针对个性化网络广告中网页与广告匹配的问题，通过将基于关键词扩展的语义分析技术引入到协同过滤系统中，提出一种基于协同过滤与语义分析结合的个性化网络广告投放方法（CFKE）。该方法首先提取网页与广告文本的关键词，并对关键词扩展同义词；然后，计算网页扩展词与广告扩展词的相似度，并与扩展词的权重进行拟合抽取，得到网页与广告最终的相似度，将三维模型降维成二维模型；最后，再利用协同过滤方法进行匹配。仿真表明，与其他算法相比，该算法不仅具有较高的准确度，同时具有较好的系统响应能力。%Aiming at the matching problems of webpage and advertisement in personalized network advertising,a personalized network network advertising method based on the combination of collaborative filtering and semantic analysis is proposed by in⁃troducing the semantic analysis technology based on keyword expansion into the collaborative filtering system. With the method, the keywords of webpage and advertising text are extracted for synonyms extension. And the similarity of webpage extension words and advertising extension words is calculated,and fitted and extracted with the weights of expansion words to obtain the final similarity of webpage and advertisement,and reduce the 3D model to 2D model. Then the collaborative filtering method is used to match with the similarity. The simulation results show that,in comparison with the other algorithms,this algorithm has higher accuracy,and better system response ability.
展开▼
