Unmanned Aerial Vehicle (UAV) Identification Methods, Electronic Devices, Media, and Products
By analyzing the measurement report data of the drone terminal, the drone can be identified and its user identification and registration status can be determined, thus solving the problem of identifying unregistered drones and achieving efficient control over "black flight" drones.
Patent Information
- Application Number
- CN202510640841.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2026-11-17
AI Technical Summary
Existing technologies struggle to effectively identify unregistered drones ("black flight" drones), which are remotely controlled via cellular mobile communication networks, making them highly stealthy and potentially threatening public safety, privacy, and air traffic.
By obtaining measurement report data from network devices, analyzing wireless data characteristics and terminal movement characteristics, identifying drone terminals, and determining their identity registration status based on user identifiers, drones that are not registered are identified as "unregistered" drones.
It can effectively identify "black flight" drones without the need for special sensing equipment and drone interaction, and achieve efficient management and control of drones that have not been registered.
Smart Images

Figure CN123123894A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to a method, electronic device, medium and product for identifying unmanned aerial vehicles (UAVs). Background Technology
[0002] Currently, some illegally assembled "black flight" drones equipped with mobile communication modules exist. Operators can control these drones via cellular mobile communication networks, enabling long-distance control and providing a high degree of stealth. The flight behavior of these drones is generally unregulated and may pose potential threats to public safety, privacy, and air traffic.
[0003] In related technologies, the detection and identification of specific drones typically relies on specialized sensing equipment, requiring interaction with the drone. However, "black flight" drones, being unregistered and without legal identity, usually refuse interaction. Therefore, the above methods are not effective in identifying "black flight" drones. How to effectively identify "black flight" drones is a problem that urgently needs to be discussed and solved. Summary of the Invention
[0004] This application provides a drone identification method, electronic device, medium, and product, which aims to effectively identify "unauthorized" drones without the need for specialized sensing devices or interaction with the drone.
[0005] In a first aspect, embodiments of this application provide a method for identifying a drone, the method comprising: acquiring measurement report data of a terminal from a network device; determining the type characteristics of the terminal based on the measurement report data of the terminal, wherein the type characteristics include at least one of the following: wireless data characteristics and terminal movement characteristics, the wireless data characteristics being used to characterize the wireless signal characteristics of the terminal, and the terminal movement characteristics being used to characterize the movement of the terminal; in response to determining that the terminal is a drone terminal based on the type characteristics of the terminal, determining the identity registration status of the drone terminal in a target area based on the user identifier of the drone terminal.
[0006] In a second aspect, embodiments of this application provide an electronic device, including: at least one processor; at least one memory for storing at least one program; and when at least one of the programs is executed by at least one of the processors, implementing the drone identification method as described in the first aspect.
[0007] Thirdly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions for performing the drone identification method as described in the first aspect.
[0008] Fourthly, embodiments of this application provide a computer program product, including a computer program or computer instructions, wherein the computer program or computer instructions are stored in a computer-readable storage medium, a processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, causing the computer device to perform the drone identification method as described in the first aspect.
[0009] This application obtains measurement report data from network devices, extracts wireless data features and / or mobile features of the terminal based on the measurement report data, and uses these features to identify whether a drone is a drone based on the differences between drones and general terminals. After identifying the terminal as a drone, it determines whether the drone has been registered based on the user identifier of the drone terminal. If the registration information of the drone terminal cannot be found, the drone terminal can be identified as an "unregistered" drone. Through the above method, "unregistered" drones can be effectively identified without special sensing equipment or interaction with the drone, achieving efficient management and control of drones that have not been registered.
[0010] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description
[0011] Figure 1 A schematic diagram of the communication network used in the drone identification method provided in an embodiment of this application;
[0012] Figure 2 A schematic diagram of the system architecture for an example of the drone identification method provided in this application;
[0013] Figure 3A A schematic diagram of a drone flight scenario in which the drone identification method provided in this application is applied;
[0014] Figure 3B A schematic diagram of a drone flight scenario for which the drone identification method is applied, as another example of this application;
[0015] Figure 4 A flowchart illustrating a drone identification method provided in an embodiment of this application;
[0016] Figure 5 A schematic diagram illustrating the division of cells as an example of this application;
[0017] Figure 6 This is a flowchart illustrating the statistical processing of the reference signal received power values of each cell, as an example provided in this application.
[0018] Figure 7 A flowchart illustrating the process for distinguishing whether MR data is indoor or outdoor data, provided as an example in this application;
[0019] Figure 8 A schematic diagram illustrating the difference in signal propagation paths between a drone terminal and a ground terminal, provided as an example of this application;
[0020] Figure 9 This is a schematic diagram of the movement trajectory of a drone terminal determined based on MR data location information of the drone terminal, as an example provided in this application.
[0021] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0023] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.
[0024] In the description of the embodiments of this application, unless otherwise expressly limited, terms such as setting, installing, and connecting should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in the embodiments of this application in combination with the specific content of the technical solution.
[0025] In this application, the terms "furthermore," "exemplarily," or "optionally" are used as examples, illustrations, or descriptions and should not be construed as being more preferred or advantageous than other embodiments or designs. The use of terms such as "furthermore," "exemplarily," or "optionally" is intended to present the relevant concepts in a specific manner.
[0026] In related technologies, UAS (Unmanned Aircraft System), i.e., drones, needs to support "broadcast operation identification" and "networked operation identification." "Broadcast operation identification" refers to the UAS broadcasting its identification information (including but not limited to identity information, flight vectors, operational status, and navigation data) in real time via specific radio frequencies and transmission protocols, without specifying any recipient, to ensure that relevant parties can identify the aircraft's operational status in real time. "Networked operation identification" refers to the UAS linking to a specific network and proactively providing its identification information in real time. End users can obtain this information through a network platform to identify the UAS's operation.
[0027] However, "black flight" drones that fail to register their identities as required or obtain flight permits as stipulated are often not subject to the aforementioned operational identification procedures. In particular, some privately assembled "black flight" drones equipped with mobile communication modules allow operators to remotely control them via mobile networks, making them highly concealed. The flight behavior of these drones is typically unregulated and may pose potential threats to public safety, privacy, and air traffic.
