首页>
外国专利>
Classification of top-level domain (TLD) websites based on a known website classification
Classification of top-level domain (TLD) websites based on a known website classification
展开▼
机译:基于已知网站分类的顶级域(TLD)网站分类
展开▼
页面导航
摘要
著录项
相似文献
摘要
Systems and methods for classification of web sites and/or their corresponding URLs based on a known web site classification are provided. According to one embodiment, a website URL is received that is known to be associated with a particular content classification. A list of candidate domain names including a host name of the website URL is generated based on a defined TLD list. For each of the candidate domain names it is determined whether an IP address of the candidate domain name is equal to an IP address of the website URL. When the result is affirmative, the particular content classification is associated with the candidate domain name; otherwise, a cosine similarity measurement process is performed between information associated with the candidate domain name and information associated with the website URL to determine whether to associate the particular content classification with the candidate domain name.
展开▼