A harmful information identification and filtering algorithm of minority ethnic language based on Boolean model

With the development of network, information amount on the internet is growing rapidly. Harmful information is a great threaten to the healthy Internet environment. This paper introduces the harmful information identification and filtering technology, and presented an algorithm based on Boolean model to deal with the Ethnic Minority Language, with the harmful information processing. The algorithm contains two parts, the principal function which describe the full text retrieval and the recognition feature function to construct index. Take Uigur as an example, experiments shows the algorithm proposed has well performance at information identification and filtering.