Abnormal access behavior detection method and system on basis of WEB logs

摘要: The invention relates to an abnormal access behavior detection method on the basis of WEB logs. includes steps 1) performing IP(internet protocol) statistics and URL after removing interference information by analyzing raw logs so as acquire IP statistic list a list, 2) according crawler characteristic recognition, error response code frequency deviation degree while updating 3) sequencing characteristics in set order precedence, outputting sequenced obtain results. By method, model is built with no depending history data, checked lateral comparison, parameter performed voting referring query strings.