172 results about "Temporal models" patented technology

The present application relates to the technical field of load prediction, and provides an electrical load prediction method and device based on spatial-temporal correlation. The method comprises: performing spatial-temporal modeling on the basis of historical electrical load data and historical environment data to obtain a multi-layer spatial-temporal model, wherein each layer model is a directed graph and represents spatial causality in the fixed time, and a directed edge between the layer models represents temporal causality; on the basis of an interpretable spatial-temporal attention transformer, performing feature extraction and priori knowledge fusion on the multi-layer spatial-temporal model to obtain spatial-temporal characteristics of an electrical load, wherein the interpretable spatial-temporal attention transformer comprises a spatial causal attention network, a temporal attention network, and a spatial dependence comparison module; and on the basis of the spatial-temporal characteristics of the electrical load, and the real-time electrical load data and the real-time environment data of a target electrical node, predicting by using a trained STEF-DHNet model to obtain the predicted electrical load data of the target electrical node. The present application can improve the prediction accuracy and the model applicability.

Techniques and systems for the dynamic generation of a map interface include generating temporal activity models by representing individual social media postings as having respective density distributions in time. Each posting's temporal density distribution spans multiple sequential time windows centered on the posting's timestamp, with density contributions decreasing in value for time windows further from the timestamp. The temporal models may be combined with spatial density distributions to generate comprehensive geo-temporal representations of social media activity. A graphical user interface displays an interactive map with overlay elements determined based on calculated activity attributes, including detected temporal patterns and anomalies identified by comparing current activity models against historical baselines. The modeling approach enables improved visualization of activity patterns while providing inherent privacy protection through probabilistic representation of individual posts.

The invention relates to the technical field of natural resource monitoring and spatial information processing, in particular to a method and a system for feeding back land utilization change based on a land spatio-temporal model. The method comprises the following steps: deploying multi-source land monitoring equipment, carrying out collaborative data acquisition and standardization processing, and constructing a land space-time reference data set; performing triple mapping on the land space-time reference data set to obtain a land semantic association graph; constructing a land utilization knowledge graph based on the land semantic association graph; constructing a land change detection initial model by using the land utilization knowledge graph; meanwhile, in a high-frequency change scene, such as an urban and rural ecologic zone or an ecological sensitive area, a traditional model is slow in response to short-term land utilization disturbance, automatic adjustment cannot be carried out through deviation feedback between historical errors and model output, and the reliability of the model in actual application scenes such as resource regulation and control is limited.

A system for automatically self-labeling a digital dataset includes a first sensor for generating a first data stream, a second sensor for collecting information to generate a second data stream, and a causal model manager (CMM). The CMM is configured to determine a first causal event from a first data segment of the first data stream, and a causal relation between the first causal event and a second data segment selected from the second data stream. The system further includes (a) an interactive time model for determining an interaction time between the first and second data segments, and (b) a self-labeling subsystem configured to derive a label from the second data segment, associate the first data segment with the derived label, form a self-labeled data pair from the associated first data segment and the derived label, and automatically annotate the self-labeled data pair with the interaction time.

The invention relates to the technical field of Internet of Things anomaly identification, in particular to an Internet of Things anomaly traffic identification method and system based on a deep neural network. The method comprises the following steps: collecting communication data of each piece of IoT equipment in real time from an edge gateway of the Internet of Things; preprocessing the collected communication data, and constructing a multi-dimensional feature vector; based on a convolutional neural network and a bidirectional long-short-term memory network, performing time sequence feature extraction and anomaly discrimination on the multi-dimensional feature vector to output a traffic anomaly probability; and comparing the abnormal probability output by the depth time sequence modeling neural network with a dynamic threshold value, and if the abnormal probability exceeds a preset threshold value, determining that the traffic is abnormal. A gating mechanism is introduced into a bidirectional long-short-term memory layer, a gating coefficient is calculated at a time step level, the influence weight of time step information on final output is dynamically adjusted, feature expression of key time steps is strengthened, noise or irrelevant information is suppressed, and the sensitivity of a model to time sequence data is improved.

