Method and system for performing topic-level privacy protection on document set

Abstract

The invention provides a method and system for performing topic-level privacy protection on a document set. The method comprises the steps of: inputting the document set and a topic-level privacy strategy, wherein the privacy strategy comprises one or more topic key words which need privacy protection; expanding the topic key words to generate one or more sensitive key words; and determining privacy documents from the document set based on the generated sensitive key words. According to different embodiments of the invention, the sensitive key words are generated based on one or both of the internal features of the document set and the external knowledge (ontology). A training document is not needed in the method provided by the invention; and therefore, the system is more efficient, flexible and practical, a large quantity of privacy strategies can be synchronously processed, furthermore, the dynamic change of the privacy strategy can be supported conveniently.

Description

technical field [0001] The present invention generally relates to privacy protection of document collections, and more particularly, to a method and system for subject-level privacy protection of document collections. Background technique [0002] With the rapid development of computer and network technology, the information available to people has been characterized by digitization and mass quantification. However, digitization and networking have also made privacy protection and management of information more challenging. Especially in occasions involving highly private information such as health information and account information, this problem needs to be solved urgently. For example, in order to facilitate the sharing of medical information, the use of electronic medical records and electronic health records has become a trend. Medical workers, medical researchers, health departments, insurance companies and other medical-related personnel can easily conduct related bu...

AI Technical Summary

Problems solved by technology

In the existing work described above, the patent EP1638032A3 uses a keyword-level privacy policy. The disadvantage of this method is that it is difficult for users to exhaust privacy-related keywords, which makes it difficult to achieve usable privacy protection.

The patent US7409406B2 transfers the access control right from the search server to the document owner to avoid the risk of privacy leakage on the server. This method cannot be applied in many practical situations, because the document owner or privacy-related persons are often offline ( Such as patients in electronic medical information systems), it is unreasonable to ask them to process access requests in real time

The patent US2009 / 0144255A1 realizes the support for topic-level privacy policies and overcomes the shortcomings of the patent EP1638032A3. However, this patent needs to prepare training documents for each privacy policy when expanding the subject keywords. However, the preparation of training documents requires manual labeling , very time consuming

Especially when there are a large number of document owners who have established a large number of privacy policies, and users may change the privacy policy during use, in this case, the method based on training documents lacks flexibility and is not applicable in practical applications

Images