[0028] In order to control these "black flight" drones based on mobile communication networks, it is necessary to identify the IMSI (International Mobile Subscriber Identity) in the mobile communication module carried by these drones, and then track and control them based on the identified IMSI.
[0029] In related technologies, it is usually necessary to use specialized sensing equipment to detect and identify specific drones, and then match their position and trajectory with the location and trajectory of end users in the mobile communication network to identify the user's identity within the mobile communication network. Alternatively, drones can be identified by actively reporting messages or by interacting with them to obtain the necessary information. However, "black flight" drones are unregistered and without legal identity, and they usually refuse to interact. Therefore, the above methods are not effective in identifying "black flight" drones. How to effectively identify "black flight" drones is a problem that urgently needs to be discussed and solved.
[0030] Based on this, embodiments of this application provide a method, electronic device, medium, and product for drone identification. By acquiring measurement report data from a terminal via a network device, and extracting the terminal's wireless data characteristics and / or mobile characteristics based on this data, the method identifies whether a drone is a drone based on the differences between drones and general terminals. After identifying the terminal as a drone, the method determines whether it has been registered based on the user identifier. If the drone terminal's registration information cannot be found, it is determined that the drone terminal is an unregistered drone. This method effectively identifies unregistered drones without requiring specialized sensing equipment or interaction with the drone, achieving efficient management of drones that have not been registered.
[0031] The embodiments of this application will be further described below with reference to the accompanying drawings.
[0032] Figure 1 This is a schematic diagram of the communication network used in a drone identification method provided in one embodiment of this application. For example... Figure 1 As shown, the communication network includes, but is not limited to, server 110, network device 120, and terminal 130.
[0033] Server 110 refers to a computer system capable of providing drone identification services. For example, it can identify whether terminal 130 is a drone based on measurement report data from terminal 130 of network device 120, and determine the drone terminal's registration status when a drone terminal is identified. Server 110 can be a single high-performance computer in a network platform, a cluster of multiple high-performance computers, a portion of a single high-performance computer (e.g., a virtual machine), or a combination of portions of multiple high-performance computers (e.g., virtual machines). Server 110 can communicate with network device 120 and exchange data via wired or wireless means.
[0034] Network device 120 is a dedicated hardware device used to interconnect various nodes such as servers, PCs, and application terminals to form an information communication network. For example, network device 120 can be a base station, a building base band unit (BBU), a remote radio unit (RRU), or customer premises equipment (CPE). Network device 120 wirelessly communicates with terminal 130 to exchange data.
[0035] Terminal 130 is a device capable of providing various functions such as communication and network services. Terminal 130 can take many forms, including drones, desktop computers, laptops, PDAs (personal digital assistants), mobile phones, vehicle terminals, home theater terminals, and dedicated terminals. It can be a single device or a collection of multiple devices. For example, multiple devices can be connected via a local area network, sharing a single display device to work collaboratively, forming a single terminal. Terminal 130 can establish a communication connection with network device 120 to exchange data.
[0036] Figure 2 This is a schematic diagram of the system architecture for an example of the drone identification method provided in this application. Figure 2 As shown, the system architecture includes a "black flight" drone user identification system, a drone cloud management system, and a mobile network operator.
[0037] The "black flight" drone user identification system includes modules such as: configuration management module, network data acquisition server, database, network data analysis module, drone cloud query interface, analysis result viewing / approval interface, and analysis result output interface.
[0038] The configuration management module is used to manage the configuration of analysis algorithm parameters, external interface server connection parameters, terrain and feature data, etc.
[0039] The network data acquisition server is used to connect to the northbound data interface server of the mobile network operator to collect mobile network interface data such as measurement report data, signaling and service details data of mobile terminal users from the base station or operator server.
[0040] Databases are used to store various types of data in the system, including configuration parameters, mobile network interface data, analysis process data, and analysis result data.
[0041] The network data analysis module is used to perform statistical analysis on the acquired measurement report data and / or signaling and service details, extract type features such as wireless data characteristics and terminal mobility characteristics of each terminal, and identify possible drone users based on the type features.
[0042] The drone cloud query interface is used to interface with the drone cloud management system to further verify whether identified potential drone users are legally registered or have filed their identities in the target area.
[0043] The analysis results viewing / review interface is used to display the analysis results to users. Users can view the analysis results and conduct manual review to further verify whether the terminal is "flying" a drone illegally.
[0044] The analysis results output interface is used to output analysis results and provide them to other management systems. For example, a list of user identifiers for "unauthorized" drones can be output to the drone cloud management system for further tracking and control of these drones.
[0045] Figure 3A This is a schematic diagram of a drone flight scenario where the drone identification method provided in this application is applied. Figure 3A As shown, the drone is equipped with a mobile communication module. A user remotely controls the drone to fly. During this process, the drone will communicate with the cellular base stations it passes through to enable the user to remotely control the drone.
[0046] For example, the data analysis system obtains measurement report data from the terminal from the cellular base station.
[0047] The data analysis system analyzes the terminal's measurement report data (MR data) to obtain the terminal's type characteristics, which include at least one of the following: wireless data characteristics and terminal mobility characteristics. Wireless data characteristics are used to characterize the terminal's wireless signal characteristics, and terminal mobility characteristics are used to characterize the terminal's mobility.
[0048] The data analysis system determines whether a terminal is a drone terminal based on its type characteristics and outputs the drone terminal identification result. Once the data analysis system determines the terminal is a drone terminal, it connects to the drone cloud system and retrieves the drone identity registration record from it. This record includes at least the user identifier, registration identity information, and flight permit information for each drone terminal. The data analysis system can make the determination based on terminal movement characteristics, wireless data characteristics, or a combination of both.
[0049] The data analysis system then compares the identified drone terminal's user identifier with the drone's identity registration record to determine the drone terminal's identity registration status in the target area. For example, if the identified drone terminal's user identifier cannot be found in the drone's identity registration record, it can be determined that the drone terminal has not been registered and requires special attention.
[0050] Finally, the data analysis system outputs the identity verification results.
