摘要
为了更准确地将工作票推荐给具备解决问题能力的系统运维专家,对历史工作票数据进行研究提出基于深度学习的工作票专家推荐算法。首先根据专业熟练度水平和领域知识构建专家能力模型,然后设计卷积神经网络框架,在输入层中引入注意力来提高模型对工作票文本特征提取能力,并度量与专家模型的匹配度,实现以推荐质量为依据的专家推荐。在真实的数据集上进行了实验,结果表明与传统的基于机器学习的推荐方法相比,该方法的准确率提升了6%,引入注意力可以有效学习特征权重。
In order to improve the accuracy of recommending trouble tickets to experts with problem-solving ability,the expert recommendation algorithm based on deep learning are studied by learning the historical trouble ticket data. According to the expert ’ s professional proficiency level and domain knowledge,an expert ’ s ability model is constructed,and an expert recommendation framework based on convolution neural network is defined. Attention mechanism is introduced into input layer of the model to enhance the ability of describing the feature extraction of tickets. This paper measures the similarity match score between the problem description and the expert ’ s model to realize expert recommendation based on quality. Experimental results on real ticket datasets show that the proposed method can improve the accuracy by about 6% compared with the traditional machine learning classification recommendation methods,and can effectively learn the weight of ticket feature by introducing attention.
作者
何柔萤
徐建
He Rouying;Xu Jian(School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China)
出处
《南京理工大学学报》
EI
CAS
CSCD
北大核心
2019年第1期13-21,47,共10页
Journal of Nanjing University of Science and Technology
基金
国家自然科学基金(61872186
61802205)
江苏省研究生科技与实践创新计划项目(KYCX17_0403)
关键词
专家推荐
卷积神经网络
注意力机制
系统运维
expert recommendation
convolutional neural network
attention mechanism
system operation and maintenance
