Power grid text data grading and classifying method and system

The invention relates to a power grid text data grading and classifying method, which comprises the following steps of collecting power grid text data, performing preprocessing and enhancement processing on the text data, and constructing a text data training set by using the added text data; constructing a power grid text data classification model framework, and inputting the text data training set into the framework to obtain probability distribution of variables in the training set; updating the parameters of the power grid text data grading and classifying model framework according to the probability distribution result of the variables, and training again; and obtaining a final power grid text data grading and classification model framework after preset rounds of training, and grading and classifying the power grid text data through the framework. 本发明涉及一种电网文本数据分级分类方法，包括以下步骤：收集电网文本数据并对文本数据进行预处理以及增强处理，将增加后的文本数据构建为文本数据训练集；构建电网文本数据分级分类模型框架，将文本数据训练集输入框架得到训练集中变量的概率分布；通过变量的概率分布结果对电网文本数据分级分类模型框架的参数进行更新并再次进行训练；经过