摘要
以改善人工校核调度操作票容易出现疏漏的缺陷,提出基于人工智能的调度操作票命令术语自学习方法。采用规则学习方法建立操作票语法规则库,将操作票语句输入隐马尔可夫模型中,利用维特比算法确定观察序列中的隐藏状态序列,通过状态转移输出最大概率状态序列,输出最大概率状态序列的分词结果即完成标注结果,依据标注结果从语法规则库中提取操作票的动作、对象、状态命令术语,完成调度操作票命令术语自学习。实验结果表明,所提方法可实现调度操作票命令术语自学习,成功执行操作票命令,降低调度人员工作量,提升操作票的调度效率。
In order to improve the defect of manual checking of dispatching operation order,a self-learning method of dispatching operation order terms based on artificial intelligence is proposed.The rule base of operation order grammar is established by rule learning method.The operation order statements are input into hidden Markov model,and the hidden state sequence in observation sequence is determined by Viterbi algorithm.The maximum probability state sequence is output by state transition,and the word segmentation result of the maximum probability state sequence is output to complete the annotation.According to the annotation results,the action,object and status command terms of operation order are extracted from the grammar rule base,and the self-learning of command terms of dispatching operation order is completed.The experimental results show that this paper can realize the self-learning of operation order terms,successfully execute the operation order,reduce the workload of dispatchers,and improve the scheduling efficiency of operation order.
作者
林泽宏
陈威洪
李敬光
张鑫
李敬航
LIN Ze-hong;CHEN Wei-hong;LI Jing-guang;ZHANG Xin;LI Jing-hang(Dongguan Power Supply Bureau of Guangdong Power Grid Co.Ltd.,Dongguan 523000 China)
出处
《自动化技术与应用》
2023年第7期179-182,共4页
Techniques of Automation and Applications
基金
广东电网有限责任公司东莞供电局项目支撑(031900KK52180161)。
关键词
人工智能
调度操作票
命令术语
隐马尔可夫
artificial intelligence
scheduling operation ticket
command terminology
hidden Markov
