Apparatus for classifying category of a text based on neural network method thereof and computer recordable medium storing program to perform the method

摘要

The present invention relates to a device for classifying categories of texts based on a neural network, a method therefor, and a computer readable recording medium for recording a program to perform the method. The device for classifying categories of texts comprises a neural network, a data converting unit, and a classifying unit. The neural network is composed of an input layer formed of a matrix, a hidden layer, and an output layer outputting a result of an arithmetic operation of the hidden layer. The neural network is made of a plurality of layers having a plurality of arithmetic operations, wherein a weighted value is applied to a result of one arithmetic operation of one layer among the plurality of layers to be inputted to an arithmetic operation of a next layer. When texts are inputted, the data converting unit converts the inputted texts into a matrix expression in accordance with the matrix of the input layer. When the texts are target data of which a category is not known, the classifying unit inputs the texts converted into the matrix expression to the input layer of the neural network and classifies categories of the texts depending on results of the plurality of arithmetic operations of the neural network. The present invention can provide the device for classifying categories of texts optimized for individual application problems.