[0051] In another example, Figure 3B A schematic diagram of a drone flight scenario for another example of the drone identification method provided in this application, such as... Figure 3BAs shown, the data analysis system also acquires the terminal's signaling and service details, such as Extended Detailed Record (XDR) data. Based on the terminal's MR data, the data analysis system obtains the terminal's radio data characteristics and mobility characteristics; based on the terminal's XDR data, it obtains the terminal's service characteristics. The data analysis system performs a multi-dimensional comprehensive judgment based on at least one of the radio data characteristics, terminal mobility characteristics, and service characteristics to determine whether the terminal is an unmanned aerial vehicle (UAV) terminal.
[0052] In another example, in addition to obtaining MR data and XDR data of the terminal from the cellular base station, the data analysis system can also obtain MR data from the operator's server, or XDR data from the operator's server or core network elements.
[0053] The above example obtains measurement report data and / or signaling and service details from the base station. Based on the measurement report data, it extracts the terminal's wireless data characteristics and / or terminal mobility characteristics, or further extracts the terminal's service characteristics based on the signaling and service details. This allows it to identify whether a drone is a drone based on the differences between drones and general terminals. After identifying a drone, it determines whether the drone has been registered based on its user identifier. If the drone's registration information cannot be found, it is determined to be an unregistered drone. This method effectively identifies unregistered drones without requiring specialized sensing equipment or interaction with the drone, enabling efficient management of unregistered drones.
[0054] Figure 4 A flowchart illustrating a drone identification method provided in an embodiment of this application. In this embodiment, the drone identification method includes, but is not limited to:
[0055] Step 410: Obtain the terminal's measurement report data from the network device;
[0056] Step 420: Based on the measurement report data of the terminal, determine the type characteristics of the terminal, wherein the type characteristics include at least one of the following: wireless data characteristics and terminal mobility characteristics. Wireless data characteristics are used to characterize the wireless signal characteristics of the terminal, and terminal mobility characteristics are used to characterize the mobility of the terminal.
[0057] Step 430: In response to determining that the terminal is a drone terminal based on the terminal type characteristics, determine the drone terminal's identity registration status in the target area based on the drone terminal's user identifier.
[0058] In step 410, the network device may include, but is not limited to, base stations, core network elements, and operator servers. During the terminal's wireless air interface communication, the network device typically participates in the terminal's communication process and is able to obtain the terminal's measurement report data and / or signaling and service details.
[0059] A terminal refers to a device capable of wireless communication and providing business functions and services to users. In the embodiments of this application, the terminal may be a drone or other ordinary mobile devices such as mobile phones and tablets.
[0060] Measurement Report (MR) data is one of the key data types used by wireless communication systems to optimize network performance. It primarily reflects wireless environmental parameters collected by terminals or base stations during communication. For example, MR data is measurement data reported by terminal devices (such as mobile phones) to the base station; it includes periodic MR and event-based MR. MR contains important information such as measurement time, current serving cell identifier, received signal reference power (RSRP) of the serving cell, timing advance (TA) of the serving cell, angle of arrival (AOA) of the serving cell, and a list of neighboring cell measurements. Some MRs also include GPS latitude and longitude location information.
[0061] For example, the fields required in MR data are shown in Table 1:
[0062]
[0063] Table 1
[0064] In step 420, type features refer to feature data used to characterize what type of device the terminal belongs to. Type features include, but are not limited to, wireless data features and terminal mobility features.
[0065] Wireless data characteristics refer to the characteristic data obtained from the analysis of MR data, which are used to characterize the wireless communication environment of the terminal. For example, they can characterize whether the wireless environment of the terminal is indoors or outdoors, whether there are many obstacles in the wireless environment, and the quality of wireless communication, etc.
[0066] Terminal mobility characteristics refer to feature data that characterizes the terminal's mobility speed, distance traveled, and environment by analyzing latitude, longitude, time, and other information carried in MR data.
[0067] In step 430, since the location, movement trajectory, and mobile communication services of a drone differ from those of a typical end user, the type characteristics obtained from the analysis can be used to determine whether the terminal belongs to a drone terminal. If the terminal is not identified as a drone terminal, the subsequent process is skipped, and the identification of the next terminal continues. If the terminal is identified as a drone terminal, the user identifier of the drone terminal during mobile communication is used to determine whether the drone terminal has undergone identity registration and flight permit status, etc. In this embodiment, the user identifier refers to the IMSI (International Mobile Subscriber Identity) in the mobile communication module, used to uniquely identify a mobile user's identity in the mobile network. For example, MR data and signaling and service details can be associated with core network data through some keyword fields to obtain the user's IMSI; for example, keyword fields such as MMEGroup ID, MME Code, and MME UE S1AP ID in 4G networks; and keyword fields such as AMFRegionID, AMFSetID, AMFPointer, and AMFUENGAPID in 5G networks.
[0068] The target area refers to the area through which the identified drone terminal flies, or the target area that needs to be controlled, or it can refer to the entire airspace in general.
[0069] Identity registration information refers to the information obtained after a drone has completed the required identity registration process. This information can typically be obtained from a drone cloud management system or other drone management platforms.
[0070] For example, the drone's identity registration status can be obtained from the drone cloud management system. By searching for the user identifiers of existing registered drones to see if the user identifier of the identified drone terminal is present, it can be determined whether the drone terminal has been registered. If the user identifier of the identified drone terminal is present among the user identifiers of the registered drones, its specific flight permit information, such as the permitted flight area, can also be obtained, thereby determining whether it can legally fly in the target area.
[0071] In the embodiments described in steps 410 to 430 above, measurement report data of the terminal is obtained from the network device. Based on the measurement report data, the wireless data characteristics and / or terminal movement characteristics of the terminal are extracted. These characteristics are then used to identify whether the device is a drone based on the differences between the drone and a general terminal. After identifying the terminal as a drone, its user identifier is used to determine whether it has been registered. If the registration information for the drone terminal cannot be found, it is determined that the drone terminal is an unregistered drone. This method effectively identifies unregistered drones without requiring specialized sensing equipment or interaction with the drone, achieving efficient management of drones that have not been registered.
[0072] The above is a general description of steps 410 to 430. The following is a detailed description of the specific implementation process of steps 410 to 430.
