To unambiguously identify topological entities such as faces, edges and vertices is one of the key issues of feature_based modelling. This makes it possible to replay the modelling history when the solid model is re_e...To unambiguously identify topological entities such as faces, edges and vertices is one of the key issues of feature_based modelling. This makes it possible to replay the modelling history when the solid model is re_evaluated. This paper describes a naming mechanism in order to fully automate model generation in terms of the constructing history. The topological naming system(TNS),presented in this paper, assigns a persistent identification to every topological entity if necessary, thus automatically generates a design variant when the design object is re_evaluated.展开更多
为有效解决构建电力运检知识图谱的关键步骤之一的电力运检命名实体识别问题,通过构建一种基于Stacking多模型融合的隐马尔可夫-条件随机场-双向长短期记忆网络(hidden Markov-conditional random fields-bi-directional long short-ter...为有效解决构建电力运检知识图谱的关键步骤之一的电力运检命名实体识别问题,通过构建一种基于Stacking多模型融合的隐马尔可夫-条件随机场-双向长短期记忆网络(hidden Markov-conditional random fields-bi-directional long short-term,HCB)模型方法研究了电力运检命名实体识别问题。HCB模型分为两层,第一层使用隐马尔可夫模型(hidden Markov model,HMM)、条件随机场(conditional random fields,CRF)和双向长短期记忆网络(bi-directional long short-term memory,Bi-LSTM)模型进行训练预测,再将预测结果输入第二层的CRF模型进行训练,经过双层模型训练预测得出最后的命名实体。结果表明:在电力运检命名实体识别问题上HCB模型的精确率、召回率及F1值等指标明显优于单模型以及其他的融合模型。可见HCB模型能有效解决电力运检命名实体识别问题。展开更多
文摘To unambiguously identify topological entities such as faces, edges and vertices is one of the key issues of feature_based modelling. This makes it possible to replay the modelling history when the solid model is re_evaluated. This paper describes a naming mechanism in order to fully automate model generation in terms of the constructing history. The topological naming system(TNS),presented in this paper, assigns a persistent identification to every topological entity if necessary, thus automatically generates a design variant when the design object is re_evaluated.
文摘为有效解决构建电力运检知识图谱的关键步骤之一的电力运检命名实体识别问题,通过构建一种基于Stacking多模型融合的隐马尔可夫-条件随机场-双向长短期记忆网络(hidden Markov-conditional random fields-bi-directional long short-term,HCB)模型方法研究了电力运检命名实体识别问题。HCB模型分为两层,第一层使用隐马尔可夫模型(hidden Markov model,HMM)、条件随机场(conditional random fields,CRF)和双向长短期记忆网络(bi-directional long short-term memory,Bi-LSTM)模型进行训练预测,再将预测结果输入第二层的CRF模型进行训练,经过双层模型训练预测得出最后的命名实体。结果表明:在电力运检命名实体识别问题上HCB模型的精确率、召回率及F1值等指标明显优于单模型以及其他的融合模型。可见HCB模型能有效解决电力运检命名实体识别问题。
