and the disaster intensity to measure the disaster resilience of the urban public services.

The invention provides a shale spatial network structure construction method and device, and belongs to the field of petroleum engineering, and the method comprises the steps: constructing a first spatial network structure of shale inorganic substance pores; converting inorganic substance pores in a preset area of the first spatial network structure into organic substance pores, and endowing the organic substance pores with pore size values to obtain a second spatial network structure; in the second spatial network structure, a contact angle is applied to the organic matter pores and the inorganic matter pores. The device comprises a network structure construction module, a new structure conversion module and a parameter endowing module. According to the method, organic matter pore space distribution, inorganic matter pore space distribution, pore size value distribution and wettability difference of the shale are considered, the construction speed of the shale spatial network structure is increased, and the calculation amount of construction of the shale spatial network structure is reduced.

The invention relates to a deep learning-based structure anti-seismic performance evaluation system, which comprises a data acquisition module, a data preprocessing module, a feature extraction module, a numerical simulation module, a deep learning model training module, an evaluation and verification module, a visualization module and a model updating and maintenance module, the data preprocessing module is used for data preprocessing, the feature extraction module is used for data feature extraction, the numerical simulation module is used for simulating seismic response of a structure, the deep learning model training module is used for constructing a deep learning model, the evaluation and verification module is used for model evaluation and verification, and the visualization module is used for evaluation result display. And the model updating and maintaining module is used for updating and maintaining the model. According to the invention, an improved seismic data feature fusion extraction algorithm is proposed for feature extraction, an improved seismic perception depth state space network is proposed for model construction, and a better scheme is provided for a deep learning-based structure seismic performance evaluation system.

The invention discloses a space computing power network task migration method and system based on dynamic environment perception, and relates to spaceflight electronics and data processing technologies, and the method comprises the steps: determining that a user node obtains a computing resource needed by a computing power service from a satellite node in a space computing power network; calculating a task migration moment caused by satellite node movement and an alternative satellite set capable of receiving tasks according to the dynamic environment information; based on a candidate satellite set, an optimal satellite is screened out according to different user expected targets, before the migration moment arrives, a calculation task is migrated to the selected satellite in advance, and seamless continuity of services is guaranteed; and for the high-priority task, carrying out redundancy migration on the alternative scheme without computing resource intersection. According to the method, the problems of low efficiency, service interruption caused by sudden faults, multi-target optimization conflicts, resource shortage scene migration failure and the like of a traditional migration algorithm in a spatial network topology dynamic scene can be effectively solved.

The invention provides a wind power plant inspection system and method based on cooperation of an unmanned aerial vehicle group, and the system enables the inspection tasks to be carried out in parallel through the cooperation of the unmanned aerial vehicle group, thereby improving the inspection efficiency. Meanwhile, the three-dimensional space network and the task allocation algorithm are applied, so that the planning of the inspection path is more accurate and reasonable, and the inspection cost is reduced; in addition, compared with manual inspection, unmanned aerial vehicle inspection has higher safety, and risks of personnel in high-altitude operation are avoided; finally, through cooperation of the unmanned aerial vehicle groups, the inspection coverage range is expanded, the inspection period is shortened, the operation state of the wind power plant can be monitored and analyzed in time, and the defects that in the wind power plant inspection process, the inspection efficiency is low, the detection coverage is incomplete, and the environmental adaptability is poor are overcome.

The invention discloses a multi-connection management method suitable for a high-orbit and low-orbit fusion satellite communication terminal, and the method comprises the steps: building a communication connection with a high-orbit satellite, and obtaining the ephemeris information of a low-orbit satellite; a visible time window of the target low earth orbit satellite is predicted, and the composite link quality at the future moment is dynamically evaluated; performing look-ahead multi-connection state management based on the visible time window and the composite link quality; wherein the multi-connection state management comprises a preparation state of triggering antenna pre-pointing before a target low-orbit satellite is visible, and a transition state of triggering high-orbit and low-orbit double-link simultaneous transmission before low-orbit satellite coverage is finished. According to the method, the defect that a communication blind area exists in the link handover period of traditional passive response type switching is overcome, the cross-track link is firstly established and then broken, and the continuity and high reliability of service data transmission in a complex space network are effectively guaranteed.