[0073] In one embodiment, the wireless data features include the proportion of indoor wireless data and the neighboring cell ratio of drone features, and the terminal movement features include movement speed features and movement trajectory features.
[0074] Step 430, which determines that the terminal is a drone terminal based on its type characteristics, includes at least one of the following:
[0075] The terminal type characteristics are compared with the corresponding threshold conditions to obtain at least one characteristic comparison result of the terminal;
[0076] Based on at least one feature comparison, determine whether the terminal is a drone terminal;
[0077] Specifically, the terminal type characteristics are compared with the corresponding threshold conditions to obtain at least one characteristic comparison result of the terminal, including at least one of the following:
[0078] The proportion of indoor wireless data of the terminal is compared with the corresponding threshold conditions to obtain the first feature comparison of the terminal.
[0079] The terminal's drone feature neighbor ratio is compared with the corresponding threshold condition to obtain the terminal's second feature comparison result;
[0080] The terminal's moving speed feature is compared with the corresponding threshold condition to obtain the comparison result of the terminal's third feature;
[0081] The terminal's movement trajectory features are compared with the corresponding threshold conditions to obtain the terminal's fourth feature comparison results.
[0082] In the above embodiments, the indoor wireless data ratio refers to the proportion of indoor MR stations in the total MR data corresponding to the terminal, used to reflect the indoor and outdoor environmental conditions of the terminal. The smaller the indoor wireless data ratio, the more likely the terminal is in an outdoor environment.
[0083] The drone-feature neighbor cell percentage refers to the proportion of MR data whose corresponding neighbor cell measurement data matches drone characteristics within the total MR data. A higher drone-feature neighbor cell percentage indicates a greater amount of MR data matching drone characteristics, and thus a higher probability that the corresponding terminal is a drone.
[0084] Movement speed characteristics refer to the movement speed of the terminal. For consumer drones, their movement speed is typically between 20 km / h and 40 km / h. Therefore, the movement speed characteristics of the terminal can be used to determine whether the terminal's movement speed is within the typical speed range of drones.
[0085] Movement trajectory features are used to characterize whether the terminal's movement trajectory conforms to the flight trajectory features of the drone. For example, the number of times a large obstacle is crossed per unit time is used as the movement trajectory feature. Since drones fly in the air, they have the ability to cross large obstacles in a short time, while ordinary mobile terminal users usually cannot cross many large obstacles in a short period of time.
[0086] Threshold conditions refer to the decision conditions used to determine whether a corresponding feature is a feature that fits the description of a drone. Feature comparison results refer to the comparison results after a feature is compared with its corresponding threshold conditions to determine whether the feature belongs to the category of drone features.
[0087] For example, after analyzing the MR data of a certain terminal, the following data was obtained, as shown in Table 2:
[0088]
[0089] Table 2
[0090] As shown in Table 2, the analysis shows that the indoor wireless data ratio of this terminal is 2%, which meets the corresponding threshold condition (<=5%). Therefore, the first characteristic comparison of the terminal matches the characteristics of a drone, and a weighted score of 25 points is determined. The analysis shows that the neighbor ratio of the terminal's drone characteristic is 85%, which meets the corresponding threshold condition (>=80%). Therefore, the second characteristic comparison of the terminal matches the characteristics of a drone, and a weighted score of 25 points is determined. The analysis shows that the terminal's moving speed is 15 km / h, which does not meet the corresponding threshold condition (20-40). Therefore, the third characteristic comparison of the terminal does not match the characteristics of a drone, and a weighted score of 0 is determined. The analysis shows that the terminal's movement trajectory characteristic (number of times the movement trajectory crosses large obstacles per unit time) is 0.81 times / minute, which meets the corresponding threshold condition (>=0.5). Therefore, the fourth characteristic comparison of the terminal matches the characteristics of a drone, and a weighted score of 25 points is determined.
[0091] Add up the scores of the above items, and the total score is 65 points. Assuming the judgment threshold is 64 points, the terminal is judged to be a drone terminal.
[0092] It should be noted that the above example is only a preferred case in the embodiments of this application. In other examples or specific implementations, one or more of the following can be selected for drone terminal determination: indoor wireless data ratio, drone feature neighbor ratio, moving speed feature, and moving trajectory feature. The order of these will not be repeated here.
[0093] In the above embodiments, by analyzing MR data, features such as the proportion of indoor wireless data of the terminal, the neighbor ratio of drone features, the moving speed features, and the moving trajectory features can be obtained to determine the terminal type. Each feature is compared with the corresponding threshold conditions to determine whether the terminal is a drone terminal, thereby enabling simple and efficient identification of whether the terminal is a drone terminal.
[0094] The above embodiments also employ multiple features simultaneously, including indoor wireless data ratio, drone feature neighbor ratio, moving speed feature, and moving trajectory feature, and respond according to preset weights and feature comparison results. This multi-dimensional comprehensive judgment of whether the terminal is a drone terminal enables efficient and accurate terminal identification.
[0095] In one embodiment, the percentage of indoor wireless data is obtained in the following way:
[0096] Determine the data type of the measurement report;
[0097] Since the data type of the measurement report is indoor data, the proportion of indoor wireless data of the terminal is determined based on the total number of indoor data and measurement report data of the terminal.
[0098] In this embodiment, the data type refers to whether the measurement report data is indoor or outdoor data. Since drones typically fly outdoors, analyzing the proportion of indoor wireless data from the terminal allows for a simple and efficient determination of whether the terminal is likely a drone terminal.
[0099] In one embodiment, the data type of the measurement report data is determined to include one of the following:
[0100] Method 1: In response to the fact that the serving cell or neighboring cell corresponding to the measurement report data of the terminal contains an indoor cell, determine that the data type of the measurement report data is indoor data;
[0101] Method 2: Obtain the average reference signal received power value of each partition under each cell. In response to the measurement difference of the terminal's measurement report data being greater than the first threshold, determine that the data type of the measurement report data is indoor data. The measurement difference is the difference between the reference signal received power value of the measurement report data and the average reference signal received power value of the corresponding partition of the measurement report data.
[0102] In this embodiment, if there are indoor cells among the serving cells and neighboring cells recorded in the MR data, the MR can be directly determined to be an indoor MR. Otherwise, the indoor / outdoor differentiation algorithm (Method 2) is executed to determine the data type of the measurement report data.
