8results about How to "Improve Grading Accuracy" patented technology

The invention discloses a data classification and grading method, system and device based on big data and a medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring to-be-graded data of a plurality of data nodes and a reference index table of a central management node; extracting content features and business attributes of the to-be-graded data, and generating corresponding data feature identifiers according to the content features and the business attributes; scanning each data feature identifier by adopting a preset sensitive word bank to generate a corresponding data sensitivity score, and evaluating each data sensitivity score through a preset data evaluation matrix to obtain corresponding data grade information; and associating the reference index table of the central management node based on the data feature identifier and the data level information of each data node to obtain a hierarchical index table, and allocating a corresponding access path to each data node in the hierarchical index table. By implementing the technical scheme provided by the invention, the data classification and grading efficiency can be improved.

The utility model relates to the technical field of wine making, and provides an intelligent wine picking and grading system which comprises at least one wine picking device, and the wine picking device comprises a wine distributing mechanism, a storage assembly, a detection assembly and a control assembly; the wine distribution mechanism is provided with an inlet, a first outlet, a second outlet and a third outlet, the inlet of the wine distribution mechanism is used for being communicated with a liquid outlet of a wine making device, the detection assembly is arranged on the wine distribution mechanism and used for detecting parameters of white wine, and the parameters of the white wine comprise the alcohol degree; the storage assembly comprises a first storage module, a second storage module and a third storage module, the detection assembly and the wine distribution mechanism are in communication connection with the control assembly, and the control assembly is used for controlling the inlet to communicate with the first outlet and communicate with the first storage module according to the alcohol content; or the control inlet is communicated with the second outlet and is communicated with the second storage module; or the control inlet is communicated with the third outlet and is communicated with the third storage module. Manual participation is not needed, graded collection is achieved, and accuracy is high.

The invention discloses an N-type hanging polycrystal material resistivity grading method, which comprises the following operation steps: in a straight pulling single crystal process, especially when an N-type circulating material is processed, the resistivity of the material is known and controlled, the resistivity is the measure of the hindering degree of the material to current flow and is influenced by the doping concentration and the temperature, and the resistivity of the material is determined according to the influence of the doping concentration and the temperature. And estimating the resistivity when the corresponding residual material amount grows through the initial head resistivity, the doping concentration and the segregation coefficient in the growth process. According to the resistivity grading method for the N-type hanging polycrystal material, the resistance value range of the N-type hanging polycrystal material is calibrated and divided according to the crucible remaining quantity of an output furnace platform through segregation theory measurement and calculation, the impurity concentration corresponding to the residual quantity of the output furnace platform of the hanging polycrystal material is calculated, and the resistivity corresponding to the current concentration is converted to obtain the tail resistance of the hanging polycrystal material; and the resistor in the range of the suspended polycrystal material is reversely pushed, so that the suspended polycrystal material can be accurately graded, and the resistivity concentration ratio is improved.

This invention provides a method and system for monitoring fatigue status of workers in high-risk industries based on EEG-eye movement fusion, belonging to the field of safety early warning technology. The method includes: real-time acquisition of workers' raw physiological signals using a smart safety helmet; performing bandpass filtering and baseline drift removal processing on the raw physiological signals to obtain multimodal physiological monitoring data containing denoised EEG signals and primary eye movement feature data including blink frequency and gaze duration; extracting blink interval temporal features and gaze point shift features from the primary eye movement feature data in the multimodal physiological monitoring data, and extracting the power spectral density of the EEG feature frequency band within a preset time window. This invention enables accurate classification and reliable early warning of worker fatigue status under complex and high-risk working conditions.

The invention discloses a grading method for core fluorescence brightness and area calculation based on deep learning. The grading method comprises the following steps: S1, forming a labeled fluorescence region data set and an unlabeled fluorescence region data set; s2, preprocessing the core fluorescence images in the labeled fluorescence region data set and the unlabeled fluorescence region data set; s3, segmenting and marking the fluorescent region; s4, constructing a semi-supervised model; s5, based on the label data and the pseudo label data in the extended data set, performing quantitative calculation on the brightness and the area of the fluorescent region by using an improved deep convolutional neural network model; s6, outputting a fluorescence brightness grade and a geological characteristic evaluation result of the rock core; and S7, storing the grading result and related calculation data in a database, and generating an analysis report. The method can improve the efficiency of large-scale data processing while improving the fluorescence brightness and area calculation precision, and can dynamically adapt to the characteristics of different rock core samples.

The application relates to a flexible switchable Euphausia superba intelligent sorting method and device, and belongs to the technical field of aquatic product processing and automatic equipment. The application not only realizes high-precision instance segmentation and flexible reference calculation of Euphausia superba through improvement of a deep learning network and a self-adaptive statistical decision model, but also creatively seamlessly converts a dynamic grading signal generated by front-end vision into a physical driving instruction of a servo motor, so that the rear-end spacing of a longitudinal involute sorting pipe is opened and closed in real time and automatically. The application establishes an intelligent linkage closed loop of "visual perception-dynamic decision-physical execution", can automatically and flexibly adjust a physical sorting channel according to real statistical characteristics of batches of materials, and realizes real flexible nondestructive intelligent grading.

The invention discloses an insomnia severity assessment method in combination with a functional near infrared spectrum, and belongs to the technical field of sleep quality. Comprising the following steps: collecting functional near infrared spectrum sequences of a plurality of channels of at least two wavelengths of a prefrontal cortex to obtain three hemoglobin concentration sequences of the plurality of channels; the method comprises the following steps of: mapping a plurality of hemoglobin concentrations into a plurality of predefined brain regions, performing weighted synthesis on channels in the same region to obtain three hemoglobin concentration brain region-level sequences, performing sliding window segmentation to generate a sample set, and calculating a time domain feature vector; obtaining a compact feature vector through feature selection and dimension reduction processing; and constructing a dynamic weight model comprising a plurality of base learners and meta learners, and training the dynamic weight model by using the sample set to obtain a trained dynamic weight model. Compared with equal weight fusion or a single model, the whole grading accuracy and separability are improved by utilizing'brain region entropy weight integration + sliding window feature + dynamic weight Stacking '.