改进的XML智能数据清洗策略

Improved XML Intelligence Data Cleaning Strategy

针对XML数据的质量问题,以XML键为基础,借助多模板隐马尔可夫模型信息抽取策略与粒子群优化算法构建新的XML数据清洗方法。为了提高XML相似性数据并行检测效率,利用波函数对粒子群优化算法进行优化。仿真实验表明,与其他XML数据清洗算法相比,该方法的自适应学习能力强、人工参与程度低、计算量小,时间性能有94%左右的提升。

Aiming at the quality of XML data, this paper proposes a new XML data cleaning method based on XML key, the information of multiple templates Hidden Markov Model（HMM） draw-out strategy and Particle Swarm Optimization（PSO）. For boosting the parallel detection efficiency of the XML similarity records, a wave function is used to give relevant improvements to PSO. Contrasted with other XML data cleaning algorithms, simulation experiments show that the optimized algorithm has powerful adaptive learning capability, lower labor cost, less calculation and better time rate around 94%.