16 results about "Time-varying network" patented technology

This invention provides a satellite network topology management method and system based on feeder link switching. The method includes: constructing a continuously time-varying network topology model, and storing the availability sequence, available bandwidth sequence, and propagation delay of each link; responding to new service requests and obtaining the source satellite node and the target ground station; selecting the target feeder link and its effective connection period based on link status information; screening inter-satellite links that are continuously connected within the time period to form a candidate set, and calculating the average propagation delay and minimum available bandwidth of each link to construct a temporary topology; calculating the transmission path from the source satellite node through inter-satellite links and the target feeder link to the target ground station on the temporary topology; and locally updating the available bandwidth sequence of each link on the path according to the path and bandwidth requirements. This invention achieves efficient management of highly dynamic satellite-ground networks through feeder link event-driven and continuously time-varying modeling, improving service continuity and reducing management overhead.

The method comprises the following steps: S1, dividing a global scheduling period into a peak window, a flat peak window and a valley window according to a task density distribution; S2, assigning different fixed discrete steps to the peak window, the flat peak window and the valley window; S3, establishing node coupling and arc segment continuity constraints at the junctions of windows with different precisions; and S4, outputting a model and optimizing. The method has the advantage of effectively suppressing calculation redundancy in a non-event triggering mode.

This invention provides a wind power interval prediction method based on mode decomposition and reconstruction and attention-based temporal network, belonging to the field of wind power interval prediction technology. The method includes: acquiring historical monitoring data of wind farms and performing empirical mode decomposition to obtain intrinsic mode function (IMF) components, which are then superimposed and reconstructed to obtain reconstructed IMF components; constructing a wind power output prediction model based on a Transformer encoder by introducing a bidirectional long short-term memory (LSTM) neural network; dividing and normalizing the reconstructed IMF components, training and predicting using the wind power output prediction model, obtaining prediction results, and superimposing them; dynamically reshaping the model through adaptive kernel density estimation to obtain a dynamic power prediction interval, thus completing the temporal network wind power interval prediction. This invention achieves efficient data processing, effectively reduces the non-stationarity and volatility of wind power data, avoids computational redundancy, and improves prediction efficiency.

This invention discloses a method for reconstructing weak transient electromagnetic signals in wells based on a bidirectional temporal Kolmogorov-Arnold network. This method addresses the problems of extremely low amplitude and susceptibility to noise in the late-stage transient electromagnetic signals in wells. First, the noisy response sequence undergoes temporal channel unification, baseline correction, drift suppression, outlier suppression, normalization, and optional amplitude logarithmic mapping. The late-stage window is then determined based on diffusion attenuation laws. Subsequently, a bidirectional temporal network consisting of a forward TKAN encoder and a backward TKAN encoder is constructed. Bidirectional hidden features are fused for each time channel, and a reconstructed sequence is output. A learnable spline function based on B-spline basis functions is introduced into the TKAN nonlinear mapping branch to enhance cross-scale nonlinear expression capabilities. Through this structural design, the method can stably recover weak transient electromagnetic signals in wells during the late-stage phase with ultra-low signal-to-noise ratios, improving the effective late-stage window and the availability of deep information.

This invention discloses a method and system for generating 3D digital human avatars based on audio-driven temporal feature enhancement. The method includes: initializing Gaussian units and extracting features based on target video and audio; constructing a dual-branch personalized temporal network, where the second branch uses a temporal feature enhancement module to output temporally smooth deformations; pre-training a general motion field to learn common movements and combining it with identity discrimination loss to promote feature decoupling; freezing the general field during personalized training and combining its basic deformations with the temporally smooth deformations of the personalized temporal network through an adaptive fusion mechanism to generate a dynamic Gaussian representation; and finally, rendering a 3D digital human video with synchronized shape and stable temporal sequence based on the driving audio. This invention achieves high-quality, highly consistent digital human generation with few samples.

