1366 results about "Time space" patented technology

The invention discloses a cross-regional virtual power plant cooperative scheduling method and device, a medium and a product, and relates to the field of data processing. The method comprises the following steps: acquiring real-time characteristic data such as space-time positions, output / demand prediction and the like of distributed energy resources and loads, and determining dynamic weights of characteristic dimensions based on a global optimization target and data of a current scheduling period; generating a dynamic resource cluster division instruction containing a member list and a coordination constraint condition according to the dynamic weight and the real-time data, and sending an initial cross-regional coordination scheduling instruction containing a net exchange power target value and the like and a compensation price signal to each dynamic resource cluster local agent; after aggregation response boundary information returned by the local agent is received, an instruction and a signal are updated, a target collaborative scheduling instruction is obtained and finally sent to each dynamic resource cluster for execution, and effective control over cross-regional virtual power plant resources is achieved. According to the method, the problem that the adaptability of the cross-regional virtual power plant collaborative scheduling instruction and the actual resource capacity is insufficient can be relieved.

The invention provides a mine abnormal event real-time identification method and system based on time sequence characteristics, and relates to the technical field of mode identification, and the method comprises the steps: carrying out the time-space alignment and semantic annotation of multi-modal monitoring data, and constructing a time sequence knowledge graph; calculating a dynamic association weight between entities, and analyzing a risk propagation path; predicting a risk situation based on a historical evolution rule; and dynamically generating a differential early warning strategy and establishing a closed-loop tracking system. According to the invention, early identification, accurate prediction and efficient disposal of mine safety risks can be realized, and the mine safety management level is improved.

The invention belongs to the technical field of time series data processing, and particularly relates to a time series data anomaly detection method based on a variable time converter. According to the method, an anomaly detection model VT-GAN is provided, the model designs a parallel generator group, and each generator extracts mode features of different time scales through expansion causal convolution; time self-attention, variable self-attention and cross attention layers are fused in the VTT architecture, and a time-space interaction relationship is explicitly modeled through a learnable gating weight; and a loss function of the VT-GAN model is adjusted and optimized in combination with temperature parameters, and data anomaly detection is carried out based on the constructed VT-GAN model. The method solves the problems that a traditional model is difficult to meet millisecond-level response requirements due to sequence calculation characteristics, the calculation complexity of a global attention mechanism in high-dimensional time series data limits the real-time performance, the false alarm rate is high, and the anomaly detection coverage rate is low.

The invention belongs to the technical field of power system load prediction, and discloses a cross-dimension multi-scale fusion load prediction method based on multi-user load time-space correlation, which comprises the following steps of: firstly, preprocessing user load statistical data, extracting time sequence dependence and periodic characteristics in a time sequence, and calculating the time sequence dependence and periodic characteristics of the user load statistical data; introducing a channel attention mechanism to adaptively mine key variable information; then, a multi-scale space-time fusion module is combined with frequency domain analysis and a graph convolutional network to realize depth feature interaction under different time scales and space levels; and finally, outputting a load prediction result under a plurality of time granularities in the future through a linear projection structure. Compared with an existing method, the method has the remarkable advantages in the aspects of capturing a complex load mode, improving model prediction precision and enhancing generalization ability, and is suitable for various application scenes such as power consumer energy consumption management and power grid load dispatching.

The invention relates to the technical field of high-precision satellite navigation and positioning, and discloses a multi-modal sensor space-time synchronization method for high-precision data acquisition, which comprises the following steps: constructing a hardware delay observation loop to calculate physical response delay in real time; establishing a receiver clock drift model and extracting a clock drift coefficient; generating a phase lead trigger instruction in response to the delay mean value and the clock drift coefficient cumulant based on the GNSS whole-second target moment; according to the method, a feed-forward control closed loop is constructed by using GNSS clock difference parameters, the intrinsic alignment of the heterogeneous sensor physical sampling action and GNSS atomic time is realized, the real-time alignment of the sensor physical sampling action and the GNSS atomic time is realized, and the real-time alignment of the sensor physical sampling action and the GNSS atomic time is realized. And a strict physical time reference is provided for high-dynamic multi-source data fusion.

