Intelligent multi-modal data desensitization method and device in vertical field

Abstract

The embodiment of the invention provides an intelligent multi-modal data desensitization method and device in the vertical field, and the method comprises the steps: collecting data and metadata thereof before and after general field desensitization, and carrying out the preprocessing of the data and metadata thereof, so as to obtain a first data set; collecting vertical field non-desensitized data and metadata thereof, and preprocessing the vertical field non-desensitized data and metadata thereof to obtain a second data set; training a preset neural network model based on the first data setto obtain a pre-training model; adjusting the pre-training model based on a second data set to obtain a data desensitization model; and inputting to-be-desensitized data and metadata thereof into thedata desensitization model, and outputting desensitized data. According to the method, the transfer learning technology is adopted, the general field data desensitization knowledge with more availabledata is learned, and the learned general field data desensitization knowledge is transferred to the vertical field with less available data, so that a large amount of repeated manual annotation workis avoided, and the data desensitization cost is reduced.

Description

technical field [0001] Embodiments of the present invention relate to the field of data desensitization, and in particular to an intelligent multimodal data desensitization method and device in the vertical field. Background technique [0002] With the development of the Internet and the widespread application of cloud computing, big data, and artificial intelligence technologies, data security issues have become increasingly prominent. In the process of scientific research, product development, and data disclosure, algorithms need to collect and use user data. In these processes, the data is inevitably exposed, causing the problem of sensitive information leakage. There are many solutions to solve the security problem of sensitive data, but the most commonly used is data desensitization technology. The traditional data desensitization technology lacks the prediction of diversified scenarios and the relevance of business production. In the face of massive data, manual inter...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide an intelligent multi-modal data desensitization method and device in the vertical field to solve the problem that the existing data desensitization methods do not take into account the specific requirements of desensitization in different industries, the reliability is not high and the flow complicated question

Images