20 results about "Spatial prediction" patented technology

This invention discloses an interpretable bidding space prediction method based on multimodal data analysis, comprising the following steps: S1, acquiring multi-source time series data and processing it to form standardized input data; S2, constructing training samples and generating lower bound labels, upper bound labels, and boundary information; S3, dividing the data into external driving forces, system endogenous inertia, and market operating state feature groups; S4, inputting an improved boundary-aware temporal Kolmogorov-Arnold network model to obtain boundary response temporal mapping features and boundary response intensity; S5, fusing and generating bidding space fusion features; S6, generating a prediction lower bound and a prediction upper bound, and updating the model parameters; S7, outputting the bidding space prediction interval and multidimensional interpretation. This invention uses an improved boundary-aware temporal Kolmogorov-Arnold network model to achieve interpretable interval prediction of the bidding space.

This application discloses a gesture recognition method, system, device, and computer-readable storage medium, relating to the field of artificial intelligence technology. The method involves training a gesture recognition model using a first training view and a second training view. The gesture recognition model is built based on a spiking neural network model. The method extracts a first spatial feature sequence and a first spatial prediction vector from the first training view generated by the gesture recognition model. It also extracts a second spatial feature sequence and a second spatial prediction vector from the second training view generated by the gesture recognition model. Based on the differences between the first spatial feature sequence and the second spatial prediction vector, and the differences between the second spatial feature sequence and the first spatial prediction vector, a temporal contrast loss value is generated. The gesture recognition model is adjusted based on the temporal contrast loss value to obtain a trained gesture recognition model. A gesture view is then acquired. Finally, the gesture recognition model is applied to recognize the gesture view to obtain the gesture recognition result. This improves the accuracy of gesture recognition.

This invention relates to a method and system for analyzing the meteorological suitability of tobacco cultivation, specifically a method for evaluating and spatially predicting the climate suitability of tobacco cultivation based on multi-source data fusion. It addresses the problems of insufficient spatial resolution of meteorological data, static evaluation models, inadequate multi-source data fusion, separation of disaster early warning and suitability evaluation, and lack of intelligent service capabilities in existing technologies. This invention collects and fuses multi-source data, filters key meteorological elements, constructs fuzzy membership functions and spatial distribution models, calculates grid meteorological element values, and calculates a comprehensive suitability index. Based on this, it classifies the data into levels and generates a climate suitability zoning map. This invention is applicable to fields such as climate suitability evaluation for tobacco cultivation, crop planting zoning, and agricultural meteorological disaster risk assessment.

This application discloses a method, apparatus, server, computer-readable storage medium, and computer program product for predicting the internal reservoir space of fractured-vuggy reservoirs. The method predicts the development location and spatial scale of fractured-vuggy reservoirs based on post-stack impedance inversion, characterizing the external contours of the fractured-vuggy reservoirs. Simultaneously, it clarifies the internal filling characteristics of the fractured-vuggy reservoirs through pre-stack physical property parameter inversion, precisely characterizing the heterogeneous changes within the fractured-vuggy reservoirs. By combining pre-stack and post-stack methods to comprehensively characterize the development scale and internal reservoir space of fractured-vuggy reservoirs, the method improves the prediction accuracy of the development scale and effective reservoir space of fractured-vuggy reservoirs, providing strong technical support for the prediction of effective reservoirs in fractured-vuggy reservoirs.

A marine weather forecasting method utilizing a multi-model ensemble technique according to an exemplary embodiment of the present invention performs a forecast of either sea wind or seawater flow using a probability density function of a bivariate normal distribution, wherein the sea wind and seawater flow are expressed as combination vectors of an east-west component vector u and a north-south component vector v, and the probability density function is a function with u and v as variables, and the correlation coefficient between u and v may be included in the probability density function. Furthermore, the weights of the correlation coefficients are calculated in real time from historical data updated based on the calculation time and may be updated according to the calculation time. Additionally, spatial interpolation reflecting the physical environmental characteristics of the observation area is performed for either sea wind or seawater flow, and a spatial distribution map can be generated by distributing ensemble weights corresponding to the space. Thus, in predicting sea wind or seawater flow, the present invention can not only reflect the speed and direction of vector variables but also mutually compensate for biases between prediction models, thereby improving the prediction reliability and accuracy of weather variables. In addition, by reflecting changes in model performance and environmental conditions over time, it is possible to provide a prediction system capable of stable operation over a long period, and to provide physically consistent and highly reliable spatial prediction information for observation points.