The embodiment of the invention relates to the technical field of ground surveying and mapping data modeling, in particular to a ground surveying and mapping driven space-time evolution modeling method and system.The method comprises the steps that firstly, multi-dimensional correlation features of elevations, coverage types and deformation data in at least three continuous periods are integrated; the limitation of single time point or single parameter analysis is broken through, and the nonlinear space-time coupling rule in earth surface evolution can be accurately captured; secondly, a spatial-temporal model construction method based on dynamic parameter optimization effectively fuses geographic spatial correlation features and coverage evolution trends, so that the model has adaptive characterization capability for a complex geographic process; in addition, by establishing a closed-loop feedback mechanism of prediction results and model parameters, real-time iterative optimization of the model parameters is realized, and long-term prediction stability in different geographical scenes is remarkably improved.

The invention discloses an artificial intelligence-driven industrial Internet of Things equipment fault prediction system, and relates to the technical field of industrial Internet of Things and predictive maintenance, an edge-cloud collaborative architecture is adopted, real-time acquisition, preprocessing and online fault prediction of industrial equipment sensing data are realized, the system uses a Transform neural network to construct a hierarchical spatio-temporal model, and the fault prediction of the industrial equipment sensing data is realized. Time sequence data are processed in a segmented mode through a sliding window method, a causal reasoning enhancement mechanism is integrated, an industrial equipment causal atlas is constructed, attention masks are generated, a model is focused on key features, and therefore prediction accuracy and interpretability are improved, meanwhile, a closed-loop continuous optimization mechanism is established by the system, and prediction efficiency is improved. And an edge fault prediction result and actual operation feedback are uploaded to a cloud, a causal atlas and model parameters are updated, adaptive optimization of the model is realized, and the system provides efficient, accurate and explainable decision support for preventive maintenance of industrial equipment.

The invention provides a spatio-temporal model pre-training method, device and equipment and a storage medium, relates to the technical field of artificial intelligence, in particular to the technical fields of neural networks, large models and the like, and can be applied to scenes related to spatio-temporal data, such as large-scale urban data analysis, traffic flow prediction, weather forecast, environment monitoring and the like. According to the specific implementation scheme, spatial features are extracted through a spatial feature extraction network of a to-be-trained spatial-temporal model based on first spatial-temporal information in a spatial-temporal diagram; extracting time sequence signal features based on the first spatio-temporal information through a time feature extraction network of the spatio-temporal model to be trained; obtaining a space guide time feature based on the space feature and the time sequence signal feature through a space-time fusion conversion network of the to-be-trained space-time model; and pre-training the to-be-trained spatiotemporal model based on second spatiotemporal information corresponding to the spatial guidance time feature and the first spatiotemporal information to obtain a pre-trained spatiotemporal model.

The invention discloses a light energy power station fault prediction system based on deep learning. The system comprises a data acquisition module used for reading equipment operation data from a sensor; the data preprocessing module is used for denoising, interpolating and standardizing the equipment data; the graph convolutional network construction module is used for constructing an equipment data graph structure and extracting features; the Lemap dimension reduction module is used for mapping the high-dimensional equipment features to a low-dimensional space; the time sequence modeling module is used for constructing a time sequence prediction model based on the low-dimensional features; the hyper-parameter optimization module is used for optimizing hyper-parameters of the time sequence model; the model verification module is used for evaluating the precision and response time of the fault prediction model; the model deployment module is used for deploying the prediction model to a monitoring system; the fault prediction and early warning module is used for monitoring in real time and generating fault early warning; and the continuous optimization module is used for regularly optimizing and retraining the fault prediction model. The method achieves the high efficiency of fault prediction of the light energy power station, remarkably improves the prediction precision and the reliability of equipment operation, and is widely suitable for equipment monitoring and early warning.

The present invention is directed to a Spatiotemporal scene-graph embedding methodology that models scene-graphs and resolves safety-focused tasks for autonomous vehicles. The present invention features a computing system comprising instructions for accepting the one or more images, extracting one or more objects from each image, computing an inverse-perspective mapping transformation of the image to generate a bird's-eye view (BEV) representation of each image, calculating relations between each object for each image, and generating a scene-graph for each image based on the aforementioned calculations. The system may further comprise instructions for calculating a confidence value for whether or not a collision will occur through the generation of a spatio-temporal graph embedding based on a spatial graph embedding and a temporal model.

