16 results about "Denormalization" patented technology

The invention relates to a rainfall nowcasting method based on U-KAN grading loss weighting and frequency self-adaption, which comprises the following steps: (1) carrying out quality control and screening on a radar puzzle, and establishing a data set; (2) dividing a training set, a verification set and a test set, and standardizing; (3) constructing a U-KAN model, selecting training parameters and inputting data: combining a traditional Unet structure with a KAN network to construct the U-KAN model; then performing model training to obtain a prediction result; the prediction result is restored to the original magnitude through destandardization; (4) introducing a loss function based on a root-mean-square error and grade weighting in a model training stage, and performing post-processing on model output by adopting a frequency deviation correction method; (5) integrating and averaging the forecast products processed by the two complementary strategies, and recording the forecast products as U-KANE; and (6) predicting a rainfall result in the next three hours by using radar echo data in the past one hour, and outputting a rainfall short-term and imminent forecast result by the U-KANE.

The invention discloses a multi-scale time sequence prediction method based on an adaptive sparse expert selection strategy and a closed continuous time neural network. The method comprises the following steps: carrying out normalization and low-dimensional feature mapping based on RevIN; performing trend-seasonal structure enhancement processing on the feature sequence after linear mapping; constructing a multi-scale expert model based on the feature sequence after trend-season enhancement; self-adaptive sparse expert selection and load balancing loss calculation are carried out; carrying out weighted aggregation and residual fusion on multi-scale expert output; global modeling of a closed continuous time neural network based on channel weighting is carried out; and finally performing prediction generation and reverse normalization. The multi-scale time series prediction method has the multi-time-scale adaptive modeling capability, the sparse expert efficient selection mechanism and the global continuous time modeling capability, and can be applied to various multivariable time series prediction scenes such as power load prediction, weather prediction, industrial production monitoring, traffic flow prediction and financial price prediction.

The invention relates to the technical field of ETL resource optimization, in particular to an ETL pipeline dynamic resource optimization method, system and device and a medium, and the method comprises the steps: collecting ETL pipeline operation environment time sequence data, and carrying out the standardization processing after the time sequence data is divided according to a time window; generating a system load index linear prediction sequence by using the linear load prediction model; generating a system load index coupling prediction sequence by using a pre-trained multi-dimensional time sequence load prediction model; integrating the two prediction sequences and then carrying out destandardization to obtain an original system load index comprehensive prediction sequence; and based on the original system load index comprehensive prediction sequence, identifying a peak period, a valley period and a resource abnormities and tension period of the system load, and dynamically adjusting and executing a scheduling strategy of the ETL task according to an identification result. According to the method, the multi-source time sequence data is collected, the comprehensive prediction sequence is generated by combining the two models, and the scheduling strategy is dynamically adjusted, so that automatic optimization of ETL pipeline resources and improvement of system efficiency are realized.

Embodiments of the present disclosure relate to metadata-driven analytical data modeling. Systems and methods are provided for converting data stored in an operational database to a format / structure optimized for a data lake bin. The data conversion is metadata-driven, where metadata characterizing the data conversion can be automatically generated via various denormalization / modeling techniques, including: path / edge / tree / log denormalization, and state machine / aggregation / adaptive modeling.

The invention relates to the technical field of prediction, and provides a data prediction method and device. The method comprises the steps of performing frequency domain moving average adaptive normalization on to-be-predicted data to obtain target normalized data; performing grouping modeling on the target normalized data to obtain inter-channel dependency data inside and outside a group; inputting the inter-channel dependency data into a large language model, and performing fine tuning on the large language model to obtain prediction data output by the large language model; and carrying out reverse normalization on the prediction data to obtain target prediction data. According to the method, the problems of non-stationarity, channel dependence and insufficient data volume of operation and maintenance data can be fully solved, so that the prediction accuracy and the prediction efficiency are improved.

