System

Abstract

To address issues of easily and efficiently performing the operation to simultaneously control a plurality of unmanned aerial vehicles.SOLUTION: Provided is a system for simultaneously controlling a plurality of unmanned aerial vehicles by using generative AI, said system comprising generation means for receiving an indication in natural language and generating an operation program for an unmanned aerial vehicle after being analyzed by AI.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present invention is to perform a simple and efficient operation for simultaneously controlling multiple unmanned aerial vehicles. [Means for solving the problem]

[0005] A system for simultaneously controlling multiple unmanned aerial vehicles using generative AI, the system including: a generating means for receiving instructions in natural language, analyzing them using AI, and then generating an operating program for the unmanned aerial vehicles. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0015] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0016] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0017] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0018] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicative of the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicative of the user input.

[0019] The output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0020] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0021] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0022] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0023] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0024] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0025] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0026] (Example 1) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a communication means. The control device is equipped with a generation means that receives instructions in natural language, analyzes the instructions by the AI, and then generates an operation program for the unmanned aerial vehicle. The unmanned aerial vehicle performs operations such as movement and rotation according to the instructions based on the generated operation program. The communication means is a means for transmitting and receiving instructions and data between the control device and the unmanned aerial vehicle. The generating means is realized, for example, by the specific processing unit 290 of the data processing device 12. The communication means is realized, for example, as a means for transmitting and receiving instructions and data to and from the unmanned aerial vehicle via the communication I / F 26 of the data processing device 12 or the communication I / F 44 of the smart device 14. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The generation means utilizes natural language processing technology to analyze instructions from a user and generate an operation program for the unmanned aerial vehicle. The generation means can also convert human oral or text input instructions into digital data using a voice recognition means and a text analysis means and interpret the contents of the digital data. This means includes a voice recognition function and converts the user's oral instructions into text data. The voice recognition means has a function of receiving the user's voice instructions and converting the voice data into text. The text analysis means performs morphological analysis and syntactic analysis to understand the contents of the instructions and grasp the intention. The text analysis means also performs morphological analysis and syntactic analysis to understand the meaning of the input text. The intention analysis means identifies the purpose or task behind the instructions, and the operation program generation means generates a specific operation program based on the analyzed intention. The intention analysis means can also identify specific tasks or purposes from instructions included in the text, and the operation program generation means can create an operation program based on the specified tasks or purposes. The operation program generation means utilizes a probabilistic algorithm or a machine learning model to develop an efficient and safe operation plan for the unmanned aerial vehicle. The operation program generating means can also define an operation sequence to be performed by the unmanned aerial vehicle and calculate the parameters required for that. The unmanned aerial vehicle automatically executes operations based on the generated operating program through the flight control means installed on the vehicle. The unmanned aerial vehicle also has a built-in flight control means, and can autonomously perform operations such as flying and rotating according to the generated operating program. The flight control means controls the attitude and position of the unmanned aerial vehicle in real time based on data from sensors and position information from GPS. The flight control means also functions by combining an attitude control function, a position control function, and a speed control function, which can also adjust the flight state of the unmanned aerial vehicle based on sensor data and GPS information. The obstacle detection means recognizes the surrounding environment, and the collision avoidance means calculates a route to avoid the obstacle. The obstacle detection means also detects surrounding obstacles using sensors such as radar and LiDAR, and the collision avoidance means can calculate an alternative route to avoid the detected obstacle, allowing the vehicle to fly safely. The communication means enables data transmission and reception between the control device and the unmanned aerial vehicle using wireless communication technology. The communication means can also transmit and receive data between the control device and the unmanned aerial vehicle using advanced wireless communication technology. The means include an encoding means for encoding and decoding signals and an error correction means for maintaining the reliability of communication. The encoding means efficiently encodes the data to be transmitted and decodes it at the receiving end to recover the meaning of the data. The error correction means detects and corrects data errors that may occur in the communication process to maintain the reliability of communication. The communication means employs a communication protocol with low latency and high bandwidth to quickly transmit and receive data on the operation program and operation status. The communication protocol can also be optimized to achieve low latency and high bandwidth and transmit the flight status, sensor data, and video feed of the unmanned aerial vehicle in real time. The control device can always grasp the status of the unmanned aerial vehicle and issue additional instructions as necessary. The unmanned aerial vehicle also transmits sensor data and video feeds during flight to the control device in real time for monitoring and analysis. The unmanned aerial vehicle can also transmit data during flight to a control device via communication means, allowing real-time monitoring by an operator and collection of data for later analysis. A variety of additional functions can be incorporated into control systems that utilize unmanned aerial vehicles. For example, an environmental monitoring function can be added to an unmanned aerial vehicle to precisely measure temperature, humidity, and atmospheric pressure from the air and collect meteorological data. In addition, in agricultural applications, it is effective to equip the vehicle with sensors that measure soil moisture and nutritional status to provide functions that support precision agriculture. Unmanned aerial vehicles can also be equipped with functions to support rescue operations. For example, in the event of a disaster, they can grasp the extent of damage to buildings and the locations of victims, and provide information to rescue teams. They can also be equipped with thermal cameras to detect smoke and fire conditions, which can be useful in directing and supporting firefighting operations. Furthermore, to improve their autonomous flight capabilities, swarm functions can be developed that use AI to allow unmanned aerial vehicles to share information with each other and cooperate as a swarm, making it possible to monitor a wider area and carry out multiple tasks simultaneously. In terms of communication, we will consider alternative means of communication such as satellite communication and laser communication to improve communication stability. This will enable us to maintain communication with unmanned aircraft even in remote areas or disaster areas where communication infrastructure has been destroyed. Furthermore, to operate unmanned aircraft more safely and efficiently, we will introduce a system that combines ground radar systems and communications with other aircraft to accurately grasp the position and status of unmanned aircraft in flight and assist in collision avoidance. Surveillance systems using unmanned aerial vehicles can incorporate advances in video analytics technology to identify objects and people from video in real time and analyze behavioral patterns. This will automate security and surveillance tasks, contributing to crime prevention and safety management. In addition, footage captured by unmanned aerial vehicles can be used for virtual reality and augmented reality to provide new experiences in education, training, tourism, and more. Finally, the control device will be equipped with a self-learning function to train machine learning models that utilize the drone's operational logs and sensor data to improve the drone's flight performance, allowing the drone to learn from past experience, select more effective flight routes, and perform tasks more efficiently. It is conceivable that generative AI installed in the control device can be used to automate tasks in other industrial fields. For example, agricultural tasks such as spraying pesticides and sowing seeds can be automated to reduce manual labor. Ultrasonic sensors and near-infrared cameras can be installed in the drones to help with crop growth and early detection of disease. In addition, a precision pesticide spraying system using drones can be developed to optimize the amount of pesticide used and reduce environmental impact. The AI ​​that generates the control device can be applied not only to unmanned aerial vehicles, but also to underwater robots and autonomous vehicles on land. By combining these different platforms, a monitoring network covering land, sea and air can be constructed, which is expected to be used in a wide range of fields such as environmental monitoring, resource exploration, and disaster response. In environmental monitoring using unmanned aerial vehicles, it is also effective to mount a composite gas sensor to monitor air pollution and measure greenhouse gases. In addition to disaster relief, the combination of the control device and unmanned aerial vehicles can also be used for rescue and search operations. Combining high-performance cameras with face recognition technology will help with searches for missing people and early detection of people in distress during coastal surveillance. A system will also be developed that will equip unmanned aerial vehicles with lifesaving kits and quickly drop rescue supplies to people in distress. The strengthening of communication methods will enable use in remote medical care, where real-time data is important, and emergency communications during disasters. By achieving high-resolution video transmission and low-latency communications, it will play a role as infrastructure for doctors to supervise surgery from remote locations and for establishing emergency communications from disaster sites. We will further evolve the AI ​​of the control device and develop algorithms that allow swarms of unmanned aerial vehicles to work together to carry out complex tasks. This will enable multiple unmanned aerial vehicles to share a large task and complete it efficiently. For example, this can be applied to transporting materials at construction sites and extinguishing fires. Ultimately, the combination of control device AI and unmanned aerial vehicles will contribute to the creation of smart cities, such as managing urban infrastructure, monitoring traffic flow, and ensuring public safety. Using real-time data provided by unmanned aerial vehicles, a system will be built to optimize city operations and respond quickly to disasters. Information collected by unmanned aerial vehicles will also be useful in formulating urban plans and transportation policies. This will support the development of sustainable and efficient cities. (Example 2) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a location information acquisition means. The control device receives instructions in natural language, analyzes the instructions using the AI, and then acquires location information of the unmanned aerial vehicles. The location information acquisition means is a means for identifying the location of the unmanned aerial vehicles using a GPS, a sensor, or the like. The control device includes a control means for controlling the unmanned aerial vehicles according to the instructions based on the acquired location information. The location information acquisition means is realized, for example, by a GPS or a sensor mounted on the unmanned aerial vehicle. The control means is realized, for example, by a specific processing unit 290 of the data processing device 12. The correspondence between each means and the device or control unit is not limited to the above example, and various modifications are possible. The control device uses an analysis means including a natural language understanding module to analyze instructions from the user and grasp the intention. The control device also includes an instruction receiving means for receiving natural language instructions from the user and a natural language understanding module for analyzing the instructions. The natural language understanding module includes a voice-to-text conversion means for converting voice instructions into text data using voice recognition technology. The voice-to-text conversion function can convert the user's instructions into text information using a voice recognition algorithm. The voice-to-text conversion function includes language processing means such as tokenization, part-of-speech tagging, noun phrase analysis, verb phrase analysis, and dependency analysis for further analyzing the converted text data. The language processing function can also clearly grasp the intention of the instructions using a tokenization means, part-of-speech tagging means, syntactic analysis means, etc. This allows commands, parameters, conditions, etc. included in the user's instructions to be accurately identified. The analyzed instructions are interpreted by the generation AI as commands necessary for controlling the unmanned aerial vehicle and transmitted to the control unit of the unmanned aerial vehicle via a command generation means for generating a corresponding action command. This allows the user's intention to be interpreted as a command and generates an action command to be transmitted to the unmanned aerial vehicle. The location information acquisition means includes a composite location information processing means for tracking the exact location of the unmanned aerial vehicle. The location information acquisition means also includes a GPS module mounted on the unmanned aerial vehicle, which can acquire location information on the earth. This GPS module acquires latitude, longitude, and altitude information of any point on the earth. Furthermore, a GNSS analysis means for analyzing a GNSS (Global Navigation Satellite System) signal can provide higher accuracy and reliability of location information. The GNSS analysis means used in conjunction with this can also improve the accuracy of the position using signals from satellites. Meanwhile, an inertial measurement unit (IMU) such as an integrated acceleration sensor and gyroscope continuously tracks the attitude and movement of the unmanned aerial vehicle, and assists in acquiring stable location information even in an environment where the GPS signal is unstable. In addition, an IMU for detecting the movement of the unmanned aerial vehicle provides information based on inertia, and can maintain the accuracy of the location information even in a situation where the GPS signal is unstable. As an example that does not include a sensor, a communication-based location information acquisition means is considered, in which the unmanned aerial vehicle acquires its own location information by communicating with a beacon or a ground station. Another example of sensor-free location acquisition is a communication-based location acquisition method. In this method, the relative and absolute position is determined through signals transmitted from ground beacons and through communication with other unmanned aircraft. The beacon transmits radio waves of a specific frequency, which is received by a receiving module on the unmanned aircraft and serves as a reference point for calculating the location information. The unmanned aircraft can also calculate its own position based on the received signal. In such a system, the current position of the unmanned aircraft and adjustments to the flight path are exchanged in real time through communication with a ground station. The control means includes a flight path planning means for planning and adjusting the flight path of the unmanned aerial vehicle. The control means also includes a flight path planning function for planning and adjusting the flight path of the unmanned aerial vehicle. This incorporates a simulation means for simulating the operation of the unmanned aerial vehicle and calculating an optimal flight path, taking into account obstacles and safety constraints on the flight path. This function can also simulate the flight path using the simulation means and calculate the optimal path, taking into account obstacle avoidance means and safety constraints. Furthermore, it also includes an emergency avoidance means for quickly responding to an emergency that the unmanned aerial vehicle may encounter, and a group control means for cooperatively controlling multiple unmanned aerial vehicles. It also includes an emergency avoidance function for responding to an emergency, and a group control function for centrally controlling multiple unmanned aerial vehicles. The control device of this embodiment can incorporate an advanced obstacle detection system to improve flight capabilities in more complex environments. For example, a function is added that utilizes 3D mapping technology using a laser scanner or ultrasonic sensor to precisely recognize the surrounding environment during flight and quickly and autonomously respond to dynamically changing obstacles. In addition, by analyzing satellite images and geographic information system (GIS) data, it is possible to take into account terrain features and obstacle information in more detail in the flight plan, enabling advanced optimization of the flight path. In controlling a group of unmanned aerial vehicles, a coordinated flight algorithm based on swarm intelligence using AI can be introduced, allowing multiple unmanned aerial vehicles to work together efficiently. For example, when multiple unmanned aerial vehicles are dispersed to perform tasks in pesticide spraying or search and rescue operations, dynamic flight path adjustments are made to maximize the overall work efficiency. This allows unmanned aerial vehicles to share roles and cooperate according to individual situations. The control device's natural language understanding module will be equipped with a specialized dictionary and context analysis function to understand technical terms and industry-specific language used by users, improving its ability to accurately analyze instructions specialized for specific industries and applications and convert them into specific operation commands. In addition, to improve the unmanned aerial vehicle's environmental awareness, a function will be added to analyze social media and internet information in addition to sensor data to grasp people's activity patterns and the occurrence of events. In terms of location information acquisition means, it is possible to introduce a differential GPS (DGPS) system that provides more accurate location information by incorporating a network of ground reference stations that provide correction signals to the GPS module used by the unmanned aircraft. Furthermore, in order to enable operation and monitoring from remote locations, a real-time data link system using satellite communications can be incorporated, allowing the unmanned aircraft to be controlled from anywhere on Earth. By integrating these functions, unmanned aerial vehicles will be able to handle more complex missions and realize flexible and advanced operations tailored to user needs, providing advanced solutions using unmanned aerial vehicles in fields such as disaster relief, environmental monitoring, and security surveillance. The control device can be equipped with a context recognition function to interpret user instructions more precisely, allowing it to take the optimal action depending on different circumstances, even with the same command. It can also have a function to ask questions to the user in response to unclear instructions through dialogue, improving the accuracy of communication and preventing misunderstandings. Furthermore, it can have a multitasking capability to process instructions from multiple users simultaneously, achieving high flexibility in large-scale operations. The location information acquisition method will add a LiDAR sensor that performs 3D scanning of the drone's surroundings in real time, achieving more advanced environmental recognition and accurate positioning. In addition, visual odometry will be used to estimate the drone's movement from images captured by the camera, providing stable location information even in environments where GPS is not available. This will enable activities in places where it is difficult to receive GPS signals, such as between high-rise buildings in urban areas or in dense forests. The control method will employ a self-learning obstacle avoidance algorithm that allows the drone to autonomously avoid obstacles and adjust its flight path. In addition, a cooperative avoidance algorithm will be introduced that allows drones to communicate with each other to share the status of surrounding drones in real time, enabling them to fly efficiently while avoiding collisions. This will enable drones to carry out their missions safely even in situations where multiple drones are flying close together. The AI ​​of the control device can continuously update the environmental model based on the data collected by the unmanned aircraft and perform predictive control based on that environmental model. This allows the unmanned aircraft to realize autonomous flight that can respond not only to the current situation but also to future changes. The unmanned aircraft can also make optimal decisions according to the situation at hand, going beyond pre-set behavior patterns. Finally, the system proposed in this embodiment is applicable to various applications such as advanced monitoring, investigation, and disaster response using unmanned aerial vehicles, and is a next-generation unmanned aerial vehicle control system that combines high autonomy and usability. It is expected that this will promote the effective use of unmanned aerial vehicles in activities in areas where human access is difficult or dangerous, and in emergency missions with time constraints. (Example 3) An embodiment of the present invention is a system including a control device equipped with a generating AI, a plurality of unmanned aerial vehicles, and a video processing means. The control device receives instructions in natural language, which are analyzed by the AI, and then processes the video of the unmanned aerial vehicle. The video processing means is a means for analyzing the video of the unmanned aerial vehicle using a camera or image recognition technology. The control device includes a control means for controlling the unmanned aerial vehicle according to the instructions based on the analyzed video information. The image processing means is realized, for example, by an image recognition technology realized by a camera mounted on the unmanned aerial vehicle or a specific processing unit 290 of the data processing device 12. The control means is realized, for example, by a specific processing unit 290 of the data processing device 12. