基于非合作博弈的电力培训平台交互信息自动抽取方法  

Automatic Extraction Method of Interactive Information of Electric Power Training Platform Based on Non-cooperative Game

在线阅读下载全文

作  者:王燕萍 徐洪伟 完泾平 周熠 WANG Yan-ping;XU Hong-wei;WAN Jing-ping;ZHOU Yi(The Training Center of State Grid Zhejiang Electric Power Co.,Ltd.,Hangzhou 310015 China;State Grid Zhejiang Electric Power Co.,Ltd.,Hangzhou 310012 China)

机构地区:[1]国网浙江省电力有限公司培训中心,浙江杭州310015 [2]国网浙江省电力有限公司,浙江杭州310012

出  处:《自动化技术与应用》2022年第8期52-55,共4页Techniques of Automation and Applications

摘  要:由于信息抽取效率以及抽取结果可信度较低,漏检率增加,提出一种基于非合作博弈的电力培训平台交互信息自动抽取方法。将一种抗强噪声的Gabor滤波方法引入到抽取过程中,深入分析Gabor算子的参数选择,采用改进的Hough变换方法进行电力培训平台交互信息去噪。组建以最小电力培训平台交互信息自动抽取次数为目标的博弈模型,通过粒子群算法和内点结合的分布式算法对模型进行求解,以实现电力培训平台交互信息自动抽取。实验结果表明,所提方法能够有效提升电力培训平台交互信息自动抽取效率以及抽取结果可信度,降低漏检率。Due to the low efficiency of information extraction and the credibility of the extraction results,the rate of missed detection increases.This paper proposes an automatic extraction method of interactive information for electric power training platform based on non cooperative game theory.In this paper,a Gabor filtering method with strong noise resistance is introduced into the extraction process,and the parameter selection of Gabor operator is deeply analyzed.The improved Hough transform method is used to denoise the interactive information of power training platform.In order to achieve the automatic extraction of interactive information of electric power training platform,a game model is set up with the objective of minimizing the number of times of automatic extraction of interactive information of power training platform.Experimental results show that the proposed method can effectively improve the efficiency of interactive information extraction and the credibility of the extraction results,and reduce the rate of missed detection.

关 键 词:非合作博弈 电力培训平台 交互信息 自动抽取 

分 类 号:TP393[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象