System and method for cloud services of drone monitoring, data analysis, and disabling using edge computing

Abstract

A system and method are provided to provide cloud consumers with drone activity cloud services using cloud and edge computing. The drone monitoring service is provided by drone sensors detecting and identifying drones, cloud and edge servers aggregating drone activity data from sensors and UAS traffic management systems, and cloud consumers monitoring drone activity using cloud and edge devices and accessing the cloud. The drone data analysis service reports drone activity statistics, predicted drone activity, and anomalous behavior to cloud consumers based on statistical and behavioral models obtained through machine learning and federative learning techniques. The drone disabling service, when initiated by a cloud consumer, determines how to optimally configure sensors and coordinately transmit signals to disable unauthorized drones. Furthermore, functional units for data processing, artificial intelligence, mobility support, and traffic management empower cloud and edge servers to support these cloud services.

Description

Technical Field

[0001] (Cross - Reference to Related Applications) This application claims the benefit of U.S. Provisional Application No. 63 / 481,693, filed on January 26, 2023, which is hereby incorporated by reference in its entirety.

[0002] The present disclosure relates to systems and methods for cloud services for drone monitoring, data analysis, and mitigation using edge computing.

Background Art

[0003] Uncrewed aircraft systems (UAS) or drones are widely used in a variety of applications. As a result, drone activities are gradually becoming a common sight in daily life. However, unpermitted drone activities around airports, stadiums, borders, and prisons can have an adverse impact on the economy and raise concerns regarding public safety and security. Therefore, the monitoring and mitigation of drone activities are very important, especially for law enforcement agencies and airport security.

Summary of the Invention

[0004] The aspects of this disclosure relate to systems and methods for providing drone activity cloud services to cloud consumers using cloud and edge computing. The drone monitoring service is provided by drone sensors detecting and identifying drones, cloud servers and edge servers aggregating drone activity data from sensors and UAS traffic management systems, and cloud consumers monitoring drone activity using cloud and edge devices and accessing the cloud. The drone data analysis service reports drone activity statistics, predicted drone activity, and anomalous behavior to cloud consumers based on statistical and behavioral models obtained through machine learning and federative learning techniques. The drone disabling service, when initiated by a cloud consumer, determines how to optimally configure sensors and how to coordinately transmit signals to disable unauthorized drones. Furthermore, functional units for data processing, artificial intelligence, mobility support, and traffic management empower cloud servers and edge servers to support these cloud services.

[0005] One embodiment is directed to a system that provides a drone activity cloud service to a cloud consumer device. The system includes a drone sensor configured to detect and identify drones; a cloud server and edge servers configured to aggregate drone activity data from the drone sensor and an unmanned aerial system (UAS) traffic management system; and a cloud consumer device configured to monitor drone activity using the cloud server and edge devices and to access the drone activity data from the cloud server and edge servers, wherein the cloud server and edge servers are further configured to perform a drone data analysis service that reports one or more of the following to the cloud consumer device: drone activity statistics, predicted drone activity, and anomalous behavior, based on statistics and behavioral models obtained by machine learning and federative learning techniques; and the drone disabling service, when initiated by the cloud consumer device, is configured to configure the drone sensor and determine how to coordinately transmit signals to disable unauthorized drones.

[0006] In some embodiments, the system further includes a cloud network comprising the cloud servers and the cloud consumer devices, and an edge network comprising the edge servers and the edge devices.

[0007] In some embodiments, the cloud consumer device includes one or more of the following: a smartphone, a tablet, a virtual reality device, an augmented reality device, a mixed reality device, a laptop, a desktop computer, a sensor node, and / or a drone.

[0008] In some embodiments, the cloud server and the edge server each include a data processing unit configured to perform filtering, fusion, and / or aggregation of the drone activity data for a drone monitoring service, and an artificial intelligence unit configured to implement the machine learning techniques and / or the federated learning techniques for the drone data analysis service.

[0009] In some embodiments, the cloud server and the edge server each include a sensor control unit configured to determine parameters for smart sensor configuration and / or intelligent jamming, a mobility support unit configured to handle the handoff of drone activity at the boundary of the cloud network or edge network when the drone moves from one network to another, and a traffic management unit configured to handle cooperative interaction with the UAS traffic management system.

[0010] In some embodiments, the drone data analysis service is further configured to generate activity notifications and trajectories of the identified drones.

