8results about How to "Realize deep mining" patented technology

The application provides a die cutting and hot stamping equipment intelligent state monitoring and fault diagnosis system and method, and relates to the field of intelligent monitoring.The method comprises the following steps: collecting working parameters of multiple key parts of the die cutting and hot stamping equipment, constructing a time sequence collection window, slidingly collecting the working parameters, and obtaining characteristic information reflecting the equipment state; based on the characteristic information, constructing an anomaly detection model, performing anomaly detection on the equipment state, obtaining an anomaly score, and judging whether the equipment state is abnormal according to the anomaly score; for the characteristic information judged as abnormal, constructing a fault diagnosis model based on the fault type to which the characteristic information belongs, performing fault diagnosis on the equipment state, and generating a diagnosis result; and generating a comprehensive diagnosis and operation and maintenance decision report according to the diagnosis result.The application realizes comprehensive perception of the internal state of a closed host through multi-sensor collaborative monitoring and dynamic time sequence collection, breaks through the limitations of traditional monitoring, and provides accurate data basis for early fault warning and predictive maintenance.

The application provides a provincial meteorological and administrative collaborative wind speed prediction method based on dynamic federal learning, relates to the cross technical field of artificial intelligence and energy meteorology, S1, basic data of N meteorological monitoring stations in a province is acquired, is divided into M initial subgraphs according to the administrative boundary of a prefecture-level city and is allocated an edge server, each collaborative subgraph pair is determined according to the Pearson correlation coefficient of the wind speed sequence of the station, the time sequence data deviation of the synchronized subgraph is synchronized through a dynamic time warping algorithm after every 3 rounds of federal iteration, and the subgraph data after synchronization is output. Through an endogenous decision and optimization framework, three links of dynamic coordination of cross-domain collaboration, local learning and gradient transmission are coordinated, and finally a global optimal provincial meteorological and administrative collaborative wind speed prediction method based on dynamic federal learning is achieved among multiple targets such as prediction accuracy, convergence speed and communication cost.

The application discloses a joint prediction model based on a three-way joint Bayesian framework and a MCI recurrence risk assessment method, and belongs to the technical field of mild cognitive impairment and dementia prevention. The method comprises the following steps: constructing a longitudinal sub-model to depict the dynamic trajectory of multi-dimensional cognitive indicators; constructing a survival sub-model containing the recurrence event and the competing risk of CRI, and establishing the correlation by using a shared vulnerable item; mapping the longitudinal characteristics to the hazard rate function by defining a three-way association structure containing the current value, the slope or the cumulative effect; and estimating the parameters by using the MCMC algorithm and performing dynamic risk prediction. The method can synchronously integrate the longitudinal data, the recurrence event and the competing risk, effectively correct the measurement error and the competing risk bias, improve the prediction accuracy, and realize the accurate identification and dynamic monitoring of the recurrence risk of the MCI reversal population.

This invention discloses a method and system for predicting pregnancy outcomes in ovulation induction cycles for PCOS patients, belonging to the field of medical artificial intelligence technology. The method includes: acquiring static and dynamic features of PCOS patients; extracting three time-series derived features from the dynamic features: dominant follicle growth rate, multiple follicle synchronous development index, and follicle size uniformity; inputting the static features into a static channel composed of a fully connected neural network, and inputting the time-series derived features into a dynamic channel composed of a gated recurrent unit network; concatenating the outputs of the two channels in a fusion layer and outputting the pregnancy probability through a classification head. This invention, through a dual-channel architecture that fuses baseline clinical parameters and follicle growth dynamic features, achieves a prediction AUC of 0.79, providing effective support for ovulation induction treatment decisions for PCOS patients.

The invention discloses a legal map construction method based on multi-subject behavior recognition and role extraction, and belongs to the technical field of natural language processing and judicial intelligent analysis. The technical problems that multi-subject behavior semantics in criminal case texts are difficult to completely recognize, master-slave roles are inaccurate to judge, and behavior cross relations are difficult to extract are solved. According to the technical scheme, the method comprises the following steps of 1, data acquisition and preprocessing; step 2, semantic role labeling SRL; step 3, multi-level semantic feature extraction; 4, performing combined extraction on entities and relationships; step 5, behavior cross relation identification; and step 6, knowledge storage and application. According to the method, the behavior logic and role relationship of multiple subjects can be accurately described in a single case context, and efficient data support is provided for judicial semantic understanding, evidence chain construction and sentencing assistance.

This invention relates to the field of fault data processing technology and discloses a method and system for fault diagnosis and early warning of mobile energy storage devices. The method includes: acquiring the operating data of the target energy storage object; analyzing the pre-processed real-time operating data to obtain a multi-dimensional situation field; the target energy storage object is an outdoor energy storage power source; calculating the multi-dimensional situation field to obtain the synaptic traces of abnormal data and identifying antibody modes; analyzing the stability of each antibody mode to obtain the mode confidence. This solution accurately captures the dynamic evolution characteristics of multi-parameter coupling of faults by constructing a dynamic cellular network and a multi-dimensional situation field, and achieves deep causal inference based on synaptic traces, antibody modes, and mode confidence. It locks the root cause of the fault by the root cause contribution and generates a fault early warning command by combining the fault outbreak potential energy. This can help non-professional outdoor personnel quickly locate faults and improve the accuracy of diagnosis and the timeliness of early warning.

The present application belongs to the technical field of medical image processing and artificial intelligence, and particularly relates to a frequency domain enhanced in-situ biological hyperspectral feature extraction and classification method. By fusing the adaptive spatial-frequency feature extraction capability of fractional Fourier transform and the local-global spectral attention mechanism, the medical hyperspectral image can be deeply featured and efficiently classified, and the rapid and accurate diagnosis of early pathological lesions can be realized. The method is particularly suitable for real-time analysis of complex non-stationary pathological signals and multi-scale spectral-spatial information in a clinical environment, and provides accurate lesion classification and diagnosis assistance for doctors.

This invention belongs to the field of electrical and magnetic variable measurement technology, specifically involving a method for measuring and identifying electromagnetic response electrical parameters based on linear background stripping and morphology-related parameters. The method involves a preset moving identification window width; within the selected window range, early and late multi-channel electrical responses of equal time periods are extracted from the first and last channels, respectively, and the summation and average are used to generate early and late characterizing multi-channel electrical responses; linear background removal is performed on the early and late characterizing multi-channel electrical responses to obtain early and late multi-channel abnormal morphology vectors; the correlation coefficient of the early multi-channel electrical responses with the late abnormal morphology is calculated to obtain the induced electromotive force (ICF) response identification factor at the center of the window; the window is moved point by point to obtain the distribution of ICF response identification factors corresponding to the overall data profile and normalized; the distribution and intensity characteristics of the ICF response in transient electromagnetic data are identified through its amplitude distribution, effectively improving the accuracy of ICF response identification in transient electromagnetic data.