238 results about "Time map" patented technology

Disclosed in the present invention is a dynamic spatial-temporal graph attention method for ship trajectory prediction, comprising the following steps: spatial graph learning: using a graph neural network to aggregate neighbor embeddings of a target entity to learn a local structure representation thereof, then calculating the effect of neighbor entities and a collaborative relationship on the target entity by means of a knowledge-aware graph attention mechanism, and finally fusing semantics and attributes from different neighbors by means of an information aggregation operation to refine the embedding of the target entity; temporal graph fusion: using a temporal graph attention layer to learn a global temporal dependency relationship of ship trajectory data, and providing interpretability for a model, then using a GRU-based sequence encoder to replace positional encoding in a conventional Transformer architecture, and capturing more local temporal dependency relationships while providing a more reasonable inductive bias for an input sequence; and feature decoding: decoding a trajectory vector having spatial-temporal attributes, generating future relative position coordinates of a ship, and achieving high-precision ship trajectory prediction.

The invention discloses an underground oil and gas well fault prediction method based on a multi-modal space-time diagram neural network, and aims to solve the problems of insufficient multi-modal feature coupling, weak space-time correlation modeling, poor real-time performance and the like of a traditional method. The method is characterized in that multi-frequency sensor data features and maintenance log semantic knowledge are respectively extracted through a time expansion convolutional network (TCN) and a BERT-BiLSTM model, and a cross-modal gating attention mechanism is designed to realize heterogeneous data dynamic fusion; an equipment space topological graph is constructed based on Delaunay triangulation, dynamic causal association between nodes is quantized in combination with transfer entropy to generate a time graph, and a fault propagation path is jointly modeled through residual space-time graph convolution; a hierarchical prediction module is constructed by adopting a bidirectional LSTM and a graph attention network (GAT), short-term fault classification and long-term equipment residual life prediction are respectively realized, and the fault prediction precision and industrial landing feasibility under complex working conditions are effectively improved.

The invention discloses a network key node identification and optimization method, system and device, and a storage medium, and relates to the field of key node identification and dynamic optimization of an electric power Internet of Things communication network, and the method comprises the steps: collecting the original data of the electric power Internet of Things, and obtaining a clean data cube in space-time alignment; constructing a dynamic space-time map, and further generating a dynamic weight matrix; evaluating the key nodes based on the dynamic weight matrix to obtain a node priority list; establishing a multi-target optimization model based on the node priority list in combination with a real-time network state; solving the multi-objective optimization model to obtain an optimal solution set, performing strategy matching and verification to obtain a verified optimization instruction set, and identifying and optimizing the network key nodes through the verified optimization instruction set; according to the method, through multi-dimensional quality portrait construction and space-time atlas analysis, network key nodes are scientifically identified and dynamically optimized, so that the stability, the safety and the performance of the network are improved.

The invention provides a real-time map route construction method and system. The method comprises the following steps: installing various sensors on an unmanned aerial vehicle to obtain multi-modal data of an environment; converting the multi-modal features into a high-dimensional embedding space, and constructing a real-time three-dimensional environment model based on a multi-modal point cloud reconstruction algorithm; deploying edge computing nodes, and distributing computing tasks to the edge computing nodes; planning a cooperative path among the multiple unmanned aerial vehicles; constructing a multi-unmanned aerial vehicle cooperative global adaptive adjustment mechanism to dynamically adjust the flight path of the unmanned aerial vehicle; and performing priority ranking on the tasks of the flight path of the unmanned aerial vehicle, constructing a path adjustment optimization mechanism according to the real-time flight condition to minimize the task failure risk, and updating the task priority and the scheduling strategy according to the feedback after each task is executed. According to the invention, a plurality of key problems in the prior art are effectively solved, and a technical guarantee is provided for successful application of the unmanned aerial vehicle in more complex application scenes.