[0011] In some embodiments, the trajectory and activity data are overlaid on a map while being updated in real time.

[0012] One embodiment is directed toward a method for providing a drone activity cloud service to a cloud consumer device. This method includes: detecting and identifying one or more drones using drone sensors; aggregating drone activity data from the drone sensors and an unmanned aerial system (UAS) traffic management system in a cloud server and an edge server; monitoring drone activity in the cloud consumer device using the cloud consumer device and an edge device and accessing the drone activity data from the cloud server and the edge server; implementing a drone data analysis service in the cloud server and the edge server that reports one or more of the following to the cloud consumer device: drone activity statistics, predicted drone activity, and anomalous behavior, based on statistics and behavioral models obtained by machine learning and federative learning techniques; and determining a method for configuring the drone sensors and coordinating the transmission of signals to neutralize unauthorized drones in response to the cloud consumer device initiating a drone disabling service.

[0013] In some embodiments, the cloud servers and cloud devices are arranged to form a cloud network, and the edge servers and edge devices are arranged to form an edge network.

[0014] In some embodiments, the cloud consumer device includes one or more of the following: a smartphone, a tablet, a virtual reality device, an augmented reality device, a mixed reality device, a laptop, a desktop computer, a sensor node, and / or a drone.

[0015] In some embodiments, the cloud server and the edge server each include a data processing unit configured to perform filtering, fusion, and / or aggregation of the drone activity data for a drone monitoring service, and an artificial intelligence unit configured to implement the machine learning techniques and / or federated learning techniques, detection of anomalous behavior, and / or collaborative learning for the drone data analysis service.

[0016] In some embodiments, the cloud server and the edge server each include a sensor control unit configured to determine parameters for smart sensor configuration and / or intelligent jamming, a mobility support unit configured to handle the handoff of drone activity at the boundary of the cloud network or edge network when the drone moves from one network to another, and a traffic management unit configured to handle cooperative interaction with the UAS traffic management system.

[0017] In some embodiments, the method further includes using the drone data analysis service to generate activity notifications and trajectories of the identified drones.

[0018] In some embodiments, the trajectory and activity data are overlaid on a map while being updated in real time.

[0019] Another embodiment is a hybrid network that provides drone activity services. This hybrid network includes a cloud network comprising a plurality of cloud servers and a plurality of cloud devices, and an edge network comprising a plurality of edge servers and a plurality of edge devices, wherein the plurality of cloud devices and the plurality of edge devices include drone sensors configured to detect and identify drones, the plurality of cloud servers and the plurality of edge servers are configured to aggregate drone activity data from the drone sensors and an unmanned aerial vehicle system (UAS) traffic management system, and the plurality of cloud devices and the plurality of edge devices are further configured to monitor drone activity and access the drone activity data aggregated from the plurality of cloud servers and the plurality of edge servers.

[0020] In some embodiments, the plurality of cloud servers and the plurality of edge servers are further configured to perform a drone data analysis service that reports one or more of the following to the plurality of cloud devices based on statistical and behavioral models obtained by machine learning and federative learning techniques: drone activity statistics, predicted drone activity, and anomalous behavior; and the drone disabling service, when initiated by the plurality of cloud devices, is configured to configure the drone sensors and determine how to coordinately transmit signals to disable unauthorized drones.

[0021] In some embodiments, the plurality of cloud devices include one or more of the following: smartphones, tablets, virtual reality devices, augmented reality devices, mixed reality devices, laptops, desktop computers, sensor nodes, and / or drones.

[0022] In some embodiments, each of the plurality of cloud servers and the plurality of edge servers includes a data processing unit configured to perform filtering, fusion, and / or aggregation of the drone activity data for the drone monitoring service, and an artificial intelligence unit configured to implement the machine learning technique and / or the federated learning technique for the drone data analysis service.

[0023] In some embodiments, each of the plurality of cloud servers and the plurality of edge servers includes a sensor control unit configured to determine parameters for the configuration of smart sensors and / or intelligent jamming, a mobility support unit configured to handle the handoff of drone activity at the boundary of the cloud network or the edge network when the drone moves from one network to another network, and a traffic management unit configured to handle the cooperative interaction with the UAS traffic management system.

[0024] In some embodiments, the drone data analysis service is further configured to generate activity notifications and trajectories of the identified drones.

