Network harmful information keyword extraction method and harmful keyword library construction method

Abstract

The invention discloses a network harmful information keyword extraction method and a harmful keyword library construction method. The network harmful information keyword extraction method comprises the following steps: acquiring initial text data information from the Internet; performing hierarchical division by taking the segmented word as the minimum unit, and performing attribute standardized description corresponding to the level on each unit divided at each level to obtain a judgment word; matching the judgment words with an original harmful keyword library by utilizing the attributes of the judgment words, and determining the harmfulness of each judgment word; and by utilizing each determined harmful segmented word, searching a segmented word which simultaneously appears with the harmful segmented word and the occurrence frequency of which meets a preset requirement in the initial text data information, and extracting the segmented word as a suspected harmful segmented word. In addition, the suspected harmful segmented words can be imported into the word bank, the performance of the word bank is checked to determine the judged harmful segmented words, and the updated harmful keyword bank is obtained by utilizing the judged harmful segmented words and the original harmful keyword bank. According to the method, the harmful information words in the internet environment can be accurately identified, and the process of constructing the keyword library is rapid in convergence and low in misjudgment rate.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a method for extracting keywords of network harmful information and a method for constructing a harmful keyword database. Background technique [0002] With the rapid development of Internet technology, my country has fully entered the information age, the storage cost of information is lower, and the dissemination is more convenient, which makes the amount of network information increase exponentially. [0003] Abundant information not only brings a lot of convenience to our life, but also provides a channel for the birth and dissemination of harmful information. At present, my country's monitoring of Internet information and the classification of information are still in the development stage, and there are still many loopholes in the official supervision system. In the face of massive data on the Internet, ordinary residents, especially minors who lack social ...

AI Technical Summary

Problems solved by technology

At present, my country's monitoring and grading of Internet information is still in the development stage, and there are still many loopholes in the official supervision system

In the face of massive data on the Internet, ordinary residents, especially minors who lack social experience, lack the ability to distinguish information and are easily affected by harmful information. A large amount of harmful information on the Internet will poison the daily life of residents and affect social stability.

Images