Data Preparation for Precise Elevator Advertising System

In recent years, elevator media has gradually become an important media, and more and more attention has been paid to it by businesses and media. At present, elevator media mainly use advertising screen in the elevator to broadcast advertisements in turn, and the advertising effect is difficult to evaluate. With the development of information technology such as big data and artificial intelligence, people begin to pay attention to the influence of big data on elevator media. People prefer to advertise by analyzing the commercial attributes of elevators. Meanwhile, advertising recommendation model based on click through rate is widely used in Internet advertising. Due to the lack of passenger commercial attributes (details of users) and feedback information of passengers watching the advertisements (the interactions), the advertising recommendation system of elevator media is mostly based on business logic or big data analysis. It is of great significance to effectively identify the commercial attributes of passengers and judge whether passengers watch advertisements for the accurate delivery of elevator media advertisements. This paper builds computer vision models to effectively identify the elevator passenger attributes and judge whether the passengers pay attention to the elevator advertising. This paper gives the solution of elevator media precise advertising recommendation for the first time, which fill the vacuum in this topic and is of great significance to elevator media precise advertising recommendation.