微型电脑应用

构建电力企业干部资质画像时，大多忽略了电力企业干部资质信息清洗的必要性，导致画像的信息覆盖率低、F₁系数低、构建时间长，由此，提出基于Agent模型的电力企业干部资质画像构建方法。引入Agent模型，建立电力企业干部资质相关信息采集系统，利用堆栈式降噪自编码器清洗电力企业干部资质信息，通过隐半马尔可夫模型提取电力企业干部的行为特征，将提取的特征输入长短期记忆网络LSTM中，构建电力企业干部资质画像。实验结果表明，所提方法的信息覆盖率高、F₁系数高、画像构建时间短。

In constructing the power enterprise cadre qualification portrait, most of them neglect the necessity of cleaning the power enterprise cadre qualification information, which leads to the low information coverage rate, low F1 coefficient and long construction time. Therefore, this paper proposes a construction method of power enterprise cadre qualification portrait based on agent model. The agent model is introduced to establish the power enterprise cadre qualification information collection system. The stack noise reduction self-encoder is used to clean the power enterprise cadre qualification information. The hidden semi Markovian model is used to extract the behavior characteristics of power enterprise cadres. The extracted features are input into the long-term and short-term memory network LSTM to construct the power enterprise cadre qualification portrait. The experimental results show that the proposed method has high information coverage, high F1 coefficient and short portrait construction time.