The invention discloses a vehicle-mounted cross-protocol data time sequence cooperative processing method, which comprises the following steps: establishing a unified time reference, and providing an accurate space-time coordinate system for heterogeneous network nodes by electing a global master clock and constructing a clock relation model and a periodic correction mechanism; systematic cognition and management of communication resources are realized, and a verified protocol capability table is generated by automatically identifying protocol types and variants; constructing an automatic mapping system from demand to execution, performing formalized packaging on a target scene by introducing a unified intermediate model, generating a cross-protocol mapping rule based on the model and a protocol capability table, and then forming a global scheduling table in combination with a unified time reference; the cooperative communication of all nodes is finally realized by using the global scheduling table, and the end-to-end delay is constrained within the preset range, so that the problem that the end-to-end time sequence in the vehicle-mounted heterogeneous network is uncontrollable is solved, and the controllability and reliability of the time sequence of the vehicle-mounted network are improved.

The invention provides a space-time decoupling feature fusion method based on space-time bidirectional Vision Mama, and the method comprises the steps: S1, extracting multi-scale space detail features from an input time sequence image through employing a plurality of cascaded 2D CNN blocks, and obtaining a feature graph; s2, a bidirectional space-time Mama structure is applied to the feature maps of the low and middle layers so as to compensate for loss of time information in the 2D CNN block; wherein for the feature map obtained in the step S1, time sequence features are extracted by applying time bidirectional Vision Mama, and then space features are extracted by using space bidirectional Vision Mama. The invention further provides a space-time decoupling feature fusion system based on the space-time bidirectional Vision Mama. According to the method, efficient and accurate feature extraction and information fusion are performed on a special time sequence multi-band multi-channel remote sensing image, and efficient and high-precision semantic segmentation of crops on a large-area scale remote sensing image is realized.

The invention discloses a building engineering full life cycle resource intelligent scheduling system and method, and belongs to the technical field of building management, and the method specifically comprises the steps: collecting dynamic physical parameters of a component installation process in a construction stage; constructing a spatio-temporal index engine, associating the dynamic physical parameters to corresponding component nodes of the BIM model, and generating a spatio-temporal binding data unit; in an engineering operation and maintenance stage, monitoring operation state data of the component, and when an abnormal state is recognized, extracting current space coordinates of the abnormal component and activating a reverse traceability channel; taking the space coordinates of the abnormal components as retrieval anchor points, matching the space-time binding data units with the same space coordinates, and obtaining a dynamic physical parameter sequence in a construction stage; comparing and mapping the dynamic physical parameter sequence and the abnormal state, generating an operation and maintenance decision instruction set with a construction defect positioning identifier, and inputting a resource scheduling sequence; according to the method, the utilization rate of operation and maintenance decisions on construction stage data is remarkably improved.

The invention discloses an intelligent ship situation awareness prediction method and system, and relates to the technical field of intelligent ship situation awareness and trajectory prediction, and the method comprises the steps: carrying out the time-space synchronization of collected operation environment data of a ship through a timestamp alignment method, and generating a ship situation data set; based on the ship situation data set, the course angle change rate and the Euclidean distance of the obstacle relative to the ship are extracted, and weighted fusion is carried out on the dynamic collision probability and the approaching time of the obstacle to obtain an obstacle threat degree index; inputting the obstacle threat degree index into a ship trajectory prediction model, and outputting the minimum meeting distance between the ship and each obstacle; and carrying out risk grade division on the minimum encounter distance according to an international maritime collision avoidance rule, outputting a graded early warning signal, and formulating a navigation strategy to execute obstacle avoidance and route adjustment. According to the method, the technical problems of risk perception lag, single and rough avoidance action and insufficient trajectory prediction accuracy in the prior art are effectively solved.

