Target trajectory tracking method based on big data

Abstract

The invention discloses a target trajectory tracking method based on big data, relates to the technical field of target trajectory tracking, and performs quasi-real-time dynamic monitoring on equipment in a target area through real-time acquisition, cleaning, processing and visualization of equipment trajectory data. And the working position, the living position and the frequently-going position of the equipment are excavated, so that the working unit, the industry and the frequently-going place of the equipment are identified. The flow condition of the specific crowd is recognized, and the personnel flow condition among the multiple specific targets is recognized. And through conjoint analysis with other existing data, the anonymous trajectory is subjected to real-name processing, and the target person is further aimed at. The problem that the target person trajectory is difficult to find is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of target trajectory tracking, and more specifically to a target trajectory tracking method based on big data. Background Art

[0002] Target trajectory tracking is one of the key technologies in the fields of computer vision, intelligent monitoring, autonomous driving, drone navigation, etc. With the popularization of the Internet of Things (IoT), sensor networks, and mobile devices, a large amount of location data and video data are constantly generated, forming a rich "big data" resource. These data provide new opportunities to improve the accuracy, real-time and robustness of target trajectory tracking. With the continuous development of informatization, the continuous increase and accumulation of massive data, a large amount of data is stored in various modules, which is difficult to extract and integrate.

[0003] Therefore, it is necessary to propose a target trajectory tracking method based on big data to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that with the continuous development of informatization and the continuous increase and accumulation of massive data, a large amount of data is stored in various modules and is difficult to extract and integrate.

[0005] In order to achieve the above-mentioned purpose, the present invention specifically adopts the following technical solutions:

[0006] A target trajectory tracking method based on big data includes the following steps:

[0007] Step 1: Collect anonymous device trajectory data in real time, collect, clean, process and visualize the data;

[0008] Step 2: Circle the target area on the map, conduct quasi-real-time dynamic monitoring of the device trajectory in the target area, and dig out the device's work location, home location, and frequently visited locations, thereby identifying the device's work unit, industry, and frequently visited locations, identifying the flow of specific groups of people, and identifying the flow of people between multiple targets;

[0009] Step 3: Jointly analyze the data of the location identified in step 2, and turn the anonymous device track into a real name to target the target person;

[0010] Step 4: Filter the latest device trajectory collection time, dig out the device trajectory that is still being updated, and continuously track the trajectory of specific personnel.

[0011] Furthermore, in the step 1, the collected data is cleaned, and the latitude and longitude point data of multiple devices are sorted by time through unique IDs to form a device trajectory route, and the processed device trajectory data is visualized in combination with a map.

[0012] Compared with the prior art, the present invention has the following beneficial effects:

[0013] 1. The present invention integrates scattered and fragmented data together to identify and discover the trajectory of the target device, thereby solving the problem that the trajectory of the target person is difficult to discover.

[0014] 2. The present invention solves the problem of difficulty in tracking the trajectory of the target person by identifying the trajectory of the target device. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1 ,

[0018] Step 1: Take a specific area as an example. Through trajectory analysis, it is identified that a certain device has appeared in the area for 5 consecutive working days, so it is determined that the device belongs to the staff of the specific area. In this way, anonymous device activity traces in a specific area can be identified and analyzed. This method can reveal those devices that work in the area but have not disclosed their identities, providing a unique perspective for in-depth understanding of their operations.

[0019] Step 2: Based on the above analysis of the staff equipment in the specific area, the number of trajectories of a certain location (range 15 meters) is analyzed between 19:00 and 8:00 the next day, and multiple trajectories in one day are counted as only one. If the number of trajectories of a certain location is the highest among all locations within this time period and reaches more than 10 times, then the location is determined to be a residential location.

[0020] At the same time, by tracking the daily movement patterns of devices, the target population’s living range, that is, their living radius, can be determined. This step can identify devices that frequently visit specific types of places, and then infer the industry characteristics of these devices.

[0021] In addition, in-depth analysis of other devices that frequently accompany devices in the target area in time and space. By carefully examining the co-occurrence relationship between the target device and other devices in time and space, more potential organization members or network connections can be revealed, which helps to identify and curb illegal activities early.

[0022] Finally, monitor the inflow and outflow of the target population, especially those abnormal flow patterns. This monitoring not only helps to understand the dynamic changes of the target population, but also can timely detect possible signs of illegal activities and provide key intelligence support.

[0023] Step 3: Match the analyzed work location and home location of the device with the work address, home address and other location data of the existing target. If the work location of the device can match the work address of the target, and the home location and home address of the device can be successfully matched, the target to which the device belongs is determined. Or match the location of the existing target at certain time points with the device trajectory. If the device trajectory can overlap with the location of the existing target at certain time points at more than 3 locations, the target to which the device belongs is determined, and the originally anonymous trajectory data is real-named.

[0024] This process not only enhances the accuracy of identifying the target person, but also helps to accurately target specific individuals. The real-name data can provide deeper insights into the target person's daily behavior patterns and social networks. This analysis method is of great significance in combating illegal social organizations and preventing and solving criminal activities, as it can be discovered in a timely manner, thereby maintaining social security and stability. In this way, potential illegal activities can be monitored and prevented more effectively.

[0025] Step 4: By accurately identifying specific personnel, we can further filter out those devices that have recently continued to update their trajectory data. This process involves careful filtering of the device's latest trajectory collection time to ensure that we focus on those devices that are active and continue to generate data. In this way, real-time trajectory tracking of these specific personnel can be achieved.

[0026] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. The patent protection scope of the present invention shall be based on the claims. All equivalent structural changes made using the contents of the description and drawings of the present invention should also be included in the protection scope of the present invention.

Claims

1. A target trajectory tracking method based on big data, characterized in that: The following steps are involved: Step 1: Collect anonymous device trajectory data in real time, collect, clean, process and visualize the data; Step 2: Circle the target area on the map, conduct quasi-real-time dynamic monitoring of the device trajectory in the target area, and dig out the device's work location, home location, and frequently visited locations, thereby identifying the device's work unit, industry, and frequently visited locations, identifying the flow of specific groups of people, and identifying the flow of people between multiple targets; Step 3: Jointly analyze the data of the location identified in step 2, and turn the anonymous device track into a real name to target the target person; Step 4: Filter the latest device trajectory collection time, dig out the device trajectory that is still being updated, and continuously track the trajectory of specific personnel.

2. The target trajectory tracking method based on big data according to claim 1, characterized in that: In the step 1, the collected data is cleaned, and the latitude and longitude point data of multiple devices are sorted by time through unique IDs to form a device trajectory route, and the processed device trajectory data is visualized in combination with a map.

Images