Web Page Classification Algorithm Based on Deep Learning

Abstract

Transmit and process information to establish a learning mechanism and realize the processing of image data and sound data. However, the current research on Web page classification algorithm (WPCA) based on deep learning (DL) is not in-depth. Therefore, the main research of this article is the research of WPCA based on DL. This article first uses the keyword weight calculation method to reduce the impact of a small number of high-frequency words in the web page document on the weight calculation and reduces the value of the low-frequency word weights so that the WPCA is more accurate in the calculation process; second, the use of Chinese web pages: the classification method calculates the similarity between the text to be classified and all the class templates and then determines the category of all texts according to the similarity and certain classification rules; finally, in order to improve the learning rate of DL, consider using adaptive parameters. The optimization algorithm automatically adjusts the size of the learning rate, making the research of WPCA based on DL more efficient. After comparing the DL-based WPCA with the traditional algorithm, the data shows that in terms of time expenditure, the DL WPCA is 354 s, the traditional algorithm is 2436 s; in terms of memory overhead, the DL WPCA is 6.35 s, the traditional algorithm is 186.25 s. The experimental results show that WPCA based on DL are faster and more efficient than traditional algorithms and consume less system memory.