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The control device includes an instruction analysis means using a natural language processing model, and has a function of receiving instructions from a user in text or voice format and understanding the intention. The instruction analysis means understands natural language sentences through morphological analysis and syntactic analysis, and accurately understands the intention of the instructions through semantic analysis. The natural language processing model mounted on the control device can receive the user's voice or text instructions and divide the data into basic units of language through a morpheme division function. Next, the syntactic analysis function can clarify the structure of the sentence, and the semantic analysis function can also identify the intention of the instructions according to the context. Based on these analysis results, a language understanding model built by machine learning accurately understands the user's intention and generates a corresponding action. In this process, a language model based on machine learning learns from training data to improve the accuracy of responses to user instructions. The image processing means installed in the unmanned aerial vehicle includes a real-time image analysis function, which instantly processes the image data captured by the unmanned aerial vehicle and identifies specific objects and scenery. This function uses an object detection model and a semantic segmentation model based on deep learning to recognize the type and location of objects and extract the characteristics of the environment captured by the unmanned aerial vehicle. The image processing means installed in the unmanned aerial vehicle can also analyze the image data in real time and identify specific objects in the screen using the object identification function. The object detection model and the semantic segmentation model can also be fused to identify the type and location of objects in the image. Pre-processing of the image data includes noise reduction and contrast adjustment, which contributes to improving the recognition accuracy. Furthermore, the image pre-processing function can perform noise reduction and contrast adjustment to improve the accuracy of the image analysis. The control means includes a flight path calculation function for the unmanned aerial vehicle, which calculates an optimal flight path to the destination based on the analyzed image information, and efficiently guides the unmanned aerial vehicle. This flight path calculation function integrates terrain data and weather information to avoid obstacles and maximize energy efficiency. In addition, as a control means, the unmanned aerial vehicle uses a flight path calculation function to calculate an efficient path to the destination. This function can combine a terrain data integration function and a weather information integration function to ensure flight safety and efficiency. In addition, the flight operation control function of the unmanned aerial vehicle precisely adjusts basic flight operations such as speed, altitude, and attitude control, and performs operations according to user instructions. In addition, the flight operation control function can also appropriately adjust the speed, altitude, and attitude of the unmanned aerial vehicle to realize operations according to user instructions. As part of the image processing means, an environmental monitoring function using an unmanned aerial vehicle is also considered. This uses an environmental change detection model to detect natural disasters and abnormal situations, enabling appropriate responses to the situation. The environmental monitoring function using an unmanned aerial vehicle can also use an environmental change detection model to quickly capture natural disasters and abnormal situations, enabling appropriate responses to the situation. This monitoring function effectively detects environmental changes over a wide area, enabling information collection and rapid response. An example of data collection that does not include sensors is a manual selection means where a user manually selects video data through a camera mounted on the unmanned aerial vehicle and transmits the data to the control device. This manual selection means is useful when a user is interested in a specific video or when video analysis is required under a specific situation. The user selects video data through an interface and transmits it to the control device, where it is analyzed by the video analysis means and handled by the control means. Alternatively, as a manual selection means, a user can select video data captured by the camera of the unmanned aerial vehicle through an interface and transmit it to the control device. This selection process allows video data to be selected based on a specific request from the user, and detailed analysis by the video processing means and appropriate flight control by the control means are performed. The control device can incorporate a reinforcement learning algorithm to learn behavioral patterns according to various situations. This algorithm enhances the adaptability of the unmanned aerial vehicle to respond to different environments and missions. The control device can also be equipped with a multi-agent system to manage the coordinated flight of multiple unmanned aerial vehicles. This allows multiple unmanned aerial vehicles to take action simultaneously and cooperate efficiently toward a single goal. Furthermore, the control device can be equipped with safety functions, including an automatic return function for the unmanned aerial vehicle in an emergency and an automatic obstacle avoidance function. This allows the unmanned aerial vehicle to complete its mission while ensuring its own safety. The image processing means may incorporate infrared cameras and heat sensing technology for high-precision image analysis even at night or in bad weather conditions, allowing the UAV to collect and analyze image data in any environment, day or night. In addition, the image processing means may also enable tracking of moving targets using object tracking algorithms in dynamic scenes. This capability allows the UAV to continuously monitor moving objects and provide critical information. The control means can be equipped with a swarm intelligence function that controls a swarm of unmanned aerial vehicles based on user instructions. This allows a swarm of unmanned aerial vehicles to fly together and perform missions more effectively in complex environments. The control means can also be equipped with a dynamic flight path recalculation function in response to real-time traffic information and weather changes. This allows the unmanned aerial vehicles to quickly respond even when information is updated mid-flight, improving the efficiency of mission execution. As part of the video processing means, a function can be included for uploading the video data collected by the unmanned aerial vehicle to a cloud service in real time for wide-ranging data analysis and sharing. This allows the video data captured by the unmanned aerial vehicle to be shared with a wide range of users for quick decision-making and information sharing. The video processing means can also have a detailed mapping function for the damage situation when a disaster occurs. This allows the unmanned aerial vehicle to get a detailed understanding of the situation immediately after the disaster occurs and provide important information for rescue teams and recovery efforts. As an example of sensor-free data collection, video data acquired by users through drones can be automatically posted to social media and news sites through AI-assisted automated analysis. This allows social events and unusual natural phenomena to be widely publicized, attracting interest and raising awareness. In addition, by including a data anonymization function to protect user privacy, video data collected by drones can be shared safely. The generation AI installed in the control device can be added with a function to analyze the video captured by the unmanned aerial vehicle in real time and identify the damage situation and the location of survivors during a disaster. This will contribute to the speed and efficiency of rescue operations. In addition, 3D mapping technology using the video data from the unmanned aerial vehicle can be integrated to create a three-dimensional map of the disaster area, enabling a more detailed understanding of the situation. The image processing means will incorporate highly sensitive sensors and image enhancement technology that are not affected by day and night or weather changes, allowing the drone to capture clear images even in low-light environments. It will also be able to recognize specific patterns and symbols in the image data, for example, to detect signs requesting help or specific obstacles. The control means has the function of automatically adjusting the formation and timing when the drones fly in a group. This allows multiple drones to cooperate to cover a wide area and efficiently collect data. In addition, the drones can be equipped with an autonomous avoidance function based on environmental recognition to quickly avoid unexpected obstacles they encounter. The video processing means may include the ability to detect motion within the video data and automatically track the camera of the unmanned aerial vehicle accordingly, allowing for uninterrupted monitoring of dynamic scenes or objects that need to be tracked. The control means is equipped with an algorithm that optimizes the energy consumption of the drone, contributing to extending mission time and reducing operating costs. In addition, the drone's flight path can be optimized in real time to flexibly respond to sudden changes in conditions. As an extension of the image processing means, it will be equipped with a function that enables multifaceted analysis of the image data collected by the unmanned aerial vehicle, enabling applications in different fields, such as evaluating the health of crops in the agricultural sector and detecting changes in ecosystems in environmental monitoring. The control device can be equipped with a function to further improve its natural language understanding capability in order to realize interactive communication with users. This will enable users to intuitively operate the unmanned aerial vehicle, enabling a wider range of users to utilize unmanned aerial vehicles. The video processing means can be equipped with a function that allows the insertion of text and annotations into live video in real time to make the content of the video easier to understand. This makes it possible, for example, to instantly provide rescue information to rescue workers and commanders on the scene during a disaster. The control means can be equipped with features to enable the UAS to self-heal and provide periodic maintenance reminders, thereby increasing the availability and reliability of the UAS for long-term, stable operation. These additional functions will dramatically improve the capabilities of unmanned aerial vehicles for surveillance, disaster response, and information gathering, making it possible to create a flexible system that can respond to a variety of situations. (Example 4) An embodiment of the present invention is a system including a control device equipped with a generating AI, a plurality of unmanned aerial vehicles, and a distance measurement means. The control device receives instructions in natural language, analyzes them using the AI, and then measures the distance to the unmanned aerial vehicles. The distance measurement means measures the distance between the unmanned aerial vehicles and obstacles using an ultrasonic sensor, a laser range finder, or the like. The control device includes a control means for controlling the unmanned aerial vehicles according to the instructions based on the measured distance information. The distance measurement means is realized, for example, by an ultrasonic sensor or a laser range finder mounted on the unmanned aerial vehicle. The control means is realized, for example, by a specific processing unit 290 of the data processing device 12. The correspondence between each means and the device or control unit is not limited to the above example, and various modifications are possible. The generation AI built into the control device has a function of understanding human instructions using natural language analysis means, and generates commands necessary for operating the unmanned aerial vehicle using this function. In addition, the generation AI mounted on the control device can understand user instructions and generate commands necessary for operating the unmanned aerial vehicle by combining a voice recognition means having a voice-to-text conversion function with a grammar analysis means and a semantic analysis means for interpreting the meaning of a sentence. The generated commands include specific instructions for planning the flight path and the operation of the unmanned aerial vehicle, which are executed by the control algorithm of the unmanned aerial vehicle. In addition, the generated commands include detailed instructions regarding the flight path and operation of the unmanned aerial vehicle, and can be executed by the control algorithm means. The ultrasonic sensor as a distance measuring means is installed on the front or side of the unmanned aerial vehicle and measures the distance by detecting the reflected sound waves from surrounding obstacles. This sensor has an echo cancellation function to adapt to the environment and a filtering function to remove interference waves, and provides accurate distance information. In addition, the ultrasonic sensor can detect the reflected waves from surrounding obstacles using the echolocation function and obtain distance information. This sensor can provide accurate distance information without being affected by environmental noise due to the interference sound wave removal function and echo cancellation function. On the other hand, the laser rangefinder can measure distance with high accuracy and is particularly suitable for measuring long distances and detecting subtle obstacles. The laser rangefinder emits a laser beam to the target and calculates the distance using the time difference of the reflected light. In addition, the laser rangefinder has a function of emitting a laser beam to the target and a function of detecting the reflected light, and can measure the distance by the reflection time difference calculation function. The laser rangefinder enables precise distance measurement and can be particularly suitable for detecting long distances and subtle obstacles. The control means has a function of adjusting the operation of the unmanned aerial vehicle based on information from the distance measurement means, and this function is realized by a flight control algorithm of the unmanned aerial vehicle. The flight control algorithm is designed based on control theories such as PID control and feedforward control, and enables the unmanned aerial vehicle to accurately execute instructed operations while maintaining stable flight. The control means adjusts the attitude and speed of the unmanned aerial vehicle in real time, and optimizes a route to reach the destination while avoiding obstacles. The control means can also have a route control function that uses information provided by the distance measurement means to adjust the attitude and speed of the unmanned aerial vehicle and avoid obstacles. The flight control algorithm means can utilize a PID control function and a feedforward control function to adjust the operation of the unmanned aerial vehicle so that the unmanned aerial vehicle flies stably and accurately according to instructions. An example of distance measurement that does not include a sensor is a positioning means using GPS. A GPS receiver mounted on an unmanned aerial vehicle receives signals transmitted from satellites and calculates the current position of the unmanned aerial vehicle based on the information. The positioning means provides wide-area position information of the environment in which the unmanned aerial vehicle flies, and is used to plan larger-scale flight plans. In addition, in order to grasp the relative positional relationship between unmanned aerial vehicles, multiple unmanned aerial vehicles share their respective GPS information and function as a means for adjusting the flight formation as a whole. Furthermore, the positioning means using GPS can determine the current location of the unmanned aerial vehicle via a GPS receiver equipped with a satellite signal receiving function. The position information calculation function can calculate the position of the unmanned aerial vehicle from the received satellite signals and contribute to the planning of a wide-area flight plan. Furthermore, by sharing position information between unmanned aerial vehicles, it can also function as a flight formation adjustment function, and flight coordination as a whole can be realized. The control device further includes an image processing means for improving the accuracy of obstacle detection. For example, an object recognition algorithm based on machine learning can be used to automatically detect obstacles from the video captured by the unmanned aerial vehicle and recognize their size and shape. This allows the unmanned aerial vehicle to fly safely in more complex environments. The control device also has the ability to analyze the video data captured by the unmanned aerial vehicle in real time and adjust the flight path according to dynamic environmental changes. Furthermore, the control device is equipped with a communication control means for adjusting communication between unmanned aerial vehicles, enabling multiple unmanned aerial vehicles to share information and fly cooperatively. The communication control means has a function of optimizing cooperative operations during formation flight and specific mission execution. The AI ​​of the control device has a self-learning function that learns from the actual flight environment, and automatically generates the optimal flight path when it encounters new obstacles or unknown situations. The AI ​​accumulates the drone's experience and improves the flight pattern by referring to past data. This learning process allows the drone to better adapt to the environment and perform its missions more effectively. The control device also has a collision avoidance algorithm when multiple drones are operating at the same time, realizing safe and efficient swarm movements. Distance measurement sensors will be supplemented with infrared sensors and thermal imaging cameras for accurate distance measurements even at night and in bad weather. These will compensate for the limitations of conventional ultrasonic sensors and laser range finders, allowing the drone to operate in more challenging environments. These sensors will also provide additional information to detect obstacle types and temperature distributions and select flight paths accordingly. The control vehicle will incorporate an advanced collision avoidance system that combines real-time environmental awareness and predictive modeling to enable the unmanned aerial vehicle to respond quickly and effectively to unexpected obstacles. The collision avoidance system will allow the unmanned aerial vehicle to automatically change its flight path to ensure safe and continuous mission completion. In addition, the control vehicle will also be capable of optimizing the unmanned aerial vehicle's energy management to extend flight time and improve mission efficiency. The generative AI installed in the control device has the ability to simultaneously monitor multiple unmanned aerial vehicles and coordinate the operation of each aircraft, enabling them to operate in a swarm-like coordinated manner. The unmanned aerial vehicles share information with each other and are aware of the surrounding environment and the positions of other aircraft, allowing them to carry out their missions efficiently and safely. This coordinated operation is particularly effective in environments with complex terrain and many obstacles, and can be applied to search and rescue operations and situational awareness during disasters. In addition, the drone's distance measurement means will use a new sensor fusion technology to reduce the risk of collision with obstacles. By integrating information from different types of sensors, the drone will achieve more accurate and reliable environmental recognition. For example, by combining distance information from an ultrasonic sensor with the precise measurement results of a laser rangefinder, the drone will be able to more precisely recognize obstacles and fly around them safely. The controller can also upload the drone's flight data to the cloud and perform large-scale data analysis based on the data. This can help discover new flight patterns that can improve the drone's flight efficiency and provide insights that can help improve future flight plans. Additionally, cloud-based simulation can be used to test flight drones in virtual environments, allowing them to learn how to respond to various scenarios before flying them in real life. The control device will also be equipped with an interface that allows users to operate intuitively. Using a touchscreen display and gesture recognition technology, users can direct the flight of the drone with simple actions. In addition, by combining virtual reality (VR) and augmented reality (AR) technologies, users can have a more intuitive experience in monitoring and controlling the flight of the drone. Furthermore, the drone will be equipped with a predictive maintenance function based on machine learning, which will identify the risk of aircraft failure in advance and perform preventative maintenance, thereby increasing the drone's uptime and contributing to maintaining its reliability over the long term. Finally, to expand the range of applications for unmanned aerial vehicles, the development of models with waterproof and dustproof functions that can be used underwater and underground will be considered. This will enable applications in areas where conventional unmanned aerial vehicles have been difficult, such as marine surveys and underground resource exploration.

