Method for drone authentication using real-time current consumption and computer device therefor

Abstract

According to an embodiment of the present application, a drone certification method using real-time current consumption and a computer device for the same are provided. The method may include the steps of: collecting real-time current consumption data of a drone to be certified for a predetermined period of time in a predetermined operating state; generating a characteristic vector related to the current consumption characteristics of the drone to be certified based on the real-time current consumption data; and inputting the characteristic vector into a pre-trained artificial intelligence learning model to determine whether the drone to be certified is a legal drone.

Description

Technology Field

[0001] The present application relates to a drone authentication method using real-time current consumption and a computer device for the same. Background Technology

[0002] Authentication technology for unmanned aerial vehicles, such as drones, is becoming increasingly important. This is necessary to ensure that only authorized and lawful drones can access specific tasks and areas, as the use of drones grows in various fields, including not only military operations but also commercial, public safety, and leisure activities. Through the certification of drone legitimacy, potential threats such as unauthorized intrusion by drones can be prevented, and the safety and security of drone operations can be ensured.

[0003] Existing authentication methods include those based on acoustic signal analysis, radio frequency signal utilization, sensor offset comparison, and Physical Unclonable Functions (PUFs). While these methods can be useful in specific environments and conditions, they share several common limitations.

[0004] First, many existing methods require attaching additional hardware to the drone. This not only increases the drone's weight and degrades flight performance but also incurs additional costs for hardware installation and maintenance. Furthermore, there is a possibility that the added hardware could negatively impact flight stability by causing electronic interference or altering the drone's physical structure.

[0005] Second, the authentication process requires complex data exchange between the drone and the central server. This process consumes large-scale computing resources, which can overload the server and network, and increases the risk of information loss or distortion during data transmission. This acts as a major factor in lowering the reliability and efficiency of the entire authentication process.

[0006] A new technology is required to overcome the limitations of such existing technologies and to identify and authenticate legitimate drones simply and efficiently without additional hardware. The problem to be solved

[0007] The purpose of this application is to provide a drone authentication method using real-time current consumption and a computer device for the same. means of solving the problem

[0008] According to an embodiment of the present application, a method for certifying a drone using real-time current consumption is provided. The method may include the steps of: collecting real-time current consumption data of a drone to be certified for a predetermined period of time in a predetermined operating state; generating a characteristic vector related to the current consumption characteristics of the drone to be certified based on the real-time current consumption data; and inputting the characteristic vector into a pre-trained artificial intelligence learning model to determine whether the drone to be certified is a legal drone.

[0009] In addition, the real-time current consumption data may be current consumption data of the brushless motor of the drone subject to certification.

[0010] In addition, the above predetermined operating state may be a state in which the certified drone is performing hovering flight, or a state in which the certified drone has landed and the brushless motor is rotating.

[0011] In addition, the drone subject to certification may have unique current consumption characteristics that allow it to be identified from other drones in the operating state according to the unique physical characteristics of the brushless motor.

[0012] Additionally, the real-time current consumption data is sequence data of current consumption measured continuously at predetermined time intervals, and the step of generating the characteristic vector may include: a step of calculating a plurality of statistical values ​​based on the sequence data; and a step of generating the characteristic vector by combining at least some of the sequence data with the statistical values.

[0013] In addition, the above artificial intelligence learning model may be a Random Forest machine learning model.

[0014] Additionally, the method may further include the step of collecting second real-time current consumption data from a plurality of certified / registered drones during a predetermined operating state for a predetermined period; the step of generating a second characteristic vector related to the current consumption characteristics of each certified / registered drone based on the second real-time current consumption data; and the step of pre-training an artificial intelligence learning model so that the artificial intelligence learning model distinguishes the certified / registered drones based on the second characteristic vector.

[0015] A computer program is provided according to an embodiment of the present application. The program may be stored on a recording medium to execute a method according to an embodiment of the present application.

[0016] According to an embodiment of the present application, a computer device for performing drone certification using real-time current consumption is provided. The device comprises at least one processor; and a memory for storing a program executable by the processor. By executing the program, the processor collects real-time current consumption data of a drone to be certified for a predetermined period of time in a predetermined operating state, generates a characteristic vector related to the current consumption characteristics of the drone to be certified based on the real-time current consumption data, and inputs the characteristic vector into a pre-trained artificial intelligence learning model to determine whether the drone to be certified is a legal drone. Effects of the invention

[0017] According to the embodiments of the present application, authorization of a drone can be performed using a sensor embedded in an existing drone without the installation of additional hardware, thereby resolving the problems of existing methods such as increased drone weight, reduced flight performance, and increased maintenance costs.

