Abstract: An asymmetric cross-modal large-model knowledge transfer method for remote sensing includes: acquiring a training sample pairs including a sample RGB image and a sample MS image corresponding to a same scene classification; inputting the sample MS image into a teacher model; determining a first image feature extracted by the teacher model from the sample MS image; determining a first scene classification, obtained by the teacher model according to the first image feature, as a pseudo label; inputting the sample RGB image into a student model; determining a second image feature extracted by the student model from the sample RGB image; determining a second scene classification obtained by the student model according to the second image feature; and training the student model according to a difference between the second image feature and the first image feature and a difference between the second scene classification and the pseudo label.

Abstract: The present application discloses a fiber optic sensor and a measurement method, apparatus, and storage medium. By performing, based on the microwave signal, intensity modulation on the optical signal, then inputting the modulated optical signal into the fiber optic containing the weak reflection grating array, a reflected signal is obtained. Thereafter by performing dispersion compensation on the amplified partial reflected signal, and based on the dispersion-compensated reflected signal and the non-dispersion-compensated reflected signal, the change amounts respectively corresponding to positions in the fiber optic containing the weak reflection grating array are determined.

Abstract: An information propagation prediction method based on a sequential hypergraph neural network with co-attention fusion. The method includes three modules: a user feature learning module learning a user embedding by utilizing a graph convolutional neural network; a cascade feature learning module constructing a sequential hypergraph neural network based on equivariant diffusion to capture a complex cascade irregular connection so as to learn a cascade embedding of internal and external features of an encapsulated cascade structure; and a feature fusion and prediction module learning an interdependence between cascade features and user features by means of a co-attention mechanism so as to capture a complex relationship and interaction between the cascade features and the user features, and then calculating a possibility of potential user infection.

Abstract: A method for detecting network attack based on kernel operating characteristics of a software switch, comprising: collecting kernel operating characteristic data of the software switch during network management and packet forwarding of the software switch, wherein the kernel operating characteristic data of the software switch can reflect characteristic data of a fine-grained operating state of a network; preprocessing the kernel operating characteristic data of the software switch; and inputting the preprocessed kernel operating characteristic data of the software switch into a pre-trained attack detection model to detect a potential attack behavior in a network. The method is applicable to all scenarios where the software switch is applicable, especially a software-defined network and a cloud data center, an industrial Internet, 5G, edge computing based on the software-defined network.

Abstract: The present invention discloses a two-dimensional photonic convolutional acceleration system and device for convolutional neural network, comprising: a multi-wavelength light source, a signal source to be convolved, a modulator, a dispersion module, a 1×M power divider, an optical fiber delay array, a microring weighting array chip, a convolutional kernel matrix control unit, a trans-impedance amplifier array, and an acquisition and processing unit. The present invention realizes two-dimensional convolutional acceleration based on wavelength-time interleaving technology, a single modulator can realize the optical domain loading of the signal, and the convolutional operation speed is only limited to the speed of the modulator.

Abstract: A method and device for interpreting a graph neural network based on FPGA acceleration propose to use FPGA hardware to accelerate interpretation process of the graph neural network oriented to node classification in parallel, and improve node traversal and shortest path search of BFS, thereby optimizing requirements of algorithm calculation and storage, and accelerating generation of interpretation results. During calculating HN values, the present disclosure optimizes multiplication operation using the matrix characteristics, transforms the dense matrix multiplication into sparse-dense matrix multiplication, and optimizes the resource occupation using multi-PE parallel processing, greatly improving performance of graph neural network interpretation acceleration.

Abstract: The present disclosure discloses a method and an apparatus for data processing, a storage medium and an electronic device, where for each second unit in the embodiments of the present disclosure, a plurality of communication links are provided between the first unit and the second unit. The first unit, in response to a data operation request, sends the data operation request to the second unit through the plurality of communication links between the first unit and the second unit. The second unit processes the target data to be processed according to the data operation instruction in the data operation request to obtain a processing result, and sends the processing result to the first unit via a plurality of communication links. The first unit executes a response strategy for the data operation request based on the processing result.

