Calculation method for social network user relationship based on statistical characteristics

Abstract

The invention provides a calculation method for a social network user relationship based on statistical characteristics. The method comprises the steps that (1) user interaction behavior data is collected from a business system; (2) a user interaction record set is generated according to the user interaction behavior data, statistics is performed on interaction frequency distribution of a user pair set and each user pair, and accordingly statistics is performed on interaction frequency distribution of each user; (3) statistics is performed on total interaction frequency and interaction frequency distribution of each user, and relationship strength factors of each user are calculated; and (4) the relationship strength of each user pair in the user pair set is calculated. According to the method, the statistical characteristics of user interactions are utilized to quantize the user relationship, the quantized value can accurately and objectively reflect the relationship between users, and accordingly the type of the user relationship is judged.

Description

technical field [0001] The invention relates to the technical field of network communication, in particular to a calculation method of social network user relationship based on statistical features. Background technique [0002] The application of user relationships based on social networks is becoming more and more widespread, such as the video recommendation website Clicker and Amazon, which provide social recommendations based on user relationships and friend recommendations in various social platforms. Among them, introducing user relationship into the recommendation system can increase the trust of the recommendation results and solve the cold start problem of the recommendation system. Therefore, how to accurately measure the relationship strength between users has become an important problem, and the measurement based on user interaction information is an effective solution. [0003] The relationship strength measure based on user interaction information is based on ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the problem of low accuracy existing in the current user relationship calculation method, and propose a social network user relationship calculation method based on statistical features. The method obtains the interaction frequency distribution according to the interaction record set, and calculates the user relationship. Intensity factor, to adjust the relationship strength between users, so that the user relationship strength can be accurately calculated

Images