The invention discloses an intelligent visual tracking method fusing memory distillation and space-time alignment, and belongs to the technical field of artificial intelligence, computer vision and target tracking. Firstly, feature extraction is carried out on an input target template frame and an input search frame through a shared backbone network, an image is divided into a non-overlapping image block sequence, and feature representation is generated. Then, the features are processed by adopting an adaptive space-time consistency attention module, the module comprises time and space attention branches, and cross-frame time sequence dependence and intra-frame target-background association are respectively modeled; then, a space-time memory distillation network is constructed, target features are maintained through a dynamic memory library and a gating read-write mechanism, and feature representation is optimized through knowledge distillation; and finally, designing a space-time consistency loss function, and carrying out joint optimization by comprehensively considering trajectory smoothness, motion consistency and feature time sequence coherence. Through the combination of the technical schemes, the performance and robustness of visual target tracking can be effectively improved.

The invention relates to the technical field of data processing systems, and discloses a command and dispatch management method and system based on artificial intelligence, and the method comprises the steps: generating a space-time occupancy statement containing an occupancy area, a time window and a task state through an edge node, and broadcasting the space-time occupancy statement to an adjacent node; and a receiver performs local conflict verification according to a state mutual exclusion rule, and triggers priority-based lightweight negotiation to adjust an occupied time window when detecting that static observation and dynamic intervention states coexist in an overlapped space-time. Postward conflict processing of traditional centralized scheduling is converted into beforehand conflict avoidance, the response speed and the operation toughness of the system are remarkably improved, and meanwhile, through physical reachability verification and a channel self-adaption mechanism, the cooperation reliability in a complex environment is guaranteed.

The invention discloses a multi-stage spatial-temporal clustering method and system based on a fused mahalanobis distance. The method comprises the following steps: acquiring a spatio-temporal data set, and determining a spatio-temporal neighbor relation of samples in the data set; calculating a space communication distance and a time decay distance of the sample; fusing the space communication distance and the time decay distance by using a mahalanobis distance to obtain a relative distance of the sample; selecting a class cluster center from the data set according to the local density of the sample and the relative distance; adopting a multi-stage distribution strategy to distribute non-class-cluster center samples to corresponding class clusters; wherein the multi-stage allocation strategy comprises an inevitable allocation stage based on space-time shared neighbor and a similarity allocation stage based on a weighted similarity matrix. According to the method, the key problems that an existing space-time clustering algorithm is insufficient in space-time attribute coupling processing and sensitive to distribution errors are solved, and the clustering accuracy, robustness and practicability in the fields of intelligent traffic analysis, seismic sequence recognition and the like are remarkably improved.

The invention relates to a multivariate time series data abnormal root cause identification method based on a space-time cause and effect diagram, and belongs to the technical field of anomaly detection. According to the method, multi-window expansion causal convolution is adopted for multivariate time series data, mutual information screening is combined, and time embedding covering short-term mutation and long-time dependence at the same time is extracted; non-local space correlation is learned through multi-head self-attention, the directional causal intensity is measured through conditional entropy, and a sparse and interpretable space-time causal graph is generated through normalization-pruning; introducing a causal enhancement graph attention network on the space-time causal graph, and performing multiple rounds of causal propagation updating on node embedding; and calculating a root cause score by integrating the abnormal degree and the causal influence, identifying a key source node in an abnormal propagation path, and realizing accurate root cause positioning of the system abnormality. According to the method, the adaptability to the dynamic behavior mode and the capturing capability to the abnormal driving factor are enhanced, and the modeling precision and the root cause identification capability of the abnormal propagation process are improved.

