中文摘要：

提出一种系统地处理XML数据流的返回结果集的方法．在该方法中，用户对数据的兴趣用XQuery表示，能够处理递归文档以及同时处理多个查询；通过运行时栈驱动的基于二进制的前缀编码，在运行时确定结果集中节点之间的关系，避免了大量结果集之间的连接操作，能够有效减少内存耗费，提高处理性能．

英文摘要：

This paper presents an approach for processing the buffer of XML stream systematically. In this approach, user interests are represented by XQueries, the recursive documents can be tackled, and the multiple queries can be processed simultaneously. This approach can determine the relationship between two nodes in results on the fly based on the binary code through runtime stack, which avoids the join among a large number of results and improves the system performance and memory usage efficiently.