Large-scale unstructured data extraction method, system of method and distributed data management platform

The invention discloses a large-scale unstructured data extraction method, a system of the method and a distributed data management platform. The method comprises the following steps of: obtaining a plurality of unstructured data objects and abstracting features of the unstructured data objects into attributes; representing the unstructured data objects by using multi-dimensional vectors corresponding to all the attributes of the unstructured data objects; taking the multi-dimensional vectors as basic units input by a convolutional neural network; learning local attributes of training data through a convolutional layer of the convolutional neural network; carrying out statistic operation on the local attributes through a pooling layer of the convolutional neural network so as to obtain a second feature vector; and inputting the second feature vector into a full connection layer of the convolutional neural network, and obtaining an unstructured data classification result by utilizing a classifier. 本发明公开了大规模非结构