[0018] According to the embodiments of the present application, by using an identification method based on real-time current consumption, the overall efficiency of the system and the load can be improved by significantly reducing complex data processing and the demand for excessive computing resources.

[0019] According to the embodiments of the present application, by utilizing machine learning to learn the current consumption pattern of a brushless motor and thereby identifying a drone, faster and more accurate identification than conventional methods can be enabled and security can be enhanced.

[0020] According to the embodiments of the present application, by enabling the automation of the identification procedure and minimizing human intervention, the possibility of errors in the authentication procedure can be reduced and rapid and efficient drone management can be supported.

[0021] The effects obtainable from the embodiments of the present application are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present application belongs from the description below. Brief explanation of the drawing

[0022] A brief description of each drawing is provided to help to better understand the drawings cited in this application. FIG. 1 is a drawing for explaining a drone certification system according to an embodiment of the present application. FIG. 2 is a flowchart of a drone authentication method using real-time current consumption according to an embodiment of the present application. FIG. 3 is a flowchart illustrating an example of step S220 of FIG. 1. FIG. 4 is a flowchart of a drone authentication method using real-time current consumption according to an embodiment of the present application. FIGS. 5 and 6 are drawings for exemplarily illustrating real-time current consumption data of a drone according to an embodiment of the present application. FIG. 7 is a block diagram showing the configuration of a computer device for performing drone authentication using real-time current consumption according to an embodiment of the present application. Specific details for implementing the invention

[0023] The technical concept of the present application is subject to various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the technical concept of the present application to specific embodiments, and it should be understood that it includes all modifications, equivalents, and substitutions that fall within the scope of the technical concept of the present application.

[0024] In explaining the technical concept of the present application, detailed descriptions of related prior art are omitted if it is determined that such descriptions may unnecessarily obscure the essence of the present application.

[0025] The terms used herein are for describing embodiments and are not intended to limit or / or restrict the present application. Singular expressions include plural expressions unless the context clearly indicates otherwise. Additionally, numbers used herein (e.g., First, Second, etc.) are merely identifiers to distinguish one component from another.

[0026] In this specification, when it is stated that a part is connected to another part, this includes not only cases where they are directly connected, but also cases where they are indirectly connected with other components in between. Furthermore, when it is stated that a part includes a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0027] Furthermore, in this application, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related configurations.

[0028] In addition, terms such as “~part,” “~device,” “~device,” and “~module” described in this application refer to a unit that processes at least one function or operation, and this can be implemented as hardware or software or a combination of hardware and software, such as a processor, microprocessor, microcontroller, CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerate Processor Unit), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), etc.

[0029] Furthermore, it is intended to clarify that the classification of the components in this application is merely based on the primary function each component is responsible for. That is, two or more components described below may be combined into a single component, or a single component may be divided into two or more components based on more subdivided functions. Additionally, each component described below may additionally perform some or all of the functions performed by other components in addition to its own primary function, and it is obvious that some of the primary functions performed by each component may be exclusively performed by other components.

[0031] The method according to the embodiment of the present application may be performed on a personal computer, workstation, server computer device, etc., equipped with computing power, or on a separate device for this purpose.

[0032] Additionally, the method may be performed on one or more computing devices. For example, at least one step of the method according to an embodiment of the present application may be performed on a client device, and other steps may be performed on a server device. In this case, the client device and the server device may be connected via a network to transmit and receive computation results. Alternatively, the method may be performed by distributed computing technology.

[0034] In this application, the term "artificial intelligence learning model" may be used interchangeably with "artificial intelligence model," "computational model," "machine learning model," etc. The artificial intelligence learning model may be trained by various algorithms, such as, for example, decision tree, random forest, Gaussian naive bayes, k-nearest neighbor, Ada Boost, support vector machine, voting, bagging, neural network, and deep learning. However, it is not limited thereto.

[0035] An artificial intelligence learning model can be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. The training of an artificial intelligence learning model may be a process of applying knowledge to the model to perform a specific action.

[0036] When algorithms such as neural networks or deep learning are applied to an artificial intelligence learning model, the AI ​​learning model may be referred to as a network function. The term "network function" can be used interchangeably with "neural network." A neural network can generally be composed of a set of interconnected computational units referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node, and the nodes may be interconnected by one or more links.