The invention discloses an electronic jacquard machine control method and system based on multi-channel collaboration, and the method comprises the steps: calculating a delay compensation value of each channel in real time according to the hardware performance difference and signal transmission delay data of each channel, and dynamically adjusting the time sequence offset of a control instruction of an electronic jacquard machine by using the delay compensation value, generating a multi-channel cooperative control signal; according to input fabric pattern data, decomposing the fabric pattern data to generate a layered instruction set, and binding the layered instruction set to a multi-channel cooperative control signal to form a time-space synchronization instruction set; according to channel operation state data acquired in real time, identifying an abnormal channel and a fault type thereof, and generating a reconstruction instruction set after fault immunization; and dynamically allocating computing resources and storage bandwidth according to the reconstruction instruction set, generating an optimization execution instruction set, and issuing the optimization execution instruction set to each channel for execution in real time. By utilizing the embodiment of the invention, the control capability of the electronic jacquard machine and the fabric production efficiency can be improved, and the intelligent development of the textile industry is promoted.

The invention discloses a large model parallel task scheduling method based on space-time two-dimensional segmentation and intelligent sharing, and particularly provides a model segmentation strategy based on space-time two dimensions, and based on significant differences of training and reasoning tasks in calculation properties, targeted optimization strategies are adopted respectively, so that the task execution efficiency is improved; the invention further provides a model placement strategy based on the heterogeneous resources and the interference model, the defects that a traditional method lacks intelligent sharing judgment and cannot be dynamically adjusted are overcome, the flexibility and adaptability of scheduling are improved, and therefore the maximum benefit of the shared resources is guaranteed. The method solves the problems that when an existing heterogeneous intelligent computing cluster scheduling method is used for processing large model training and reasoning tasks, the model placement optimization technology of model segmentation and heterogeneous resource adaptation is not fully utilized, intelligent sharing scheduling of computing resources in a cluster is lacked, system task scheduling is unreasonable, and the scheduling efficiency is high. And the utilization rate of computing resources is low.

The invention relates to the technical field of ocean data interpolation filling, in particular to a space-time deficiency filling method and system based on context association and physical guidance. The method comprises the following steps: acquiring seawater dissolved oxygen data and context data; multivariable space-time dependence extraction is carried out based on the obtained seawater dissolved oxygen data and context data; gaussian noise diffusion is carried out based on the obtained seawater dissolved oxygen data; noise prediction is carried out based on double-view space-time correlation; and the prediction error is constrained based on the joint loss function. According to the method, a physical consistency constraint mechanism based on a partial differential equation is introduced in a model training process, so that model output better conforms to a physical coupling rule among variables in a marine environment. The constraint effectively inhibits non-physical fluctuation possibly occurring in the interpolation result, enhances the physical credibility and interpretability of the result, and provides a more reliable data basis for subsequent scientific analysis and process modeling.

The invention discloses an engineering machinery fault prediction and intelligent maintenance method based on deep learning, and belongs to the technical field of intelligent operation and maintenance of engineering machinery. The method comprises the following steps: firstly, performing timestamp synchronization and feature enhancement on multi-source sensor data to generate a space-time alignment tensor; fusing the image and time sequence features through a multi-modal feature distillation network, and constructing a cross-modal unified feature vector; thirdly, calculating a fault probability and residual life distribution, and constructing a Markov decision model in combination with a resource state; and finally, dynamically optimizing the maintenance instruction by using deep reinforcement learning, and continuously updating the model through closed-loop feedback. According to the method, early-stage accurate prediction of the fault and dynamic optimization of the maintenance strategy are realized, the problems of inaccurate prediction, decision lag, resource waste and the like in a traditional method are effectively solved, and the availability rate and the maintenance economy of equipment are remarkably improved.