The present application relates to a kind of based on heat-power collaborative perception's crystallizer sticking breakout intelligent prediction method, belong to continuous casting safety monitoring and intelligent manufacturing technical field.It includes: in the matrix arrangement MEMS thermal sensor array on crystallizer copper plate, copper plate local temperature and heat flux density are synchronously detected online;Online detection crystallizer friction force;Single time network model and group space network model are constructed, and thermal quantity dynamic characteristic and space propagation characteristic are extracted;Thermal quantity neural network model is constructed to the mode recognition of characteristic waveform;Friction force signal is decomposed by empirical mode, and trend quantity change characteristic is extracted;Friction force neural network prediction model is constructed, and abnormal state is identified by forecast deviation;Steel grade composition crack sensitive index and other auxiliary judgment index are calculated;Finally, through the weighted score and the multi-source information fusion decision maker of dynamic threshold correction output sticking breakout prediction grade.

The application discloses a congestion-aware routing method for a deep space network. In order to solve the problem of redundant inter-satellite forwarding and transmission efficiency reduction caused by the lack of remote link queue state awareness in a distributed long-delay deep space network, an exogenous mapping load element is maintained for each contact at each node. When the node perceives the loop risk caused by inconsistent queue states through the quasi-loop data packet, the delay increment interval of unknown remote traffic is solved by using the locally known routing information without explicit information exchange, and the exogenous mapping load is updated accordingly. Then, the load is mapped to the subsequent route estimation time cost calculation as an available capacity penalty term, so as to actively suppress the selection of contacts with potential congestion risk in the forward routing stage. The application can improve the remote traffic awareness capability of the long-delay distributed network, reduce the redundant inter-satellite relay, and improve the end-to-end transmission efficiency and reliability of the deep space network without increasing the signaling overhead.

This application discloses a training method, apparatus, device, and storage medium for a joint angle prediction model, relating to the field of computer technology. The method includes: acquiring training sample data, which includes skeletal parameters, sample wrist joint pose sequences, and arm angle labels for the sample wrist joint pose sequences; obtaining arm angle feature information based on the sample wrist joint pose sequences using a selective state-space network of the joint angle prediction model to be trained; obtaining elbow position prediction information based on the arm angle feature information and skeletal parameters using a differentiable kinematic layer of the joint angle prediction model to be trained; and iteratively updating and training the joint angle prediction model to be trained based on a preset objective function, the training sample data, the arm angle feature information, and the elbow position prediction information to obtain a trained joint angle prediction model.

The application discloses a space network networking method and device, a network resource arrangement platform and a storage medium. The method comprises the following steps: in the case that a UAV service accesses a network, the position of the UAV performing the UAV service is determined; the service score corresponding to the cell within the preset distance range from the position of the UAV is determined; the preset number of cells with the highest service score are determined as the space candidate working cells, and the number of adjustable beams of the space candidate working cells is determined; and the space-to-air beam and the ground-to-air beam of the space candidate working cells are determined and set according to the number of adjustable beams. The application solves the technical problems that the UAV space coverage scheme in the related art mostly needs to add equipment for transmission transformation, the cost is too high, the scheme of covering the space by directly using the existing site resources has too great influence on the ground coverage, and the beam resources for covering the space are wasted.

The application discloses a self-iteration-based deep subspace training method and device, which comprises the following steps: a pre-training step, in which a first optimization function is minimized to train a deep subspace network, so as to initialize a similarity matrix; a training step, in which when the iteration number t is less than a first iteration number, a self-expression coefficient matrix is fixed, the second iteration number is iterated, the deep subspace network parameters are updated by minimizing a second optimization function; the deep subspace network parameters are fixed, the third iteration number is iterated, the self-expression coefficient matrix is updated by minimizing a third optimization function, the similarity matrix generated in the tth iteration is updated according to the updated self-expression coefficient matrix, and finally the update of the similarity matrix in the first t iterations is realized; and the iteration number t is increased by 1, and the training step is repeated. The application introduces the idea of self-iteration, supervises the training of the model through the results of the previous training, and can discard the previous training results, so that the memory and the calculation resources are saved.

The present application provides an information security interconnection method for a hybrid space network. Among them, obtain the communication connection requirements requested by the user; based on the communication connection requirements, query multiple space network nodes that match the communication connection requirements in a pre-established space network node set, and generate initial routing paths corresponding to the multiple space network nodes; perform optimization processing on the initial routing paths corresponding to the multiple space network nodes to generate target routing paths for the multiple space network nodes; use a pre-created security policy to encrypt the target routing paths of the selected space network nodes, and batch-apply the encryption operation to the target routing paths of the remaining multiple space network nodes. The technical solution provided by the present application can significantly reduce the time delay of data transmission and improve the overall efficiency of space network communication.