The present invention relates to an atmospheric radioactive release source term inversion method under incomplete data conditions, comprising: S1, inputting and normalizing the transport matrix H m×n and the observation vector y obs m , m represents the amount of data provided by the measurement point during the complete simulation period, and n represents the time step of the simulation; S2, initialize the source term release rate vector σ n ; S3, solve the total variation regularization parameter λ; S4, obtain the cost function expression and its gradient expression; S5, set the constraint boundary of the solution; S6, update the source term release rate σ n ; S7, determine whether the convergence condition is met, if yes, go to S9, otherwise go to S8; S8, determine whether the number of iterations reaches N max If yes, go to S9, otherwise return to S6; S9, solve the release rate σ n Denormalization is performed to obtain the source term inversion results based on incomplete observation data.

The invention discloses an irrigation area underground water level burial depth prediction method based on a CNN-LSTM combination model, and the method comprises the steps: obtaining the data of the influence factors of the irrigation area underground water level burial depth, and carrying out the normalization processing; sorting the normalized data into a data set according to a time sequence, and dividing the data set into a training set and a test set; extracting data features of each influence factor of the underground water level burial depth; inputting the data features into a long short-term memory network to construct an underground water level burial depth prediction model, and finally obtaining the monthly underground water level burial depth after an output result is subjected to reverse normalization processing; and calculating a Nash efficiency coefficient NSE according to a prediction result, and performing parameter optimization on the CNN-LSTM combined prediction model to obtain an appropriate prediction model. According to the model, local and global information can be considered at the same time, so that the prediction result is higher in precision and stable; for an overfitting phenomenon easily occurring in small sample data, a method of discarding part of neurons is adopted, so that the problem can be effectively solved, and a relatively good prediction result can be obtained.

The application discloses a material preparation prediction method, device and equipment and a storage medium. In the application, production information is subjected to feature extraction, the screened time sequence features are normalized, then the normalized second production features are input into a Transformer model comprising a destabilization attention mechanism, and finally the output of the Transformer model is denormalized to realize material preparation prediction, thereby eliminating the scale difference between different variables in multivariate time sequence data. In addition, in the process of predicting the material preparation, the disturbance information is normalized and input into a second encoder, the target disturbance features are obtained, the target disturbance features are fused with the third production features, the fused features are input into the decoder of the Transformer model, and then denormalization is performed to obtain the target preparation prediction result, so that various disturbances are considered in the production process of the product and the required material quantity is recalculated, and the accuracy of predicting the preparation quantity of the material is improved.

The invention relates to the technical field of inventory management, and discloses an electricity coal inventory prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining multi-source time series data related to the electricity coal inventory; aiming at a fluctuation rule of the multi-source time series data, carrying out adaptive learning to obtain a normalization parameter of a historical window and an anti-normalization parameter of a prediction window; the normalization parameters are utilized to carry out normalization transformation on the multi-source time sequence data, the normalized data are input into a preset multi-scale time sequence prediction model to obtain a preliminary prediction result, the multi-scale time sequence prediction model is used for extracting and fusing time sequence features of different time scales, prediction is carried out based on the fused multi-scale time sequence features, and the prediction result is obtained. Obtaining a preliminary prediction result; and performing anti-normalization on the preliminary prediction result by using the anti-normalization parameter to obtain a final electricity-coal inventory prediction value. According to the method, the data inherent rule is fully mined, the capturing capability of the model for complex time sequence changes is enhanced, and the accuracy of electricity-coal inventory prediction is improved.

The application discloses a container throughput prediction method based on stacked ensemble learning, and relates to the technical field of intelligent ports. In the system operation, multi-source data is collected from a port operation system, an economic statistics platform and a shipping database, a comprehensive feature system containing throughput, freight rate, transportation time, policy variable, seasonal characteristics and macroeconomic indicators is constructed, and serialization and standardization processing are performed, and an improved model is constructed. The improved CNN-LSTM model introduces a deep separable convolution, a bidirectional LSTM and an improved attention mechanism to enhance the representation ability of key time steps, adopts Bayesian optimization to automatically search for hyperparameters, combines an early stopping strategy to control overfitting, simultaneously realizes multi-model integration based on inverse error weighting and meta-learning linear regression model, adaptively adjusts the rolling prediction window size according to the data coefficient of variation, generates future multi-period throughput prediction results through multi-step rolling prediction, and performs denormalization output.