Brief Description of the Drawings

[0025] [Figure 1] Shows a cloud infrastructure with edge computing for drone monitoring, drone data analysis, and drone neutralization. [Figure 2] Shows an abstraction model of a cloud infrastructure with edge computing. [Figure 3] Shows a block diagram of a cloud server or an edge server for cloud services using edge computing according to an aspect of the present disclosure. [Figure 4] Shows a screenshot of a drone activity notification and a drone trajectory from a cloud service displayed on a display of a cloud device.

Best Mode for Carrying Out the Invention

[0026] Drone monitoring is usually carried out by a drone detection system or a counter-UAS (C-UAS) system. These systems often operate independently, and the drone activity information and services provided are limited. Furthermore, even when these systems are connected to a network, they generally lack scalability and do not operate in cooperation with other systems within the network. Therefore, next-generation C-UAS systems are designed as part of the latest cloud infrastructure and are coming to have artificial intelligence (AI) capabilities to provide state-of-the-art drone activity services.

[0027] Advances in edge computing in recent years have provided a cloud infrastructure suitable for large-scale drone monitoring and neutralization. First, since drone monitoring and neutralization are very sensitive to latency, edge computing reduces the latency of cloud services by placing edge servers close to drone sensors and customers. Second, compared to directly connecting drone sensors and cloud servers, edge computing supports large-scale and high-density distributed deployment of drone sensors and promotes cooperation between sensors, thereby achieving better detection performance and neutralization performance. Furthermore, by using edge computing, data analysis and machine learning become more efficient and accurate, and a more satisfactory customized customer experience is provided.

[0028] Aspects of the present disclosure relate to major drone activity services for drone monitoring, drone data analysis, and drone neutralization based on the paradigm of edge computing. In conventional drone monitoring systems, edge computing has been used to manage activities for controlling permitted drones and performing specific tasks such as delivery and event monitoring. These solutions typically fully control the drones in question.

[0029] In contrast to conventional drone monitoring systems, aspects of this disclosure provide a cloud service using edge computing that monitors both authorized and unauthorized drone activities and disables unauthorized drone activities without directly controlling authorized or unauthorized drones. In certain embodiments, the system can perform edge computing-based drone activity monitoring and disablement based on federated learning techniques for data analysis of drone activities.

[0030] The cloud network includes cloud servers and cloud devices connected via wired connections (e.g., Ethernet®, fiber optic) and / or wireless connections (e.g., Wi-Fi, 4G LTE / 5G NR / 6G cellular, satellite communications). The cloud infrastructure may include one or more edge networks connected to the cloud network. Nodes within the cloud infrastructure can be servers, gateways, mobile devices, sensors, or any device with processors, storage, memory, and computing capabilities.

[0031] Cloud servers are typically located in data centers and may be physically far from edge networks and cloud consumers. Edge networks, on the other hand, are generally closer to cloud consumers than cloud servers. Edge networks can also be deployed densely in the same or different geographic areas. Figure 1 shows an example of a cloud infrastructure 100 with edge computing for drone monitoring, drone data analysis, and drone deactivation. As shown in Figure 1, the cloud infrastructure may include one or more cloud servers 102, one or more providers 104, one or more customer devices 106, one or more edge servers 108, one or more satellites 110, one or more sensors 112, and / or one or more drones 114.

[0032] Figure 2 shows an abstraction model 200 of a cloud network infrastructure. As shown in Figure 2, Model 200 includes one or more cloud networks 202, each containing one or more cloud servers 204 (e.g., cloud server 102 in Figure 1), and one or more cloud devices 206 (e.g., provider 104, consumer device 106, and / or sensor 112 in Figure 1). Model 200 also includes one or more edge networks 208, each containing one or more edge servers 210 (e.g., edge server 108 in Figure 1) and one or more edge devices 212 (e.g., sensor 112, provider 104, and / or customer device 106 in Figure 1).

[0033] One or more cloud devices 206 may include smartphones, tablets, virtual reality (VR) / augmented reality (AR) / mixed reality (MR) devices, laptops, desktop computers, sensor nodes, drones, and other devices. Cloud devices can access the cloud by connecting to one or more edge servers 210 within one or more edge networks 208, or they can connect directly to the cloud (for example, via one or more cloud servers 204) if the edge servers 210 are not nearby. In the former case, the cloud devices within the edge network 208 are referred to as edge devices 212. Note that if terrestrial network infrastructure is unavailable in that area, cloud devices can access the cloud via satellite links.