The invention belongs to the technical field of data processing, and particularly discloses a dynamic path planning method and system for an inspection robot, and the method comprises the steps: collecting field data through a sensor, processing a laser scanning point cloud and a camera image through a positioning mapping algorithm, and fusing multi-source information to generate a real-time map. Obtaining a three-dimensional environment model containing a dynamic obstacle position; according to the three-dimensional environment model, obstacle features are extracted, a deep learning model is adopted to identify moving personnel and randomly placed goods, obstacle types and movement tracks are judged, and a classified obstacle data set is obtained; through the classified obstacle data set, the distance and the relative speed between the obstacle and the current position of the robot are calculated, and if the distance is smaller than a preset threshold value and the speed is larger than zero, high-priority interference is marked; according to the invention, the problem of inaccurate dynamic obstacle identification and obstacle avoidance in a complex scene in the prior art is solved.

The invention provides a map building and path planning method based on multi-modal SLAM, a robot system collects data through a multi-modal sensor, a data fusion module fuses the collected data by using an AI model, a map building module carries out real-time map building according to the fused data, and a path planning module carries out path planning according to the fused data. The global path planning module performs global path planning through an AI model, the actual path planning module outputs a local path by using the AI model, and the robot system dynamically adjusts and outputs an execution path according to the local path in combination with the latest data of the multi-modal sensor. The motion execution module controls the robot to move to a task position according to the output execution path, monitors the execution condition of the path in real time and feeds back the execution condition to the positioning and posture estimation module and the path planning module, and the positioning and posture estimation module updates the current positioning and adjusts the posture of the robot according to feedback data. And the path planning module finely adjusts the global path and the local path according to feedback data to improve the path planning quality.

Network computing equipment may receive one or more radio parameter measurement reports generated by one or more user equipment. A report may comprise radio parameter values measured by user equipment corresponding to signals transmitted by a radio access network node and time information corresponding to the report. The computing equipment may perform temporal analysis based on time information corresponding to one or more reports and may generate a temporal graph based on the time information. Edges of the temporal graph may correspond to connection activity of user equipment that generated the reports with respect to one or more radio access network nodes. The edges may be ranked using a graph-based model and optimally combined with anomaly scores, determined based on the measured radio parameter values, into combined anomaly scores that may be compared to a criterion to determine that a radio access network node is a fake base station.

The invention relates to the technical field of computer vision, in particular to a human body behavior recognition method and system. According to the method, a multi-head space hypergraph convolution module is arranged before each time graph convolution of an ST-GCN model, and a human body behavior recognition model is constructed; the multi-head space hypergraph convolution module constructs a non-uniform hypergraph to represent the topological relation of the human skeleton through the maximum number, which can be contained by hyperedges, of each node, and generates the output of the module in combination with a physical adjacency matrix reflecting the relation of each joint; virtual connection is also added, virtual features which are the same as the input channel dimension and the time dimension of the multi-head space hypergraph convolution module are constructed, and the virtual features and modal data features are spliced along the joint dimension and then serve as module input again, so that global semantic information of real nodes is enriched, generalization information of human body behavior modes is supplemented, and the real-time performance of the multi-head space hypergraph convolution module is improved. And stage dense connection is introduced between different layers to smooth the change degree of the features, so that the human behavior recognition precision is improved.

The invention provides a task priority and equipment state linkage path adjustment method and related equipment, and relates to the technical field of intelligent distribution center systems. Task queue information, production system feedback information and equipment state information are obtained in real time, the dynamic priority score of each task is calculated based on the information, the urgency of a production critical path and the equipment suitability are integrated in the scores, and therefore it is ensured that priority calculation focuses on the core target of avoiding production interruption. Then, the system ranks the tasks according to the dynamic priority scores, and adopts a strategy of'high priority priority planning + path reservation '; the path of the high-priority task is preferentially planned and reserved on the space-time map, and path conflicts among multiple devices are avoided from the source. The low priority tasks are then directed to avoid these reserved areas. Finally, the planned conflict-free path is issued to the robot equipment for execution, and the overall operation efficiency and stability of the intelligent distribution center system are comprehensively improved.

The invention discloses an unmanned aerial vehicle routing inspection path planning method and system for a power grid line, and particularly relates to the technical field of power grid routing inspection, and the method comprises the steps: 1, dynamically fusing a multi-source sensor and prior data, and constructing and updating a comprehensive threat field with a time attenuation mechanism and a passability map in real time; 2, decomposing an inspection line into subtask sections, and generating a reference route of each section by combining static safety cost; 3, on the basis of a real-time map in the flight of the unmanned aerial vehicle, a local optimal track is solved online through rolling window optimization of adaptive weight adjustment; and step 4, realizing multi-machine collaboration and automatic handover of blocked tasks through a block chain type distributed task state account book and an intelligent contract rule. According to the invention, the real-time avoidance capability, the environmental adaptability and the task continuity of the unmanned aerial vehicle to dynamic obstacles are remarkably enhanced, and the safety and the efficiency of power grid inspection operation are effectively guaranteed.