The application provides a short-notice weather radar echo prediction method and system based on a video generation model, relates to the field of weather prediction, and solves the technical problem that the prior art is difficult to model the multi-modal uncertainty and structural mutation behavior in the evolution of a strong convective system with high fidelity under the condition that non-uniform missing often exists in real observation. The method comprises the following steps: obtaining a historical weather radar echo reflectivity factor image sequence of a target area, and inputting the historical weather radar echo reflectivity factor image sequence into an encoder of a video variational autoencoder to obtain a conditional latent variable; inputting the conditional latent variable into a spatiotemporal diffusion Transformer model to output a radar echo latent space prediction sequence of a future preset time length; and inputting the radar echo latent space prediction sequence into a decoder of the video variational autoencoder to obtain a prediction result of a future radar echo reflectivity factor image sequence. The application is used in the process of weather prediction.

This invention relates to a method, device, and medium for predicting electric vehicle charging load. The method includes the following steps: acquiring electric vehicle charging load data and performing clustering; constructing an adaptive correlation graph based on the clustering results, where each node corresponds to a cluster, and the node feature is the average sequence of all load curves within that cluster; adaptively adjusting the connection weights between nodes using a learnable embedding matrix; using the adaptive correlation graph as prior knowledge, extracting spatiotemporal features, and inputting them into a load prediction model; the load prediction model independently performs subspace prediction for each node, implicitly clustering the sequence features in the time dimension through multi-scale gated convolution to obtain deep clustering features, inputting them into an autocorrelation mechanism to identify and aggregate periodic patterns in the time series, outputting the prediction results of each cluster node, and weighted summing to obtain the global load prediction value. Compared with existing technologies, this invention has advantages such as high feature utilization efficiency and high prediction accuracy.

The application discloses a kind of based on compact manifold mapping linearization processing method of high-dimensional data, it is related to data processing technical field.The application is adaptively preprocessed to high-dimensional time series data, through improved order-preserving compression transformation, combined with the scale and attenuation factor of dynamic adjustment, each dimension non-negative infinite domain data is mapped to one-dimensional torus compact manifold angle coordinate;Linear state vector is constructed by angle coordinate, and linear state space model containing sparse regularization and adaptive noise suppression is established;Rolling window multi-step prediction combined with attention mechanism is used, window and model parameters are dynamically updated, and spatial prediction value is obtained;The spatial prediction value is restored to original data domain by accurate inverse transformation;The rationality of prediction is judged by triple check, and related parameters are dynamically adjusted according to the type of anomaly.The application maps infinite domain data to compact manifold, realizes that the computational complexity is reduced from exponential level to linear level, and has wide application value.

This application provides a method, apparatus, electronic device, and system for generating continuous linear structures on an irregular spherical surface. The method, in response to a path generation command, performs spatial offset prediction processing based on the current path orientation to generate a predicted step vector and a predicted growth position; based on the predicted growth position, it performs terrain adaptation detection processing to determine the target landing coordinates and local surface normal on the irregular spherical surface; based on the local surface normal, it performs path attitude correction processing on the predicted step vector to generate a corrected growth tangent adapted to the local terrain, and accordingly generates a segmented structural model placed at the target landing coordinates. This application, through a closed-loop mechanism of spatial prediction and terrain adaptive correction, effectively alleviates the problems of clipping, suspension, and connection breaks caused by linear structures on irregular spherical terrain, improving the fit and continuity of the structure with the complex surface.

The present application relates to the technical field of photovoltaic power prediction, and provides a distributed photovoltaic power prediction method and system fusing dynamic regions and space-time. The method comprises the following steps: according to historical power data and corresponding key meteorological characteristics representing power stations, a time model is used to extract time series trend characteristics, and preliminary time prediction values and time prediction errors of sub-regions of the power stations are obtained; the power stations are taken as nodes to construct a graph structure, and a space model is used to extract space correlation characteristics therein, and preliminary space prediction values and space prediction errors of the sub-regions of the power stations are obtained; the contribution degrees of the time model and the space model are dynamically adjusted by using an information entropy method, and combined prediction powers of the sub-regions of the power stations are obtained; data quality evaluation scores of the sub-regions of the power stations are determined, a scale-up weight is obtained through a proportion of the data quality evaluation scores, and the combined prediction powers of the sub-regions of the power stations are weighted and summed, and a total power of a region is predicted, so that the super-short-term prediction accuracy and robustness are effectively improved.

