电子病历的检索和结果多样化算法研究

Exploiting Algorithms for Retrieval and Sorting Diversification Results of Electronic Medical Records

为使用户在电子病历中的检索更贴近用户意图,提出用图结构来表示电子病历数据的研究方法。根据电子病历所具有的实体和属性联系与图的拓扑结构类似的特性,首先将电子病历数据和检索图结构化;将EMRSearch算法与EMR-Tree索引结合,并引入新的Upper bound模型进行裁剪;然后进行匹配,最后将匹配得到的结果集通过Sort Diversity算法进行多样性重排序。实验结果表明,该方法不仅可以提高用户检索效率,还可以提高用户搜索满意度。

To close to the user＇s intention in the query of EMR （electronic medical records）, a design method of showing the structure of EMR by graph structure is presented. Because EMR＇ s structure which has relation between entity and property is similar to the graph data which has topology. First, the data and query of EMR were structured by graph, then the query was searched and matched by combining EMRSearch algorithm and EMR-Tree index. A new pruning strategy called upper bound was introduced. Finally the result set after matching was reordered through the algorithm SortDiversity. Consequently, the experimental results demonstrate that this method can improve the efficiency of user queries, and improve the satisfaction of a user＇s search.