This invention discloses a maneuvering target tracking method based on a Mamba tracking network, comprising: 1. Preprocessing trajectory data, calculating the mean and standard deviation, and normalizing the input data to eliminate sequence non-stationarity; 2. Constructing a maneuvering factor generator to map statistical features into adjustment factors reflecting the target's maneuvering characteristics; 3. Constructing a target tracking network based on a Mamba tracking network, extracting long-range spatiotemporal dependence features of the trajectory using a selective scanning mechanism, and dynamically adjusting the network feature response through adjustment factors; 4. Performing denormalization on the network output to recover the target state prediction value at the physical scale. This invention, through the organic combination of the Mamba tracking network and adjustment factors, effectively compensates for the loss of maneuvering information during the normalization process, significantly improving the accuracy and generalization ability of tracking highly maneuvering targets while maintaining linear computational complexity, and has significant application value.

Systems and methods are provided for transforming data stored in an operational database to a format / structure optimized for use in a data lakehouse. The data transformation is metadata-driven, where the metadata characterizing the transformation of data may be automatically generated via the performance of various denormalization / modeling techniques, including: path / edge / tree / log denormalization, and state machine / aggregate / adaptive modeling.

The invention discloses a data processing method, a computer readable storage medium and a computer program product, and relates to the field of integrated circuit design. The method comprises the steps that first data is determined based on input data, the input data is an index of an exponential function, and the first data is a decimal part of a fixed point number obtained by converting the input data; under the condition that the input data does not meet the normalization requirement, B-spline curve fitting is conducted on the first data, a first processing result is obtained, the normalization requirement is the requirement which needs to be met when the exponential function calculation result is a normalization number, and B-spline curve fitting is achieved through partial sum array calculation; performing normalization processing on the first processing result to obtain a second processing result; generating a non-normalized exponential function calculation result based on a preset index and the second processing result; wherein the index part of the non-normalized exponential function calculation result is a preset index, and the mantissa part of the non-normalized exponential function calculation result is a second processing result.

A system and computer implemented method for execution of aggregation expressions on a distributed non-relational database system is provided. According to one aspect, an aggregation operation may be provided that permits more complex operations using separate collections. For instance, it may be desirable to create a report from one collection using information grouped according to information stored in another collection. Such a capability may be provided within other conventional database systems, however, in a non-relational database system such as NoSQL, the system is not capable of performing server-side joins, such a capability may not be performed without denormalizing the attributes into each object that references it, or by performing application-level joins which is not efficient and leads to unnecessarily complex code within the application that interfaces with the NoSQL database system.

The invention discloses an ocean temperature prediction method based on the Kupman theory and comparative learning. The method mainly comprises a data processing module, a dual-core modeling module, a loss optimization module and a result output module. The data processing module comprises a Golden ocean and environment monitoring service data set acquisition unit, a 7: 1: 2 proportion data segmentation and loading unit and a time window-based normalization and anti-normalization unit; the dual-core modeling module comprises an EDMD module and an FE-LSTM module; the loss optimization module comprises a GCL calculation unit fusing multiple factors and a parameter optimization unit adopting an AdamW optimizer; and the result output module combines the prediction results and evaluates and outputs the prediction results through R2, MAE and RMSE. According to the method, the non-stationarity of the ocean data is effectively processed, the prediction accuracy of the sea surface temperature is improved, 1-7-day prediction is supported, reliable data is provided for climate research, ocean management and disaster early warning, and the technical shortages of a traditional method are filled up.

Systems and methods address the inefficiencies in document creation and management within large, globally dispersed organizations. The system leverages multiple independent cloud-based Generative AI (GenAI) models, each specialized and context-sensitive, to dynamically generate and contextualize documents tailored to specific regional and contextual requirements. A global repository meticulously catalogs and annotates documents with detailed metadata, enabling precise retrieval based on user-specific search criteria. The system employs a denormalization slant to generalize search queries, facilitating global context searches and affinity mapping to ensure relevance. A Primary Context Controller Hyper Model orchestrates the confederation of independent GenAI models, refining and enhancing documents to meet precise user needs while adhering to local nuances. Automated, rule-based approvers ensure instant validation and quality control, while a feedback loop mechanism continuously improves the models' accuracy and relevance. This decentralized, scalable approach reduces computational burden and costs, providing a robust, efficient solution for high-quality, context-aware document generation.