[0037] Neural networks may include deep neural networks (DNNs). Deep neural networks may include convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders, restricted Boltzmann machines (RBMs), deep belief networks (DBNs), Q networks, U networks, Siamese networks, and Generative Adversarial Networks (GANs), but are not limited to these.

[0039] Hereinafter, embodiments of the present application will be described in detail in turn.

[0041] FIG. 1 is a drawing for explaining a drone certification system according to an embodiment of the present application.

[0042] Referring to FIG. 1, the drone certification system includes a plurality of drones (10) and a certification device (20), and the certification device (20) can certify whether the drone (10) corresponds to a legally registered drone.

[0043] Each of the multiple drones (10) includes a brushless motor and a current sensor, and can measure current consumption data in real time. The measured current consumption data can be transmitted to an authentication device (20) via wireless communication.

[0044] The authentication device (20) can analyze the current consumption characteristics of the drone based on the received data and determine whether the drone is legal through a pre-trained artificial intelligence learning model.

[0045] The authentication device (20) is linked to a surveillance system to detect a drone performing sensitive acts and, if necessary, initiate an authentication process. Sensitive acts may include entering a restricted access area, entering a military area, or moving to a delivery item pickup location. A drone (10) that responds to an authentication request transmits real-time current consumption data, and the authentication device (20) can analyze this to verify its legality.

[0046] The configuration of the system illustrated in FIG. 1 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0048] FIG. 2 is a flowchart of a drone authentication method using real-time current consumption according to an embodiment of the present application, and FIG. 3 is a flowchart for explaining an embodiment of step S220 of FIG. 1.

[0049] In step S210, the authentication device (20) can collect real-time current consumption data of the drone to be authenticated in a specific operating state.

[0050] Real-time current consumption data reflects the unique current consumption characteristics of the certified drone (in particular, brushless motor) and thus can serve as a unique identifier to identify each certified drone. The reason real-time current consumption data is a unique characteristic of the certified drone is that brushless motors have different physical characteristics due to minute differences in the manufacturing process. These characteristics may appear as a pattern of current consumption that occurs when the motor rotates in a specific operating state (e.g., a stationary flight state or a landing state) of the drone (10).

[0051] Real-time current consumption data is continuously collected at specific time intervals by the authentication device (20), and the unique characteristics of the drone to be authenticated can be analyzed based on the data during the specific time period.

[0052] For example, a monitoring system linked with an authentication device (20) can continuously monitor whether the drone to be authenticated attempts sensitive actions (such as entering a restricted access area, entering a military area, or moving to a pickup location for delivery items). When such sensitive actions are detected, the monitoring system transmits an authentication request to the drone (10) through the authentication device (20), and in response, the drone to be authenticated can transmit real-time current consumption data to the authentication device (20).

[0053] In the embodiment, real-time current consumption data may be collected using a current sensor embedded in the drone to be authenticated. For example, the sensor may include a Hall sensor that measures changes in the magnetic field according to the current, and the real-time current consumption of each or all of the plurality of brushless motors may be continuously measured at a first time interval (e.g., 0.5-second interval) and the measured data may be transmitted to the authentication device (20) upon the request of the authentication device (20). However, the type of current sensor and the measurement interval of the current consumption are exemplary and may be varied according to the embodiment to which the present application is applied.

[0054] In the embodiment, the real-time current consumption data may be current consumption data for at least one of a plurality of brushless motors mounted on the certified drone, or current consumption data for all brushless motors.

[0055] In step S220, the authentication device (20) can generate a characteristic vector related to the current consumption characteristics of the drone to be authenticated based on real-time current consumption data.

[0056] In the embodiment, step S220 may include steps S221 to S222, as illustrated in FIG. 3.

[0057] In step S221, the authentication device (20) can calculate a plurality of statistical figures based on sequence data regarding real-time current consumption.

[0058] Here, the sequence data is data regarding the amount of current consumed continuously at regular time intervals over a certain period of time. The sequence data may be data at the same interval as the first time interval recorded by the current sensor in the drone to be authenticated, or data at the second time interval defined by the authentication device (20). In this case, the second time interval may be a multiple of the first time interval.

[0059] For example, real-time current consumption data may be sequence data containing 20 measurements measured or recorded at 0.5-second intervals for 10 seconds.

[0060] In step S221, the authentication device (20) may calculate multiple statistical values, such as standard deviation, variance, minimum value, and maximum value, for a plurality of measurements included in the sequence data. However, these statistical items are exemplary, and various statistical items may be applied according to the embodiment.

