Identity matching method and device

Abstract

The embodiment of the invention discloses an identity matching method and device. The method comprises the steps: obtaining social network data related to a target person, and making a communication relation graph according to the social network data; wherein the communication relationship graph represents the contact information among the plurality of contact ways; wherein the plurality of contact ways comprise a second contact way related to the target person; obtaining one or more contact way sequences according to the communication relationship graph to form a contact way sequence set; training a preset model by taking the contact way sequence set as a training data set to obtain a vector of each contact way; and performing correlation calculation on the obtained vectors of the plurality of contact ways, and obtaining a second contact way matched with the target person according to a calculation result. The scheme of the embodiment does not depend on manual experience, the real identities of related personnel are automatically mined, the labor cost is reduced, convenience is brought to case detection, and the case detection efficiency and the mining accuracy are improved.

Description

technical field [0001] This article relates to information processing technology, especially an identity matching method and device. Background technique [0002] In order to carry out relevant investigation work more effectively, the public security department needs to track the mobile phone number of the suspect. If the suspect's mobile phone number is discarded or changed, all current tracking clues will be interrupted, making it difficult to continue the investigation. [0003] At present, it is basically based on summarizing the work experience of police officers, condensing these experiences into rules of program language, and screening through these rules. [0004] This technical method relies heavily on human experience, and the calculation efficiency of the screening model composed of refined rules is relatively low, time-consuming and laborious, and the effect is poor. There are often a lot of results screened out by the rule model, and a lot of manual further sc...

AI Technical Summary

Problems solved by technology

[0004] This technical method relies heavily on manual experience, and the calculation efficiency of the screening model composed of refined rules is relatively low, time-consuming and laborious, and the effect is poor

There are often a lot of results screened by the rule model, and a lot of manual further screening is required

At the same time, there may be conflicts between different rules, which brings difficulties to programming implementation

Images