The invention provides an intelligent identification and early warning method and system. The method comprises the following steps: receiving real-time environment sensing data, performing dynamic matching processing, and generating a potential abnormal activity list; on the basis of the potential abnormal activity list, dynamically capturing time sequence data and spatial relevance by applying a spatio-temporal dynamic graph neural flow algorithm and through a continuous time graph convolution mechanism, and weighting key spatio-temporal feature points by adopting a feature weighting method to generate an abnormal behavior trend prediction model; based on the abnormal behavior trend prediction model, carrying out emergency degree grading analysis by using a federated transfer learning algorithm based on differential privacy, and carrying out causal relationship analysis by using a causal inference technology to generate an abnormal behavior emergency degree; and outputting a customized safety notification based on the abnormal behavior emergency degree, sending the customized safety notification to a target source group, performing continuous monitoring, and generating an intelligent identification and early warning strategy. According to the technical scheme provided by the invention, the intelligent identification accuracy and the early warning response timeliness are remarkably improved.

The invention relates to a dynamic gesture recognition method for a multi-feature fusion network under complex scene interference, and the method comprises the steps: obtaining a baseband intermediate frequency signal, carrying out the processing of the baseband intermediate frequency signal, and obtaining a distance-time diagram and a Doppler-time diagram; inputting the distance-time graph and the Doppler-time graph into a gesture recognition model to obtain a gesture recognition result; the gesture recognition model is obtained by training a lightweight neural network model by using a training set; and extracting space displacement features and gesture speed change information of the distance-time chart and the Doppler-time chart based on a DSCC module in the gesture recognition model, obtaining a feature map, combining the feature map with position codes, inputting the feature map into a Transform module for global feature extraction, and obtaining a gesture recognition result. According to the method, through extraction and fusion of multiple features, the distance, speed and time information of the target gesture is expressed more comprehensively, and the richness and expression ability of the gesture features in a complex scene are improved.

A temporal graph database system is disclosed. In various embodiments, a call to a graph temporal application programming interface (API) is received via a communication interface. An estimated cardinality associated with the API call is determined. A selected graph temporal store to be used to generate a response to the API call is selected based at least in part on the estimated cardinality, wherein the selected graph temporal store is included in a plurality of graph temporal stores associated with a graph with which the API call is associated. The selected graph temporal store is used to generate a response to the API call.

The invention belongs to the technical field of data processing, and particularly discloses an intelligent path planning and control system for an automatic driving carrying robot, and the system is operated through the following method: collecting environment data through a multi-mode sensor, and processing a laser radar point cloud and a camera image; fusing multi-source information to generate a real-time map, and obtaining a three-dimensional environment model containing dynamic obstacle positions; according to the three-dimensional environment model, obstacle features are extracted, an improved neural network model is adopted to identify a plurality of current obstacles, obstacle types and movement tracks are judged, and a classified obstacle data set is obtained; through the classified obstacle data set, the distance and the relative speed between the obstacle and the current position of the robot are calculated, and if the distance is smaller than a preset threshold value and the speed is larger than zero, high-priority interference is marked; the objective of the invention is to solve the problem that accurate sensing, real-time decision making and efficient obstacle avoidance are difficult to realize in a complex dynamic environment in the prior art.

Network computing equipment may receive one or more radio parameter measurement reports generated by one or more user equipment. A report may comprise radio parameter values measured by user equipment corresponding to signals transmitted by a radio access network node and time information corresponding to the report. The computing equipment may perform temporal analysis based on time information corresponding to one or more reports and may generate a temporal graph based on the time information. Edges of the temporal graph may correspond to connection activity of user equipment that generated the reports with respect to one or more radio access network nodes. The edges may be ranked using a graph-based model and optimally combined with anomaly scores, determined based on the measured radio parameter values, into combined anomaly scores that may be compared to a criterion to determine that a radio access network node is a fake base station.