[0061] In step S222, the authentication device (20) can generate a characteristic vector related to the current consumption characteristics of the drone to be authenticated by combining at least some of the sequence data with statistical figures.

[0062] In the embodiments, the feature vector may be in the form of combining all the statistical values ​​calculated for the entire sequence data, or in the form of combining a part of the sequence data and at least a part of the calculated statistical values.

[0063] For example, if sequence data is [21.14, 20.55, 21.22, ...], the feature vector for it can be constructed as [21.14, 20.55, 21.22, ..., 20.80 (mean), 0.52 (standard deviation), 0.27 (variance), 20.59 (maximum value), 19.38 (minimum value)].

[0064] However, this is merely an example, and the feature vector can be configured in various data formats capable of effectively expressing the unique current consumption characteristics of the drone by processing real-time current consumption data.

[0065] In step S230, the authentication device (20) can input the generated feature vector into a pre-trained artificial intelligence learning model to determine whether the drone to be authenticated is a legal drone.

[0066] As described below with reference to FIG. 4, the current consumption characteristics of a plurality of drones are represented by characteristic vectors, and an artificial intelligence learning model can be pre-trained to identify each of the plurality of drones based on these characteristic vectors. Through the training of such an artificial intelligence learning model, a legally compliant drone can be pre-registered based on its unique current consumption characteristics.

[0067] Therefore, when a characteristic vector regarding the current consumption characteristics of a drone subject to certification is input into a pre-trained artificial intelligence learning model, the artificial intelligence learning model can determine whether the drone subject to certification is a legal drone by determining whether the corresponding characteristic vector matches the current consumption characteristics of a previously registered drone.

[0068] In the embodiment, the artificial intelligence learning model may be a machine learning model such as Random Forest.

[0069] In this way, if it is determined through step S230 that the drone is legal, the monitoring system linked with the authentication device (20) can allow sensitive actions of the drone.

[0070] The method (200) illustrated in FIG. 2 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0072] FIG. 4 is a flowchart of a drone certification method using real-time current consumption according to an embodiment of the present application. More specifically, FIG. 4 is a flowchart illustrating the process of registering a legal drone through the unique current consumption characteristics of a plurality of drones subject to certification registration.

[0073] In step S410, the authentication device (20) can collect second real-time current consumption data from multiple certified registered drones.

[0074] At this time, the second real-time current consumption data can be collected in the same manner as the first real-time current consumption data collection method (100) described in FIG. 2, and consists of data that continuously records the current consumption of the brushless motor in a specific operating state of the drone.

[0075] However, for a single drone subject to certification registration, multiple real-time current consumption data can be collected repeatedly by varying the collection time intervals, rather than using a single data set. For example, a dataset containing 10 real-time current consumption data points can be generated for each drone. This method can contribute to improving the accuracy of the model by more precisely reflecting the current consumption characteristics of the drone and ensuring diversity in the training data.

[0076] The authentication device (20) records data when the brushless motor is rotating while the drone is hovering or landing, and the data can be measured at fixed time intervals (e.g., 0.5 seconds).

[0077] In step S420, the authentication device (20) can generate a second characteristic vector related to the current consumption characteristics of each certified registered drone based on the second real-time current consumption data.

[0078] At this time, the second characteristic vector can be generated in the same manner as steps S221 to S222 described above with reference to FIG. 3. That is, various statistical values ​​such as the mean, standard deviation, variance, minimum value, and maximum value are calculated for sequence data regarding real-time current consumption, and a characteristic vector is finally generated by combining the statistical values ​​and some or all of the sequence data.

[0079] For example, statistical figures can be calculated from each of the 10 real-time current consumption data sets collected for a single certified drone, and combined to generate 10 second characteristic vectors representing the unique characteristics of the drone. The characteristic vectors are data representations that reflect the unique physical characteristics and operating status of each drone, and can provide differentiation from other drones.

[0080] In step S430, the authentication device (20) can pre-train an artificial intelligence learning model to distinguish between drones subject to authentication registration based on a second characteristic vector.

[0081] As mentioned above, machine learning models such as Random Forest can be used in this stage, and the model training process can be carried out using the k-fold cross-validation technique. For example, the generalization performance and accuracy of the model can be improved by dividing the data into multiple sets and repeatedly performing training and validation.

[0082] Through steps S410 to S430, multiple drones subject to certification registration can be registered as lawful drones based on their respective unique current consumption characteristics.