The invention relates to a multi-dimensional and multi-level capability modeling method for production plan scheduling. The method comprises the following steps: defining process basic data based on a time model of each process stage in a production process; defining product basic data based on the material archive and the bill of material; defining resource basic data based on the device capability and the personnel capability; classifying the products based on the characteristics of the product families and the raw materials to obtain each product group; classifying processes based on product processes and process requirements to obtain each process group; classifying the resources based on the grouping of the equipment and the personnel to obtain each resource group; a production plan target is determined, capability modeling is carried out based on the production plan target and constraint conditions to obtain a production plan scheduling model, and the constraint conditions comprise constraints of basic data of products / product groups, working procedures / working procedure groups and products / product groups, so that the data processing efficiency is improved, and formulation of a production plan is optimized.

The invention discloses a deep learning model for picking up a seismic phase from a seismic signal with a low signal-to-noise ratio. The deep learning model comprises a feature extraction trunk, a bidirectional time sequence-channel attention module (BTCA) and a multi-scale dilated convolutional layer module (DSCN). According to the feature extraction trunk, a cascaded LiteMobileBlock module is used, shallow high-resolution features are extracted from an original waveform step by step, and an initial feature map is generated; the bidirectional time sequence-channel attention module integrates the time sequence modeling capability of the bidirectional LSTM and the spectrum sensing capability (emphasizing importance of different sensors / directions) of a channel attention mechanism, and outputs fusion features; and the multi-scale cavity convolution layer module utilizes parallel cavity convolution modules with different expansion coefficients to synchronously capture a local mutation and global oscillation mode of a waveform to generate multi-scale enhancement features, further enhance the capture capability of the model on long-range time dependence in seismic signals through LSTM, and output time sequence enhancement features. According to the model, a multi-scale cavity convolution module, a bidirectional time-frequency attention mechanism module and an LSTM enhanced sequence modeling module are fused, so that the feature extraction and time sequence modeling capability of a seismic signal with a low signal-to-noise ratio is improved, and robust pickup of a seismic phase is realized.

The invention provides a 3D small sample segmentation method and system based on registration alignment and interlayer consistency. The method comprises the following steps: S1, supporting memory extraction; and S2, carrying out sequential segmentation. According to the invention, a 3D medical image is regarded as a series of 2D slice sequences, and sequential processing is carried out by fully using the time sequence modeling capability of SAM2. In this way, the FSMIS-SAM2 can maintain good space consistency between the slices, and the segmentation precision is remarkably improved. The core technology of the FSMI-SAM2 framework is to process a 3D medical image sequence by using a memory enhancement converter of the SAM2. In addition, the invention further provides an innovative inference initial position estimation method, the most appropriate initial slice can be determined for inference through accurate registration according to changes of the anatomical structure of a patient, it is ensured that a high-confidence-coefficient segmentation result can be obtained in the initial stage of sequence inference, and high-quality initialization is provided for subsequent slice segmentation.

The invention provides an intelligent baking temperature control system and method based on the Internet of Things. The system comprises a data sensing module, a dynamic modeling module, an intelligent decision-making module and an interactive monitoring module. The method comprises the following steps: firstly, collecting multi-source heterogeneous data, performing data cleaning and feature alignment, and outputting a standardized baking data set; thirdly, constructing a temperature field space-time model based on the standardized baking data set, and generating a digital twinborn body; then, on the basis of the digital twin, a control instruction set is generated through conjoint analysis of a temperature control strategy and energy consumption optimization, equipment is driven to execute temperature control operation, and execution state data is fed back in real time to form closed-loop control; and finally, the interactive monitoring module provides a visual interface, displays temperature field evolution, an equipment state and material response information, and supports a user to adjust a control instruction. Through multi-source data fusion, temperature modeling, intelligent optimization analysis and user interaction, the temperature control precision, the energy efficiency and the user operation experience are improved.

The invention relates to the field of data fusion, in particular to a data fusion method and system based on reservoir multi-source data. The method comprises the following steps: performing coarse alignment on sensor data with different acquisition frequencies to obtain coarse alignment data; training a deep learning model according to the coarse alignment data to obtain a pre-trained fine alignment time model; setting an initial offset, inputting the coarse alignment data superposed with the initial offset into the branch network to obtain feature vectors, and stacking the feature vectors to obtain a two-dimensional matrix; inputting the two-dimensional matrix into a pre-trained fine alignment time model, carrying out secondary model training, and taking an offset parameter value in a last training result as an optimal offset; and superposing the optimal offset to the coarse alignment data to complete data correction, so that the timestamps of the sensor data are aligned, and performing data fusion on the corrected data through a Kalman filter to obtain fused multi-source data. The method has the effect of improving the precision of fused data.

