Behavior recognition method and device and storage medium

Abstract

The embodiment of the invention provides a behavior recognition method and device and a storage medium, and the method comprises the steps of obtaining the latitude and longitude of a preset track point, which is about to pass by a connection user, in each subtask in a task chain according to the task information of each subtask in the task chain and preset connection path data; obtaining a first track point, a second track point and a distance between the first track point and the second track point according to all actual connection points of the connection user in the task time period and the starting point longitude and latitude and the ending point longitude and latitude of the subtask; when it is determined that the distances between the multiple first track points and the multiple second track points are within multiple preset distances, calculating the passing rate of each task chain; and if the passing rate of the task chain is lower than the minimum passing rate threshold, determining that the task chain has an invalid connection behavior. According to the scheme, the false connection identification accuracy can be improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of the Internet, and in particular, to a method, device, and storage medium for behavior recognition. Background technique [0002] In the existing mechanism, when transporting between outlets and courier brothers, the connection operation is recorded by the bus, and the company gives the connection user a commission based on the connection operation record. In practical applications, there may be false connection, and the connection user does not have the actual shipping waybill. However, some of the waybills have been connected and scanned to obtain a commission. The phenomenon of false connection will lead to an increase in the cost of enterprise management and control. [0003] During the research and practice of the existing mechanism, the inventor of the present invention found that in the connection process of the existing mechanism, the original manual experience setting...

AI Technical Summary

Problems solved by technology

False connections will lead to an increase in corporate control costs

[0003] During the research and practice of the existing mechanism, the inventor of the present invention found that in the connection process of the existing mechanism, the original manual experience settings of "connecting yourself", "connecting each other", "within 5 minutes "Connection", "connection time is later than the end time of the current shift", "non-planned connection" and other abnormal connection calculation tags have a low recognition rate, and there is a large space for avoiding operations. Employees can avoid these exceptions through certain operations Phenomenon

The abnormal connection calculation label error rate of the original manual experience setting is high, it is easy to misjudge the normal connection and miss the false connection

The abnormal connection calculation label set by the original manual experience is not very interpretable, and it is impossible to verify whether it is a false connection

[0004] It can be seen that the connection behavior in the existing mechanism is easy to falsify and difficult to identify

Images