[0034] One or more edge networks 208 are formed by connecting edge devices 212 to edge servers 210 / gateways via wired or wireless connections within a geographical area. The edge servers 210 perform edge computing, data processing, and data analysis, store data in or retrieve data from a database in local storage, and send or retrieve data to the cloud and edge devices 212. In addition to normal network management functions, the cloud and edge servers 210 may have at least five functional units to support cloud services.

[0035] Figure 3 shows a block diagram of a cloud or edge server 300 for a cloud service using edge computing according to an aspect of the present disclosure. As shown in Figure 3, the cloud or edge server 300 may include a processor 302, memory 304, display / input 306, storage 308, front end 310, and network interface 312. As described herein, the storage 308 may include a drone target database configured to store processed drone activity data. This processed drone activity data may be processed based on raw RF samples and / or drone activity data received from sensors (e.g., sensor 112 in Figure 1). The front end 310 may be configured to provide wireless connectivity to cloud devices and / or edge devices (e.g., cloud device 206 and / or edge device 212 in Figure 2). The network interface 312 may be configured to provide wired connectivity to cloud devices and / or edge devices.

[0036] Cloud or edge server 300, A data processing unit 314 configured to process the filtering, fusion, and aggregation of drone activity data for drone surveillance services; AI unit 316 configured to handle machine learning, deep learning, and federative learning tasks for data analysis, anomaly detection, and collaborative learning; A sensor control unit 318 configured to calculate and / or determine parameters for smart sensor configuration and intelligent jamming; A mobility support unit 320 configured to handle the handoff of drone activities at the boundary of a cloud network or edge network when a drone moves from one network to another; and / or It may also include a traffic management unit 322 configured to handle cooperative interaction with a UAS Traffic Management (UTM) system.

[0037] The cloud or edge server 300 may be connected to the network management component 324.

[0038] Sensor nodes (or simply referred to as "sensors") may be deployed as cloud / edge devices deployed by the C-UAS system provider (e.g., cloud device 206 and / or edge device 212 in Figure 2), or as smart devices used by cloud consumers (e.g., smartphones, tablets, or drones). These devices can be used to detect and identify drones and their radio controllers (RCs). Sensor types for drone detection can be RF (radio frequency), radar, and / or optical. These sensors can transmit raw RF samples or drone activity data directly to the edge server 300 and cloud server 300 for processing. After processing, the data is stored in the drone target databases of these servers. Drone activity data generated by sensors may include drone ID (remote ID, persistent ID, serial number, or other form of ID), telemetry data, drone geolocation information, drone pilot / home location, drone hardware status, etc. An exemplary sensor node is described in U.S. Patent Application Publication No. 2021 / 0407305 (December 30, 2021), which is part of this disclosure.

[0039] This paradigm involves at least two types of cloud consumers: C-UAS system providers (also called providers) and C-UAS system customers (also called customers). Providers may include cloud consumers that deploy multiple sensor nodes and edge gateways / edge servers 300 at various geographical locations to detect drones and collect drone activity data. Customers may include cloud consumers that utilize drone monitoring and disabling services. Customers are provided with access to drone activity data, can visualize this data on a map, and can initiate drone disabling via a cloud user interface (e.g., an app or web browser). Customers' smart devices can also detect drones and report drone activity data. In this case, customers can also function as sensors.

[0040] Figure 4 shows a screenshot 400 of the drone activity notification 402 and drone trajectory 404 for the drone 406 provided by the cloud service, as displayed on the cloud device's screen.

[0041] There are at least three main types of drone activity services: surveillance, data analysis, and neutralization.

[0042] <Drone Surveillance Service> Drone detection and identification When sensors detect the presence of one or more drones, those sensors generate drone activity data and can transmit the raw and / or generated data to edge servers and / or cloud servers. Drone activity data can be transmitted from sensors to servers synchronously or asynchronously. The data received by the server may contain duplicate or redundant information from multiple sensors regarding a particular drone target.