The embodiment of the invention provides a hypoxia risk spatio-temporal distribution prediction method and device, equipment and a medium, and belongs to the technical field of safety monitoring. The method comprises the following steps: collecting geographic coordinates, low-oxygen threshold values and real-time oxygen contents of all monitoring nodes in a region; calculating an edge generation index based on the node coordinates and a threshold value, and if the index is lower than a preset value, connecting the two nodes (regarded as similar oxygen change trends) to form a node network; the connected nodes are clustered into monitoring sets, and the number of low-oxygen nodes (the nodes with the oxygen content lower than the threshold mean value of all the nodes) in each set is counted; the oxygen growth rate of each node is calculated, and a hypoxia condition prediction index of the set is generated by combining the number of hypoxia nodes in the set, the total number of nodes, the average growth rate and the average oxygen content; and finally, plotting a set area of which the prediction index exceeds a threshold value on the map as a hypoxia risk area. According to the method, the low-oxygen high-risk area is identified and drawn based on the spatial network and set division and comprehensive indexes, and accurate prediction of the low-oxygen area is realized.

The invention discloses an autonomous positioning method and terminal equipment, and the method comprises the steps: obtaining a first observation position of a mobile body in a world coordinate system at a current moment, the first observation position being determined according to a positioning signal of a positioning sensor of the mobile body at the current moment; matching the first observation position with local road information in a road network map to obtain a target road point where the mobile subject is currently located, the target road point being a projection point of the first observation position in the road network map; calculating road network observation noise at the current moment by taking the position of the target road point as road network observation quantity according to the spatial network attribute information of the target road point; and according to the road network observation noise, determining an estimated position of the mobile body in the world coordinate system at the current moment so as to update the state of the mobile body according to the estimated position.

The invention discloses an unsupervised anomaly detection method for an aviation composite material hole wall, and relates to the technical field of aviation composite material processing detection, and the method comprises the steps: carrying out the fusion of public texture data and a gray-scale map of a hole wall through an anomaly mask to construct an anomaly training sample, and carrying out the manual annotation, in addition, the Mama state space model is introduced into the anomaly detection field to construct a visual state space network model of a Unet structure, and the difference between a prediction mask generated by the visual state space network model and an anomaly mask is evaluated to obtain a loss function which can be used for training the model; by means of the method, under the condition that defect data does not need to be marked, CFRP complex fiber textures and unknown defect types can be effectively handled, and the accuracy of detection is improved. And an efficient and accurate solution with a wide application prospect is provided for automatic detection of the inner wall defects of the aviation composite hole.

In one embodiment, a method is disclosed, comprising: receiving a packet; processing the packet in a Control Unit–User Plane (CU-UP) as a user-space application with kernel-bypass networking; performing packet Input / Output (I / O) by the CU-UP user-space application, wherein the CU-UP performs Internet Protocol (IP) validation on received user-plane packets before processing Packet Data Convergence Protocol (PDCP), Service Data Adaptation Protocol (SDAP) and General Packet Radio Service Tunnelling Protocol (GTPU) protocol stack and performing direct I / O to a Network Interface Controller (NIC) for sending the packet over a network to a Distributed Unit (DU). The method may further comprise using a containerized CU-UP. The method may further comprise using a plurality of worker threads. The method may further comprise using a polling user space networking accelerator framework.

The present application relates to the technical field of data transmission management, and more particularly to a data flow circulation method across data spaces, which determines a plurality of data flow circulation spaces by acquiring node parameters of adjacent device nodes on a data transmission path, determines data flow circulation characteristic time periods by determining a plurality of circulation state explicit nodes on traffic variation curves of different data flow circulation spaces, determines whether there is an invalid circulation phenomenon by performing continuity analysis on the data flow circulation characteristic time periods determined according to a first constraint condition, and determines whether to transmit data of the space network cache node to a target device node having an interface mapping relationship according to a second constraint condition by setting a space network cache node between adjacent device nodes. The present application performs associated recognition analysis on the data flow circulation states of adjacent nodes across data spaces, thereby avoiding waste of data flow circulation resources caused by redundant transmission, response delay and other problems.