The invention belongs to the technical field of water meter assembly. The invention provides a single-workbench water meter assembly method and system based on body intelligence. A four-layer framework of perception, prediction, planning and execution is adopted. The sensing module outputs a water meter part state and a structured scene map based on the 3D scene reconstruction network; the prediction module generates collision risk and assembly execution time prediction based on the Transform multi-task sequential network; the planning module generates an optimal assembly action sequence through hierarchical reinforcement learning; and the execution layer executes operation in a position-force hybrid control mode, and feeds back data in real time to form a closed loop. According to the scheme, the problems that traditional manual assembly is low in efficiency and existing automatic equipment lacks self-adaptive capacity are solved, the defects that sudden working conditions are difficult to deal with and multi-model adaptation is poor are overcome, the assembly efficiency and consistency are improved, manual intervention is reduced, assembly interruption and part damage are avoided, and flexible automation of the whole water meter assembly process is achieved.

This invention discloses an AI-assisted intelligent schistosomiasis control information monitoring, early warning, and management method and system, relating to the field of deep learning technology. The method includes: acquiring multi-source monitoring data through an intelligent data acquisition terminal network; constructing a multimodal spatiotemporal knowledge graph and a multi-timescale feature library; constructing a deep temporal network with enhanced spatiotemporal attention based on the multimodal spatiotemporal knowledge graph to capture the spatiotemporal evolution pattern of media propagation and generate predicted infection numbers for each grid unit; extracting historical weather features and infection number sequences from the multi-timescale feature library, calculating weighted baseline values ​​for weather-similar days and moving percentile anomaly reference values, and fusing them into a dynamic early warning baseline. This invention significantly improves prediction accuracy and interpretability in data-sparse areas by capturing key historical fragments through an attention mechanism in the temporal dimension and aggregating neighborhood propagation information through a graph structure in the spatial dimension.

This invention provides a method and related apparatus for joint scheduling of task offloading and routing planning in low-Earth orbit (LEO) satellite networks based on time-spreading graphs, belonging to the field of wireless communication technology. The method constructs a dynamically time-varying LEO satellite network; represents the constructed network as a directed network topology graph based on time series using a time-spreading graph; constructs a joint scheduling model using the time-series directed network topology graph; sets constraints on the joint scheduling model; solves the objective function of the constructed model based on the set constraints to obtain the optimal result; and performs joint scheduling of task offloading and routing planning on the LEO satellite network based on the obtained optimal result to obtain the joint scheduling result. This invention solves the problem of poor global performance optimization caused by not fully considering the coupling relationship between task offloading and routing planning in dynamically time-varying network scenarios.

The application provides a method for improving controllability of a symmetric network by time segmentation, and relates to the technical field of network performance optimization. The method adopts a time segmentation method to divide a symmetric network into a symmetric time-varying network composed of multiple snapshots, and realizes the structural controllability of the whole network through the control of each snapshot. Given a symmetric network, the black and white coloring is performed through a breadth-first search algorithm for classification; the maximum matching of edges in the symmetric network is found; the undirected cactus is constructed according to the unmatched nodes and the matched edges; the network graph composed of each undirected cactus is used to construct a snapshot, and the number of snapshots is the same as the number of undirected cacti. When a symmetric network is divided into a symmetric time-varying network composed of multiple snapshots, the time segmentation method can effectively reduce the number of drive nodes in the symmetric network and improve the network controllability.

This invention discloses a method, system, device, and storage medium for recognizing human behavior. The method includes: generating an image frame sequence based on acquired static and / or dynamic image information of the human behavior to be recognized; inputting the image frame sequence into an optical flow feature extraction network and / or a lightweight network and / or a temporal network for human behavior recognition to obtain the behavior category of the human being to be recognized. This invention achieves human behavior recognition based on optical flow feature extraction networks, lightweight networks, and temporal networks, mitigating the influence of adverse factors such as network depth, light intensity, external object occlusion, and shooting orientation, improving recognition speed and accuracy, and achieving better recognition results.

This invention relates to the field of wearable motion monitoring and human motion analysis technology, specifically to an upper limb motion estimation method based on motion semantic constraints. The method includes simultaneously acquiring IMU and sEMG signals; performing time alignment processing on the IMU and sEMG signals to obtain a multimodal input sequence; processing the multimodal input sequence through a lightweight temporal network to generate prior information; inputting the prior information into a semantic-action constraint transfer layer to obtain a constraint vector; inputting the IMU data sequence into an upper limb motion estimation network to output correction information; wherein the upper limb motion estimation network includes multiple temporal convolutional blocks, and generating modulation parameters for each temporal convolutional block based on the constraint vector; superimposing the correction information with the prior information to obtain the final estimate. This invention introduces motion semantic constraints to solve problems such as long-term drift, sensitivity to wearing changes, and insufficient cross-individual generalization in upper limb motion estimation.