The invention provides a children practice situation evaluation method, medium and system, and belongs to the technical field of deep learning models.The children practice situation evaluation method includes the steps that children and standard playing audio signals are collected and preprocessed into time-frequency representation, a time window sequence is constructed to calculate window similarity, beat mark points are extracted to form a rhythm sequence, and the rhythm sequence is obtained; a rhythm perception analysis model is input to generate a rhythm feature representation vector, a multi-dimensional deviation vector is formed by applying multi-level time model analysis, a rhythm deviation tolerance range matrix is constructed, deviation similarity is calculated, and finally a rhythm performance score is output through a rhythm evaluation neural network model. According to the method, a convolutional neural network, a long-short term memory network and an attention mechanism are fused, and comprehensive quantitative evaluation of the playing rhythm performance of the children is realized through large-scale data set training and expert scoring verification.

The invention relates to the technical field of video analysis, in particular to a time sequence action positioning method and device based on bidirectional interaction and dynamic feature enhancement. The method comprises the following steps: constructing a self-adaptive feature enhancement strategy, and carrying out layered network architecture integrated dynamic modeling and local and global time sequence interactive modeling through the self-adaptive feature enhancement strategy; the adaptive feature enhancement method comprises a multi-scale dynamic time sequence modeling module and a global and local adaptive bidirectional interaction module. Introducing a self-adaptive feature enhancement strategy into the encoder; and performing feature enhancement on the initial feature through an encoder to generate an enhanced time sequence feature. The invention provides an effective self-adaptive two-way interactive dynamic time sequence enhancement framework, which uses learnable local and global affine matrixes to carry out time sequence modeling in parallel. The parallel structure supports iterative bidirectional information transmission between characteristics and adaptive balance of short-term and long-term dependencies.

The present disclosure relates to the technical field of optimization of charging facilities, and in particular, to a day-ahead coordinated optimization scheduling method for a truck mobile charging station. The method includes: constructing an optimization scheduling model framework, wherein the optimization scheduling model framework includes: an EV charging demand generation model and a TMCS spatial-temporal model, the EV model is used to determine the position and time of the TMCS charging demand, and the TMCS scheduling model is used to describe the spatial-temporal dynamic characteristics of TMCS operation and complete the coordinated optimization scheduling of TMCS between EV charging service and energy arbitrage; capturing a charging decision process of heterogeneous EV users by adopting MCS and a multinomial Logit model; establishing an extended graph model to describe the spatial-temporal dynamic characteristics of TMCS; and then expressing the coordinated scheduling model as a mixed integer linear programming model.

The invention provides a learning performance precise teaching management method based on time sequence behavior modeling. The learning performance precise teaching management method comprises the following steps: S1, carrying out multi-modal learning behavior data acquisition; s2, aligning and segmenting the time sequence data; s3, performing knowledge retention rate differential modeling; s4, carrying out time sequence feature extraction; s5, constructing a mixed time sequence model; s6, performing dynamic learning ability evaluation; s7, carrying out adaptive resource recommendation; s8, carrying out cross-correction knowledge diffusion optimization; the method has the following advantages: the method is real-time and accurate; the data is acquired to acquire the intervened closed-loop delay lt; compared with the traditional method, the time is increased by 40 times. And cost optimization: the workload of teachers is reduced by 58% and the resource purchase cost is reduced by 42% through an automation strategy. The scale effect is that federal learning supports ten-thousand-person-level concurrence, and the model updating period is shortened to the hour level from the quarter level. Education fairness: cross-school knowledge diffusion enables the superior rate of weak schools to be improved by 29%.