[0027] The process flow of each embodiment will be described below.

[0028] (Example 1) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program based on the instructions analyzed by the AI. Step 3: The generated operation program is sent to the unmanned aerial vehicle, which then performs operations such as moving and rotating according to the instructions. (Example 2) Step 1: The controller receives a natural language instruction. Step 2: Obtain the drone's location information based on the instructions analyzed by AI. Step 3: Based on the acquired position information, the control device controls the unmanned aerial vehicle. (Example 3) Step 1: The controller receives a natural language instruction. Step 2: Process the drone footage based on instructions analyzed by AI. Step 3: Using the video processing means, the control device analyzes the video of the unmanned aerial vehicle. Step 4: Based on the analyzed video information, the control device controls the unmanned aerial vehicle. (Example 4) Step 1: The controller receives a natural language instruction. Step 2: Based on the instructions analyzed by the AI, measure the distance between the drone and the obstacle. Step 3: Using the distance measurement means, the control device measures the distance between the unmanned aerial vehicle and the obstacle. Step 4: Based on the measured distance information, the control device controls the unmanned aerial vehicle.

[0029] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0030] (Example 1) The embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device has a generation means for receiving instructions in natural language, analyzing them by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine has a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is happy, the flight speed of the unmanned aerial vehicle is increased and the viewpoint of the camera is set to a wide range. The generating means is realized, for example, by the specific processing unit 290 of the data processing device 12. The recognizing means and the reflecting means are realized, for example, by the control unit 46A of the smart device 14. The recognizing means and the reflecting means may also be realized, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The control device includes an analysis means using natural language understanding (NLU) technology, which interprets the instructions given by the user according to their intention. The analysis means tokenizes the user's speech and performs part-of-speech tagging and syntactic analysis. The analysis means also includes a program generation means that functions by combining a tokenization means for tokenizing the contents of the speech, a part-of-speech tagging means for identifying parts of speech, and a syntactic analysis means for analyzing the structure of a sentence, and generates an operation program according to the user's command. Furthermore, the intention recognition means identifies the purpose of the utterance and extracts information for generating an appropriate operation program. The operation program generation means generates specific operation commands such as the flight path, speed, and camera operation of the unmanned aerial vehicle based on the analyzed instructions. The operation program generation means also forms instructions for controlling the flight path, camera operation, etc. of the unmanned aerial vehicle, and sets parameters necessary for the unmanned aerial vehicle to perform its mission. The emotion recognition means includes a function for grasping the emotional state of the user using voice analysis and facial expression analysis techniques. The voice analysis means reads emotions from changes in tone and pitch of the speech. The voice analysis means estimates emotions from the speech. The facial expression analysis means identifies emotions such as happiness and sadness from the facial expressions of the user captured by the camera. The facial expression analysis means identifies emotions based on visual information. These means are trained using machine learning models to recognize emotions with high accuracy. The emotion reflection means adjusts the flight pattern and camera settings of the unmanned aerial vehicle according to the recognized emotion. For example, if the user shows joy, the unmanned aerial vehicle will take a more dynamic flight pattern and widen the viewing angle of the camera to capture a wider range of scenery. The emotion reflection means also changes the behavior of the unmanned aerial vehicle based on the recognized emotion, for example, responding to a user who is feeling joy by increasing the flight speed. The flight control means of the unmanned aerial vehicle understands the control characteristics of each model of the unmanned aerial vehicle and calculates the optimal flight path based on the characteristics. The unmanned aerial vehicle also has a flight control means that understands the characteristics of each aircraft and calculates the optimal flight path. The obstacle avoidance means analyzes the surrounding environment information obtained by the sensor and plans a safe flight path in real time. The unmanned aerial vehicle also has an obstacle avoidance means that detects obstacles and calculates a path to avoid them. This obstacle avoidance means combines a predictive model based on machine learning and sensor fusion technology to flexibly respond to environmental changes. The camera control means automatically performs pan, tilt, and zoom operations of the camera based on the user's instructions and emotional state. This makes it possible to capture images and videos that the user desires. The camera control means also remotely controls the camera of the unmanned aerial vehicle based on the user's instructions to capture the desired video. The overall configuration of the system is modular and can be flexibly customized to suit the type of unmanned aerial vehicle and the operating environment. In addition, the system is designed so that each module has an independent function and can be customized to suit the type of unmanned aerial vehicle and the operating environment, and the cloud-based infrastructure allows centralized management of data and remote updating of control logic. This improves the scalability and adaptability of the system and enables the provision of services according to the needs of users. In addition, the system adopts a cloud-based architecture, and data processing and updating of the control logic of the unmanned aerial vehicle can be performed remotely. This makes it easy to maintain and upgrade the system and enables the latest technology to be introduced quickly. In addition, as a means of collecting data that does not include sensors, there is a method of registering instructions and emotional expressions directly entered by the user into the system, which customizes the operation of the unmanned aerial vehicle and camera control. The control device equipped with the generation AI of the present invention can add context recognition capabilities to better understand user instructions and refine the drone's operating program. This allows the user's instructions to be optimized for specific situations and environments, for example, adjusting the drone's flight pattern based on outdoor weather conditions and ambient noise levels. In addition, real-time environmental recognition using sensor data allows the drone to automatically adapt to weather changes and generate operating programs that maintain safe flight. As for the emotion engine, the integration of biosensors that analyze the user's physiological signals makes it possible to read the user's emotional state more accurately from heart rate, skin activity, etc. This allows the drone to fly calmly and adjust the camera to capture a tranquil landscape if the user is feeling stressed. In addition, the drone can provide entertainment functions such as playing music in response to changes in the user's emotions. A group flight function will be added to the unmanned aerial vehicle, allowing multiple unmanned aerial vehicles to cooperate with each other to realize complex flight patterns and shooting. With this function, for example, one unmanned aerial vehicle will be able to track a subject while other unmanned aerial vehicles will take auxiliary images from different angles, generating images from multiple angles. By incorporating augmented reality (AR) and virtual reality (VR) technologies into the camera control means, it is possible to overlay digital information on the captured image in real time, providing the user with an immersive visual experience. For example, map information and annotations can be added to images captured by unmanned aerial vehicles, and used as tourist guides or educational content. The controller also allows users to add trigger functions that allow the drone to preprogram its behavior and execute automatically when certain events or conditions are met, allowing users to set up scenarios where a certain flight pattern is triggered when the user displays a certain emotion, for example. The system as a whole is designed to allow each module to be easily replaced or upgraded, and a mechanism is provided to reflect user feedback in the system. This allows the system to continue to evolve in response to user usage and requests, and continue to provide value over the long term. In addition, in the event of a breakdown or damage to the unmanned aerial vehicle, the self-diagnosis function can identify the problem and notify the user or maintenance personnel. In this way, the present invention provides a user-centered interactive experience using an unmanned aerial vehicle, and is expected to be used in a variety of application fields. The control unit can be equipped with the ability to have the drone generate specific lighting effects in response to the user's emotions. For example, when the user is excited, the drone could create an aerial light show using brightly colored LED lights. The drone could also emit scents tailored to the situation as it flies around the user, providing a multi-sensory experience. To improve the accuracy of user emotion recognition, the emotion engine will build an emotion prediction model by analyzing data from social media posts and daily behavior patterns, allowing the drone to predict changes in user emotions in advance and respond in a more timely manner. The drone's flight control means will be equipped with a function to analyze environmental sounds to grasp the surrounding situation, automatically adjusting the flight altitude in noisy areas to reduce the impact of noise, and a function to recognize the brightness of the surroundings and provide appropriate lighting during night flights. The camera control means will be equipped with a function to apply effects and filters to the captured images in real time, helping to create beautiful images, and will also add a function to automatically post the images captured by the drone to the user's social media accounts. The system as a whole takes user privacy into consideration, setting up a privacy policy for the collection and use of emotion and behavioral data, allowing users to easily control it. In addition, communication between drones is encrypted to strengthen security, ensuring thorough protection of user data. The drones will be able to send SOS signals and contact nearby rescue agencies so that users can respond quickly in emergencies, and they will also be able to pinpoint the location of survivors and provide information to rescue teams during search and rescue operations after disasters. With these functions, the unmanned aircraft system of the present invention is expected to enrich users' lives by providing convenience and safety in a wide range of situations, such as entertainment, daily companion, and emergency assistance. (Example 2) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device includes a generation means for receiving instructions in natural language, analyzing the instructions by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine includes a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is angry, the flight speed of the unmanned aerial vehicle is reduced and the viewpoint of the camera is stabilized. The generating means is realized, for example, by the specific processing unit 290 of the data processing device 12. The recognizing means and the reflecting means are realized, for example, by the control unit 46A of the smart device 14. The recognizing means and the reflecting means may also be realized, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The generating means mounted on the control device includes a receiving means for receiving instructions in natural language from the user, and the receiving means extracts text information from the user's speech using voice recognition technology. The received text information has an analyzing means for analyzing the natural language information using natural language processing technology and understanding the intention and content of the instruction. Based on the analysis result, the AI ​​has a generating means for generating an operation program for the unmanned aerial vehicle, and the generating means incorporates a machine learning algorithm and a rule-based algorithm. In addition, the generating AI incorporated in the control device has a voice recognition means for converting a command in natural language issued by the user into text, and the voice recognition means utilizes a voice analysis algorithm for converting the user's speech into text data. The textual instructions are then examined by the intention analysis means and processed by an AI algorithm for generating an operation program for the unmanned aerial vehicle. The AI ​​algorithm has a conditional branching function and a parameter adjustment function, and determines the flight path and behavior pattern of the unmanned aerial vehicle based on the user's instructions. The emotion recognition means includes sensors and cameras for analyzing the user's tone of voice, facial expressions, body language, etc., and uses data obtained from these to determine the user's emotional state. This determination is made through a means for estimating emotions from the pitch, strength, and speed of voice using voice analysis technology, and a means for reading emotions from the user's facial expressions using face recognition technology. The emotion engine includes a composite sensing means for identifying the user's emotional state, which integrates and processes information from the voice sensor and the visual sensor. The voice sensor estimates emotions from the user's tone of voice and speech rhythm using an emotion analysis algorithm. The visual sensor detects changes in facial expressions using face recognition technology to analyze the emotional state. The emotion data obtained by these sensors is processed by an emotion reflection algorithm to affect the operation of the unmanned aerial vehicle. The operation program of the unmanned aerial vehicle includes, for example, a navigation route calculation means for making a flight plan and a sensor data processing means for avoiding obstacles. The navigation route calculation means calculates the optimal flight route using GPS data and map information. The flight program of the unmanned aerial vehicle also includes a navigation route calculation means, which plans a flight route by referring to geographic information system (GIS) data and weather information. The sensor data processing means processes information obtained from a lidar or ultrasonic sensor, and instructs the unmanned aerial vehicle to detect and avoid obstacles in the vicinity. In addition, as an obstacle avoidance means, data from a sensor array mounted on the unmanned aerial vehicle is analyzed to grasp the surrounding environment and avoid the risk of collision. The communication means is responsible for transferring data and sending commands between the control device and the unmanned aerial vehicle, enabling real-time flight control. In addition, the unmanned aerial vehicle constantly exchanges data with the control device via the communication means during flight, and adjusts its operation according to the situation in real time. The system also has a user interface that is intuitively designed to allow users to easily control the drone, and some systems incorporate touch screen input means and gesture recognition means to enhance operability. Sensor-free data collection includes interactive input that is operated directly by the user, allowing