3results about How to "No conflict" patented technology

This patent discloses a convolutional neural network processing method and apparatus, belonging to the field of convolutional neural networks, used to improve data transmission efficiency, optimize the computation process of deep learning, increase computation speed, and reduce power consumption. The main technical solution of this invention is as follows: Weight data is input to a multiplier array according to a first preset method; based on the channels corresponding to each weight data in each row of multipliers, a sub-feature data set corresponding to each row of multipliers is determined; based on the sub-feature data set corresponding to each row of multipliers, the sub-feature data set is input to the multiplier array; the weight data in each multiplier of any row of multipliers is multiplied by each element feature data in the sub-feature data set corresponding to that row of multipliers to obtain a first set of dot product results; the obtained first set of dot product results is input to an accumulator for accumulation; in response to the completion of the accumulator accumulation, the processing result corresponding to the feature data set to be processed is obtained.

The application relates to the technical field of material analysis, and particularly discloses a method and system for regulating an electrospray ion source of a mass spectrometer, a terminal, and a storage medium. The method comprises the following steps: performing feature-level fusion on a multivariate isomer monitoring data set of the electrospray ion source to obtain a digitized state feature vector; periodically dividing the digitized state feature vector to analyze the change trend of a current period state feature vector and obtain a predicted numerical value interval; performing multidimensional compound logic comparison on the current period state feature vector and the predicted numerical value interval to obtain an enhanced state evaluation result; performing state tracing attribution on the current period state feature vector to obtain a core feature dimension and a corresponding change trend, and mapping the core feature dimension and the corresponding change trend to a preset regulation rule library to obtain a working state adjustment parameter set; and encoding the working state adjustment parameter set into a regulation instruction. The application can improve the regulation efficiency of the electrospray ion source of the mass spectrometer.