Method for identifying internet users and device thereof

Abstract

The embodiment of the invention discloses a method for identifying Internet users and a device thereof. the method comprises the following steps: a first user behavior of a first-class user identification and a second user behavior of a second-class user identification are obtained; the above first-class user identification is a scene user identity identification, and the second-class user identification is a user identity identification notified by users; and if relevance between the first user behavior and the second user behavior reaches a predetermined threshold, users corresponding to the above first-class user identification and the second-class user identification are identified as the same user. Based on the above scheme, the above first-class user identification can guarantee the percentage of user identification, and the second-class user identification can guarantee validity and stability of user identification. Through relevance between the user behaviors, whether the users are the same user is determined. If the same user determined, identifications can be unified, and success rate and validity of user identity identification are prompted on the precondition of guaranteeing the coverage.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a method and device for identifying Internet users. Background technique [0002] User behavior analysis has many applications in the Internet industry, such as: personalized search, recommendation system, advertising system, etc. The implementation of these applications generally requires separate analysis and modeling of user historical behavior data, so that user identities need to be identified to distinguish different users. [0003] Since each user has a different user identity, different users can be distinguished through the user identity. The current user identity schemes generally have the following types: [0004] Login account: When users visit the website, they need to register and log in to the account. The website can use the account to identify the user. [0005] Third-party account: Similar to the login account, except that the website uses OAuth (provid...

AI Technical Summary

Problems solved by technology

[0009] In the process of realizing the embodiment of the present invention, the inventor found that: the above solutions can be roughly classified into two categories, one is the solution that requires the user to inform the identity, such as: login account, third-party account; less coverage

The other is a scheme that does not require the user to inform the identity identification. This type of scheme uses scene information to distinguish users, such as: program version identifier, cookie_id, IP address, etc. This type of scheme cannot be distinguished when the scene changes or multiple users are in the same scene user, causing the user ID to fail, so the user ID is also invalid

Images