[0043] Drone data aggregation and collection Cloud servers or edge servers can receive drone activity data from sensors and UTMs, filter out redundant information, remove duplicates, integrate data, generate data analysis, update statistics and learning models, store selected data locally, and / or send selected data to cloud servers for processing and storage in the data center. In this way, duplicate and redundant information is removed, and customers are not presented with redundant information.

[0044] Visualization and monitoring of drone activities Drone activity data stored at the edge or in the cloud can be accessed at any time by cloud consumers (both providers and customers) in any connected location via a cloud user interface using cloud or edge devices. Provider and consumer software on servers and devices can acquire and display drone activity on real-time updated 2D or 3D maps (e.g., satellite maps, Street View). Customers can visualize drone activity, such as drone trajectories and home points, on the map in real time within a selected area. The visualization, combined with data aggregation and collection performed by cloud or edge servers, presents unified accounting for drone activity. Customers also receive notifications and statistics on drone activity in their area of ​​interest.

[0045] Drone traffic management Upon receiving real-time drone constraint information from the UTM, the cloud and servers within that area can monitor drone activity and analyze the activity data. The cloud and servers can also report violations to the UTM and notify customers (e.g., law enforcement agencies) via APIs on cloud and edge devices.

[0046] <Drone Data Analysis Service> Drone activity statistics and customer behavior models Data analysis can be performed periodically by incorporating new data into previously collected data to generate statistics on drone activity and build customer behavior profiles based on service usage. These models are established and adaptively updated using data transmitted from cloud devices and edge devices (e.g., sensors or customers) and federated learning techniques that enable collaborative machine learning.

[0047] Data and statistics related to drones are available upon request from providers and customers. Some examples include the following: • The frequency with which drones appear in the selected area every hour for one month. • The location of drone activities in a certain area over a certain period of time, and • Ranking of drones most frequently sighted in a particular area over a certain period of time.

[0048] Customer behavioral profiles and models can reveal customer preferences regarding cloud service usage and drone activity inquiries. These profiles can also be used to provide customized information via the cloud user interface for better customer service and to prioritize global / local data storage on cloud servers / edge servers to minimize data retrieval delays.

[0049] Drone activity forecast Drone activity prediction services can provide customers with predictions of drone activity based on drone data analysis, activity statistics, and customer inquiries. For example, law enforcement agencies may be interested in locations where unauthorized drones might be operating the following day, or in real-time predicted drone trajectories.

[0050] Anomaly detection Anomaly detection can be used to detect abnormal behavior in any drone target. Anomaly detection can generate and warn customers in real time regarding concerns such as public safety. Anomaly detection can also detect abnormal behavior in any server and device connected to the network. Anomaly detection can notify providers to investigate system failures or security issues. This service can detect malfunctioning sensors, compromised edge devices, and intruders, ensuring system security, data integrity, and customer privacy.

[0051] <Drone Disabling Service> Intelligent jamming and smart sensor configuration Customers can request, via a cloud user interface, to disable the activity of one or more unauthorized drones in real time. Upon receiving the request from the customer, the cloud server or edge server sends commands to selected sensor nodes based on the target deactivation strategy, configuring the transmitters and antennas of these nodes for beamforming and coordinated jamming. As a result, communication between the target and its pilot is disrupted. The deactivated unauthorized target is forced to land or return to its base where the pilot is located.

[0052] In addition to intelligent jamming, this service can dynamically configure sensors to optimize detection schedules, reduce power consumption, expand detection range, improve detection accuracy, and make drone detection more effective and efficient.

[0053] Disabling drone activities by authorized drone pilots Customers may possess a drone force (authorized drones) that can be configured, directed, managed, and / or controlled by their authorized drone pilots for a given task or mission. The cloud service provides authorized drone pilots with drone activity information and visualizations to assist them in their tasks and missions. For example, by providing law enforcement agencies with drone activity information (both authorized and unauthorized drones), the service enables authorized pilots to cooperate with each other to ensure smooth drone flight, track unauthorized drones, and locate illegal pilots. Similarly, the service can also support first responders in disaster relief operations by providing authorized drone activity information to enable pilots to coordinate drone operations to survey disaster areas, coordinate work, and monitor progress.

[0054] <Implementation System and Terminology> Embodiments disclosed herein provide systems, methods, and apparatus for cloud services of drone monitoring, data analysis, and deactivation using edge computing. It should also be noted that as used herein, “couple,” “coupling,” “coupled,” or other variations of the term “coupled” may indicate either an indirect or direct connection. For example, when a first component is “coupled” to a second component, the first component may be indirectly connected to the second component through other components, or it may be directly connected to the second component.

