Data classification method and device

Abstract

The present disclosure relates to a method and device for classifying data. The method includes: identifying the category of each training sample in the preset sample database; respectively selecting the first training sample set and the second training sample set in the preset sample database; determining The average sample of the training samples of each category; use the preset iterative algorithm to perform iterative operation on the average samples of all categories to obtain the classification dictionary of the first training sample set; decompose each training sample in the second training sample set under the classification dictionary Obtain a training sparse coefficient vector; concatenate all the obtained training sparse coefficient vectors to obtain a training matrix; determine the category label of each column vector in the training matrix according to the category of each training sample in the second training sample set, and save the training matrix The class label corresponding to each column vector in . The method can increase the speed of training the dictionary during data classification, reduce the time consumed, and improve the overall efficiency of data classification.

Description

technical field [0001] The present disclosure relates to the technical field of data mining, in particular to a data classification method and device. Background technique [0002] Classification can be used for prediction. The purpose of prediction is to automatically deduce the trend description of the given data from the historical data records in the future, so as to make class predictions for future data. Data classification has a wide range of applications, such as: medical diagnosis, credit grading for credit card systems, image pattern recognition, etc. [0003] The purpose of classification is to learn a classifier (classification function or classification model), which can map the data items to be classified in the data block to a given specific category. However, in related technologies, when training a classifier, a large amount of random signals are usually used as input signals to train a classification dictionary (ie, a classifier), which makes the training ...

AI Technical Summary

Problems solved by technology

However, in related technologies, when training a classifier, a large amount of random signals are usually used as input signals to train a classification dictionary (ie, a classifier), which makes the training process of the classification dictionary complicated and takes a long time, resulting in a slow speed of data classification. slower and less efficient

Images