This invention relates to the field of network security technology, specifically disclosing a network threat detection method and system based on unified clustering. The method includes: in a temporal network graph, nodes represent network entities, and edges represent communication relationships between network entities; the temporal network graph is input into a pre-trained unified graph clustering network; through parallel node-level clustering branches and graph-level clustering branches in the unified graph clustering network, node-level node clustering results and graph-level subgraph clustering results are output respectively; based on a preset joint contrastive learning objective, the node-level clustering results and the graph-level clustering results are collaboratively optimized, and a threat detection report containing the abnormal network entities and the attack patterns is output. This allows for the simultaneous identification of abnormal network entities and discovery of attack patterns within a unified framework, and outputs accurate malicious host identification results and clear attack pattern classification results.

This application provides an on-demand routing intelligent agent system and generation method for low-Earth orbit (LEO) satellite networks, relating to the field of satellite communication technology. The intelligent agent system includes a planning and decision-making module, a network perception module, and an execution module. The planning and decision-making module includes a large model integrating carefully designed system prompts and parses user request text to obtain communication request parameters. The network perception module is used to perceive the time-varying network state of the LEO satellite network and output a network topology map. The execution module includes a satellite access tool and a routing selection tool. The satellite access tool is used to determine the uplink and downlink access satellites corresponding to the latitude and longitude coordinates of the originating and ending users based on the network topology map and the uplink and downlink access satellites, using QoS parameter values ​​as constraints and a routing calculation strategy corresponding to the QoS parameter type, to determine the routing path between the uplink and downlink access satellites, thereby improving the service quality and intelligence level of the LEO satellite network.

This invention provides a dynamic compensation method for the heat-sealing temperature of laundry detergent pods that considers fluctuations in the thickness of the water-soluble film. By integrating microstructure pressure sensing, near-infrared spectroscopy, and polarization birefringence imaging, it achieves multi-dimensional real-time perception of film material pressure, compositional changes, and residual stress, while simultaneously acquiring and calibrating deformation, spectral, and stress signals. A multi-branch convolutional temporal network is used to extract features associated with defects, forming an equivalent thickness state vector. Combined with historical data and process environment, an interpretable gated loop unit is used to adaptively generate a heat-sealing temperature correction strategy. Through closed-loop power control and real-time quality assessment, adaptive temperature compensation under multiple variables is achieved, effectively improving sealing consistency and process intelligence.

This invention relates to the field of grain processing control technology, and discloses a rice milling control method and system based on rice processing precision. It aims to solve the problems of existing methods, such as detection lag, poor control precision, and inability to adapt to the processing requirements of new batches of brown rice. The solution mainly includes: acquiring dynamic images of rice milling using an industrial camera and extracting multi-dimensional visual features; extracting initial features of brown rice before milling and retrieving benchmark parameters from a database; dividing the milling stage according to dynamic temporal features and adjusting the sampling frequency; fusing the features through cross-attention and a temporal network to obtain a visual milling index, which is then mapped to processing precision; dynamically predicting the remaining time based on the visual index and benchmark parameters, and automatically stopping the machine when deviation and time conditions are met. This invention achieves in-situ dynamic visual perception and closed-loop adaptive control of the rice milling process, solves the cold start problem in batch-independent scenarios, and significantly improves the consistency of rice milling precision and control efficiency.

This invention relates to the field of health status assessment technology, specifically to a method and system for dynamic assessment of sub-health status based on multimodal biosignals. It includes synchronous acquisition and alignment of multi-source physiological signals, extraction of synergistic abnormal fragments, analysis of dominant modalities, construction of fusion feature vectors, generation of sub-health representations, input of deep model predictions of status and trends, delivery of personalized intervention suggestions, and closed-loop optimization of assessment feedback. This invention improves the comprehensiveness of assessment through synchronous acquisition and alignment of multimodal physiological signals, enhances adaptability to individual differences by introducing dominant modality recognition and adaptive weighting strategies, improves prediction accuracy and timeliness by combining deep temporal networks and environmental context, and constructs a closed-loop feedback mechanism to achieve dynamic iteration of assessment, intervention, and verification, providing personalized, real-time, and accurate sub-health assessment services.