The present application belongs to the technical field of hydrogeology, and discloses a prediction method for spatial distribution of groundwater recovery force and uncertainty thereof, comprising: calculating groundwater recovery force by using groundwater performance index and recovery force index; and quantitatively analyzing the relationship between the groundwater recovery force and nine kinds of groundwater control factors, i.e., lithology, topography, slope, distance to river, soil, canal system density, permeability coefficient, groundwater depth and land use, based on GIS technology combined with DS model to generate a groundwater recovery force zoning map. The present application can reliably predict the spatial distribution of groundwater recovery force. The present application can not only output the support degree of the evidence layer to the prediction result through the belief function, but also can quantify the uncertainty of the prediction result to reflect systematic error and random error, so that the generated spatial prediction result is accurate and reliable.

A device includes a decoder that includes a spatial prediction engine, a temporal prediction engine, a reconstruction engine, and a decoded picture buffer. The decoder is configured to, in a base resolution mode, reconstruct a base resolution version of a block of a frame using the reconstruction engine and at least one of the spatial prediction engine or the temporal prediction engine. The decoder is also configured to, in an enhanced resolution mode, generate an enhanced resolution version of the block based on a transfer distance between the frame and a key frame.

This invention relates to the field of state recognition technology, specifically a method and system for health status recognition of thoracic surgery patients. The method includes the following steps: acquiring postoperative heart rate, blood pressure, and respiratory rate data; normalizing and constructing a recovery rhythm sequence; using a variational autoencoder to map and calculate the residuals to extract the maximum deviation; calibrating the unstable intervals; determining the synchronous transition critical point; constructing a recovery sequence; identifying abnormal chains; and outputting the state result. In this invention, by constructing the original recovery rhythm sequence and introducing a latent space prediction mechanism, and using differential calculation of residual vectors combined with a fluctuation tolerance threshold to calibrate the unstable intervals, rhythm abnormalities are more accurately judged. By extracting directional consistency and average dwell time indicators from the recovery sub-paths composed of continuous states, and combining this with standard path matching to form a potential abnormal chain identification method, this invention effectively solves the problems of inaccurate identification caused by multi-parameter disconnection, missed transition nodes, and lack of temporal trend in traditional methods.

The application discloses a recommendation method and model training method and device, equipment and readable storage medium in the technical field of computer application, and the method comprises the steps of obtaining historical text information of an accessed text and candidate text information of a candidate text; inputting the historical text information and the candidate text information into a prompt template to obtain an answer word; selecting a mark from the answer word and converting the historical text information, the candidate text information and the mark into a natural language sentence; inputting the natural language sentence into a natural language processing model, predicting the mark by using an answer space, and obtaining a mark probability; and selecting a recommended text from a plurality of candidate texts based on the mark probability. The technical effect of the application is that the language information of a real world large-scale corpus can be fully utilized, and an individualized text intelligent recommendation task is converted into a mask prediction task based on multi-template prompt learning, so that content interested by a user is recommended.

The present application relates to the field of meteorological remote sensing, and specifically discloses a sandstorm source area susceptibility spatial prediction method based on an sp-GSH-EL model; including sandstorm source point extraction, non-sandstorm source point extraction, obtaining a covariant, defining a response variable, integrated learning model training, and sandstorm source area susceptibility prediction; by combining aerosol optical depth (AOD) threshold method and hourly AOD change rate, the dynamic change of dust source point can be more accurately captured, and the timeliness and accuracy of sandstorm source area monitoring can be improved. At the same time, it has the ability to capture spatial heterogeneity: the sp-GSH-EL model combines different spatial proximities to optimize the description ability of local heterogeneity, global similarity and non-linear relationship, and improve the modeling accuracy of multi-scale spatial data.