The invention relates to the technical field of mine environment positioning, in particular to a mine scene self-adaptive repositioning method based on multi-modal perception, which comprises the following steps of: S1, acquiring information, and acquiring visual images, spatial features, wireless signal features and inertial motion data of an internal environment of a mine by using a multi-modal sensor; s2, extracting information, namely extracting the feature data obtained in the step S1, forming a dynamic topological map, and marking temporary obstacle information at the same time; s3, information processing: adaptively adjusting data fusion weights of different sensors according to the information extracted in the step S2 based on a dynamic environment sensing result; and S4, information updating: combining particle filtering and a graph optimization algorithm to realize robust pose estimation and real-time map updating. According to the invention, the failure risk of a single sensor is reduced through multi-mode complementation, and the positioning error is reduced by more than 40%; and through semantic auxiliary matching, the relocation time consumption is reduced.

The invention discloses a moving target detection method and segmentation method of an event camera and electronic equipment, and belongs to the technical field of event cameras. Projecting a to-be-detected event stream to an image plane corresponding to the event camera, constructing a time graph, and normalizing to obtain a two-dimensional global motion confidence graph; the two-dimensional global motion confidence map can reflect the possibility of an independent moving target to a certain extent, and the initial position of the moving target can be determined by performing threshold segmentation on the two-dimensional global motion confidence map; constructing an initial three-dimensional point cloud corresponding to the moving target, and performing plane fitting on the three-dimensional point cloud to obtain a fitted plane and a point, the distance between which and the plane is smaller than a preset distance; and taking the fitted plane as a moving target point distribution plane, taking a point, which has a distance smaller than a preset distance from the moving target point distribution plane, in the three-dimensional point cloud as a moving target point, and forming a moving target point cloud, thereby realizing detection of a moving target. According to the invention, the moving target in any shape can be accurately detected.

This document describes techniques and systems related to a radar system using a machine-learned model for stationary object detection. The radar system includes a processor that can receive radar data as time-series frames associated with electromagnetic (EM) energy. The processor uses the radar data to generate a range-time map of the EM energy that is input to a machine-learned model. The machine-learned model can receive as inputs extracted features corresponding to the stationary objects from the range-time map for multiple range bins at each of the time-series frames. In this way, the described radar system and techniques can accurately detect stationary objects of various sizes and extract critical features corresponding to the stationary objects.

Systems and methods that enhance the navigation of autonomous mobile robots in dynamic environments, such as inspection yards or manufacturing facilities in which positions and states of objects frequently change. This is achieved by integrating static maps, which provide information about permanent structures and areas, with dynamic maps, which focus on zones with movable objects and inspection zones where the robot performs tasks like monitoring or object inspection. Various embodiments utilize simultaneous localization and mapping (SLAM) techniques to generate maps that account for frequently changing elements in the environments. Real-time map generation and updates comprise splitting an environmental map into static and dynamic regions and calculating the robot's absolute position in the environment and its relative position to objects of interest. This dual estimation leverages different map datasets to perform efficient and accurate self-position estimation, thus ensuring consistent and reliable navigation based on real-time monitoring of the robot's surroundings.

The invention discloses a high-precision satellite attitude correction method, system and equipment for a maximum initial positioning error, and belongs to the technical field of machine vision image matching. A proper reference region is selected to prepare a first reference image and a second reference image, and feature descriptors of the reference images are extracted offline; performing down-sampling on a remote sensing image acquired by a satellite remote sensing camera, and performing image matching on a real-time image after down-sampling and the first reference image; calculating the optimal window position of the ground calibration point of the reference area in the real-time image according to the matching result; cutting the real-time image according to the window position to obtain a high-resolution calibration point real-time image; performing image matching on the high-resolution calibration point real-time image and the second reference image; and calculating latitude and longitude coordinates of the center of the real-time image according to a matching result for satellite attitude correction. The position error of the target area is gradually reduced in a two-stage remote sensing image matching mode, the longitude and latitude coordinates of the center of the real-time image are accurately positioned, and high-precision satellite attitude correction is realized.

