7results about How to "Efficient and accurate extraction" patented technology

This invention discloses a method for constructing a parameter extraction model for active ingredients in traditional Chinese and Tibetan medicines. The method involves acquiring multi-source sample data of traditional Chinese and Tibetan medicines and constructing key derived features from the preprocessed multi-source sample data. A random forest model is used to generate a corresponding importance score for each key derived feature, forming a feature importance vector. The feature importance vector and the key derived features are weighted and summed to obtain a fusion feature, and the variance and correlation coefficient matrices corresponding to the fusion feature are calculated. The average values ​​of the variance and correlation coefficient matrices are weighted and summed to obtain a comprehensive score. The depth and width of the parameter extraction model to be trained are determined based on the comprehensive score. The number of fully connected modules and neurons in the parameter extraction model is determined by the depth and width to obtain the corresponding target architecture. The parameter extraction model under the target architecture is trained using the fusion features and extracted parameter data to obtain a trained parameter extraction model.

The application provides a kind of multimodal synergistic industrial voice control method.Application to intelligent manufacturing technology field, the method includes collecting industrial field original voice stream, generates noise spectrum entropy value by frequency domain feature analysis, according to the noise interference level determined by dynamic matching array beam forming weight and adaptive filter coefficient, and gets pure voice instruction by noise reduction;Extract its voiceprint features and semantic text, generate instruction semantic structure tree combined with industrial knowledge graph, calculate identity matching degree and semantic analysis confidence respectively, and get instruction comprehensive effectiveness coefficient by weighting;Satisfy the benchmark time to map it to sub-instruction, evaluate process conflict and equipment risk through digital twin pre-play, determine execution strategy;Real-time acquisition of running data in execution, whether to trigger abnormal rollback is determined according to trajectory deviation rate.This improves the efficiency of industrial voice control.

The invention aims to provide a rolling bearing weak fault feature enhancement extraction method, and belongs to the field of rolling bearing fault diagnosis. Firstly, a 1 / 3 binary tree filter bank is adopted to divide an original signal into a plurality of frequency bands, then spectrum amplitude modulation (SAM) is carried out on each filtered signal, a discrete normalized envelope spectrum peak factor (DNESP) index is established, the most MO range is selected in a self-adaptive mode, and then a normalized square envelope spectrum is reconstructed. And finally, constructing a normalized envelope spectrum peak factor (NESP) as an evaluation index, quantizing and reconstructing the richness of fault information in the normalized square envelope spectrum, and adaptively selecting a demodulation band with significant fault information according to the richness, thereby realizing enhanced extraction of fault features. The method provided by the invention can effectively extract weak fault features of the rolling bearing, and has good robustness for various interferences and noises.

The application discloses a vegetation evolution three-dimensional dynamic feature extraction and visualization method based on remote sensing data, and belongs to the technical field of remote sensing information processing and ecological environment monitoring. The method comprises the following steps: step 1, basic data acquisition and processing; step 2, horizontal gradient vegetation coverage spatial centroid migration calculation; step 3, vertical gradient vegetation evolution feature identification; and step 4, vegetation evolution three-dimensional dynamic feature extraction and visualization. The method disclosed by the application is based on multi-dimensional space fusion analysis of remote sensing vegetation index and digital elevation model data, can identify the horizontal migration characteristics and vertical gradient evolution characteristics of vegetation coverage, comprehensively consider the horizontal and vertical vegetation dynamic change characteristics, construct a vegetation three-dimensional curved surface model, efficiently and accurately extract and visualize the spatial structure and dynamic change trend of large-scale vegetation, and provide high-precision spatial analysis technical support for ecological environment monitoring, surface vegetation dynamic research and ecological restoration evaluation.

This invention belongs to the field of signal analysis and processing technology, and provides a fault diagnosis method and system based on broadband data compression processing. The method includes: acquiring the fault current signal of the optical-pile-load system; decomposing the fault current signal using wavelet transform to obtain the wavelet packet coefficients and decomposition levels for each frequency band of the fault current; calculating the corresponding wavelet energy entropy based on the wavelet packet decomposition results of the fault current signal under various combinations of wavelet functions and decomposition levels, thereby determining the optimal combination of wavelet mother function and decomposition level; performing wavelet packet decomposition on the normal current signal and the fault current signal based on the optimal combination of wavelet mother function and decomposition level, reconstructing the current signals of each frequency band before and after the fault, and calculating the Tsallis entropy ratio of the current signals of each frequency band before and after the fault to determine the characteristic frequency bands of the fault current signal. This invention can accurately extract the fault characteristic frequency bands from the MHz-level broadband electrical state data of the optical-pile-load system.

The application provides a dynamic gesture recognition method based on light-weight multivariate space-time convolution, which comprises the following steps: constructing a space feature extraction module based on a pseudo 3D gated attention fusion network; extracting multi-scale space features by using the space feature extraction module; injecting a guided heat map by using a gated attention fusion module to enhance key region features and suppress background interference, so as to obtain a space refinement feature sequence; decomposing the space refinement feature sequence into multiple sub-variables; capturing long-range and local time dependence in parallel by using a modern convolution module; and modeling the intra-variable and inter-variable relationships respectively by using a decoupling feature interaction network, so as to obtain a dynamic gesture recognition result. By combining the multivariate feature decomposition strategy with the modern convolution, the double-branch design advantage of the modern convolution is to balance long-range dependence and local details, solve the limitations of traditional convolution in capturing long-range time dependence, and model complex dynamics.

The application provides a steel coil number recognition method and system based on DBNet and CRNN. The steel coil number recognition method based on DBNet and CRNN comprises the following steps: acquiring a steel coil image; using a DBNet model to extract a target frame region of a steel coil number in the steel coil image, and returning coordinate information corresponding to the target frame region; cutting the steel coil image according to the coordinate information to obtain a regional image of each steel coil number; taking each regional image obtained by cutting as input, and using a CRNN network model to recognize the character sequence of the number text. The steel coil number recognition method provided in the embodiment of the application can realize automatic, efficient and accurate steel coil number extraction and recognition, and is suitable for steel coil related automatic processing and management scenarios.