the user to manually communicate emotion and behavior preferences to the system. Another example of sensor-free data collection is data based on emotional states and situations manually input by the user. In this case, the user directly specifies their emotions and desired drone behavior through an application or web interface. The drone then executes a program that operates based on the user's manual input. The implementation of each means utilizes hardware components such as a microprocessor, memory, and communication interfaces, which support the efficient operation of the entire system. The system of the present invention can be enhanced with additional capabilities to operate the drone based on the user's emotions and intent. For example, a generative AI built into the controller can learn from the user's past commands and reaction patterns to generate more personalized responses and behavioral programs. This learning capability allows the system to predict the user's behavior and preferences and automatically adjust the drone's behavior accordingly. Additionally, drones can be equipped with acoustic sensing capabilities to identify environmental sounds and use that information to estimate the user's emotional state, allowing the system to analyze surrounding noise, music, animal sounds, etc. to get a more detailed picture of the atmosphere in the user's environment. The emotion engine can also be integrated with wearable devices to track the user's bio-signals, collecting vital information such as heart rate, electrodermal activity, and body temperature, and incorporating this data into emotion estimation to more accurately identify the user's emotional state. The flight program of the drone can also incorporate an automatic return function in case of an emergency and an evasive maneuver function to ensure the safety of the user, allowing the drone to autonomously take safe action in the face of unexpected obstacles or changing weather conditions. Furthermore, facial expression recognition and gesture analysis functions can be added to the drone to realize interactive communication with the user, allowing the drone to recognize the gestures and facial expressions made by the user toward the drone and take action accordingly. The communication method uses a low-latency, high-bandwidth communication protocol, which allows faster and more stable data transfer between the control device and the unmanned aerial vehicle. This advanced communication technology enables the system to exchange information in real time, enabling precise flight control without delays. With the addition of such functions, the system of the present invention can better understand the user's emotions and intentions and provide more advanced and flexible services using unmanned aerial vehicles. User-system interactions can bring a more intuitive and richer experience, helping users complete their desired tasks more efficiently and safely. The generative AI installed in the control device can be equipped with a predictive function to improve the response speed to user instructions. This function analyzes the user's instruction patterns and habits to predict the next command that will be issued, allowing the drone to respond immediately. By anticipating the user's intentions and initiating actions, the drone can reduce reaction time and achieve more fluid operation. The flight program of the drones can also incorporate swarm intelligence capabilities that allow multiple drones to work together in a coordinated manner, allowing them to form a swarm to efficiently cover an area and share complex tasks based on user instructions. As for the emotion engine, a function can be added to control the lighting and sounds of the drone according to the user's emotions. For example, when the user is relaxing, the drone can play soft lighting and calming music to make the surrounding atmosphere more pleasant. Additionally, drones can be equipped with a projection mapping function to visually communicate user instructions, allowing the drone to project information onto the ground or walls, providing intuitive feedback to the user. The communications means can also be enhanced with the ability to link with a global communications network using satellite communications, allowing the drone to receive commands from a control device anywhere on Earth and handle a wide range of tasks. The drone's sensor array will be equipped with an environmental monitoring function, capable of measuring air pollution and greenhouse gas concentrations and transmitting the data to a control system in real time, making the system part of an environmental monitoring system. These additional features allow the system of the present invention to more intelligently control the drone in a way that reflects the user's emotions and intentions, and adapts to a wide variety of application scenarios, providing the user with a more comfortable and satisfying experience and greatly improving the usability of the system. (Example 3) The embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device includes a generation means for receiving instructions in natural language, analyzing the instructions by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine includes a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is surprised, the flight route of the unmanned aerial vehicle is changed, or the viewpoint of the camera is directed to a specific target. The generating means is realized, for example, by the specific processing unit 290 of the data processing device 12. The recognizing means and the reflecting means are realized, for example, by the control unit 46A of the smart device 14. The recognizing means and the reflecting means may also be realized, for example, by the specific processing unit 290 of the data processing device 12. The correspondence between each means and the device or control unit is not limited to the above example, and various changes are possible. The generating means includes an analyzing means for analyzing instructions from a user using natural language processing (NLP) technology, and a program generating means for creating an operation program for the unmanned aerial vehicle based on the analyzed instructions. The generating means also has a function for analyzing the natural language instructions of the user and generating an operation program for the unmanned aerial vehicle. The generating means is integrated as a modularized software component in a data processing device or a smart device, and is also provided as a cloud-based service as necessary. The analyzing means converts the user's utterance into text using a voice recognition technology, and grasps the purpose and content of the instruction using an intention analysis function. The analyzing means also converts the user's voice instructions into text, and utilizes a voice recognition technology and an intention analysis function to understand the content. The program generating means automatically generates an operation program such as a flight path, speed, altitude, and camera operation of the unmanned aerial vehicle according to the analyzed user's instructions. The program generating means also automatically creates a specific operation program such as a flight path and camera operation of the unmanned aerial vehicle based on the analyzed instruction content. In this process, an algorithm that takes into account flight safety regulations and physical constraints is used so that the unmanned aerial vehicle is operated safely. In addition, the generation process applies algorithms that comply with flight safety regulations and take physical constraints into account to ensure the safe operation of the unmanned aerial vehicle. The recognition means includes an emotion analysis function that estimates emotions from the user's facial expressions, tone of voice, choice of words, etc. The emotion engine also includes a recognition means for capturing the user's emotions in real time. This function estimates the user's emotional state in real time using an emotion recognition model trained by machine learning. The emotion recognition model is trained to analyze a large amount of facial expression images and voice data and identify specific emotion patterns. The recognition means includes an emotion analysis function that estimates emotions from the user's facial expressions, tone of voice, choice of words, etc., and instantaneously estimates the user's emotional state using an emotion recognition model based on machine learning. The model is trained to identify various emotion patterns by analyzing a large amount of facial expression images and voice data. The reflecting means includes an operation change function that changes the operation of the unmanned aerial vehicle according to the recognized user's emotion. For example, when the user shows an emotion of surprise, the flight path of the unmanned aerial vehicle is immediately changed to respond according to the emotion, such as pointing the camera at an object of the user's interest. This function is for adjusting the operation program of the unmanned aerial vehicle in real time to improve the user's experience. In addition, when the user's emotion is recognized, the reflecting means reflects the emotion in the operation of the unmanned aerial vehicle. The operation change function responds according to the emotion, such as changing the flight path of the unmanned aerial vehicle or adjusting the viewpoint of the camera, according to the user's emotion. This function improves the user's experience and makes the operation of the unmanned aerial vehicle more dynamic and attractive. In addition, the input emotion data is reflected in the operation program of the unmanned aerial vehicle by the reflecting means. In this case, sensor technology is not required for emotion recognition, and the system operates based on user-driven information provision. In addition, when the user provides information by directly inputting his / her own emotional state, this does not require emotion recognition by a sensor, but is performed by manual input through an interface. The input emotion data is provided to the system at the user's initiative and reflected in the unmanned aerial vehicle's operating program, enabling it to be operated in accordance with the user's intentions. Further functional expansion is possible for the system of this embodiment. A function for dynamically controlling a swarm of unmanned aerial vehicles and realizing a complex aerial show can be added. This is expected to be used in events and entertainment fields. The emotion engine also has a function for measuring the user's stress level and providing specific flight patterns and images to promote relaxation. Music and images for the user to relax are played simultaneously, providing a whole-body relaxation experience based on emotions. Furthermore, the control device can also incorporate a prediction means that predicts user behavior and environmental changes and anticipates the behavior of the unmanned aerial vehicle. The prediction means utilizes past flight data and information from environmental sensors to optimize future flight patterns. This allows the unmanned aerial vehicle to automatically change its flight route according to the situation, achieving efficient flight. In addition, by having a function to automatically adjust the flight route according to environmental changes, it can quickly respond to sudden weather changes and the appearance of obstacles. To strengthen security, encryption technology will be used for the means of communication between the control device and the unmanned aerial vehicle. This will prevent unauthorized access from outside and ensure secure communication. As for the emotion engine, the user's emotion data will be anonymized and data processing will be performed with an emphasis on privacy protection. The anonymized emotion data can be used for research purposes and to develop more advanced emotion recognition models. The drone will be equipped with a sensor that maps the surrounding environment in 3D, enhancing its real-time environmental awareness. The 3D mapping data will be sent to the control device and used as information for flight safety. This data will also contribute to rescue operations in emergencies and understanding of the situation during disasters. The generator evolves the drone's motion program by learning from user feedback. This learning function improves the drone's performance and enables more sophisticated operation. The feedback-based learning function enables customization to suit the user's preferences and needs. Finally, the system provides a more intuitive and user-friendly operation experience by improving the user interface. The interface is automatically optimized based on the user's operation history and preferences, and provides a guide to simplify the operation of the drone. This makes drones more comfortable for users of all ages. Systems using unmanned aerial vehicles can be equipped with features to further enhance the capabilities of the emotion engine. For example, sensors that measure the user's biosignals in real time can be incorporated to more accurately grasp changes in emotions from heart rate and electrical resistance of the skin. In addition, the accuracy of user emotion recognition can be improved by having the unmanned aerial vehicle's camera capture the user's facial expressions and having the emotion engine analyze the video data. Regarding the generation means of the control device, a multitasking function can be added that processes instructions from multiple users simultaneously and assigns appropriate operation programs to each unmanned aerial vehicle. This makes it possible to operate the unmanned aerial vehicle according to each user's request, even if multiple users have different requests at one event. In addition, it is possible to implement an environmental adaptation function that uses data from sensors possessed by the unmanned aerial vehicle to detect changes in the environment and automatically adjust the flight program. This allows the unmanned aerial vehicle to take appropriate actions more autonomously, for example, to avoid people at a crowded event or to select the optimal angle to photograph a particular landscape. Regarding communication, it is possible to build a network where drones can share information with each other, enabling them to move intelligently as a swarm. Drones can grasp each other's positions and status in real time, and cooperate to efficiently carry out multiple tasks. In addition, by flexibly changing the formation formed by drones according to user instructions, new applications such as visual art and advertising are expected. The emotion engine can also be equipped with an automatic music and lighting adjustment function according to the user's emotions. It can enhance the emotion-based experience via the drone by providing bright and active music and lighting when the user is feeling joyful, and calm music and lighting when the user is feeling calm. In addition, the drone can add a health monitoring function to support the user's health and wellness, providing regular health checks and relaxation activities. With these expansions, systems using unmanned aerial vehicles are expected to be used in a wide range of fields, not only for entertainment, but also for health management, improving personal wellness, emergency response, etc. In addition, improvements to the user interface will enable more people to intuitively operate unmanned aerial vehicles, and their convenience will be widely recognized.

[0031] The process flow of each embodiment will be described below.

[0032] (Example 1) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone will move, rotate, and perform other operations according to instructions. (Example 2) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program for the unmanned aircraft based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone will move, rotate, and perform other operations according to instructions. (Example 3) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program for the unmanned aircraft based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone performs operations such as moving and rotating according to the instructions. For example, if the user is happy, the drone will move more aggressively. Conversely, if the user is angry, the drone will move more cautiously.

[0033] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0034] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58.