[0083] The method (400) illustrated in FIG. 4 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0085] FIGS. 5 and 6 are drawings for exemplarily illustrating real-time current consumption data of a drone according to an embodiment of the present application.

[0086] Referring to Figures 5 and 6, sequence data of the current consumed by the brushless motor of the drone in a specific operating state (i.e., real-time current consumption data) and statistical figures calculated based thereon are shown.

[0087] Figure 5 illustrates sequence data of current consumption measured over a certain period of time in a specific operating state (e.g., hovering state or landing drive state) of a drone. The X-axis represents the passage of time, and the Y-axis represents the measured current value (Ampere). For example, the data for a specific drone may consist of current values ​​collected at 0.5-second intervals.

[0088] As illustrated in Fig. 6, sequence data can be represented in the form [21.14, 20.55, 21.22, ...], and statistical figures can be calculated based on this sequence data. The statistical figures consist of, for example, the mean, standard deviation (StdDev), variance (Variance), minimum value (Min), and maximum value (Max) of the sequence data, which quantitatively represent the unique current consumption characteristics of the drone.

[0089] Figures 5 and 6 allow for the visual confirmation of the unique current consumption patterns of each drone, and this data is used as basic data for generating characteristic vectors in the authentication device. Through this, the unique characteristics of each drone can be accurately analyzed, and legal drones can be identified by utilizing an artificial intelligence learning model.

[0091] FIG. 7 is a block diagram showing the configuration of a computer device for performing drone authentication using real-time current consumption according to an embodiment of the present application.

[0092] Referring to FIG. 7, the computer device (700) may include a communication unit (710), an input unit (720), a memory (730), and a processor (740). The computer device (700) may be the authentication device (20) described above with reference to FIG. 1.

[0093] The communication unit (710) can receive or transmit data from inside or outside. The communication unit (710) may include a wired or wireless communication unit. If the communication unit (710) includes a wired communication unit, the communication unit (710) may include one or more components that enable communication through a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof. Additionally, if the communication unit (710) includes a wireless communication unit, the communication unit (710) may transmit or receive data or signals wirelessly using cellular communication, a wireless LAN (e.g., Wi-Fi), etc. In an embodiment, the communication unit (710) may transmit or receive data or signals to or from an external device or an external server under the control of a processor (740).

[0094] The input unit (720) can receive various user commands through external operation. To this end, the input unit (720) may include or be connected to one or more input devices. For example, the input unit (720) may receive user commands by being connected to an interface for various inputs, such as a keypad or a mouse. To this end, the input unit (720) may include an interface such as a USB port as well as a Thunderbolt. Additionally, the input unit (720) may receive external user commands by including or combining with various input devices such as a touchscreen or a button.

[0095] The memory (730) can store programs and / or program instructions for the operation of the processor (740) and can temporarily or permanently store input / output data. Specifically, the memory (730) can store various data, programs (one or more instructions), applications, software, instructions, code, etc. for driving and controlling the processor (740). For example, the memory (730) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), SRAM, ROM, EEPROM, PROM, magnetic memory, magnetic disk, and optical disk.

[0096] In an embodiment, the memory (730) may store instructions for implementing at least one module, learning model, etc. for processing a method according to the embodiments of the present application.

[0097] The processor (740) can control the overall operation of the computer device (700). The processor (740) can execute one or more programs or software stored in memory (730). The processor (740) may mean a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or a dedicated processor (740) on which the methods according to embodiments of the present application are performed.

[0098] In an embodiment, the processor (740) collects real-time current consumption data of the certified drone for a predetermined time in a predetermined operating state, generates a characteristic vector related to the current consumption characteristics of the certified drone based on the real-time current consumption data, and inputs the characteristic vector into a pre-trained artificial intelligence learning model to determine whether the certified drone is a legal drone.

[0099] Here, the real-time current consumption data is the current consumption data of the brushless motor of the certified drone, and the predetermined operating state may be a state in which the certified drone is performing hovering flight, or a state in which the certified drone has landed and the brushless motor is rotating.

[0100] In addition, each of the multiple drones, including the drone subject to certification, may have unique current consumption characteristics that allow them to be identified from one another in the operating state according to the unique physical characteristics of the brushless motor.

[0101] In an embodiment, real-time current consumption data is sequence data for current consumption measured continuously at predetermined time intervals, and the processor (740) can calculate a plurality of statistical values ​​based on the sequence data and generate a characteristic vector by combining at least some of the sequence data with the statistical values.

[0102] Here, the artificial intelligence learning model can be a Random Forest machine learning model.