The invention is suitable for the technical field of earth surface monitoring, and provides an earth surface deformation monitoring method and system based on a time sequence InSAR, and the method comprises the following steps: carrying out the SAR image screening and interferogram generation, and collecting corresponding meteorological data and thermal infrared data; performing space-time adaptive atmospheric phase correction, taking the air pressure vertical gradient and the temperature anomaly as driving factors of atmospheric delay, and separating an atmospheric phase through a space-time weighted model; dynamic deformation modeling is carried out, and deformation is decomposed into linear deformation and nonlinear deformation; the method comprises the following steps: taking a mining area road network as a geometric constraint, unwrapping a coherent region by adopting a minimum cost flow algorithm, converting an unwrapping phase into sight-line-direction deformation, and calculating horizontal and vertical deformation components in combination with InSAR sight-line-direction deformation and a digital elevation model. The method adapts to a complex deformation mechanism of a mining area by capturing linear and nonlinear deformation. Through sight line deformation and DEM geometric projection, vertical and horizontal deformation separation is realized, and the deformation direction is determined.

The embodiment of the invention provides a simulation evaluation method and device for a multi-satellite cooperative task, and the method comprises the steps: building a unified time-space reference based on a standard time signal, and building a complete environment disturbance model comprising sunlight pressure, atmospheric resistance and geomagnetic field interference. A fault injection mechanism of load, attitude and orbit control is innovatively designed, and real simulation of multi-satellite cooperative motion is realized. According to the system, a system-level, subsystem-level and component-level multi-level evaluation index system is established, a dynamic weight calculation method based on a task execution state is adopted, and matching analysis of a three-dimensional error curve and a key event time sequence is combined, so that accurate evaluation of multi-satellite cooperative task performance is realized; and a reliable decision basis is provided for space task planning and system optimization.

The invention provides a cross-time-space conversion method with a Fourier filtering operator for multivariable time sequence classification. The cross-time-space conversion method comprises the following steps: mapping an input time sequence to a target variable; mapping a time sequence data set to a group of C category labels Y; after training, the CSTFormer model outputs a vector containing C values so as to estimate the probability that the time sequence belongs to each category; in the CSTFormer model, data input by a multivariable time sequence firstly passes through a LayerNorm layer and then enters a global adaptive Fourier neural operator module, noise is adaptively filtered, and important frequency information is enhanced; the output passes through a LayerNorm layer and then enters a time-space consistency learning module; the time-space consistency learning module is composed of three sub-modules, namely a dynamic multi-scale time attention module, a dynamic space attention module and a dynamic cross-distribution fusion module; respectively learning a time context and a space context, and fusing to obtain a learned time-space consistency context; and finally, outputting a classification result by the classification head.

The invention discloses a power transformer temperature prediction method and system based on multi-feature extraction and fusion, and the method comprises the steps: carrying out the time-space decoupling standardization and causal emergence clustering of all temperature variables in data, and obtaining a clustering result; extracting a common pattern from each class of the clustering result to obtain an information complemented multivariable time sequence, and performing down-sampling on the information complemented multivariable time sequence to obtain a plurality of subsequences; performing feature extraction on the multivariable time sequence and the sub-sequence after information completion through a dynamic time-frequency domain MLP mechanism to obtain overall features and local features, and fusing the overall features and the local features to obtain time sequence features; acquiring an external environment covariable, inputting the external environment covariable into the self-attention mechanism network to obtain a covariable self-feature, and performing feature fusion on the covariable self-feature and the time sequence feature through a covariable-driven causal convolution fusion mechanism to obtain a fusion feature; and inputting the fusion feature into a dynamic attention feature weighted prediction model for prediction to obtain a prediction result. And the precision and reliability of temperature prediction of the power transformer are obviously improved.

