In order to improve the ability of gradual learning on the training set gotten in batches of Naive Bayesian classifier, an incremental Naïve Bayesian learning algorithm is improved with the research on the existing incremental Naïve Bayesian learning algorithms. Aiming at the problems with the existing incremental amending sample selection strategy, the paper introduced the concept of sample Classification Contribution Degree in the process of incremental learning, based on the comprehensive consideration about classification discrimination, noisy and redundancy of the new training data. The definition and theoretical analysis of sample Classification Contribution Degree is given in this paper. Then the paper proposed the incremental Naïve Bayesian classification method based on the Classification Contribution Degree. The experimental results show that the algorithm simplified the incremental learning process, improved the classification accuracy of incremental learning.

By analyzing a large number of web pages, we proposed a page segment algorithm which is based on DOM tree structural features and visual features. The algorithm segments the pages to the small particles. It produces basic processing units for recognition algorithms. After segmenting the pages, we extracted the structural and visual features of the pages, and proposed a method to identify the body of the web article. The method uses clustering algorithm and heuristic rules to produce an automatic wrapper. A testing experiment demonstrated the efficacy of the algorithm.