Abstract: An endogenous security protection method for configuration data in an operating system of a network node includes: when a data backup module receives a network message flow, target configuration data is backed up in the data backup module, a distribution module send the received network message flow to each dynamic heterogeneous redundant executer respectively, each dynamic heterogeneous redundant executer stores the target configuration data, a synchronization module read the target configuration data stored by each dynamic heterogeneous redundant executer respectively, a judgment module performs consistency judgment, the synchronization module performs online-offline scheduling on the executers based on a judgment result, a target executer with data disorder is taken offline, a candidate executer is brought online, and the candidate executer obtains the target configuration data from the data backup module.

Abstract: A training data effectiveness evaluation method includes: acquiring a training set, where the training set is acquired by uniform downsampling from target data; acquiring a test set, where the test set includes at least one benchmark test set and at least one correlated test set; training a probe model based on the training set; testing the probe model based on the test set, and recording test metrics; generating an observation plot based on the test metrics, where the generating the observation plot includes: establishing a Cartesian coordinate system with a test metric of the benchmark test set as a horizontal axis and a test metric of the correlated test set as a vertical axis, and plotting key points in the Cartesian coordinate system based on the test metrics; and evaluating effectiveness of the target data based on the observation plot. The present disclosure has the following advantages.

Abstract: A method of signaling interaction in 5G space-ground integrated heterogeneous network architecture is provided, which enables publicly available data for trusted satellite discovery to be registered to the 5G core network based on the function framework of the 5G core network. When searching for satellites, a gNB can utilize the publicly available data of the trusted satellite registered in the 5G core network to speed up satellite searching, improve satellite link services, and filter out untrusted satellites.

Abstract: A process for generating an intermediate representation methodically compiles a neural network into a computation graph. First, a distinct node is built for every tensor variable within the graph, and this node is linked to a collection of pointers that reference the variable. Next, the method undertakes an analysis of the constraint relationships among these tensor variables. Using this information, it iteratively builds a topological graph that serves as the intermediate representation. Finally, this representation allows for the crucial step of analyzing variables that use different aliases but point to the same memory location, enabling the system to efficiently allocate a register for these aliased tensor variables.

Abstract: A method for incremental metapath storage and dynamic maintenance is provided, which includes, reformatting metapath instances, from a designated heterogeneous graph and of a designated metapath type, into path graphs; executing graph updating tasks and performing dynamic maintenance on the updated path graphs, traversing the path graph to obtain the location of metapath updates and update the path graph; for metapaths with length greater than 2 and with symmetrical central portion, central merge operation is performed to simplify path graph and perform subsequent restoration operation; and directly perform restoration operation on path graphs that do not meet the merging conditions. The present disclosure utilizes characteristics of graph update to obtain locality of metapath updates, and combines internal relationship characteristics of metapath instances to greatly speed up metapath generation and achieve real-time inference of dynamic heterogeneous graph models.

Abstract: An adaptive adjustment method of packet-level transmission priority for delay guarantee in programmable networks. The method realizes the adaptive adjustment of packet-level transmission priority in programmable networks from three aspects to satisfy the preset transmission delay requirements, namely: adaptive adjustment of priority in programmable switches based on processing delay state and switch queuing state, adaptive adjustment of priority among programmable switches based on transmission delay in upstream switches, and adaptive adjustment of global parameters based on packet transmission delay satisfaction, so as to realize the packet-level transmission delay guarantee in different positions with different time scales.

Abstract: The present disclosure provides a multiplexer and a detector. The multiplexer includes a dielectric base plate, a connection structure, and a plurality of bandpass filters with different operation frequencies. A conductive thin film layer is disposed on a side plane of the dielectric base plate, the conductive thin film layer includes a signal wire and one or more grounding plates on a side of the signal wire. The connection structure is disposed on a side, on which the conductive thin film layer is provided, of the dielectric base plate, and includes a main branch and a plurality of branches, where the main branch is connected to the plurality of branches respectively, and the main branch serves as an input port of the multiplexer. Each of the plurality of bandpass filters with different operation frequencies is disposed on the side, on which the conductive thin film layer is provided, of the dielectric base plate, and is connected to the signal wire and the one or more grounding plates.

