一种融合用户学习过程的用户查询意图模型

用户查询意图模型是查询扩展和查询推荐研究中的一个热点。然而,日志包含的大量噪声对主流的用户查询意图模型构建过程具有较大负面影响。观察日志发现,用户试探性点击是日志噪声的一个主要来源。由此,基于试探性点击的特征提出了一种融合用户学习过程的用户查询意图模型。该模型对用户从试探性点击中学习到的经验进行建模,并基于用户学习到的经验对试探性点击进行识别和过滤。一系列实验结果表明,该模型在日志噪声较高的情况下能够有效过滤试探性点击产生的噪声,提高用户查询意图描述的准确率。将该模型应用于查询推荐后,能有效提高查询条件间的相似性计算结果,并提高查询推荐结果的准确率。

The user intent model fused with studying process

User intent modeling is a hot point in researches of query expansion and query recommendation. But the large amount of noise in search log has great negative impact on the construction of user intent model. By observing the log it can be found that tentative click of the user is one of the main causations of irrelevant feedbacks. To solve the problem, the user intent model fused with studying process is proposed. It models the experiences users learn from tentative clicks, and then identifies and filters those tentative clicks by characteristics it has mine. Test results show that the model can effectively filter noises coming from tentative clicks when log is high level noisy. After applied the model into query recommendation it can improve the precision of similarity computation among queries, and increase the precision of query recommendation obviously.