The present application relates to the technical field of disease distribution prediction, and discloses a method and system for predicting the spatial distribution of alveolar echinococcosis based on multi-source environmental factors, comprising: obtaining multi-source environmental data of alveolar echinococcosis case points in a study area, processing the multi-source environmental data, and screening key environmental factors; obtaining a data set of sample points based on the key environmental factors, and dividing the data set into a training set and a test set; selecting a spatial prediction model, training and testing the spatial prediction model based on the training set and the test set, and obtaining an alveolar echinococcosis spatial prediction model; dividing the study area into a plurality of geographic units, obtaining the incidence probability of alveolar echinococcosis of each geographic unit based on the alveolar echinococcosis spatial prediction model, and determining the risk level. The present application can accurately predict the spatial distribution of alveolar echinococcosis by comprehensively considering multi-source environmental factors.

The application provides a pipeline leakage detection method and system based on visual space-time, comprising: capturing a video using a fixed camera; adopting an adaptive block method to detect a target in a static single-frame image in the video to obtain a static target area; adopting a background difference method and an inter-frame filtering method to analyze dynamic characteristics of a space-time domain of the video to obtain a dynamic target area; and judging a position relationship based on the static target area and the dynamic target area, and simultaneously satisfying a region of space prediction and time sequence prediction, which is a real leakage area. The application comprehensively analyzes static characteristics and dynamic characteristics of a chemical pipeline video through an adaptive block detection algorithm, a background difference method and an inter-frame filtering detection method, realizes real-time dynamic detection of a small leakage, greatly reduces a false detection rate of the leakage, and simultaneously avoids manual detection of pipeline faults, thereby saving manpower and resources.

The application provides a soil thickness spatial prediction method and device, electronic equipment and storage medium, wherein the soil thickness spatial prediction method comprises: obtaining a soil thickness sample data set; obtaining a mixed feature space based on geographical coordinates of sample points and environmental factors of the sample points; clustering all soil sample points based on the mixed feature space to obtain a plurality of geographical and ecological homogeneous partitions; independently training a soil thickness prediction model of each geographical and ecological homogeneous partition based on soil thickness samples corresponding to each geographical and ecological homogeneous partition, and verifying the soil thickness prediction model of the geographical and ecological homogeneous partition based on measured soil thickness values of the sample points; determining a target geographical and ecological homogeneous partition to which a to-be-predicted point belongs; and obtaining a soil thickness prediction value of the to-be-predicted point based on a soil thickness prediction model of the target geographical and ecological homogeneous partition. The application can improve the soil thickness spatial prediction accuracy.

The application discloses a method for reducing pH value of newly-built terrace, and particularly relates to the field of agricultural soil improvement, and the method comprises the following steps: detecting the pH value of soil samples of representative areas of the newly-built terrace; sampling and analyzing the pH value and the vertical distribution of main water-soluble ions of the soil profile of the natural slope surface; realizing the spatial prediction of the pH value of the soil of the whole newly-built terrace by using the unmanned aerial vehicle remote sensing and the convolutional neural network image recognition technology; and guiding the fertilization machinery to carry out the fixed-point strip fertilization on the red area of the thermal map by using the navigation system. The application realizes the effective improvement of the high-pH soil by accurately monitoring and analyzing the spatial distribution of the pH value of the soil of the newly-built terrace and combining the fixed-point strip application of the organic fertilizer and the ferrous sulfate.

This invention discloses a method for constructing and screening pseudo-positive samples based on InSAR and a prior model, relating to the field of geological disaster prediction and evaluation technology. First, this invention identifies high-deformation regions based on InSAR deformation rate fields and constructs an initial pseudo-positive sample set by combining this with high-susceptibility units from a prior susceptibility model. Then, a basic classification model is trained using real positive samples to predict the confidence levels of the pseudo-positive samples. A semi-supervised self-training mechanism is used to iteratively screen the pseudo-positive samples, obtaining reliable pseudo-positive samples through confidence threshold constraints and sample stability judgments. Finally, the real positive samples and the screened pseudo-positive samples are merged to form an enhanced positive sample set for machine learning modeling of geological disaster susceptibility or hazard. This invention can effectively supplement high-confidence positive samples in sparse positive sample regions, improving model training quality and spatial prediction stability, and is applicable to susceptibility assessment of various types of geological disasters such as landslides, collapses, debris flows, and ground subsidence.