[0035] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0036] [Second embodiment]

[0037] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0038] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0039] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0040] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0041] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0042] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0044] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0045] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0046] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0047] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0048] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0049] (Example 1) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a communication means. The control device is equipped with a generation means that receives instructions in natural language, analyzes the instructions by the AI, and then generates an operation program for the unmanned aerial vehicle. The unmanned aerial vehicle performs operations such as movement and rotation according to the instructions based on the generated operation program. The communication means is a means for transmitting and receiving instructions and data between the control device and the unmanned aerial vehicle. The generation means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and then generates an operation program for the unmanned aerial vehicle. The communication means is a means for transmitting and receiving instructions and data between the data processing device 12 and the unmanned aerial vehicle, and is realized by the communication I / F 26 of the data processing device 12. The unmanned aerial vehicle includes a control unit for performing operations such as movement and rotation according to instructions based on the generated operation program. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The generation means utilizes natural language processing technology to analyze instructions from a user and generate an operation program for the unmanned aerial vehicle. The generation means can also convert human oral or text input instructions into digital data using a voice recognition means and a text analysis means and interpret the contents of the digital data. This means includes a voice recognition function and converts the user's oral instructions into text data. The voice recognition means has a function of receiving the user's voice instructions and converting the voice data into text. The text analysis means performs morphological analysis and syntactic analysis to understand the contents of the instructions and grasp the intention. The text analysis means also performs morphological analysis and syntactic analysis to understand the meaning of the input text. The intention analysis means identifies the purpose or task behind the instructions, and the operation program generation means generates a specific operation program based on the analyzed intention. The intention analysis means can also identify specific tasks or purposes from instructions included in the text, and the operation program generation means can create an operation program based on the specified tasks or purposes. The operation program generation means utilizes a probabilistic algorithm or a machine learning model to develop an efficient and safe operation plan for the unmanned aerial vehicle. The operation program generating means can also define an operation sequence to be performed by the unmanned aerial vehicle and calculate the parameters required for that. The unmanned aerial vehicle automatically executes operations based on the generated operating program through the flight control means installed on the vehicle. The unmanned aerial vehicle also has a built-in flight control means, and can autonomously perform operations such as flying and rotating according to the generated operating program. The flight control means controls the attitude and position of the unmanned aerial vehicle in real time based on data from sensors and position information from GPS. The flight control means also functions by combining an attitude control function, a position control function, and a speed control function, which can also adjust the flight state of the unmanned aerial vehicle based on sensor data and GPS information. The obstacle detection means recognizes the surrounding environment, and the collision avoidance means calculates a route to avoid the obstacle. The obstacle detection means also detects surrounding obstacles using sensors such as radar and LiDAR, and the collision avoidance means can calculate an alternative route to avoid the detected obstacle, allowing the vehicle to fly safely. The communication means enables data transmission and reception between the control device and the unmanned aerial vehicle using wireless communication technology. The communication means can also transmit and receive data between the control device and the unmanned aerial vehicle using advanced wireless communication technology. The means include an encoding means for encoding and decoding signals and an error correction means for maintaining the reliability of communication. The encoding means efficiently encodes the data to be transmitted and decodes it at the receiving end to recover the meaning of the data. The error correction means detects and corrects data errors that may occur in the communication process to maintain the reliability of communication. The communication means employs a communication protocol with low latency and high bandwidth to quickly transmit and receive data on the operation program and operation status. The communication protocol can also be optimized to achieve low latency and high bandwidth and transmit the flight status, sensor data, and video feed of the unmanned aerial vehicle in real time. The control device can always grasp the status of the unmanned aerial vehicle and issue additional instructions as necessary. The unmanned aerial vehicle also transmits sensor data and video feeds during flight to the control device in real time for monitoring and analysis. The unmanned aerial vehicle can also transmit data during flight to a control device via communication means, allowing real-time monitoring by an operator and collection of data for later analysis. A variety of additional functions can be incorporated into control systems that utilize unmanned aerial vehicles. For example, an environmental monitoring function can be added to an unmanned aerial vehicle to precisely measure temperature, humidity, and atmospheric pressure from the air and collect meteorological data. In addition, in agricultural applications, it is effective to equip the vehicle with sensors that measure soil moisture and nutritional status to provide functions that support precision agriculture. Unmanned aerial vehicles can also be equipped with functions to support rescue operations. For example, in the event of a disaster, they can grasp the extent of damage to buildings and the locations of victims, and provide information to rescue teams. They can also be equipped with thermal cameras to detect smoke and fire conditions, which can be useful in directing and supporting firefighting operations. Furthermore, to improve their autonomous flight capabilities, swarm functions can be developed that use AI to allow unmanned aerial vehicles to share information with each other and cooperate as a swarm, making it possible to monitor a wider area and carry out multiple tasks simultaneously. In terms of communication, we will consider alternative means of communication such as satellite communication and laser communication to improve communication stability. This will enable us to maintain communication with unmanned aircraft even in remote areas or disaster areas where communication infrastructure has been destroyed. Furthermore, to operate unmanned aircraft more safely and efficiently, we will introduce a system that combines ground radar systems and communications with other aircraft to accurately grasp the position and status of unmanned aircraft in flight and assist in collision avoidance. Surveillance systems using unmanned aerial vehicles can incorporate advances in video analytics technology to identify objects and people from video in real time and analyze behavioral patterns. This will automate security and surveillance tasks, contributing to crime prevention and safety management. In addition, footage captured by unmanned aerial vehicles can be used for virtual reality and augmented reality to provide new experiences in education, training, tourism, and more. Finally, the control device will be equipped with a self-learning function to train machine learning models that utilize the drone's operational logs and sensor data to improve the drone's flight performance, allowing the drone to learn from past experience, select more effective flight routes, and perform tasks more efficiently. It is conceivable that generative AI installed in the control device can be used to automate tasks in other industrial fields. For example, agricultural tasks such as spraying pesticides and sowing seeds can be automated to reduce manual labor. Ultrasonic sensors and near-infrared cameras can be installed in the drones to help with crop growth and early detection of disease. In addition, a precision pesticide spraying system using drones can be developed to optimize the amount of pesticide used and reduce environmental impact. The AI ​​that generates the control device can be applied not only to unmanned aerial vehicles, but also to underwater robots and autonomous vehicles on land. By combining these different platforms, a monitoring network covering land, sea and air can be constructed, which is expected to be used in a wide range of fields such as environmental monitoring, resource exploration, and disaster response. In environmental monitoring using unmanned aerial vehicles, it is also effective to mount a composite gas sensor to monitor air pollution and measure greenhouse gases. In addition to disaster relief, the combination of the control device and unmanned aerial vehicles can also be used for rescue and search operations. Combining high-performance cameras with face recognition technology will help with searches for missing people and early detection of people in distress during coastal surveillance. A system will also be developed that will equip unmanned aerial vehicles with lifesaving kits and quickly drop rescue supplies to people in distress. The strengthening of communication methods will enable use in remote medical care, where real-time data is important, and emergency communications during disasters. By achieving high-resolution video transmission and low-latency communications, it will play a role as infrastructure for doctors to supervise surgery from remote locations and for establishing emergency communications from disaster sites. We will further evolve the AI ​​of the control device and develop algorithms that allow swarms of unmanned aerial vehicles to work together to carry out complex tasks. This will enable multiple unmanned aerial vehicles to share a large task and complete it efficiently. For example, this can be applied to transporting materials at construction sites and extinguishing fires. Ultimately, the combination of control device AI and unmanned aerial vehicles will contribute to the creation of smart cities, such as managing urban infrastructure, monitoring traffic flow, and ensuring public safety. Using real-time data provided by unmanned aerial vehicles, a system will be built to optimize city operations and respond quickly to disasters. Information collected by unmanned aerial vehicles will also be useful in formulating urban plans and transportation policies. This will support the development of sustainable and efficient cities. (Example 2) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a location information acquisition means. The control device receives instructions in natural language, analyzes the instructions using the AI, and then acquires location information of the unmanned aerial vehicles. The location information acquisition means is a means for identifying the location of the unmanned aerial vehicles using a GPS, a sensor, or the like. The control device includes a control means for controlling the unmanned aerial vehicles according to the instructions based on the acquired location information. The location information acquisition means is realized by a GPS or a sensor mounted on the unmanned aerial vehicle. The control means is realized by a specific processing unit 290 of the data processing device 12, and controls the unmanned aerial vehicle according to instructions based on the acquired location information. The unmanned aerial vehicle includes a control unit for operating based on instructions from the control device. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The control device uses an analysis means including a natural language understanding module to analyze instructions from the user and grasp the intention. The control device also includes an instruction receiving means for receiving natural language instructions from the user and a natural language understanding module for analyzing the instructions. The natural language understanding module includes a voice-to-text conversion means for converting voice instructions into text data using voice recognition technology. The voice-to-text conversion function can convert the user's instructions into text information using a voice recognition algorithm. The voice-to-text conversion function includes language processing means such as tokenization, part-of-speech tagging, noun phrase analysis, verb phrase analysis, and dependency analysis for further analyzing the converted text data. The language processing function can also clearly grasp the intention of the instructions using a tokenization means, part-of-speech tagging means, syntactic analysis means, etc. This allows commands, parameters, conditions, etc. included in the user's instructions to be accurately identified. The analyzed instructions are interpreted by the generation AI as commands necessary for controlling the unmanned aerial vehicle and transmitted to the control unit of the unmanned aerial vehicle via a command generation means for generating a corresponding action command. This allows the user's intention to be interpreted as a command and generates an action command to be transmitted to the unmanned aerial vehicle. The location information acquisition means includes a composite location information processing means for tracking the exact location of the unmanned aerial vehicle. The location information acquisition means also includes a GPS module mounted on the unmanned aerial vehicle, which can acquire location information on the earth. This GPS module acquires latitude, longitude, and altitude information of any point on the earth. Furthermore, a GNSS analysis means for analyzing a GNSS (Global Navigation Satellite System) signal can provide higher accuracy and reliability of location information. The GNSS analysis means used in conjunction with this can also improve the accuracy of the position using signals from satellites. Meanwhile, an inertial measurement unit (IMU) such as an integrated acceleration sensor and gyroscope continuously tracks the attitude and movement of the unmanned aerial vehicle, and assists in acquiring stable location information even in an environment where the GPS signal is unstable. In addition, an IMU for detecting the movement of the unmanned aerial vehicle provides information based on inertia, and can maintain the accuracy of the location information even in a situation where the GPS signal is unstable. As an example that does not include a sensor, a communication-based location information acquisition means is considered, in which the unmanned aerial vehicle acquires its own location information by communicating with a beacon or a ground station. Another example of sensor-free location acquisition is a communication-based location acquisition method. In this method, the relative and absolute position is determined through signals transmitted from ground beacons and through communication with other unmanned aircraft. The beacon transmits radio waves of a specific frequency, which is received by a receiving module on the unmanned aircraft and serves as a reference point for calculating the location information. The unmanned aircraft can also calculate its own position based on the received signal. In such a system, the current position of the unmanned aircraft and adjustments to the flight path are exchanged in real time through communication with a ground station. The control means includes a flight path planning means for planning and adjusting the flight path of the unmanned aerial vehicle. The control means also includes a flight path planning function for planning and adjusting the flight path of the unmanned aerial vehicle. This incorporates a simulation means for simulating the operation of the unmanned aerial vehicle and calculating an optimal flight path, taking into account obstacles and safety constraints on the flight path. This function can also simulate the flight path using the simulation means and calculate the optimal path, taking into account obstacle avoidance means and safety constraints. Furthermore, it also includes an emergency avoidance means for quickly responding to an emergency that the unmanned aerial vehicle may encounter, and a group control means for cooperatively controlling multiple unmanned aerial vehicles. It also includes an emergency avoidance function for responding to an emergency, and a group control function for centrally controlling multiple unmanned aerial vehicles. The control device of this embodiment can incorporate an advanced obstacle detection system to improve flight capabilities in more complex environments. For example, a function is added that utilizes 3D mapping technology using a laser scanner or ultrasonic sensor to precisely recognize the surrounding environment during flight and quickly and autonomously respond to dynamically changing obstacles. In addition, by analyzing satellite images and geographic information system (GIS) data, it is possible to take into account terrain features and obstacle information in more detail in the flight plan, enabling advanced optimization of the flight path. In controlling a group of unmanned aerial vehicles, a coordinated flight algorithm based on swarm intelligence using AI can be introduced, allowing multiple unmanned aerial vehicles to work together efficiently. For example, when multiple unmanned aerial vehicles are dispersed to perform tasks in pesticide spraying or search and rescue operations, dynamic flight path adjustments are made to maximize the overall work efficiency. This allows unmanned aerial vehicles to share roles and cooperate according to individual situations. The control device's natural language understanding module will be equipped with a specialized dictionary and context analysis function to understand technical terms and industry-specific language used by users, improving its ability to accurately analyze instructions specialized for specific industries and applications and convert them into specific operation commands. In addition, to improve the unmanned aerial vehicle's environmental awareness, a function will be added to analyze social media and internet information in addition to sensor data to grasp people's activity patterns and the occurrence of events. In terms of location information acquisition means, it is possible to introduce a differential GPS (DGPS) system that provides more accurate location information by incorporating a network of ground reference stations that provide correction signals to the GPS module used by the unmanned aircraft. Furthermore, in order to enable operation and monitoring from remote locations, a real-time data link system using satellite communications can be incorporated, allowing the unmanned aircraft to be controlled from anywhere on Earth. By integrating these functions, unmanned aerial vehicles will be able to handle more complex missions and realize flexible and advanced operations tailored to user needs, providing advanced solutions using unmanned aerial vehicles in fields such as disaster relief, environmental monitoring, and security surveillance. The control device can be equipped with a context recognition function to interpret user instructions more precisely, allowing it to take the optimal action depending on different circumstances, even with the same command. It can also have a function to ask questions to the user in response to unclear instructions through dialogue, improving the accuracy of communication and preventing misunderstandings. Furthermore, it can have a multitasking capability to process instructions from multiple users simultaneously, achieving high flexibility in large-scale operations. The location information acquisition method will add a LiDAR sensor that performs 3D scanning of the drone's surroundings in real time, achieving more advanced environmental recognition and accurate positioning. In addition, visual odometry will be used to estimate the drone's movement from images captured by the camera, providing stable location information even in environments where GPS is not available. This will enable activities in places where it is difficult to receive GPS signals, such as between high-rise buildings in urban areas or in dense forests. The control method will employ a self-learning obstacle avoidance algorithm that allows the drone to autonomously avoid obstacles and adjust its flight path. In addition, a cooperative avoidance algorithm will be introduced that allows drones to communicate with each other to share the status of surrounding drones in real time, enabling them to fly efficiently while avoiding collisions. This will enable drones to carry out their missions safely even in situations where multiple drones are flying close together. The AI ​​of the control device can continuously update the environmental model based on the data collected by the unmanned aircraft and perform predictive control based on that environmental model. This allows the unmanned aircraft to realize autonomous flight that can respond not only to the current situation but also to future changes. The unmanned aircraft can also make optimal decisions according to the situation at hand, going beyond pre-set behavior patterns. Finally, the system proposed in this embodiment is applicable to various applications such as advanced monitoring, investigation, and disaster response using unmanned aerial vehicles, and is a next-generation unmanned aerial vehicle control system that combines high autonomy and usability. It is expected that this will promote the effective use of unmanned aerial vehicles in activities in areas where human access is difficult or dangerous, and in emergency missions with time constraints. (Example 3) An embodiment of the present invention is a system including a control device equipped with a generating AI, a plurality of unmanned aerial vehicles, and a video processing means. The control device receives instructions in natural language, which are analyzed by the AI, and then processes the video of the unmanned aerial vehicle. The video processing means is a means for analyzing the video of the unmanned aerial vehicle using a camera or image recognition technology. The control device includes a control means for controlling the unmanned aerial vehicle according to the instructions based on the analyzed video information. The image processing means is realized by a camera mounted on the unmanned aerial vehicle and image recognition technology. The control means is realized by a specific processing unit 290 of the data processing device 12, and controls the unmanned aerial vehicle according to instructions based on the analyzed image information. The unmanned aerial vehicle includes a control unit for operating based on instructions from the control device. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The control device includes an instruction analysis means using a natural language processing model, and has a function of receiving instructions from a user in text or voice format and understanding the intention. The instruction analysis means understands natural language sentences through morphological analysis and syntactic analysis, and accurately understands the intention of the instructions through semantic analysis. The natural language processing model mounted on the control device can receive the user's voice or text instructions and divide the data into basic units of language through a morpheme division function. Next, the syntactic analysis function can clarify the structure of the sentence, and the semantic analysis function can also identify the intention of the instructions according to the context. Based on these analysis results, a language understanding model built by machine learning accurately understands the user's intention and generates a corresponding action. In this process, a language model based on machine learning learns from training data to improve the accuracy of responses to user instructions. The image processing means installed in the unmanned aerial vehicle includes a real-time image analysis function, which instantly processes the image data captured by the unmanned aerial vehicle and identifies specific objects and scenery. This function uses an object detection model and a semantic segmentation model based on deep learning to recognize the type and location of objects and extract the characteristics of the environment captured by the unmanned aerial vehicle. The image processing means installed in the unmanned aerial vehicle can also analyze the image data in real time and identify specific objects in the screen using the object identification function. The object detection model and the semantic segmentation model can also be fused to identify the type and location of objects in the image. Pre-processing of the image data includes noise reduction and contrast adjustment, which contributes to improving the recognition accuracy. Furthermore, the image pre-processing function can perform noise reduction and contrast adjustment to improve the accuracy of the image analysis. The control means includes a flight path calculation function for the unmanned aerial vehicle, which calculates an optimal flight path to the destination based on the analyzed image information, and efficiently guides the unmanned aerial vehicle. This flight path calculation function integrates terrain data and weather information to avoid obstacles and maximize energy efficiency. In addition, as a control means, the unmanned aerial vehicle uses a flight path calculation function to calculate an efficient path to the destination. This function can combine a terrain data integration function and a weather information integration function to ensure flight safety and efficiency. In addition, the flight operation control function of the unmanned aerial vehicle precisely adjusts basic flight operations such as speed, altitude, and attitude control, and performs operations according to user instructions. In addition, the flight operation control function can also appropriately adjust the speed, altitude, and attitude of the unmanned aerial vehicle to realize operations according to user instructions. As part of the image processing means, an environmental monitoring function using an unmanned aerial vehicle is also considered. This uses an environmental change detection model to detect natural disasters and abnormal situations, enabling appropriate responses to the situation. The environmental monitoring function using an unmanned aerial vehicle can also use an environmental change detection model to quickly capture natural disasters and abnormal situations, enabling appropriate responses to the situation. This monitoring function effectively detects environmental changes over a wide area, enabling information collection and rapid response. An example of data collection that does not include sensors is a manual selection means where a user manually selects video data through a camera mounted on the unmanned aerial vehicle and transmits the data to the control device. This manual selection means is useful when a user is interested in a specific video or when video analysis is required under a specific situation. The user selects video data through an interface and transmits it to the control device, where it is analyzed by the video analysis means and handled by the control means. Alternatively, as a manual selection means, a user can select video data captured by the camera of the unmanned aerial vehicle through an interface and transmit it to the control device. This selection process allows video data to be selected based on a specific request from the user, and detailed analysis by the video processing means and appropriate flight control by the control means are performed. The control device can incorporate a reinforcement learning algorithm to learn behavioral patterns according to various situations. This algorithm enhances the adaptability of the unmanned aerial vehicle to respond to different environments and missions. The control device can also be equipped with a multi-agent system to manage the coordinated flight of multiple unmanned aerial vehicles. This allows multiple unmanned aerial vehicles to take action simultaneously and cooperate efficiently toward a single goal. Furthermore, the control device can be equipped with safety functions, including an automatic return function for the unmanned aerial vehicle in an emergency and an automatic obstacle avoidance function. This allows the unmanned aerial vehicle to complete its mission while ensuring its own safety. The image processing means may incorporate infrared cameras and heat sensing technology for high-precision image analysis even at night or in bad weather conditions, allowing the UAV to collect and analyze image data in any environment, day or night. In addition, the image processing means may also enable tracking of moving targets using object tracking algorithms in dynamic scenes. This capability allows the UAV to continuously monitor moving objects and provide critical information. The control means can be equipped with a swarm intelligence function that controls a swarm of unmanned aerial vehicles based on user instructions. This allows a swarm of unmanned aerial vehicles to fly together and perform missions more effectively in complex environments. The control means can also be equipped with a dynamic flight path recalculation function in response to real-time traffic information and weather changes. This allows the unmanned aerial vehicles to quickly respond even when information is updated mid-flight, improving the efficiency of mission execution. As part of the video processing means, a function can be included for uploading the video data collected by the unmanned aerial vehicle to a cloud service in real time for wide-ranging data analysis and sharing. This allows the video data captured by the unmanned aerial vehicle to be shared with a wide range of users for quick decision-making and information sharing. The video processing means can also have a detailed mapping function for the damage situation when a disaster occurs. This allows the unmanned aerial vehicle to get a detailed understanding of the situation immediately after the disaster occurs and provide important information for rescue teams and recovery efforts. As an example of sensor-free data collection, video data acquired by users through drones can be automatically posted to social media and news sites through AI-assisted automated analysis. This allows social events and unusual natural phenomena to be widely publicized, attracting interest and raising awareness. In addition, by including a data anonymization function to protect user privacy, video data collected by drones can be shared safely. The generation AI installed in the control device can be added with a function to analyze the video captured by the unmanned aerial vehicle in real time and identify the damage situation and the location of survivors during a disaster. This will contribute to the speed and efficiency of rescue operations. In addition, 3D mapping technology using the video data from the unmanned aerial vehicle can be integrated to create a three-dimensional map of the disaster area, enabling a more detailed understanding of the situation. The image processing means will incorporate highly sensitive sensors and image enhancement technology that are not affected by day and night or weather changes, allowing the drone to capture clear images even in low-light environments. It will also be able to recognize specific patterns and symbols in the image data, for example, to detect signs requesting help or specific obstacles. The control means has the function of automatically adjusting the formation and timing when the drones fly in a group. This allows multiple drones to cooperate to cover a wide area and efficiently collect data. In addition, the drones can be equipped with an autonomous avoidance function based on environmental recognition to quickly avoid unexpected obstacles they encounter. The video processing means may include the ability to detect motion within the video data and automatically track the camera of the unmanned aerial vehicle accordingly, allowing for uninterrupted monitoring of dynamic scenes or objects that need to be tracked. The control means is equipped with an algorithm that optimizes the energy consumption of the drone, contributing to extending mission time and reducing operating costs. In addition, the drone's flight path can be optimized in real time to flexibly respond to sudden changes in conditions. As an extension of the image processing means, it will be equipped with a function that enables multifaceted analysis of the image data collected by the unmanned aerial vehicle, enabling applications in different fields, such as evaluating the health of crops in the agricultural sector and detecting changes in ecosystems in environmental monitoring. The control device can be equipped with a function to further improve its natural language understanding capability in order to realize interactive communication with users. This will enable users to intuitively operate the unmanned aerial vehicle, enabling a wider range of users to utilize unmanned aerial vehicles. The video processing means can be equipped with a function that allows the insertion of text and annotations into live video in real time to make the content of the video easier to understand. This makes it possible, for example, to instantly provide rescue information to rescue workers and commanders on the scene during a disaster. The control means can be equipped with features to enable the UAS to self-heal and provide periodic maintenance reminders, thereby increasing the availability and reliability of the UAS for long-term, stable operation. These additional functions will dramatically improve the capabilities of unmanned aerial vehicles for surveillance, disaster response, and information gathering, making it possible to create a flexible system that can respond to a variety of situations. (Example 4) An embodiment of the present invention is a system including a control device equipped with a generating AI, a plurality of unmanned aerial vehicles, and a distance measurement means. The control device receives instructions in natural language, analyzes them using the AI, and then measures the distance to the unmanned aerial vehicles. The distance measurement means measures the distance between the unmanned aerial vehicles and obstacles using an ultrasonic sensor, a laser range finder, or the like. The control device includes a control means for controlling the unmanned aerial vehicles according to the instructions based on the measured distance information. The distance measurement means is realized by an ultrasonic sensor or a laser range finder mounted on the unmanned aerial vehicle. The control means is realized by a specific processing unit 290 of the data processing device 12, and controls the unmanned aerial vehicle according to instructions based on the measured distance information. The unmanned aerial vehicle includes a control unit for operating based on instructions from the control device. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The generation AI built into the control device has a function of understanding human instructions using natural language analysis means, and generates commands necessary for operating the unmanned aerial vehicle using this function. In addition, the generation AI mounted on the control device can understand user instructions and generate commands necessary for operating the unmanned aerial vehicle by combining a voice recognition means having a voice-to-text conversion function with a grammar analysis means and a semantic analysis means for interpreting the meaning of a sentence. The generated commands include specific instructions for planning the flight path and the operation of the unmanned aerial vehicle, which are executed by the control algorithm of the unmanned aerial vehicle. In addition, the generated commands include detailed instructions regarding the flight path and operation of the unmanned aerial vehicle, and can be executed by the control algorithm means. The ultrasonic sensor as a distance measuring means is installed on the front or side of the unmanned aerial vehicle and measures the distance by detecting the reflected sound waves from surrounding obstacles. This sensor has an echo cancellation function to adapt to the environment and a filtering function to remove interference waves, and provides accurate distance information. In addition, the ultrasonic sensor can detect the reflected waves from surrounding obstacles using the echolocation function and obtain distance information. This sensor can provide accurate distance information without being affected by environmental noise due to the interference sound wave removal function and echo cancellation function. On the other hand, the laser rangefinder can measure distance with high accuracy and is particularly suitable for measuring long distances and detecting subtle obstacles. The laser rangefinder emits a laser beam to the target and calculates the distance using the time difference of the reflected light. In addition, the laser rangefinder has a function of emitting a laser beam to the target and a function of detecting the reflected light, and can measure the distance by the reflection time difference calculation function. The laser rangefinder enables precise distance measurement and can be particularly suitable for detecting long distances and subtle obstacles. The control means has a function of adjusting the operation of the unmanned aerial vehicle based on information from the distance measurement means, and this function is realized by a flight control algorithm of the unmanned aerial vehicle. The flight control algorithm is designed based on control theories such as PID control and feedforward control, and enables the unmanned aerial vehicle to accurately execute instructed operations while maintaining stable flight. The control means adjusts the attitude and speed of the unmanned aerial vehicle in real time, and optimizes a route to reach the destination while avoiding obstacles. The control means can also have a route control function that uses information provided by the distance measurement means to adjust the attitude and speed of the unmanned aerial vehicle and avoid obstacles. The flight control algorithm means can utilize a PID control function and a feedforward control function to adjust the operation of the unmanned aerial vehicle so that the unmanned aerial vehicle flies stably and accurately according to instructions. An example of distance measurement that does not include a sensor is a positioning means using GPS. A GPS receiver mounted on an unmanned aerial vehicle receives signals transmitted from satellites and calculates the current position of the unmanned aerial vehicle based on the information. The positioning means provides wide-area position information of the environment in which the unmanned aerial vehicle flies, and is used to plan larger-scale flight plans. In addition, in order to grasp the relative positional relationship between unmanned aerial vehicles, multiple unmanned aerial vehicles share their respective GPS information and function as a means for adjusting the flight formation as a whole. Furthermore, the positioning means using GPS can determine the current location of the unmanned aerial vehicle via a GPS receiver equipped with a satellite signal receiving function. The position information calculation function can calculate the position of the unmanned aerial vehicle from the received satellite signals and contribute to the planning of a wide-area flight plan. Furthermore, by sharing position information between unmanned aerial vehicles, it can also function as a flight formation adjustment function, and flight coordination as a whole can be realized. The control device further includes an image processing means for improving the accuracy of obstacle detection. For example, an object recognition algorithm based on machine learning can be used to automatically detect obstacles from the video captured by the unmanned aerial vehicle and recognize their size and shape. This allows the unmanned aerial vehicle to fly safely in more complex environments. The control device also has the ability to analyze the video data captured by the unmanned aerial vehicle in real time and adjust the flight path according to dynamic environmental changes. Furthermore, the control device is equipped with a communication control means for adjusting communication between unmanned aerial vehicles, enabling multiple unmanned aerial vehicles to share information and fly cooperatively. The communication control means has a function of optimizing cooperative operations during formation flight and specific mission execution. The AI ​​of the control device has a self-learning function that learns from the actual flight environment, and automatically generates the optimal flight path when it encounters new obstacles or unknown situations. The AI ​​accumulates the drone's experience and improves the flight pattern by referring to past data. This learning process allows the drone to better adapt to the environment and perform its missions more effectively. The control device also has a collision avoidance algorithm when multiple drones are operating at the same time, realizing safe and efficient swarm movements. Distance measurement sensors will be supplemented with infrared sensors and thermal imaging cameras for accurate distance measurements even at night and in bad weather. These will compensate for the limitations of conventional ultrasonic sensors and laser range finders, allowing the drone to operate in more challenging environments. These sensors will also provide additional information to detect obstacle types and temperature distributions and select flight paths accordingly. The control vehicle will incorporate an advanced collision avoidance system that combines real-time environmental awareness and predictive modeling to enable the unmanned aerial vehicle to respond quickly and effectively to unexpected obstacles. The collision avoidance system will allow the unmanned aerial vehicle to automatically change its flight path to ensure safe and continuous mission completion. In addition, the control vehicle will also be capable of optimizing the unmanned aerial vehicle's energy management to extend flight time and improve mission efficiency. The generative AI installed in the control device has the ability to simultaneously monitor multiple unmanned aerial vehicles and coordinate the operation of each aircraft, enabling them to operate in a swarm-like coordinated manner. The unmanned aerial vehicles share information with each other and are aware of the surrounding environment and the positions of other aircraft, allowing them to carry out their missions efficiently and safely. This coordinated operation is particularly effective in environments with complex terrain and many obstacles, and can be applied to search and rescue operations and situational awareness during disasters. In addition, the drone's distance measurement means will use a new sensor fusion technology to reduce the risk of collision with obstacles. By integrating information from different types of sensors, the drone will achieve more accurate and reliable environmental recognition. For example, by combining distance information from an ultrasonic sensor with the precise measurement results of a laser rangefinder, the drone will be able to more precisely recognize obstacles and fly around them safely. The controller can also upload the drone's flight data to the cloud and perform large-scale data analysis based on the data. This can help discover new flight patterns that can improve the drone's flight efficiency and provide insights that can help improve future flight plans. Additionally, cloud-based simulation can be used to test flight drones in virtual environments, allowing them to learn how to respond to various scenarios before flying them in real life. The control device will also be equipped with an interface that allows users to operate intuitively. Using a touchscreen display and gesture recognition technology, users can direct the flight of the drone with simple actions. In addition, by combining virtual reality (VR) and augmented reality (AR) technologies, users can have a more intuitive experience in monitoring and controlling the flight of the drone. Furthermore, the drone will be equipped with a predictive maintenance function based on machine learning, which will identify the risk of aircraft failure in advance and perform preventative maintenance, thereby increasing the drone's uptime and contributing to maintaining its reliability over the long term. Finally, to expand the range of applications for unmanned aerial vehicles, the development of models with waterproof and dustproof functions that can be used underwater and underground will be considered. This will enable applications in areas where conventional unmanned aerial vehicles have been difficult, such as marine surveys and underground resource exploration.