The invention discloses a pedestrian trajectory prediction method based on space-time interaction perception, and aims to solve the problem of complex space-time interaction behaviors of pedestrians and improve trajectory prediction precision. The method comprises the following steps: firstly, processing a pedestrian trajectory data set, and constructing a time diagram and a space diagram as input; extracting space and time features among pedestrians through a self-attention mechanism, and inputting the space and time features into a space-time interaction perception module to learn a dynamic coupling relationship between motion and interaction to obtain interaction perception features; and then inputting the interactive features into a graph convolutional network to obtain trajectory representation features, finally predicting two-dimensional Gaussian distribution of future trajectories through a full-dimensional dynamic time sequence convolutional network, and outputting a high-precision trajectory prediction result. According to the invention, through a spatio-temporal joint modeling framework, spatio-temporal feature dynamic fusion of pedestrian motion is realized, and the accuracy and robustness of pedestrian trajectory prediction are improved.

The invention provides an artificial intelligence-based lumen lesion feature recognition method and system, and the method comprises the steps: obtaining an original image frame sequence collected by an electronic endoscope and a collection timestamp of each frame, and forming a pseudo-time image sequence set; inputting the pseudo time image sequence set into a pre-constructed candidate region extraction model, and outputting a focus candidate region set; performing vascular structure enhancement on the lesion candidate region set, constructing a graph neural network, extracting structural features through the graph neural network, outputting a lesion confidence score in combination with the region features, and finally generating an enhanced structured candidate region set in combination with the lesion candidate region set, the structural features and the lesion confidence score; performing trajectory aggregation on the structured candidate region set based on structural feature similarity and time continuity to form a cross-frame focus trajectory set; and calculating a space center position and a time range of a focus track according to the cross-frame focus track set, and generating a structured report.

The application provides an underground inspection path planning method for an inspection robot, and relates to the technical field of robot path planning.The method comprises the following steps: acquiring basic map data, robot basic data and an inspection plan; acquiring real-time map data and robot real-time data; determining an inspection node; determining a selectable inspection path; determining an inspection consumption coefficient; determining a preset inspection path according to the robot basic data, the real-time map data, the inspection consumption coefficient and the basic map data; determining whether the preset inspection path needs to be changed according to the basic map data, the robot basic data and the robot real-time data; in the case that it is determined that the preset inspection path needs to be changed, determining a changed inspection path according to the robot basic data, the basic map data and the robot real-time data, and performing inspection according to the changed inspection path. According to the application, the rationality of underground inspection path planning can be improved.

The invention discloses a port operation vehicle scheduling method and system based on map data, and particularly relates to the technical field of scheduling optimization. Real-time map state information of a port channel network is generated by collecting real-time map data of the port channel network and analyzing the real-time occupation state of a port channel road section. And analyzing the local change trend of the occupation state of the port channel road section and the priority change of the vehicle task based on the real-time map state information, outputting dynamically updated vehicle task priority information and local area map data updating information, identifying a priority propagation abnormal area, and generating priority inversion risk early warning information. By identifying the vehicle path conflict points causing the traffic jam, generating the path conflict resolution strategy information, adjusting the vehicle path planning and executing the vehicle scheduling, the collaboration, responsiveness and traffic efficiency of the operation vehicle scheduling in the port environment are effectively improved.

The invention discloses an ultrasonic guided wave damage ellipse imaging positioning method and equipment for a layer decreasing composite material laminated plate. The method comprises the following steps: S1, acquiring thickness change direction information of the laminated plate and position coordinates of an excitation transducer and a receiving transducer; s2, according to the material characteristic parameters, simulating and calculating the propagation time of ultrasonic guided waves transmitted from an excitation transducer to any point to generate a first theoretical propagation time map, and simulating and calculating the propagation time of the ultrasonic guided waves transmitted from any point to a receiving transducer to generate a second theoretical propagation time map to generate a second theoretical propagation time map; coupling influence of thickness change and material anisotropy on guided wave propagation is considered in the simulation process; s3, transmitting an ultrasonic guided wave signal, and extracting the actual flight time of a damaged wave packet; s4, calculating theoretical total propagation time, and determining a candidate area where damage exists; and S5, on the basis of repeated operation of the multiple groups of transducer pairs, taking a plurality of candidate region intersections to determine a final damage position. The objective of the invention is to solve the positioning error problem caused by the structural characteristics of a laminated plate in a traditional algorithm, and to realize more accurate damage detection and positioning.

