A privacy-protected big data recommendation method and system

Abstract

The invention discloses a big data recommendation method and system with the privacy protection function. The method includes the following steps that behavior data of users are acquired and are subjected to anonymization processing on a big data processing end; the attributes of the behavior data, subjected to anonymization processing, of the users are subjected to statistics, a statistical attribute behavior list is established, each attribute of the list represents one piece of personal information of each user, and the statistical result of each attribute is converted into an enumeration value; similar user behaviors are searched for, the similarity of every two user behaviors is calculated according to the enumeration values of data of the two user behaviors, a similarity value and a corresponding threshold are compared, and recommendation information is generated according to a comparison result. The big data recommendation method and system can protect the privacy of the users, encryption is not needed, use is convenient and fast, the calculation amount is small, and implementation is easy.

Description

technical field [0001] The invention relates to the field of big data security, in particular to a privacy-protected big data recommendation algorithm and system. Background technique [0002] There are a large number of personalized search and recommendation services in the Internet, social networks, and e-commerce. For example, in a social network, it is often necessary to find common friends of two or more social individuals, such as "Who is your mutual friend?" However, the served individual in the social network may not wish to disclose their specific friend information (or Real friend information, such as name, etc.) to the social network to search, therefore, the social network needs to find the information of common friends without knowing the specific friend information. [0003] Similarly, in e-commerce, shopping sites usually have a recommendation function, which is usually done on the basis of finding common shopping items, for example, "People who bought this i...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a method that can not only protect privacy, but also does not need to be encrypted, and is convenient and fast, with a small amount of calculation and easy to implement, aiming at the defect that the search and recommendation methods in the big data technology in the prior art cannot protect user privacy. Privacy-protected big data recommendation method and system

Images