3 results about "Linear dependency" patented technology

This invention discloses a daily runoff prediction method based on the Long Short-Term Component Neural Network (LSTCNet) model. LSTCNet leverages the advantages of convolutional layers to extract features. An attention mechanism (AM) is introduced in the long-term component to automatically select relative times across all time steps of the long-term data. The short-term component utilizes a multi-layer residual structure to fuse multi-level features from the short-term data, effectively improving model performance. Furthermore, a traditional AR model is used as a linear neural network component to enhance the learning of linear dependencies between variables and modify the output prediction values. Experimental results show that the proposed method has good performance in daily runoff prediction; the long-term and short-term components can effectively learn from their respective data, demonstrating the strength of the ensemble model.

The invention provides an LLM-driven data query dependency retrieval method and device, equipment and a medium, and relates to the technical field of large model data retrieval processing. The method comprises the following steps: acquiring a user query demand input into an LLM and a pre-constructed entity relationship library; extracting an associated entity from a user query demand, and extracting a query constraint corresponding to the associated entity to form an entity constraint pair; then, matching query rules among the associated entities from the entity relationship library to form a linear dependency chain type structure, and obtaining a query association chain; taking each associated entity in the query association chain with successful validity verification as an independent task node, and performing recursive retrieval query according to the association sequence number to obtain a task query result corresponding to the association sequence number; and finally, integrating task query results to obtain a structured strategy. According to the method, the problems of system flow redundancy, multi-generation strategy and step-by-step triggering of data query in the traditional step-by-step retrieval are solved.

This invention relates to the fields of stochastic processes and Monte Carlo computation, and particularly to a method for constructing a Markov transition operator. The aim is to improve the spectral properties of traditional Markov operators by introducing a higher-order transition structure, thereby enhancing sampling efficiency. First, starting with a basic Markov transition operator that satisfies the invariance of the target distribution, this method, based on the Metropolis–Hastings (MH) framework, introduces a two-step hybrid update mechanism to construct a polynomial Markov operator. Through spectral structure analysis of this operator, its eigenvalue transformation relationship is established, and it is proven that it has a larger spectral gap and better convergence performance compared to the original operator, while also reducing the asymptotic variance of the corresponding statistics. Second, further analysis of the autocorrelation function and integration time shows that the Ishikawa-MCMC algorithm can effectively suppress linear dependencies between samples, resulting in a faster decay rate of the autocovariance, thereby reducing the Monte Carlo covariance. The operator construction method proposed in this invention overcomes the problem of slow convergence of traditional single transition operators under high-dimensional or complex distributions by integrating multi-order transition information. It provides a new operator design framework for Markov chain Monte Carlo algorithms and can be widely applied in fields such as Bayesian statistical inference, complex probability distribution sampling, and stochastic simulation.