Social security character portrait method based on multi-view learning

Abstract

The invention discloses a social security character portrait method based on multi-view learning. In social security application of multi-source identity big data, complete priori knowledge and annotation samples are difficult to obtain, a multi-view cooperative training model based on part of domain knowledge, a small number of annotation samples and a large number of unannotated samples is constructed, and accurate mapping from identity attributes to portrait labels is achieved. The method comprises the following steps: firstly, learning three attribute sub-views including a physical space,a social space and a network space and corresponding weights from ternary space identity attributes through ternary space view decomposition of a labeled sample data set; secondly, portrait label classification is conducted on unlabeled samples through a ternary space multi-view classifier, credible classified samples are generated in combination with domain knowledge voting and added to a labeledsample data set, and labeled samples are enriched; the method has an important application value in the field of social safety.

Description

technical field [0001] The invention belongs to the technical field of data analysis, and relates to a method for portrait of a person, in particular to a method for portrait of a social security person based on multi-view learning. [0002] technical background [0003] Every move of a person will leave digital traces in physical, social and cyberspace; physical space includes surveillance video clips collected by a large number of cameras installed in the city, spatial positions recorded by positioning and navigation equipment, and human-computer interaction behavior data; Space includes phone calls, WeChat, text messages, making friends on social platforms, chatting, shopping records on e-commerce platforms, Weibo, etc. to generate various behavioral data; A large amount of basic data in public security, social conditions and public opinion surveys. [0004] Whether it is general Internet rumors, cyber crimes such as fraud, or violent terrorist crimes with major hazards, ...

AI Technical Summary

Problems solved by technology

However, in social security application scenarios, it is difficult to obtain complete prior knowledge and labeled samples, and only part of the domain knowledge and a small number of labeled samples can be obtained, which brings great challenges to the portrait label learning of security suspects.

Images