5 results about "Pattern learning" patented technology

This invention belongs to the field of soft measurement modeling technology and discloses a soft measurement modeling method based on mode-related spatiotemporal diffusion generation, which includes the following steps: (1) acquiring data of multi-mode dynamic processes; (2) data partitioning and preprocessing operations; (3) establishing a mode-related spatiotemporal diffusion model and generating virtual samples; (4) predicting pressure variables of three-phase flow processes and evaluating model performance. This invention proposes a soft measurement modeling method based on mode-related spatiotemporal diffusion generation. By using the DSTN-Net noise prediction network to capture the dependence of dynamic data in the time and space dimensions, the mode learner learns the multi-mode distribution characteristics and distinguishes the data distribution of different modes, which can generate virtual samples with high similarity to the original samples, thereby improving the prediction performance of the soft measurement model in the case of small samples.

This invention relates to the field of intelligent medical data analysis, specifically to an intelligent data analysis method for hospital infection control. The method includes the following steps: multi-source infection control behavior data collection, infection control behavior feature modeling, infection control behavior correlation modeling, graph-based behavior pattern learning, multi-modal fusion infection risk assessment calculation, and dynamic evolution analysis of infection risk. This invention, by constructing an infection control behavior relationship graph and introducing a joint embedding representation mechanism of behavior nodes and related features, achieves modeling of complex correlations between multi-source infection control behaviors, overcoming the limitations of existing technologies that rely solely on single rules or independent data indicators for analysis. Furthermore, this invention, by constructing an anomaly identification mechanism based on the deviation between predicted and actual behaviors, and combining cross-modal attention fusion and feature contribution analysis methods, achieves dynamic assessment and interpretable analysis of infection risk.

The application discloses a new energy charging pile fire hazard analysis method and system based on pattern recognition, and relates to the technical field of fire pattern recognition. The method comprises the following steps: reading real-time sensing data set of a target charging pile; performing pattern correlation anomaly detection based on real-time pattern recognition labels to obtain a detection matrix; performing multi-pattern learning by using ternary predetermined pattern labels to obtain a fire hazard detection channel; guiding channel analysis matrix by the real-time labels to obtain a first result; compensating the first result by using adjacent charging piles to obtain a second result; constructing a current pattern correlation topology network to optimize the second result to generate a third result. The technical problems of false negatives and false positives caused by single mode, lack of multi-mode cooperation and topology correlation in the prior art new energy charging pile fire hazard detection are solved, the accuracy and reliability of fire hazard detection are improved through multi-mode adaptive learning and topology correlation optimization, and the technical effects of early warning and active protection are realized.

This invention belongs to the field of large language model technology, specifically a method for constructing large language models based on DSL, SYSML, and UML constraints. The method includes: constructing a five-layer unified capability stack, embedding constraint concepts into the large language model at the architectural level; defining a unified intermediate representation (UIR) as a universal data format; injecting constraint concepts into model weights at the parameter level through a four-stage unified adjustment process of corpus immersion, graph semantic learning, inference pattern learning, and capability alignment; constructing a unified inference pattern library covering requirements analysis, architecture design, behavioral modeling, constraint verification, code generation, and document generation; and using the UIR and the inference pattern library to guide inference, achieving synchronous generation and constraint verification of multiple output types. This invention enables the large language model to form structured constraints internally, resulting in outputs that naturally meet engineering requirements, and solves the problems of easy failure of external constraints and poor cross-domain adaptability.

The application discloses a brain electrical signal visual decoding method and system based on neural co-occurrence pattern learning, and comprises a neural co-occurrence Transformer model, specifically comprises a space-time convolution feature extraction module and a neural co-occurrence encoder, and the neural co-occurrence encoder comprises feature identity embedding and a Transformer encoding block.The feature identity embedding is that a set of learnable vector parameters are initialized as unique identity identifiers of each feature block, and the parameters are directly superimposed on the feature blocks output by the space-time convolution feature extraction module, so that the neural activity patterns stably co-occurring under specific visual stimulation are automatically discovered and focused; then the neural activity patterns are input into the Transformer encoding block to obtain brain electrical representation vectors; and the brain electrical signal is decoded by adopting a multi-modal contrast learning mode and discarding traditional time position coding and instead capturing the co-occurrence patterns of neural signals, so that the visual decoding precision of the brain electrical signal is significantly improved.