The invention provides a traffic flow prediction method based on a space-time sequence, and relates to the technical field of traffic prediction, and the method comprises the steps: obtaining open-source network traffic flow data, and carrying out the preprocessing of the data, and obtaining a traffic flow sequence; inputting a traffic flow sequence into a data embedding layer to obtain high-dimensional representation of input features, performing periodic embedding and adaptive space-time embedding, and connecting the three kinds of embedding to obtain hidden space-time representation; inputting the hidden space-time representation into a space-time encoder for modeling of space dependence and time dependence to obtain a hidden state; and inputting the hidden state into an output layer, and outputting to obtain a traffic flow prediction result. According to the method, the deep features of the traffic flow data can be extracted more effectively, the complex spatial-temporal change rule of the traffic flow is captured, and the accuracy of urban traffic flow prediction is further improved.

The invention relates to the field of computer vision technology and the like, and discloses a video action recognition method and system based on space-time interaction Transform and object interactivity prediction.The method constructs the video action recognition system by integrating the space-time interaction Transform and the object interactivity prediction.The action in a video can be effectively recognized and analyzed, and the video action recognition efficiency is improved. The method has a good effect especially in a multi-user interaction scene, and comprises the following specific steps: preprocessing an original video, and obtaining necessary video data comprising a video frame sequence and multi-modal features; encoding the preprocessed video data into a discrete token sequence; the token sequence is input into Transform, M-layer self-attention calculation is carried out, and spatial-temporal features are extracted; an object interactivity prediction module is used for judging and modeling the interaction relationship between objects in the video data; and carrying out classification by utilizing the fused multi-modal features, and outputting action categories in the video.

The invention discloses a real-time interaction and intelligent management method for a multi-dimensional data space, and relates to the technical field of data interaction management, and the method comprises the following steps: I, collecting multi-source data, including structured data, unstructured data and spatio-temporal data, in real time through a diversified collection terminal, and dynamically adjusting the sampling frequency based on a data entropy value, carrying out cross-device space-time synchronization calibration and edge end lightweight processing on the acquired data; iI, preprocessing the data flow in real time, fusing the multi-modal data, and the like. According to the method, the sampling frequency is dynamically adjusted based on the data entropy value, and in combination with edge end lightweight processing, invalid data transmission is reduced, and the key data acquisition efficiency is improved; hot data is stored in a time sequence database and a memory database, real-time monitoring of an emergency scene and second-level response of emergency command are supported, dynamic capacity expansion and shrinkage of computing resources are matched, edge-cloud end collaboratively distributes tasks, network delay is reduced, and system stability and response speed in a high-concurrency scene are guaranteed.

The invention relates to a target trajectory prediction method and system based on a bidirectional long-short-term memory network, and the method mainly comprises the following steps: firstly, carrying out the spatial-temporal feature extraction of target trajectory data through a bidirectional long-short-term memory network layer, obtaining the spatial-temporal feature vector of target data, capturing a long-term dependency relationship and a short-term dependency relationship, and carrying out the spatial-temporal feature extraction of the target trajectory data; wherein the long-term dependency describes the time sequence and continuity of motion, and the short-term dependency describes the maneuvering characteristics of the motion; secondly, a prediction model is constructed, and hyper-parameters of the prediction model are optimized, so that the prediction performance and generalization ability of the model are improved; and finally, predicting a future trajectory of the target by using the trained optimization model, outputting a trajectory coordinate sequence of a plurality of time points in the future, and realizing accurate prediction of the target in a period of time in the future. According to the method, the bidirectional long-short-term memory network and hyper-parameter optimization are combined, so that high-precision trajectory prediction of the target is realized, and the adaptability of the prediction model to complex motion characteristics is enhanced.

The invention discloses a dynamic gesture recognition method based on space-time interaction and rate perception. The method comprises a space-time decoupling feature extraction module, a rate feature injection module and a space-time feature injection interaction module. The space-time decoupling feature extraction is formed by three-dimensional convolution, an Inception module and a multi-scale Transform, and the rate feature injection module realizes visual rhythm feature extraction based on similarity calculation and an optical flow estimation algorithm, performs feature enhancement on an initial feature by using the visual rhythm feature, and performs feature extraction on the initial feature. The spatial-temporal feature injection interaction module is composed of a spatial feature injection module and a time feature interaction module, and the spatial feature injection module and the time feature interaction module are realized based on an attention mechanism. The space-time decoupling feature extraction is a backbone network, and other modules are embedded in the backbone network and play roles of feature injection, feature enhancement and the like. The method relates to the fields of man-machine interaction, dynamic gesture recognition algorithms, deep learning, computer vision and the like, and has the advantages of comprehensive features and accurate recognition.