[0050] The process flow of each embodiment will be described below.

[0051] (Example 1) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program based on the instructions analyzed by the AI. Step 3: The generated operation program is sent to the unmanned aerial vehicle, which then performs operations such as moving and rotating according to the instructions. (Example 2) Step 1: The controller receives a natural language instruction. Step 2: Obtain the drone's location information based on the instructions analyzed by AI. Step 3: Based on the acquired position information, the control device controls the unmanned aerial vehicle. (Example 3) Step 1: The controller receives a natural language instruction. Step 2: Process the drone footage based on instructions analyzed by AI. Step 3: Using the video processing means, the control device analyzes the video of the unmanned aerial vehicle. Step 4: Based on the analyzed video information, the control device controls the unmanned aerial vehicle. (Example 4) Step 1: The controller receives a natural language instruction. Step 2: Based on the instructions analyzed by the AI, measure the distance between the drone and the obstacle. Step 3: Using the distance measurement means, the control device measures the distance between the unmanned aerial vehicle and the obstacle. Step 4: Based on the measured distance information, the control device controls the unmanned aerial vehicle.

[0052] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0053] (Example 1) The embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device has a generation means for receiving instructions in natural language, analyzing them by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine has a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is happy, the flight speed of the unmanned aerial vehicle is increased and the viewpoint of the camera is set to a wide range. The generating means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and generates an operation program for the unmanned aerial vehicle. The recognizing means includes an emotion engine and is realized by a device different from the data processing device 12. The reflecting means is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the operation of the unmanned aerial vehicle based on the result of recognizing the user's emotion. For example, when the user is happy, the flight speed of the unmanned aerial vehicle is increased, or the viewpoint of the camera is set to a wide range. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The control device includes an analysis means using natural language understanding (NLU) technology, which interprets the instructions given by the user according to their intention. The analysis means tokenizes the user's speech and performs part-of-speech tagging and syntactic analysis. The analysis means also includes a program generation means that functions by combining a tokenization means for tokenizing the contents of the speech, a part-of-speech tagging means for identifying parts of speech, and a syntactic analysis means for analyzing the structure of a sentence, and generates an operation program according to the user's command. Furthermore, the intention recognition means identifies the purpose of the utterance and extracts information for generating an appropriate operation program. The operation program generation means generates specific operation commands such as the flight path, speed, and camera operation of the unmanned aerial vehicle based on the analyzed instructions. The operation program generation means also forms instructions for controlling the flight path, camera operation, etc. of the unmanned aerial vehicle, and sets parameters necessary for the unmanned aerial vehicle to perform its mission. The emotion recognition means includes a function for grasping the emotional state of the user using voice analysis and facial expression analysis techniques. The voice analysis means reads emotions from changes in tone and pitch of the speech. The voice analysis means estimates emotions from the speech. The facial expression analysis means identifies emotions such as happiness and sadness from the facial expressions of the user captured by the camera. The facial expression analysis means identifies emotions based on visual information. These means are trained using machine learning models to recognize emotions with high accuracy. The emotion reflection means adjusts the flight pattern and camera settings of the unmanned aerial vehicle according to the recognized emotion. For example, if the user shows joy, the unmanned aerial vehicle will take a more dynamic flight pattern and widen the viewing angle of the camera to capture a wider range of scenery. The emotion reflection means also changes the behavior of the unmanned aerial vehicle based on the recognized emotion, for example, responding to a user who is feeling joy by increasing the flight speed. The flight control means of the unmanned aerial vehicle understands the control characteristics of each model of the unmanned aerial vehicle and calculates the optimal flight path based on the characteristics. The unmanned aerial vehicle also has a flight control means that understands the characteristics of each aircraft and calculates the optimal flight path. The obstacle avoidance means analyzes the surrounding environment information obtained by the sensor and plans a safe flight path in real time. The unmanned aerial vehicle also has an obstacle avoidance means that detects obstacles and calculates a path to avoid them. This obstacle avoidance means combines a predictive model based on machine learning and sensor fusion technology to flexibly respond to environmental changes. The camera control means automatically performs pan, tilt, and zoom operations of the camera based on the user's instructions and emotional state. This makes it possible to capture images and videos that the user desires. The camera control means also remotely controls the camera of the unmanned aerial vehicle based on the user's instructions to capture the desired video. The overall configuration of the system is modular and can be flexibly customized to suit the type of unmanned aerial vehicle and the operating environment. In addition, the system is designed so that each module has an independent function and can be customized to suit the type of unmanned aerial vehicle and the operating environment, and the cloud-based infrastructure allows centralized management of data and remote updating of control logic. This improves the scalability and adaptability of the system and enables the provision of services according to the needs of users. In addition, the system adopts a cloud-based architecture, and data processing and updating of the control logic of the unmanned aerial vehicle can be performed remotely. This makes it easy to maintain and upgrade the system and enables the latest technology to be introduced quickly. In addition, as a means of collecting data that does not include sensors, there is a method of registering instructions and emotional expressions directly entered by the user into the system, which customizes the operation of the unmanned aerial vehicle and camera control. The control device equipped with the generation AI of the present invention can add context recognition capabilities to better understand user instructions and refine the drone's operating program. This allows the user's instructions to be optimized for specific situations and environments, for example, adjusting the drone's flight pattern based on outdoor weather conditions and ambient noise levels. In addition, real-time environmental recognition using sensor data allows the drone to automatically adapt to weather changes and generate operating programs that maintain safe flight. As for the emotion engine, the integration of biosensors that analyze the user's physiological signals makes it possible to read the user's emotional state more accurately from heart rate, skin activity, etc. This allows the drone to fly calmly and adjust the camera to capture a tranquil landscape if the user is feeling stressed. In addition, the drone can provide entertainment functions such as playing music in response to changes in the user's emotions. A group flight function will be added to the unmanned aerial vehicle, allowing multiple unmanned aerial vehicles to cooperate with each other to realize complex flight patterns and shooting. With this function, for example, one unmanned aerial vehicle will be able to track a subject while other unmanned aerial vehicles will take auxiliary images from different angles, generating images from multiple angles. By incorporating augmented reality (AR) and virtual reality (VR) technologies into the camera control means, it is possible to overlay digital information on the captured image in real time, providing the user with an immersive visual experience. For example, map information and annotations can be added to images captured by unmanned aerial vehicles, and used as tourist guides or educational content. The controller also allows users to add trigger functions that allow the drone to preprogram its behavior and execute automatically when certain events or conditions are met, allowing users to set up scenarios where a certain flight pattern is triggered when the user displays a certain emotion, for example. The system as a whole is designed to allow each module to be easily replaced or upgraded, and a mechanism is provided to reflect user feedback in the system. This allows the system to continue to evolve in response to user usage and requests, and continue to provide value over the long term. In addition, in the event of a breakdown or damage to the unmanned aerial vehicle, the self-diagnosis function can identify the problem and notify the user or maintenance personnel. In this way, the present invention provides a user-centered interactive experience using an unmanned aerial vehicle, and is expected to be used in a variety of application fields. The control unit can be equipped with the ability to have the drone generate specific lighting effects in response to the user's emotions. For example, when the user is excited, the drone could create an aerial light show using brightly colored LED lights. The drone could also emit scents tailored to the situation as it flies around the user, providing a multi-sensory experience. To improve the accuracy of user emotion recognition, the emotion engine will build an emotion prediction model by analyzing data from social media posts and daily behavior patterns, allowing the drone to predict changes in user emotions in advance and respond in a more timely manner. The drone's flight control means will be equipped with a function to analyze environmental sounds to grasp the surrounding situation, automatically adjusting the flight altitude in noisy areas to reduce the impact of noise, and a function to recognize the brightness of the surroundings and provide appropriate lighting during night flights. The camera control means will be equipped with a function to apply effects and filters to the captured images in real time, helping to create beautiful images, and will also add a function to automatically post the images captured by the drone to the user's social media accounts. The system as a whole takes user privacy into consideration, setting up a privacy policy for the collection and use of emotion and behavioral data, allowing users to easily control it. In addition, communication between drones is encrypted to strengthen security, ensuring thorough protection of user data. The drones will be able to send SOS signals and contact nearby rescue agencies so that users can respond quickly in emergencies, and they will also be able to pinpoint the location of survivors and provide information to rescue teams during search and rescue operations after disasters. With these functions, the unmanned aircraft system of the present invention is expected to enrich users' lives by providing convenience and safety in a wide range of situations, such as entertainment, daily companion, and emergency assistance. (Example 2) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device includes a generation means for receiving instructions in natural language, analyzing the instructions by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine includes a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is angry, the flight speed of the unmanned aerial vehicle is reduced and the viewpoint of the camera is stabilized. The generating means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and generates an operation program for the unmanned aerial vehicle. The recognizing means includes an emotion engine and is realized by a device different from the data processing device 12. The reflecting means is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the operation of the unmanned aerial vehicle based on the result of recognizing the user's emotion. For example, if the user is angry, the flight speed of the unmanned aerial vehicle is reduced or the viewpoint of the camera is stabilized. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The generating means mounted on the control device includes a receiving means for receiving instructions in natural language from the user, and the receiving means extracts text information from the user's speech using voice recognition technology. The received text information has an analyzing means for analyzing the natural language information using natural language processing technology and understanding the intention and content of the instruction. Based on the analysis result, the AI ​​has a generating means for generating an operation program for the unmanned aerial vehicle, and the generating means incorporates a machine learning algorithm and a rule-based algorithm. In addition, the generating AI incorporated in the control device has a voice recognition means for converting a command in natural language issued by the user into text, and the voice recognition means utilizes a voice analysis algorithm for converting the user's speech into text data. The textual instructions are then examined by the intention analysis means and processed by an AI algorithm for generating an operation program for the unmanned aerial vehicle. The AI ​​algorithm has a conditional branching function and a parameter adjustment function, and determines the flight path and behavior pattern of the unmanned aerial vehicle based on the user's instructions. The emotion recognition means includes sensors and cameras for analyzing the user's tone of voice, facial expressions, body language, etc., and uses data obtained from these to determine the user's emotional state. This determination is made through a means for estimating emotions from the pitch, strength, and speed of voice using voice analysis technology, and a means for reading emotions from the user's facial expressions using face recognition technology. The emotion engine includes a composite sensing means for identifying the user's emotional state, which integrates and processes information from the voice sensor and the visual sensor. The voice sensor estimates emotions from the user's tone of voice and speech rhythm using an emotion analysis algorithm. The visual sensor detects changes in facial expressions using face recognition technology to analyze the emotional state. The emotion data obtained by these sensors is processed by an emotion reflection algorithm to affect the operation of the unmanned aerial vehicle. The operation program of the unmanned aerial vehicle includes, for example, a navigation route calculation means for making a flight plan and a sensor data processing means for avoiding obstacles. The navigation route calculation means calculates the optimal flight route using GPS data and map information. The flight program of the unmanned aerial vehicle also includes a navigation route calculation means, which plans a flight route by referring to geographic information system (GIS) data and weather information. The sensor data processing means processes information obtained from a lidar or ultrasonic sensor, and instructs the unmanned aerial vehicle to detect and avoid obstacles in the vicinity. In addition, as an obstacle avoidance means, data from a sensor array mounted on the unmanned aerial vehicle is analyzed to grasp the surrounding environment and avoid the risk of collision. The communication means is responsible for transferring data and sending commands between the control device and the unmanned aerial vehicle, enabling real-time flight control. In addition, the unmanned aerial vehicle constantly exchanges data with the control device via the communication means during flight, and adjusts its operation according to the situation in real time. The system also has a user interface that is intuitively designed to allow users to easily control the drone, and some systems incorporate touch screen input means and gesture recognition means to enhance operability. Sensor-free data collection includes interactive input that is operated directly by the user, allowing the user to manually communicate emotion and behavior preferences to the system. Another example of sensor-free data collection is data based on emotional states and situations manually input by the user. In this case, the user directly specifies their emotions and desired drone behavior through an application or web interface. The drone then executes a program that operates based on the user's manual input. The implementation of each means utilizes hardware components such as a microprocessor, memory, and communication interfaces, which support the efficient operation of the entire system. The system of the present invention can be enhanced with additional capabilities to operate the drone based on the user's emotions and intent. For example, a generative AI built into the controller can learn from the user's past commands and reaction patterns to generate more personalized responses and behavioral programs. This