Abstract: A 6.4 Tbps silicon-based photonics engine transceiver chip module for high-speed optical communication manufactured based on processing techniques of semiconductors such as silicon-on-insulator (SOI) and indium phosphide (InP). The photonics engine transceiver chip module uses a silicon photonic chip as a substrate, and optical chips of an InP laser and an optical amplifier are heterogeneously integrated with the silicon photonic chip through bonding or flip-chip soldering. As a pump light source, the laser generates a soliton-based optical frequency comb by using an ultra-low loss silicon nitride (SiN) resonator cavity, and can be used as a multi-wavelength laser. This reduces use of a single-wavelength laser chip, reduces a power consumption and heat conduction of a laser in an optical chip of a photonic engine, and improves an integration level of an optical device. The optical frequency comb generates an optical carrier with wide bandwidth coverage and a large quantity of wavelengths.

Abstract: An event prediction method based on a satellite orbit threat domain knowledge graph is provided. By constructing a knowledge graph of the satellite orbit threat domain, and utilizing steps such as meta-path extraction, hyperedge construction, feature encoding, and feature aggregation, target features that can comprehensively and accurately describe each entity and the complex relationships between each entity in the satellite orbit threat domain are obtained, and a prediction model is trained by using the target features of each entity.

Abstract: The present disclosure provides a man-machine interactive method and apparatus for a long-endurance operation based on a dynamic time pressure, belonging to the technical field of man-machine ergonomics. The method specifically includes: constructing a maximum performance-time pressure-time function curve based on a performance-time pressure function curve corresponding to a long-endurance operation; calculating a response time of a next long-endurance operation based on a historical response time of man-machine interaction after the current long-endurance operation is completed; calculating a maximum performance value corresponding to an initial time of the next long-endurance operation and a time pressure corresponding to the maximum performance value based on the maximum performance-time pressure-time function curve; and calculating an optimal reserved time corresponding to the maximum performance value based on the response time of the next long-endurance operation and the time pressure.

Abstract: The present invention discloses a method and an apparatus for rebuilding a relightable implicit human body model. A human body is represented as a deformable implicit neural representation, and a geometric shape, material attributes, and ambient lighting of the human body are decomposed to obtain a relightable and drivable implicit human body model. In addition, a volumetric lighting grid including a plurality of spherical Gaussian models is introduced to represent complex lighting with spatial variation, and visible probes capable of changing in position with change in human pose are introduced to record dynamic self-occlusion caused by human motion. With the method, drivable implicit models capable of being used for high-fidelity human body relighting may be generated in cases of sparse video input and even monocular input.

Abstract: Disclosed in the present invention is a terahertz kinetic inductance bolometer, including a superconducting thin film layer, a terahertz antenna, a cutoff layer and a Si substrate, wherein the superconducting thin film layer and the terahertz antenna are respectively deposited on the cutoff layer, and the cutoff layer is deposited on the Si substrate; the superconducting thin film layer includes a superconducting feeder line, an inter-digital capacitor and an inductor coil; the inter-digital capacitor is connected with the inductor coil in parallel to form an oscillation circuit; the terahertz antenna is adjacent to the inductor coil and is used to convert a received terahertz signal into heat so that the inductor coil produces an inductance change; a resonance frequency in the inter-digital capacitor changes through the inductance change; and the superconducting feeder line receives the varying resonance frequency, through which an light intensity of the terahertz signal can be obtained to complete the detec

Abstract: The present disclosure provides an exception handling system and method for a space environment, and a detection device. The exception handling system includes: a detection device, an interrupt controller, and a to-be-detected storage device, the to-be-detected storage device includes a statistical unit and registers; the statistical unit is configured to read monitoring data from a specified position of the to-be-detected storage device, generate statistical data based on the monitoring data and reference data written into the specified position in advance, and store the statistical data in the registers; the detection device is configured to read the statistical data from the registers, determine an exception detection result, generate an interrupt signal based on the exception detection result, and send the interrupt signal to the interrupt controller; and the interrupt controller is configured to perform an exception handling based on the interrupt signal.