The invention relates to the technical field of online education, in particular to an intelligent learning scene pushing system based on a spatio-temporal sequence, which comprises a spatio-temporal data acquisition module, a spatio-temporal feature analysis module, a learning scene recommendation module, a feedback collection module, a self-adaptive optimization module and a data security protection module, the spatio-temporal data acquisition module is used for acquiring learning time and spatial data of a user in real time, the spatio-temporal feature analysis module extracts a user learning rule based on data analysis, the learning scene recommendation module pushes learning content suitable for a current environment according to an analysis result, and the adaptive optimization module dynamically adjusts a learning strategy according to user feedback. Personalized learning experience is ensured, and the data security protection module guarantees user privacy and data security through encryption and authority management; according to the invention, accurate and efficient learning pushing can be realized under different learning situations, and the method is suitable for the fields of online education, intelligent learning platforms and the like.

The invention provides a multi-dimensional multi-spatio-temporal data base plate construction method and system, and the method comprises the steps: carrying out the standardization processing of obtained original multi-source heterogeneous data, and generating a standardized data set; performing multi-level space fusion and dynamic time weighting processing based on the standardized data set to generate a multi-level fusion spatio-temporal data set; performing space-time grid aggregation and adaptive node screening on the multi-level fusion space-time data set to generate an optimized space-time node set; based on the optimized space-time node set, dynamic association is constructed, and an association model is generated and comprises event rules, topological relations and dynamic weights; and generating a multi-dimensional multi-spatiotemporal data base plate based on the optimized spatiotemporal node set and the association model. By adopting the method, the data base plate which can cover global features and has real-time response capability can be constructed, and the decision-making precision and efficiency of scenes such as water conservancy disaster prevention and control and environment monitoring can be improved.

The invention belongs to the technical field of power system application, and particularly relates to an intelligent power flow data filling method based on space-time coupling. The invention provides an intelligent power flow data filling method based on space-time coupling, which comprises the following steps: firstly, carrying out data preprocessing on original data through Hampel filtering, phase alignment and normalization, constructing a space-time encoder through joint coding of adaptive graph convolution (Adaptive GCN) and attention LSTM, capturing space-time coupling characteristics, and carrying out data processing on the space-time coupling characteristics; a multi-physical constraint generative adversarial network (Pry-GAN) is designed through generator physical constraints and a multi-scale discriminator to realize data filling, and it is ensured that a filling result has both numerical reasonability and physical feasibility.

The invention provides a seismic event space-time density peak value clustering method and device, a medium and electronic equipment. The seismic event space-time density peak value clustering method comprises the steps of determining a space-time neighbor set of samples in a space-time data set; calculating a space weight coefficient and a time weight coefficient of the samples, and calculating the local density of each sample under space-time constraint; calculating the relative distance of the samples; calculating a decision value of each sample for selecting a potential cluster center of the spatio-temporal data set; eliminating potential cluster centers with merging potential according to the comprehensive similarity of the cluster centers to obtain cluster centers of various clusters; distributing the remaining samples after the cluster centers are determined; and carrying out abnormal point identification in each cluster to obtain a final clustering result of the sample data set. By applying the method, time and space constraints are introduced into a cluster center merging rule at the same time, so that a class cluster center with higher accuracy and consistency is obtained; a more flexible multi-step distribution strategy is adopted to replace a single distribution mode, and an abnormal point identification mechanism based on double criteria is combined, so that the clustering effect is improved.