Method for recommending microblog, wechat and mobile client cross-information-source accounts

Abstract

The invention discloses a method for recommending microblog, wechat and mobile client cross-information-source accounts. The method comprises the following steps: dividing microblog, wechat and mobileclient cross-information-source account correlativity measurement indexes into three levels comprising a plurality of primary correlativity measurement indexes, wherein various primary indexes are issued to a plurality of secondary indexes, and various dimension data fields corresponding to the secondary indexes are tertiary indexes; determining seed accounts and a plurality of target accounts; acquiring various dimension data under the tertiary indexes, and quantifying similarity of the various dimension data; determining primary index weight and weights of various secondary indexes under the primary indexes on the basis of user attention needs; and calculating the weighted sum of the similarities of the various dimension data under the obtained various tertiary correlativity measurementindexes and the respective weights to obtain correlativity exponents of various target accounts, and recommending the correlativity exponents of the target accounts in an inverted order. The method can recommend the accounts in a cross-information-source manner, and the recommending result is accurate and reasonable.

Description

technical field [0001] The invention relates to the field of Internet application technology. More specifically, the present invention relates to a cross-source account recommendation method for two micro-ends and one end. Background technique [0002] With the popularization of mobile networks, Weibo, WeChat, and news clients (hereinafter referred to as: two micro-ends and one end) cover an increasing number of people, and social media is becoming the source of generation and fermentation of hot events in the network society, often driven by the influence of communication. News websites and traditional media followed up with reports. However, in order to attract the attention of netizens, there is no shortage of information such as vulgar tastes, extreme thoughts, free thoughts, and false rumors in order to attract attention. There are also groups of domestic and foreign forces using self-media to infiltrate the Internet and maliciously spread demagogic and incendiary rem...

AI Technical Summary

Problems solved by technology

These account recommendation methods have the problem of a single factor in the recommendation results. Some account information that users care about is often ranked behind the big V account due to the number of fans and blog posts.

Images