The invention discloses a millimeter wave radar gesture recognition method and system based on gating collaborative fusion, and belongs to the technical field of artificial intelligence and man-machine interaction. The method comprises the following steps: firstly, acquiring and preprocessing original data through a millimeter wave radar sensor; secondly, extracting a global spatial feature map (such as a two-dimensional point cloud map) capable of representing the overall motion track of the gesture and a plurality of local dynamic feature maps (such as a distance-time map, a Doppler-time map and the like) capable of representing dynamic information of the gesture in parallel; and then, the extracted multi-modal features are processed through the gated collaborative fusion network designed by the invention. The core of the method is that the global spatial feature map is processed through a first neural network and a global average pooling layer to generate a static global feature vector; dynamically modulating a local feature sequence processed by a second neural network through a gating unit by using the static global feature vector; and finally, fusing all modulated sequences, inputting the fused sequences into a time sequence processing module for analysis, and outputting a final gesture category. According to the method, through an innovative gating fusion mechanism, dynamic cooperation of multi-modal features is realized, the problem that a traditional fusion method cannot adapt to different gesture feature changes is effectively solved, and the accuracy and robustness of gesture recognition are remarkably improved.

Provided is a blind guide stick comprising: a data communication device for acquiring a real-time map; the plurality of sensors are used for acquiring data of a current environment and positioning data of the blind guiding stick; the controller is used for generating guidance information based on the real-time map, the positioning data and the data of the current environment; and a user interface device for guiding the user based on the guidance information. Therefore, more robust navigation can be provided in various scenes.

The invention provides a robot interactive local map construction method and system based on a depth camera, and relates to the technical field of robot real-time map construction. Comprising the following steps: acquiring a depth image and a color image through a depth camera, and acquiring IMU data through an IMU; the color image and IMU data are input into a global speedometer module, and the pose of the robot in a global coordinate system is estimated in real time; an elevation grid map with the robot as the center is constructed according to the global pose and the depth image, the topographic feature and the passing cost of each grid are calculated, and a local trafficability map is constructed; and obtaining a to-be-modified area selected by an operator in the color image, obtaining a map grid corresponding to the to-be-modified area in the color image based on the image alignment module, and modifying the passing cost of the corresponding grid to realize interactive modification of the local passability map. According to the method, the data of the depth camera and the operation intention of a human operator are combined, and interactive construction and modification of the map are realized.

The invention discloses a robot path planning method based on an improved Theta * algorithm, and the method comprises the following steps: building a three-dimensional space-time map based on a search space of a robot target task, converting a dynamic obstacle coordinate into a static obstacle coordinate, and obtaining a three-dimensional space-time obstacle map; an improved Theta * algorithm is adopted, and path planning of the robot from a starting node to a target node is carried out on the three-dimensional space-time obstacle map; wherein the Theta * algorithm improvement comprises improvement of node properties, improvement of a node expansion mode, improvement of a cost function and improvement of an LOS judgment mechanism from two dimensions to three dimensions. According to the invention, by introducing the time dimension and improving the Theta * algorithm, path planning is expanded from a two-dimensional space to a three-dimensional time-space domain; through dynamic environment perception and path optimization, the obstacle avoidance capability and path quality of the robot in a dynamic environment are improved.

The invention relates to a self-adaptive mask space-time alignment GPR positioning method, device and equipment, and aims to sequentially solve the problem of channel and time dimension dislocation in a GPR sequence by adopting a self-adaptive alignment and dynamic time warping strategy and then calibrate a query sequence. In addition, GPR low-frequency features can be enhanced through multi-stage discrete wavelet transform, meanwhile, signals can be optimized through channel dimension self-adaptive alignment, and the positioning precision when channel dimension features are distorted under the influence of rain and snow weather is remarkably improved. In addition, a local matching DTW algorithm is introduced to achieve robust temporal image sequence alignment. A wide range of experiments have been performed on a common LGPR data set GROUNDED and self-collected data covering five challenging scenes, and the result shows that compared with an existing method, the method provided by the invention has higher positioning precision and stronger robustness.