基于机器学习的调度操作行为挖掘与推荐技术研究及应用

Research and Application of Dispatch Operation Behavior Mining and Recommendation Technologies Based on Machine Learning

受互联网用户推荐技术的启发,基于调度系统中运行人员的历史操作记录,结合数据分析与机器学习算法提出了一种有效的调度操作行为模式挖掘与推荐技术。首先,所提技术采集记录调度员日常操作数据,并通过页面类型划分、会话识别、事务识别等过程实现数据预处理。然后,利用模式分析和聚类分析完成调度员行为模式挖掘,并结合关联规则将模式数据压缩至频繁模式树(FP-tree)。最后,利用基于模式树结构的实时推荐系统为调度员提供操作推荐服务。在实际调度系统上进行验证和应用,结果表明所提技术能有效识别出调度员的操作行为模式并为调度员提供较为精准的操作推荐,进而提高调度员与调度系统的交互效率,减少调度员的工作量。

Inspired by the Internet user recommendation technology,an effective dispatch operation behavior pattern mining and recommendation technology is proposed based on the historical operation records of operators in the dispatch system,combined with data analysis and machine learning algorithms.Firstly,the proposed technology collects and records the daily operation data of dispatchers and performs the data preprocessing through page type division,session recognition,and routine identification.Then,the behavior pattern mining of dispatchers is completed by using pattern analysis and cluster analysis,and the pattern data is compressed to a frequent pattern tree(FP-tree)by association rules.Finally,the real-time recommendation system based on the pattern tree structure is used to provide the operation recommendation services for dispatchers.The results of the verification and application in the actual dispatch system show that the proposed technology can effectively identify the operation behavior pattern of dispatchers and provide more accurate operation recommendation for dispatchers,thereby improving the interaction efficiency between the dispatcher and the dispatch system,and reducing the workload of dispatchers.