Target location determination method, device, electronic equipment and computer storage medium

Abstract

The present application provides a target location determination method, device, electronic equipment and computer storage medium. The method for determining a target location includes: acquiring a plurality of target track data of the user within a preset historical time period; determining that each target track data belongs to a corresponding type of preset information point, and determining the corresponding preset information point. The first weight of the first weight and the second weight corresponding to different time periods; according to the first weight and the second weight, carry out weighted clustering on each target trajectory data respectively to determine the target location cluster; calculate the geographic center point of the target location cluster; The center point is determined as the target location. According to the embodiment of the present application, the target location can be determined more accurately.

Description

technical field [0001] The present application belongs to the technical field of target location determination, and in particular relates to a target location determination method, device, electronic equipment and computer storage medium. Background technique [0002] With the continuous development and popularization of smart phones and information and communication technologies, large-scale trajectory data storage has become more common and has become an important source for mining user behavior patterns. Target locations such as workplaces and residences are important manifestations of user behavior patterns. It is used to assist the construction of smart cities, such as optimizing commuting routes, industrial layout, analyzing population flow, etc., so as to reduce traffic congestion and improve the convenience and satisfaction of citizens. [0003] At present, there are mainly two methods for locating the place of work and residence, one is based on rules, and the other...

AI Technical Summary

Problems solved by technology

[0006] However, the rule-based method has relatively large limitations. Different industries have their own rules and data with a specific structure, which is not universal enough; it is difficult to exhaust all the rules, and the adaptability to abnormal situations is not good enough, complex and not accurate enough; model-based The method requires manual labeling, the cost is high and the entire calculation process is relatively complicated, and the accuracy rate is highly dependent on the representativeness of features and the breadth of sample coverage

[0007] The place of work and residence calculated by the existing method often does not conform to the business logic. For example, most of the normal work places should be distributed in point of information (POI) such as office buildings and industrial parks, and a small part should be distributed in other places such as restaurants and shopping malls. Various types of POIs; normal residences should be mostly distributed in POIs such as communities, villas, and apartments, and a small part are distributed in other types of POIs; however, the calculation results of existing methods are greatly affected by the data source and cannot To ensure this, a large number of workplaces may appear in the community, and a large number of residences may appear in office buildings or shopping malls, etc., resulting in unavailable business

Images