Data table connection sequence selection method based on machine learning

The invention discloses a data table connection sequence selection method based on machine learning. The method comprises the following steps: S1, encoding SQL statements, and respectively generating eigenvectors of columns, data tables and connection relationships; s2, designing a vector tree AT according to the eigenvectors of the columns and the data table to generate eigenvectors of a connection tree; s3, designing a partial connection plan model SP to generate a feature vector of a partial connection plan according to the columns, the data table, the connection relationship and the feature vector of the connection tree, and further generating a feature vector of a connection state at the next moment; and S4, constructing a deep reinforcement learning model J according to the feature vector of the connection state at the next moment, and generating an optimal connection sequence of the data table in combination with the partial connection plan model SP and the vector tree AT. The problem that the query ef