The invention provides a weak supervision video anomaly detection method and system based on prompt learning, and belongs to the technical field of abnormal event detection based on computer vision, and the method comprises the steps: obtaining to-be-processed video data; and processing the acquired to-be-processed video data by using a pre-trained anomaly detection model to obtain a specific classification result of the abnormal events in the video. According to the invention, a video local and global adaptive time modeling module is introduced to capture local and global dependency relationships at the same time, and the relationship between the demand of detailed time modeling and the calculation efficiency is balanced; by utilizing an external knowledge base, the distinguishing capability of the model on different categories is improved; according to the method, a text-video comparison loss function is designed, the similarity of a correctly matched text-video pair is enhanced, the similarity of wrong matching is reduced, and too high similarity of a negative sample is effectively inhibited, so that the distinguishing capability of the model is improved, the matching of the text and the video is more accurate, and the video and text alignment capability of the model is enhanced.

The invention relates to the technical field of large model reasoning, in particular to a reasoning performance optimization method and system based on a large model, and the method comprises the following steps: initializing a reasoning performance optimization agent; collecting hardware environment indexes in real time, wherein the hardware environment indexes comprise a video memory utilization rate, a CPU (Central Processing Unit) exchange number, residual video card resources, storage IOPS (Input / Output Per Second) and network throughput; the method has the beneficial effects that related statistical indexes, including model types, model weight file total volume, model average sequence length, the number of tokens per second output by the model, first token time of the model, a display card list occupied by the model, the size of a KVcache block, the size of a KVcache sliding window and the like, of each model in a service system are comprehensively collected and analyzed; the system performance is comprehensively evaluated, and the defects that in the prior art, performance evaluation is not comprehensive, and a real-time monitoring mechanism for key indexes such as memory occupation and network bandwidth is lacked are overcome.

The invention discloses a method for constructing a neural network tracking controller of a hypersonic flight vehicle. The method comprises the following steps: 1, establishing a longitudinal dynamic model of the hypersonic flight vehicle; 2, calculating a group of balance points of the hypersonic aircraft according to the longitudinal dynamic model at a constant speed and a constant height; 3, performing coordinate transformation and discretization processing on the group of balance points to construct a discrete time model of the hypersonic flight vehicle based on a discrete time nonlinear output regulation theory so as to construct a closed-loop system of the discrete time model of the hypersonic flight vehicle; 4, constructing a feed-forward function based on a closed-loop system of the discrete time model of the hypersonic aircraft, and approaching the feed-forward function by adopting a neural network to construct an output feedback controller; and 5, finding the optimal weight of the neural network, and performing coordinate transformation on an output feedback controller to construct a neural network tracking controller. According to the invention, tracking control of the hypersonic flight vehicle can be realized, and tracking performance with relatively high precision is realized.

The invention belongs to the field of traffic control systems, and relates to a traffic flow prediction system and method based on an adaptive gating space-time diagram convolutional network, the system is obtained by training an AG-STGCN model, and the AG-STGCN model comprises a feature fusion module, a causal convolutional layer, an adaptive gating diagram convolutional layer and an output module; a feature fusion module is added to the starting part of the AG-STGCN model, node input features are smoothed, and a one-way graph edge trimming mechanism is proposed in the construction of a road network structure, so that the graph structure is more sparse, and the over-smoothing and over-fitting problems are relieved; then adaptively updating and forgetting node features by using an adaptive gating graph convolutional network by using a gating thought; further utilizing an attention mode to aggregate different layers of gating map convolutional network features, and fully utilizing local and global information of a road network; a traffic flow prediction space-time model is constructed in combination with lightweight time sequence causal convolution, the model can predict traffic flow conditions of 12 time steps in the future, and the prediction result is accurate and reliable.

The invention belongs to the technical field of universal time Transform models, and particularly relates to a universal time Transform model zero sample prediction training method which comprises the following specific steps: S1, data preprocessing and enhancement: firstly collecting and integrating time series data of multiple fields, then performing feature engineering on the time series data, and then enhancing the data; s2, improving a model structure and a training strategy: firstly, adding an adaptive weight adjustment mechanism in an attention module of a universal time Transform model; through the multi-field data fusion and data enhancement technology, types and features of training data are enriched, so that the model can learn wider data modes and laws; therefore, the model can be better generalized when facing zero sample prediction tasks in different fields, the prediction accuracy and stability are improved, and the overfitting problem caused by single data is reduced.