[0055] The drone detection, analysis, and disabling functions described herein can be stored as one or more instructions in processor-readable or computer-readable media. The term "computer-readable media" refers to any available media accessible by a computer or processor. Examples of such media include, but are not limited to, RAM, ROM, EEPROM, flash memory, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or other media that can be used to store desired program code in the form of computer-accessible instructions or data structures. Note that computer-readable media may be tangible or non-temporary. As used herein, the term "code" may refer to software, instructions, code, or data executable by a computing device or processor.

[0056] The methods disclosed herein include one or more steps or actions to implement the described method. The steps and / or actions of the method are interchangeable without departing from the claims. In other words, the order and / or use of any particular steps and / or actions can be changed without departing from the claims, unless a particular order of steps or actions is required to properly operate the described method.

[0057] As used herein, the term “multiple” means two or more. For example, “multiple components” refers to two or more components. The term “determining” encompasses a variety of actions, and therefore “determining” can include calculation, operation, processing, derivation, investigation, retrieval (e.g., retrieval in tables, databases or other data structures), confirmation, etc. Also, “determining” can include receiving (e.g., receiving information), accessing (e.g., accessing data in memory), etc. Also, “determining” can include resolving, selecting, choosing, establishing, etc.

[0058] The phrase "based on" does not mean "based solely on" unless explicitly stated otherwise. In other words, the phrase "based on" can mean both "based solely on" and "based at least on."

[0059] The foregoing description of the disclosed embodiments is provided to enable those skilled in the art to complete or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the scope of the invention. For example, those skilled in the art will understand that a number of corresponding alternative and equivalent structural details can be used, such as equivalent methods for fastening, mounting, joining, or engaging tool components, equivalent mechanisms for producing specific operating actions, and equivalent mechanisms for supplying electrical energy. Accordingly, the invention is not intended to be limited to the embodiments shown herein, but rather should be given the broadest scope that is consistent with the principles and novel features disclosed herein.

Claims

1. A system that provides cloud services for drone activity to cloud consumer devices, A drone sensor configured to detect and identify drones, A cloud server and an edge server configured to aggregate drone activity data from the aforementioned drone sensors and unmanned aerial system (UAS) traffic management system, A cloud consumer device configured to monitor drone activity using the aforementioned cloud server and edge device, and to access the drone activity data from the aforementioned cloud server and edge server, Equipped with, The cloud server and the edge server are further configured to implement a drone data analysis service that reports one or more of the following to the cloud consumer device: statistics on drone activity, predicted drone activity, and anomalous behavior, based on statistics and behavioral models obtained by machine learning and federative learning technologies. The drone disabling service, when initiated by the cloud consumer device, is configured to configure the drone sensors and determine how to coordinately transmit signals to disable unauthorized drones. system.

2. A cloud network including the aforementioned cloud server and the aforementioned cloud consumer device, An edge network including the edge server and the edge device, The system according to claim 1, further comprising:

3. The system according to claim 1, wherein the cloud consumer device includes one or more of the following: a smartphone, a tablet, a virtual reality device, an augmented reality device, a mixed reality device, a laptop, a desktop computer, a sensor node, and / or a drone.

4. The aforementioned cloud server and the aforementioned edge server are, respectively, A data processing unit configured to perform filtering, merging, and / or aggregation of the drone activity data for a drone monitoring service, An artificial intelligence unit configured to implement the machine learning technology and / or the federative learning technology for the drone data analysis service, The system according to claim 1, comprising:

5. The aforementioned cloud server and the aforementioned edge server are, respectively, A sensor control unit configured to determine the configuration of a smart sensor and / or parameters for intelligent jamming, A mobility support unit configured to handle the handoff of drone activities at the boundary of a cloud network or edge network when the drone moves from one network to another, A traffic management unit configured to handle cooperative interaction with the UAS traffic management system, The system according to claim 1, comprising:

6. The system according to claim 1, wherein the drone data analysis service is further configured to generate activity notifications and trajectories of the identified drones.

7. The system according to claim 6, wherein the trajectory and drone activity data are overlaid on a map while being updated in real time.