[0103] A zoning refers to dividing a cell into multiple areas, resulting in sub-areas. The average reference signal received power value is the average value of the reference signal received power obtained from each zoning of the serving cell within the target time period. The specific calculation of the average signal received power value is described in the following embodiment and will not be repeated here.
[0104] The first threshold is a preset threshold value used to determine whether the measurement report data from the terminal belongs to indoor data. When the measurement difference of the measurement report data is greater than the first threshold, it indicates that the measurement report data is indoor data; otherwise, it is outdoor data.
[0105] By calculating the measurement difference in the measurement report data of the terminal, it is possible to determine the change of the reference signal received power value of the terminal's measurement report relative to the average reference signal received power value of the corresponding zone, thereby accurately determining whether the measurement report belongs to indoor MR.
[0106] In one embodiment, obtaining the average reference signal received power value for each partition under each cell includes:
[0107] The cell is divided into multiple zones based on timing advance and signal arrival angle.
[0108] Obtain the reference signal received power value of each cell within the target time period;
[0109] The average reference signal received power value of each partition under each cell is determined by statistically analyzing the reference signal received power values of each partition.
[0110] In this embodiment, "cell" refers to the serving cell. Timing Advance (TA) is used to ensure signal synchronization between different terminals and the base station; its value is closely related to the distance from the terminal to the base station. Angle of Arrival (AOA) is the direction in which the terminal signal reaches the base station receiver. By segmenting through multiple TAs and AOAs, the serving cell is divided into multiple fine-grained subdivisions; for example, such as... Figure 5 As shown, the TA is divided into segments of 8 units each, for example, TA: 0~7, TA: 8~15, TA: 16~23… The AOA is divided into equal segments of 15° each, for example, AOA: -30°~-15°, AOA: -15°~0°, AOA: 0°~15°, AOA: 15°~30°…
[0111] The target time period refers to the adjacent historical time period of a preset value, such as the last 3 days. The reference signal received power (RSP) value of each cell can be obtained by acquiring the MR data of each cell within the target time period and extracting the corresponding RSP value from the MR data. For each cell, the MR data of that cell within the target time period are statistically analyzed based on the TA and AOA values carried in the MR data and assigned to the corresponding partition. The RSP values corresponding to the MR data in each partition are then averaged to obtain the average RSP value of each partition.
[0112] By segmenting the TA and AOA, the cell is divided into multiple finer-grained partitions. Then, the average reference signal received power (RSW) value for each partition is calculated based on the RSW values within these finer-grained partitions. Comparing the average RSW value obtained from these finer-grained partition statistics with the RSW value of the measurement report data from the terminal to be identified allows for a more accurate determination of whether the measurement report data from the terminal to be identified belongs to indoor data.
[0113] For example, Figure 6 This is a flowchart illustrating the statistical processing of reference signal received power values for each cell, as an example provided in this application. Figure 6As shown, recent (e.g., within the last 3 days) MR data for each cell is collected. The MR data is then grouped and summarized according to the TA and AOA segments. The average reference received power (RSRP) value for each "TA segment + AOA segment" (i.e., partition) of the serving cell is calculated and saved as the RSRP feature sample of the serving cell. Since outdoor cell signals experience signal loss when penetrating building exteriors, indoor MR data at adjacent locations is often 10dB to 40dB lower than outdoor MR data. Therefore, the average RSRP value of the cells grouped by "TA segment" and "AOA segment" can be used as the indoor / outdoor differentiation model parameter data for that cell in different geographical areas. Data examples are shown in Table 3.
[0114]
[0115]
[0116] Table 3
[0117] Furthermore, for the RSRP measurements of each neighboring cell in the MR data of the serving cell, the data can also be aggregated and statistically analyzed separately for each neighboring cell in the same "TA segment + AOA segment" grouping, calculating the average RSRP value of each neighboring cell in that partition, and saving it as neighboring cell RSRP feature samples, which serve as the neighboring cell feature data for that partition. Data examples are shown in Table 4:
[0118] Service Community TA segment AOA segment Neighboring community Average RSRP 10011_11 0~7 -60~-45 10011_12 -92.1 10011_11 0~7 -60~-45 10012_11 -95.2 ... ... ... ... ... 10011_11 0~7 -60~-45 10071_13 -105.7 10011_11 0~7 -45~-30 10011_12 -93.3 ... ... ... ... ... 10011_12 0~7 -60~-45 10012_11 -96.4 ... ... ... ... ...
[0119] Table 4
[0120] It should be noted that the average RSRP value of each neighboring cell in this partition is the characteristic reference signal received power value in other embodiments of this application.
[0121] After obtaining the average RSRP values of each serving cell in each partition (as shown in Table 3) and the average RSRP values of the neighboring cells corresponding to each serving cell in each partition (as shown in Table 4), for example, as follows: Figure 7 As shown, the process of distinguishing between indoor and outdoor data for the MR data of the terminal to be identified is as follows: First, it is determined whether the serving cell or neighboring cell corresponding to the MR data contains an indoor cell. If the serving cell or neighboring cell of the MR data contains an indoor cell, the MR data is directly determined to be indoor data. Otherwise, the indoor / outdoor distinction algorithm is executed. Based on the TA value and AOA value of the MR data, the indoor / outdoor distinction model parameters of the serving cell are queried according to the "TA segment" + "AOA segment" (e.g., Table 3). The measured difference between the RSRP value of the MR data and the queried average RSRP value is calculated. If the difference is greater than the first threshold (e.g., 15dB), the MR data is determined to be indoor data.
[0122] In one embodiment, the UAV feature neighbor ratio is obtained in the following way:
[0123] Obtain the characteristic reference signal received power value of each neighboring cell in each partition of each cell, wherein the neighboring cells are determined based on the measurement report data;
[0124] Determine the average difference of reference signal received power for each measurement report data of the terminal, wherein the average difference of reference signal received power is determined based on the reference signal received power values of each neighboring cell and the characteristic reference signal received power values of each neighboring cell contained in the measurement report data;
[0125] When the average difference in the received power of the reference signal is greater than the second threshold, the corresponding measurement report data is determined to be UAV characteristic neighboring cell data.