The invention provides an unmanned aerial vehicle path planning method and system based on an intelligent logistics cabinet, and relates to the field of logistics planning, and the method comprises the steps: obtaining a distribution task set, and calculating the total travel time corresponding to all distribution tasks in the distribution task set, so as to determine a scheduling time range; grouping the distribution task set to obtain a plurality of task groups; configuring constraint conditions for modeling; introducing a binary variable and using a time extension network method to introduce a time dimension to construct a target planning model; and solving the target planning model through a preset solver. Through time discretization, a dynamic problem is converted into a static network problem, so that the problem is more visual and easy to understand and analyze. The target planning model is easy to expand, the problem that a continuous time model is difficult to model can be converted into the problem that modeling can be carried out, and modeling and solving of complex problems are achieved.

The invention relates to the technical field of face recognition, in particular to a safety management system based on face capture, which comprises a multispectral acquisition module, a biological feature extraction module and a space-time modeling module, comprising face image data of a visible light wave band and a near-infrared wave band; the biological feature extraction module performs subcutaneous biological tissue chromatographic analysis based on spectral absorption difference according to the facial image data of the near-infrared band; according to the face image data of the visible light wave band and the near-infrared wave band, surface material reflection characteristic identification is carried out; according to the face image data of the visible light wave band, dynamic micro-expression relevance feature extraction is carried out; the space-time modeling module receives a processing result of the biological feature extraction module and constructs a feature model including a short-term dynamic mode and a long-term evolution trend.

The invention discloses a soil texture remote sensing mapping method based on time window screening. The method comprises the following steps: step 1, collecting and testing a soil sample; 2, screening a remote sensing image time window; step 3, acquiring and preprocessing an environment covariable; 4, constructing a multi-source data set; 5, constructing a soil texture prediction model; 6, multi-temporal remote sensing covariable combination optimization modeling is carried out; and step 7, soil texture mapping based on the optimal multi-temporal remote sensing combination. And fusing the multi-source environment covariable and the multi-temporal remote sensing data, and constructing a soil texture prediction model based on the optimal multi-temporal model combination by adopting an extreme gradient lifting algorithm. The problems of insufficient representativeness and weak generalization ability of single-time-phase remote sensing data are solved. On one hand, the generalization ability of the model is improved, and on the other hand, quantitative analysis of the key environmental factors is realized in combination with the SHAP technology, the interpretability of the model is enhanced, and meanwhile, the soil texture prediction precision is effectively improved.

The invention provides an aerospace craft discrete trajectory precision reconstruction method based on a variable order, and the method comprises the following steps: calculating the order of a reconstruction model based on a given highest-order dynamic parameter of an aerospace craft discrete trajectory; calculating a coefficient of the reconstruction model; based on a given aerospace craft discrete trajectory, constructing a continuous time model of a flight trajectory; and substituting any moment into the continuous time model of the flight trajectory to obtain trajectory data of the aerospace craft at any moment. According to the method, reconstruction can be completed with higher precision based on given discrete trajectory data, and trajectory continuity is considered; order configuration can be flexibly carried out, and the adaptability to discrete trajectories with different dynamic change rules is improved.

In various examples, machine learning models that benefit from temporal context while being computationally efficient to train and use are described herein. For instance, the disclosed systems and methods may apply a temporal series of images to a model and use intermediate features output from one or more backbone layers of the model as training data. In some examples, one or more recursive layers and / or one or more head layers of the model—or another model—may be trained using the training data by applying the intermediate features to the recursive layer(s). The recursive layer(s) may output a state representative of a temporal combination of the intermediate features, and the state may be applied to the head layer(s) to make one or more predictions. During inference, the recursive layer(s) may, in some examples, continuously update the state based on previous states of the recursive layer(s).

The invention discloses a human behavior recognition method and device based on multi-modal knowledge graph reasoning enhancement, and relates to the technical field of image processing, and the method comprises the steps: obtaining to-be-recognized video data; uniformly sampling to-be-identified video data to obtain a plurality of key frames; processing the plurality of key frames by adopting a trained human body behavior recognition network, and obtaining a category result of the video data to be recognized by utilizing complementarity between the visual information and the text information; wherein the trained human body behavior recognition network is obtained by training the initial human body behavior recognition network by taking data of a preset category as a training set. According to the method, the semantic comprehension capability and the space-time modeling capability of the model can be improved.