8. A method for providing drone activity cloud services to cloud consumer devices, Detecting and identifying one or more drones using drone sensors, The cloud server and edge server will aggregate drone activity data from the drone sensors and the unmanned aerial system (UAS) traffic management system, The cloud consumer device monitors drone activity using the cloud consumer device and edge devices, and accesses the drone activity data from the cloud server and the edge server. The cloud server and the edge server implement a drone data analysis service that reports one or more of the following to the cloud consumer device: statistics on drone activity, predicted drone activity, and abnormal behavior, based on statistics and behavioral models obtained by machine learning technology and federative learning technology. In response to the commencement of the drone disabling service by the aforementioned cloud consumer device, the method for configuring the drone sensor and coordinating the transmission of signals to neutralize unauthorized drones is determined. A method that includes this.

9. The aforementioned cloud servers and cloud devices are arranged to form a cloud network. The edge server and the edge device are arranged to form an edge network. The method according to claim 8.

10. The method according to claim 8, wherein the cloud consumer device includes one or more of the following: a smartphone, a tablet, a virtual reality device, an augmented reality device, a mixed reality device, a laptop, a desktop computer, a sensor node, and / or a drone.

11. The aforementioned cloud server and the aforementioned edge server are, respectively, A data processing unit configured to perform filtering, merging, and / or aggregation of the drone activity data for a drone monitoring service, An artificial intelligence unit configured to implement the machine learning technology and / or the federative learning technology, abnormal behavior detection, and / or collaborative learning for the drone data analysis service, The method according to claim 8, comprising:

12. The aforementioned cloud server and the aforementioned edge server are, respectively, A sensor control unit configured to determine the configuration of a smart sensor and / or parameters for intelligent jamming, A mobility support unit configured to handle the handoff of drone activities at the boundary of a cloud network or edge network when the drone moves from one network to another, A traffic management unit configured to handle cooperative interaction with the UAS traffic management system, The method according to claim 8, comprising:

13. The method according to claim 8, further comprising using the drone data analysis service to generate activity notifications and trajectories of the identified drones.

14. The method according to claim 13, wherein the trajectory and drone activity data are overlaid on a map while being updated in real time.

15. A hybrid network that provides drone activity services, A cloud network including multiple cloud servers and multiple cloud devices, An edge network including multiple edge servers and multiple edge devices, Equipped with, The plurality of cloud devices and the plurality of edge devices are equipped with drone sensors configured to detect and identify drones. The aforementioned plurality of cloud servers and the plurality of edge servers are configured to aggregate drone activity data from the drone sensors and the unmanned aerial system (UAS) traffic management system. The plurality of cloud devices and the plurality of edge devices are further configured to monitor drone activity and access the drone activity data aggregated from the plurality of cloud servers and the plurality of edge servers. Hybrid network.

16. The aforementioned multiple cloud servers and multiple edge servers are further configured to implement a drone data analysis service that reports one or more of the following to the multiple cloud devices based on statistics and behavioral models obtained by machine learning and federative learning technologies: statistics on drone activity, predicted drone activity, and anomalous behavior. The drone disabling service, when initiated by the multiple cloud devices, is configured to determine how to configure the drone sensors and how to coordinately transmit signals to disable unauthorized drones. The hybrid network according to claim 15.

17. The hybrid network according to claim 15, wherein the plurality of cloud devices include one or more of smartphones, tablets, virtual reality devices, augmented reality devices, mixed reality devices, laptops, desktop computers, sensor nodes, and / or drones.

18. Each of the aforementioned plurality of cloud servers and the plurality of edge servers is: A data processing unit configured to perform filtering, merging, and / or aggregation of the drone activity data for a drone monitoring service, An artificial intelligence unit configured to implement the machine learning technology and / or the federative learning technology for the drone data analysis service, The hybrid network according to claim 15, comprising:

19. Each of the aforementioned plurality of cloud servers and the plurality of edge servers is: A sensor control unit configured to determine the configuration of a smart sensor and / or parameters for intelligent jamming, A mobility support unit configured to handle the handoff of drone activities at the boundary of the cloud network or the edge network when the drone moves from one network to another, A traffic management unit configured to handle cooperative interaction with the UAS traffic management system, The hybrid network according to claim 15, comprising:

20. The hybrid network according to claim 15, wherein the drone data analysis service is further configured to generate activity notifications and trajectories of the identified drones.

Images