[0103] In an embodiment, the processor (740) collects second real-time current consumption data from a plurality of certified registered drones for a predetermined time in a predetermined operating state, generates a second characteristic vector related to the current consumption characteristics of each certified registered drone based on the second real-time current consumption data, and can pre-train an artificial intelligence learning model so that the artificial intelligence learning model distinguishes certified registered drones based on the second characteristic vector.

[0104] The configuration of the computer device (700) shown in FIG. 7 is exemplary, and various configurations may be applied according to embodiments of the present application.

[0106] The method according to an embodiment of the present application may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present application or may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROMs and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0107] Additionally, the method according to the disclosed embodiments may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product.

[0108] A computer program product may include a software program and a computer-readable storage medium on which the software program is stored. For example, a computer program product may include a product in the form of a software program (e.g., a downloadable app) that is electronically distributed through a manufacturer of an electronic device or an electronic market (e.g., Google Play Store, App Store). For electronic distribution, at least a portion of the software program may be stored on a storage medium or temporarily created. In this case, the storage medium may be a server of the manufacturer, a server of the electronic market, or a storage medium of a relay server that temporarily stores the software program.

[0109] A computer program product may include a storage medium of a server or a storage medium of a client device in a system composed of a server and a client device. Alternatively, if there is a third device (e.g., a smartphone) that communicates with the server or the client device, the computer program product may include a storage medium of the third device. Alternatively, the computer program product may include the S / W program itself that is transmitted from the server to the client device or the third device, or transmitted from the third device to the client device.

[0110] In this case, one of the server, the client device, and the third device may execute the computer program product to perform the method according to the disclosed embodiments. Alternatively, two or more of the server, the client device, and the third device may execute the computer program product to perform the method according to the disclosed embodiments in a distributed manner.

[0111] For example, a server (e.g., a cloud server or an artificial intelligence server, etc.) can execute a computer program product stored on the server to control a client device connected to the server in communication to perform a method according to the disclosed embodiments.

[0113] Although the embodiments have been described in detail above, the scope of the present application is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present application as defined in the following claims also fall within the scope of the present application.

Claims

Claim 1 A method for certifying a drone using real-time current consumption, wherein each step is performed by a computer device comprising at least one processor, comprising: a step of collecting real-time current consumption data of a drone to be certified for a predetermined time period in a predetermined operating state; a step of generating a characteristic vector related to the current consumption characteristics of the drone to be certified based on the real-time current consumption data; and a step of inputting the characteristic vector into a pre-trained artificial intelligence learning model to determine whether the drone to be certified is a lawful drone. Claim 2 In claim 1, the method wherein the real-time current consumption data is the current consumption data of the brushless motor of the certified drone. Claim 3 A method according to claim 2, wherein the predetermined operating state is a state in which the certified drone is performing hovering flight, or a state in which the certified drone has landed and the brushless motor is rotating. Claim 4 In claim 2, the method wherein the certified drone has a unique current consumption characteristic that is identifiable from other drones in the operating state according to the unique physical characteristics of the brushless motor. Claim 5 In claim 2, the real-time current consumption data is sequence data for current consumption measured continuously at predetermined time intervals, and the step of generating the characteristic vector comprises: a step of calculating a plurality of statistical values ​​based on the sequence data; and a step of generating the characteristic vector by combining at least some of the sequence data with the statistical values. Claim 6 In claim 2, the method wherein the artificial intelligence learning model is a Random Forest machine learning model. Claim 7 A method according to claim 2, further comprising: a step of collecting second real-time current consumption data from a plurality of certified / registered drones during a predetermined operating state for a predetermined time period; a step of generating a second characteristic vector related to the current consumption characteristics of each certified / registered drone based on the second real-time current consumption data; and a step of pre-training an artificial intelligence learning model so that the artificial intelligence learning model distinguishes the certified / registered drones based on the second characteristic vector. Claim 8 A computer program stored on a computer-readable recording medium to execute a method according to any one of claims 1 to 7. Claim 9 A computer device for performing drone certification using real-time current consumption, comprising: at least one processor; and a memory for storing a program executable by said processor, wherein the processor, by executing said program, collects real-time current consumption data of a drone to be certified for a predetermined period of time in a predetermined operating state, generates a characteristic vector related to the current consumption characteristics of the drone to be certified based on said real-time current consumption data, and inputs said characteristic vector into a pre-trained artificial intelligence learning model to determine whether the drone to be certified is a lawful drone.

Images