[0126] The drone feature neighbor ratio of the terminal is determined based on the total number of drone feature neighbor data in the terminal and the total number of measurement report data.
[0127] In this embodiment, the Feature Reference Signal Received Power value refers to the average RSRP value of each neighboring cell of the serving cell in each partition, as shown in Table 4 of the example above. For example, the neighboring cells corresponding to the current MR data can be determined based on the neighboring cell list carried by the MR data of the terminal to be identified.
[0128] The average difference in reference signal received power refers to the average of the differences between the reference signal received power values of each neighboring cell included in the measurement report data and the statistically obtained characteristic reference signal received power values of each neighboring cell.
[0129] The second threshold refers to a pre-set threshold value used to determine whether the neighboring cell measurement data of the terminal's measurement report data conforms to the characteristics of the UAV.
[0130] For example, Figure 8 This is a schematic diagram illustrating the difference in signal propagation paths between a drone terminal and a ground terminal, as provided as an example in this application. Figure 8 As shown, because the drone flies in the air, the signal propagation path between it and the serving cell and neighboring cells is mainly line-of-sight propagation (as shown by the dotted line in the figure). That is, the radio wave propagation path between the terminal and the base station is basically a straight line, and is less affected by buildings and terrain features. However, pedestrians or vehicles on the ground cause signal propagation to be obstructed or reflected due to various objects and obstacles in the environment (such as buildings, trees, terrain, etc.), which is non-line-of-sight propagation, resulting in a decrease in signal quality.
[0131] For the RSRP data of each neighboring cell in the MR neighboring cell measurement list, it is compared with the "TA segment + AOA segment" grouped neighboring cell characteristic data of the serving cell. The average difference between the RSRP of each neighboring cell and the characteristic RSRP of that neighboring cell is calculated, which is the average difference of the reference signal received power. The formula for calculating the average difference of the reference signal received power is as follows:
[0132]
[0133] Among them, RSRP cell_i RSRP_festure is the RSRP measurement value of the i-th neighboring cell in the neighboring cell measurement list of MR data. cell_i This is the RSRP value of the i-th neighboring cell in the "TA segment + AOA segment" grouped neighboring cell feature data of the serving cell corresponding to the MR data. If the RSRP value of the i-th neighboring cell cannot be found, then the RSRP value of that neighboring cell is -140dBm.
[0134] If the number of neighboring cells in the MR data is higher than the threshold (e.g., more than 10), and the calculated result of the average difference in the received power of the above reference signal is higher than the threshold (e.g., 20dBm), then the neighboring cell measurement data of this MR data is considered to conform to the characteristics of a UAV.
[0135] In the above embodiments, the average difference in reference signal received power of each neighboring cell corresponding to the MR data of the terminal to be identified is calculated to determine whether the neighboring cell measurement data of the MR data conforms to the characteristics of a drone. The drone characteristic neighboring cell ratio is obtained based on the proportion of MR data in the total MR data where the neighboring cell measurement data conforms to the characteristics of a drone. By using the drone characteristic neighboring cell ratio of the terminal, the characteristics of the neighboring cell measurement data can be fully combined with the signal propagation environment between cells to determine whether the terminal is a drone terminal, thereby improving the accuracy of drone terminal identification.
[0136] In one embodiment, the movement speed characteristic is obtained in the following way:
[0137] Sort the various measurement report data from the terminal by time;
[0138] The speed between any two sets of measurement report data is determined based on the time difference and distance difference between each set of sorted measurement report data.
[0139] The terminal's movement speed characteristics are determined based on the speed between every two measured data reports.
[0140] In this embodiment, the time difference between two measurement report data can be determined by the difference in the measurement times recorded in the two measurement report data; the distance difference between two measurement report data can be determined by the distance between the location points corresponding to the two measurement report data. The terminal's moving speed characteristics can be obtained by averaging the speeds between every two measurement report data in each of the terminal's measurement report data.
[0141] For example, if the MR data reported by the terminal includes GPS latitude and longitude data, this GPS latitude and longitude data can be directly used as the location point. Typically, drones have a built-in GPS receiver to obtain their location, including longitude, latitude, and altitude. This allows the drone to accurately locate itself in three-dimensional space and record its flight path. If the MR data does not contain GPS latitude and longitude data, geometric calculations can be performed based on the serving cell identifier, serving cell RSRP, serving cell TA, neighbor cell measurement list, and other data in the MR data, combined with the cell's latitude, longitude, and azimuth from network engineering parameters, to obtain the location point corresponding to the MR data.
[0142] For example, by sorting multiple MR data points from the same terminal according to measurement time, and connecting the corresponding location points of each MR data point end to end, the motion trajectory of the terminal can be obtained. The distance between the location points of two adjacent MR data points divided by the time yields the movement speed between the two MR data points. Excluding the lowest 20% of speeds (which may be hovering and stationary) and the highest 20% of speeds (which may be due to abnormal location data), the average speed of the terminal is obtained by averaging the remaining 60%.
[0143] Assuming a terminal has 16 MR (Matchmaking) data entries, sort them by time and calculate the distance and speed of adjacent MR entries, as shown in Table 5:
[0144]
[0145]
[0146] Table 5 sorts the calculated moving speed between each pair of MR data points by magnitude, as shown in Table 6:
[0147]
[0148]
[0149] Table 6
[0150] After removing the lowest 20% (the first 3) and highest 20% (the last 3), the average of the remaining 60% is taken, resulting in a user's average speed of approximately 36.56 km / h. Consumer drones typically operate at speeds between 20 km / h and 40 km / h. Comparing the calculated terminal's speed to this range, if it falls within this range, the terminal's speed characteristics are considered consistent with those of a drone.
[0151] In one embodiment, the movement trajectory features are obtained in the following way:
[0152] The terminal's movement trajectory is obtained based on the various measurement report data from the terminal;
[0153] The terminal's movement trajectory is compared with the terrain data of the corresponding area to determine the number of times the terminal crosses large obstacles per unit time.
[0154] The characteristics of the terminal's movement trajectory are determined by the number of times the terminal crosses large obstacles per unit time.
