User profile construction method and system based on passive WiFi and deep clustering

Abstract

The invention relates to a user profile construction method and system based on passive WiFi and deep clustering. The user profile construction system based on passive WiFi and deep clustering includes a plurality of WiFi detectors, a server for data processing training, and a database for storing data. The user profile construction method based on passive WiFi and deep clustering includes the steps: scanning a mobile phone through a passive WiFi technology, and performing clustering analysis with deep learning so as to depict a typical profile. The user profile construction method and systembased on passive WiFi and deep clustering have the advantages of having no demand for carrying special equipment or additional download terminals by means of the popular device with the WiFi function,thus being easy to promote; being wide in the coverage and being convenient to operate by performing non-inductive detection by the passive WiFi; and performing prediction on foot passenger distribution by means of a deep learning K-means model, thus achieving accurate depiction of a user profile.

Description

technical field [0001] The present invention relates to a passive WiFi positioning technology, a machine learning method, and a deep learning method, in particular to a user portrait construction method and system based on passive WiFi and deep clustering. Background technique [0002] User portrait is a tagged user model abstracted based on information such as user social attributes, living habits, and consumption behavior. The core value of user portraits lies in understanding users, guessing potential needs of users, finely locating crowd characteristics, and tapping potential user groups. Since the 21st century, with the continuous development and innovation of smart phones and Internet technology, the mobile Internet, as a product of the combination of the two, has developed rapidly in recent years. As the duration and frequency of people using smartphones continue to increase, their user behavior data increases exponentially, but users' time tends to be more and more ...

AI Technical Summary

Problems solved by technology

At the present stage, the data source of user portraits mainly relies on the capture and description of network user behaviors. Users’ network behaviors can certainly provide a large number of data samples for user portraits, but under the background of diversified life, there are great differences in users’ network behaviors. limitations, making the portrayal of the user's portrait inaccurate

Images