Multi-dimensional portrait construction method and system for crowd with specific tendency

Abstract

The invention relates to a multi-dimensional portrait construction method for a crowd with specific tendency. The method specifically comprises the following steps: S1, taking an input method data source as a target crowd data source; s2, constructing at least one feature library of a set with at least one specific tendency feature according to an input method data source and actual requirements; s3, matching the input method data source of the to-be-analyzed crowd with the feature library, and screening out a target crowd with specific tendency; s4, extracting input original text data of the target crowd, and constructing a single-channel target crowd portrait library; s5, exporting individual identification class information, and associating network accounts of the individual existing in all Internet platforms; and S6, carrying out cross-Internet platform network data fusion: fusing heterogeneous network data of each Internet platform, adjusting the specific tendency of an individual according to an analysis result, forming a specific tendency target crowd multi-dimensional portrait library, and adjusting and perfecting the related tendency hierarchical feature library in the S2.

Description

technical field [0001] The invention relates to a method for constructing multi-dimensional portraits of people with specific tendencies. [0002] The invention also relates to a system for constructing multi-dimensional portraits of people with specific tendencies. Background technique [0003] With the popularization of mobile Internet and social media, the dissemination of various types of illegal information has intensified, the means of dissemination have become increasingly concealed, and the shortcomings of existing monitoring methods have become increasingly prominent. The development of the Internet has brought unprecedented challenges for relevant departments to carry out special work such as anti-illegal activities. The popularity of various network applications including cloud disks, instant messaging, forum blogs and online finance has made people with specific illegal tendencies use a large number of private and group-oriented network tools to incite, recruit,...

AI Technical Summary

Problems solved by technology

In recent years, the total amount of global Internet data has maintained a relatively high growth rate. On the one hand, the technical monitoring area is far behind the data growth rate of the entire network, and it is difficult to achieve results simply by adding human or technical resources; on the other hand, new technologies and applications of network communication have caused Monitoring blind spots mainly include closed communication platforms such as various social media, network disks, email groups, and instant messaging groups, as well as semi-closed communication platforms such as Moments, content sharing communities, and live barrage

As a result, the management and control of topical harmful information is "fortified layer by layer, and difficult to prevent layer by layer".

[0005] In addition, compared with conventional harmful information, the dissemination of various illegal information is more organized and purposeful, and has obvious characteristics: content production is more concealed, dissemination is circled and private, outbreaks are more random, and domestic and foreign exchanges are frequent

These characteristics make it very difficult to identify and monitor such harmful information, and it is difficult to find the source and predict in advance, but once it appears, it will cause extremely bad effects, resulting in a passive supervision situation.

Images