Social relationship recommendation method

Abstract

The invention discloses a social relationship recommendation method, comprising the following steps: S1, carrying out data collection, namely acquiring data of a user, integrating and classifying thedata, and analyzing the data, so that interestingness of the user and social contact attention are obtained; S2, carrying out data searching, namely searching similar data according to the interestingness of the user in the step S1, and carrying out primary screening on the searched data, so that data of target users is obtained; and S3, carrying out data comparison, namely comparing the screeneddata with the data of the user, recording a comparison result, and then preliminarily sorting the searched target users according to interest similarity. The method disclosed by the invention carriesout screening on the collected information for multiple times, the information is sorted, and useless repeated information is eliminated, so that the collected information is more accurate and ordered, the target users can be obtained more accurately and rapidly, and time is saved.

Description

technical field [0001] The present invention relates to the technical field of social relationship recommendation, in particular to a social relationship recommendation method. Background technique [0002] With the advancement of network technology, users usually need to find other users who have a certain relationship with themselves or have certain interests and hobbies, and build social relationships with them, so as to get the desired content from other users. After retrieval, the application number is 201310213578.0 The patent document of discloses a social relationship recommendation method and system. The method includes: the social relationship recommendation system acquires the user's music behavior data, counts the user's preference for each music label according to the music behavior data, and calculates the user's preference for each music label The music similarity between users is calculated by the preference value of the label, and user recommendations are ma...

AI Technical Summary

Problems solved by technology

However, this recommendation method is inconvenient to integrate the collected data, resulting in large and disorganized information, which brings some troubles to the recommendation, and is not convenient for accurate and fast recommendation of target users.