[0155] In this embodiment, the movement trajectory of the terminal can be obtained by connecting the location points (MR latitude and longitude recorded in the MR data) corresponding to each MR data point of the terminal end to end.
[0156] Topographic data is spatial data describing the shape and features of the Earth's surface. Topographic data can be extracted from maps of the corresponding region and includes at least the latitude and longitude locations of rivers, lakes, roads, and various buildings. Large obstacles refer to objects such as rivers, lakes, and large buildings.
[0157] For example, Figure 9 This is a schematic diagram illustrating the movement trajectory of a drone terminal determined based on MR data location information from the drone terminal, as provided in an example of this application. For example... Figure 9 As shown, by comparing the terminal's movement trajectory with the building data and terrain data of the area, the number of times the user's movement trajectory crosses obstacles such as large buildings, rivers, and lakes per unit time can be counted, and the number of times large obstacles are crossed per unit time can be used as the feature of the terminal's movement trajectory.
[0158] By acquiring the movement trajectory characteristics of the terminal, it is possible to quickly and effectively identify whether the terminal is a regular terminal or a potential drone terminal.
[0159] In one embodiment, the drone identification method further includes: obtaining signaling and detailed service data of the terminal from a network device;
[0160] Based on the terminal's signaling and detailed service data, determine the terminal's service characteristics, including the terminal's service type, service duration, and service traffic ratio.
[0161] Based on the terminal's business characteristics, determine whether the terminal is a drone terminal.
[0162] In this embodiment, signaling and service details data refer to detailed records of each service (which may be a call or a data service) that the terminal performs. These records include important information such as service type, duration, access cell, release cell, uplink and downlink traffic, and XDR (Extended Detail Record) data.
[0163] Business characteristics refer to data used to characterize the business status of a terminal, obtained by analyzing the terminal's business metrics. For example, the following business metrics are analyzed from the terminal's XDR data: determining whether a voice call service exists based on the service establishment reason field; calculating the service duration based on the access time and release time; uplink traffic of data services; and downlink traffic of data services.
[0164] Service type is used to characterize whether a terminal is using voice services, service duration is used to characterize the duration of a service that is using voice services, and service flow ratio is determined by dividing uplink traffic by downlink traffic.
[0165] By analyzing signaling and detailed service data, the service characteristics of the terminal can be obtained. These characteristics can be used to initially screen whether the terminal is a drone terminal. For example, if the service type in the service characteristics of a terminal is voice service, then the terminal can be directly determined to be a non-drone terminal.
[0166] In one embodiment, determining that the terminal is a drone terminal based on type characteristics includes:
[0167] Determine whether the terminal is a drone terminal based on its business characteristics and type characteristics.
[0168] In this embodiment, a multi-dimensional judgment is made by combining the business features extracted from XDR data and the type features extracted from MR data to determine whether the terminal is a drone terminal. This enables efficient and accurate identification of whether a terminal is a drone terminal without the need for interaction with the drone or specialized sensing equipment.
[0169] In one embodiment, determining that the terminal is a drone terminal based on service characteristics and type characteristics includes:
[0170] Since the service type is voice service, the terminal is determined to be a drone terminal;
[0171] Alternatively, the type of terminal can be determined based on the duration of the service, the ratio of service traffic, and the characteristics of the type.
[0172] In this embodiment, the type features include at least one of the following: indoor wireless data ratio, drone feature neighbor ratio, movement speed feature, and movement trajectory feature.
[0173] Leveraging the characteristic that drone terminals do not engage in voice services, the first step is to determine whether the terminal's service type is voice-based. If it is, the terminal can be directly identified as a non-drone terminal, eliminating the need for further data analysis and identification, thus improving identification efficiency. If it is not a voice-based terminal, a multi-dimensional comprehensive analysis using service duration, traffic ratio, and type characteristics is conducted to efficiently and accurately identify the drone terminal. This provides an accurate basis for further analysis of whether the drone terminal has undergone identity registration.
[0174] For example, the business characteristics and type characteristics obtained from terminal-based MR data and XDR data analysis are used to perform multi-dimensional comprehensive analysis and decision rules, as shown in Table 7 below:
[0175]
[0176]
[0177] Table 7
[0178] For example, after analyzing the MR and XDR data of a certain terminal, the data shown in Table 8 is obtained:
[0179]
[0180] Table 8
[0181] As shown in Table 8, the scores of the above items are added together, and the total score is 85 points. Assuming that the judgment threshold is greater than 80 points, the terminal is judged to be a suspected drone terminal.
[0182] Once it is determined that the terminal may be a drone terminal, it is connected to the drone cloud system. The suspected drone user IMSI obtained from the above analysis is compared with the IMSI of a properly registered user in the drone cloud system to identify whether the drone terminal is an unregistered "black flight" drone terminal.
[0183] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 10 As shown, the electronic device 2000 includes a memory 2100 and a processor 2200. The number of memory 2100 and processor 2200 can be one or more. Figure 10 Taking a memory 2101 and a processor 2201 as an example; the memory 2101 and processor 2201 in the network device can be connected via a bus or other means. Figure 10 Taking the example of a connection between China and Israel via a bus.
[0184] The memory 2101, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods provided in any embodiment of this application. The processor 2201 implements the UAV identification method provided in any of the above embodiments by running the software programs, instructions, and modules stored in the memory 2101.
[0185] Memory 2101 may primarily include a program storage area and a data storage area, wherein the program storage area may store the operating system and application programs required for at least one function. Furthermore, memory 2101 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, memory 2101 further includes memory remotely located relative to processor 2201, and this remote memory can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0186] One embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions for performing the drone identification method as provided in any embodiment of this application.
[0187] An embodiment of this application also provides a computer program product, including a computer program or computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium and executes the computer program or computer instructions, causing the computer device to perform the drone identification method provided in any embodiment of this application.
[0188] The system architecture and application scenarios described in this application are intended to more clearly illustrate the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. Those skilled in the art will understand that as system architectures evolve and new application scenarios emerge, the technical solutions provided in this application are also applicable to similar technical problems.
[0189] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.
[0190] In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.
[0191] The terms “component,” “module,” “system,” etc., used in this specification are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process or execution thread, and components may be located on a single computer or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, or a network, such as the Internet interacting with other systems via signals).
[0192] The above description, with reference to the accompanying drawings, illustrates some embodiments of this application, but does not limit the scope of this application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and spirit of this application shall be within the scope of this application.
Claims
1. A method for identifying unmanned aerial vehicles (UAVs), characterized in that, The method includes: Obtain measurement report data from the terminal via network devices; Based on the measurement report data of the terminal, the type characteristics of the terminal are determined, wherein the type characteristics include at least one of the following: wireless data characteristics and terminal mobility characteristics, wherein the wireless data characteristics are used to characterize the wireless signal characteristics of the terminal and the terminal mobility characteristics are used to characterize the mobility of the terminal; In response to determining that the terminal is a drone terminal based on the type characteristics of the terminal, the identity registration status of the drone terminal in the target area is determined based on the user identifier of the drone terminal.
2. The UAV identification method according to claim 1, characterized in that, The wireless data features include the proportion of indoor wireless data and the neighboring cell ratio of drone features; the terminal movement features include movement speed features and movement trajectory features. The determination that the terminal is a drone terminal based on the type characteristics of the terminal includes at least one of the following: The type feature of the terminal is compared with the corresponding threshold condition to obtain at least one feature comparison result of the terminal; Based on at least one of the aforementioned feature comparisons, determine whether the terminal is a drone terminal; The step of comparing the type feature of the terminal with the corresponding threshold condition to obtain at least one feature comparison result of the terminal includes at least one of the following: The proportion of indoor wireless data of the terminal is compared with the corresponding threshold condition to obtain the first feature comparison situation of the terminal; The terminal's UAV feature neighbor ratio is compared with the corresponding threshold condition to obtain the terminal's second feature comparison result; The moving speed feature of the terminal is compared with the corresponding threshold condition to obtain the third feature comparison result of the terminal; The movement trajectory features of the terminal are compared with the corresponding threshold conditions to obtain the fourth feature comparison results of the terminal.
3. The UAV identification method according to claim 2, characterized in that, The percentage of indoor wireless data was obtained in the following way: Determine the data type of the measurement report data; Since the data type of the measurement report data is indoor data, the proportion of indoor wireless data of the terminal is determined based on the total number of indoor data and measurement report data of the terminal.
4. The UAV identification method according to claim 3, characterized in that, The determination of the data type of the measurement report data includes one of the following: In response to the fact that the serving cell or neighboring cell corresponding to the measurement report data of the terminal contains an indoor cell, the data type of the measurement report data is determined to be indoor data; The average reference signal received power value of each partition under each cell is obtained. In response to the measurement difference of the measurement report data of the terminal being greater than a first threshold, the data type of the measurement report data is determined to be indoor data, wherein the measurement difference is the difference between the reference signal received power value of the measurement report data and the average reference signal received power value of the measurement report data corresponding to the partition.
5. The UAV identification method according to claim 4, characterized in that, The step of obtaining the average reference signal received power value for each partition under each cell includes: The cell is divided into multiple zones based on timing advance and signal arrival angle. Obtain the reference signal received power value of each cell within the target time period; The average reference signal received power value of each partition under each cell is determined by statistically analyzing the reference signal received power value of each partition according to the partition.
6. The UAV identification method according to claim 2, characterized in that, The drone feature neighbor ratio is obtained in the following way: Obtain the characteristic reference signal received power value of each neighboring cell in each partition of each cell, wherein the neighboring cells are determined based on the measurement report data; The average difference in reference signal received power for each of the measurement report data of the terminal is determined, wherein the average difference in reference signal received power is determined based on the reference signal received power values of each of the neighboring cells and the characteristic reference signal received power values of each of the neighboring cells contained in the measurement report data; When the average difference in the received power of the reference signal is greater than the second threshold, the corresponding measurement report data is determined to be UAV characteristic neighboring cell data. The ratio of UAV feature neighboring regions in the terminal is determined based on the total number of UAV feature neighboring region data and measurement report data in the terminal.
7. The UAV identification method according to claim 2, characterized in that, The movement speed characteristic is obtained in the following way: Sort the measurement report data of the terminal according to time; The speed between each pair of measurement report data is determined based on the time difference and distance difference between each pair of sorted measurement report data. The movement speed characteristics of the terminal are determined based on the speed between every two of the measured data reports.
8. The UAV identification method according to claim 2, characterized in that, The movement trajectory features are obtained in the following way: The movement trajectory of the terminal is obtained based on the various measurement report data of the terminal; The movement trajectory of the terminal is compared with the terrain data of the corresponding area to determine the number of times the terminal crosses large obstacles per unit time. The movement trajectory characteristics of the terminal are determined based on the number of times the terminal crosses large obstacles per unit time.
9. The UAV identification method according to claim 1 or 2, characterized in that, The method further includes: Obtain the signaling and detailed service data of the terminal from the network device; Based on the signaling and detailed service data of the terminal, the service characteristics of the terminal are determined, wherein the service characteristics include the service type, service duration and service traffic ratio of the terminal; Based on the service characteristics of the terminal, determine whether the terminal is the drone terminal.
10. The UAV identification method according to claim 9, characterized in that, The step of determining that the terminal is a drone terminal based on the type characteristics includes: The terminal is determined to be the drone terminal based on the business characteristics and the type characteristics.
11. The UAV identification method according to claim 10, characterized in that, The step of determining the terminal as the drone terminal based on the business characteristics and the type characteristics includes: In response to the fact that the service type is voice service, the terminal is determined to be the drone terminal; Alternatively, the terminal may be determined as the drone terminal based on the service duration, the service traffic ratio, and the type characteristics.
12. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; The method as described in any one of claims 1 to 11 is implemented when at least one of the programs is executed by at least one of the processors.
13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for performing the method as described in any one of claims 1 to 11.
14. A computer program product, comprising a computer program or computer instructions, characterized in that, The computer program or the computer instructions are stored in a computer-readable storage medium, and the processor of the computer device reads the computer program or the computer instructions from the computer-readable storage medium. The processor executes the computer program or the computer instructions, causing the computer device to perform the method as described in any one of claims 1 to 11.