learning capability allows the system to predict the user's behavior and preferences and automatically adjust the drone's behavior accordingly. Additionally, drones can be equipped with acoustic sensing capabilities to identify environmental sounds and use that information to estimate the user's emotional state, allowing the system to analyze surrounding noise, music, animal sounds, etc. to get a more detailed picture of the atmosphere in the user's environment. The emotion engine can also be integrated with wearable devices to track the user's bio-signals, collecting vital information such as heart rate, electrodermal activity, and body temperature, and incorporating this data into emotion estimation to more accurately identify the user's emotional state. The flight program of the drone can also incorporate an automatic return function in case of an emergency and an evasive maneuver function to ensure the safety of the user, allowing the drone to autonomously take safe action in the face of unexpected obstacles or changing weather conditions. Furthermore, facial expression recognition and gesture analysis functions can be added to the drone to realize interactive communication with the user, allowing the drone to recognize the gestures and facial expressions made by the user toward the drone and take action accordingly. The communication method uses a low-latency, high-bandwidth communication protocol, which allows faster and more stable data transfer between the control device and the unmanned aerial vehicle. This advanced communication technology enables the system to exchange information in real time, enabling precise flight control without delays. With the addition of such functions, the system of the present invention can better understand the user's emotions and intentions and provide more advanced and flexible services using unmanned aerial vehicles. User-system interactions can bring a more intuitive and richer experience, helping users complete their desired tasks more efficiently and safely. The generative AI installed in the control device can be equipped with a predictive function to improve the response speed to user instructions. This function analyzes the user's instruction patterns and habits to predict the next command that will be issued, allowing the drone to respond immediately. By anticipating the user's intentions and initiating actions, the drone can reduce reaction time and achieve more fluid operation. The flight program of the drones can also incorporate swarm intelligence capabilities that allow multiple drones to work together in a coordinated manner, allowing them to form a swarm to efficiently cover an area and share complex tasks based on user instructions. As for the emotion engine, a function can be added to control the lighting and sounds of the drone according to the user's emotions. For example, when the user is relaxing, the drone can play soft lighting and calming music to make the surrounding atmosphere more pleasant. Additionally, drones can be equipped with a projection mapping function to visually communicate user instructions, allowing the drone to project information onto the ground or walls, providing intuitive feedback to the user. The communications means can also be enhanced with the ability to link with a global communications network using satellite communications, allowing the drone to receive commands from a control device anywhere on Earth and handle a wide range of tasks. The drone's sensor array will be equipped with an environmental monitoring function, capable of measuring air pollution and greenhouse gas concentrations and transmitting the data to a control system in real time, making the system part of an environmental monitoring system. These additional features allow the system of the present invention to more intelligently control the drone in a way that reflects the user's emotions and intentions, and adapts to a wide variety of application scenarios, providing the user with a more comfortable and satisfying experience and greatly improving the usability of the system. (Example 3) The embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device includes a generation means for receiving instructions in natural language, analyzing the instructions by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine includes a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is surprised, the flight route of the unmanned aerial vehicle is changed, or the viewpoint of the camera is directed to a specific target. The generating means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and generates an operation program for the unmanned aerial vehicle. The recognizing means includes an emotion engine and is realized by a device different from the data processing device 12. The reflecting means is realized, for example, by the specific processing unit 290 of the data processing device 12, and adjusts the operation of the unmanned aerial vehicle based on the result of recognizing the user's emotion. For example, if the user is surprised, the flight route of the unmanned aerial vehicle is changed, or the viewpoint of the camera is directed to a specific target. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The generating means includes an analyzing means for analyzing instructions from a user using natural language processing (NLP) technology, and a program generating means for creating an operation program for the unmanned aerial vehicle based on the analyzed instructions. The generating means also has a function for analyzing the natural language instructions of the user and generating an operation program for the unmanned aerial vehicle. The generating means is integrated as a modularized software component in a data processing device or a smart device, and is also provided as a cloud-based service as necessary. The analyzing means converts the user's utterance into text using a voice recognition technology, and grasps the purpose and content of the instruction using an intention analysis function. The analyzing means also converts the user's voice instructions into text, and utilizes a voice recognition technology and an intention analysis function to understand the content. The program generating means automatically generates an operation program such as a flight path, speed, altitude, and camera operation of the unmanned aerial vehicle according to the analyzed user's instructions. The program generating means also automatically creates a specific operation program such as a flight path and camera operation of the unmanned aerial vehicle based on the analyzed instruction content. In this process, an algorithm that takes into account flight safety regulations and physical constraints is used so that the unmanned aerial vehicle is operated safely. In addition, the generation process applies algorithms that comply with flight safety regulations and take physical constraints into account to ensure the safe operation of the unmanned aerial vehicle. The recognition means includes an emotion analysis function that estimates emotions from the user's facial expressions, tone of voice, choice of words, etc. The emotion engine also includes a recognition means for capturing the user's emotions in real time. This function estimates the user's emotional state in real time using an emotion recognition model trained by machine learning. The emotion recognition model is trained to analyze a large amount of facial expression images and voice data and identify specific emotion patterns. The recognition means includes an emotion analysis function that estimates emotions from the user's facial expressions, tone of voice, choice of words, etc., and instantaneously estimates the user's emotional state using an emotion recognition model based on machine learning. The model is trained to identify various emotion patterns by analyzing a large amount of facial expression images and voice data. The reflecting means includes an operation change function that changes the operation of the unmanned aerial vehicle according to the recognized user's emotion. For example, when the user shows an emotion of surprise, the flight path of the unmanned aerial vehicle is immediately changed to respond according to the emotion, such as pointing the camera at an object of the user's interest. This function is for adjusting the operation program of the unmanned aerial vehicle in real time to improve the user's experience. In addition, when the user's emotion is recognized, the reflecting means reflects the emotion in the operation of the unmanned aerial vehicle. The operation change function responds according to the emotion, such as changing the flight path of the unmanned aerial vehicle or adjusting the viewpoint of the camera, according to the user's emotion. This function improves the user's experience and makes the operation of the unmanned aerial vehicle more dynamic and attractive. In addition, the input emotion data is reflected in the operation program of the unmanned aerial vehicle by the reflecting means. In this case, sensor technology is not required for emotion recognition, and the system operates based on user-driven information provision. In addition, when the user provides information by directly inputting his / her own emotional state, this does not require emotion recognition by a sensor, but is performed by manual input through an interface. The input emotion data is provided to the system at the user's initiative and reflected in the unmanned aerial vehicle's operating program, enabling it to be operated in accordance with the user's intentions. Further functional expansion is possible for the system of this embodiment. A function for dynamically controlling a swarm of unmanned aerial vehicles and realizing a complex aerial show can be added. This is expected to be used in events and entertainment fields. The emotion engine also has a function for measuring the user's stress level and providing specific flight patterns and images to promote relaxation. Music and images for the user to relax are played simultaneously, providing a whole-body relaxation experience based on emotions. Furthermore, the control device can also incorporate a prediction means that predicts user behavior and environmental changes and anticipates the behavior of the unmanned aerial vehicle. The prediction means utilizes past flight data and information from environmental sensors to optimize future flight patterns. This allows the unmanned aerial vehicle to automatically change its flight route according to the situation, achieving efficient flight. In addition, by having a function to automatically adjust the flight route according to environmental changes, it can quickly respond to sudden weather changes and the appearance of obstacles. To strengthen security, encryption technology will be used for the means of communication between the control device and the unmanned aerial vehicle. This will prevent unauthorized access from outside and ensure secure communication. As for the emotion engine, the user's emotion data will be anonymized and data processing will be performed with an emphasis on privacy protection. The anonymized emotion data can be used for research purposes and to develop more advanced emotion recognition models. The drone will be equipped with sensors that map the surrounding environment in 3D, enhancing its real-time environmental awareness. The 3D mapping data will be sent to the control device and used as information for flight safety. This data will also contribute to rescue operations in emergencies and understanding of the situation during disasters. The generator evolves the drone's motion program by learning from user feedback. This learning function improves the drone's performance and enables more sophisticated operation. The feedback-based learning function enables customization to suit the user's preferences and needs. Finally, the system provides a more intuitive and user-friendly operation experience by improving the user interface. The interface is automatically optimized based on the user's operation history and preferences, and provides a guide to simplify the operation of the drone. This makes drones more comfortable for users of all ages. Systems using unmanned aerial vehicles can be equipped with features to further enhance the capabilities of the emotion engine. For example, sensors that measure the user's biosignals in real time can be incorporated to more accurately grasp changes in emotions from heart rate and electrical resistance of the skin. In addition, the accuracy of user emotion recognition can be improved by having the unmanned aerial vehicle's camera capture the user's facial expressions and having the emotion engine analyze the video data. Regarding the generation means of the control device, a multitasking function can be added that processes instructions from multiple users simultaneously and assigns appropriate operation programs to each unmanned aerial vehicle. This makes it possible to operate the unmanned aerial vehicle according to each user's request, even if multiple users have different requests at one event. In addition, it is possible to implement an environmental adaptation function that uses data from sensors possessed by the unmanned aerial vehicle to detect changes in the environment and automatically adjust the flight program. This allows the unmanned aerial vehicle to take appropriate actions more autonomously, for example, to avoid people at a crowded event or to select the optimal angle to photograph a particular landscape. Regarding communication, it is possible to build a network where drones can share information with each other, enabling them to move intelligently as a swarm. Drones can grasp each other's positions and status in real time, and cooperate to efficiently carry out multiple tasks. In addition, by flexibly changing the formation formed by drones according to user instructions, new applications such as visual art and advertising are expected. The emotion engine can also be equipped with an automatic music and lighting adjustment function according to the user's emotions. It can enhance the emotion-based experience via the drone by providing bright and active music and lighting when the user is feeling joyful, and calm music and lighting when the user is feeling calm. In addition, the drone can add a health monitoring function to support the user's health and wellness, providing regular health checks and relaxation activities. With these expansions, systems using unmanned aerial vehicles are expected to be used in a wide range of fields, not only for entertainment, but also for health management, improving personal wellness, emergency response, etc. In addition, improvements to the user interface will enable more people to intuitively operate unmanned aerial vehicles, and their convenience will be widely recognized.

[0054] The process flow of each embodiment will be described below.

[0055] (Example 1) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone will move, rotate, and perform other operations according to instructions. (Example 2) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program for the unmanned aircraft based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone will move, rotate, and perform other operations according to instructions. (Example 3) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program for the unmanned aircraft based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone performs operations such as moving and rotating according to the instructions. For example, if the user is happy, the drone will move more aggressively. Conversely, if the user is angry, the drone will move more cautiously.

[0056] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0057] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58.

[0058] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0059] [Third embodiment]

[0060] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0061] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0062] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0063] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0064] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0065] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0066] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0067] Fig. 6 shows an example of main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0068] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0069] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0070] In the headset type terminal 314, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0071] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0072] (Example 1) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a communication means. The control device is equipped with a generation means that receives instructions in natural language, analyzes the instructions by the AI, and then generates an operation program for the unmanned aerial vehicle. The unmanned aerial vehicle performs operations such as movement and rotation according to the instructions based on the generated operation program. The communication means is a means for transmitting and receiving instructions and data between the control device and the unmanned aerial vehicle. The generation means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them using AI, and then generates an operation program for the unmanned aerial vehicle. The unmanned aerial vehicle performs operations such as movement and rotation according to the instructions based on the generated operation program. The communication means is a means for transmitting and receiving instructions and data between the control device and the unmanned aerial vehicle using the communication I / F 26 of the data processing device 12 and the communication I / F 44 of the headset terminal 314. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The generation means utilizes natural language processing technology to analyze instructions from a user and generate an operation program for the unmanned aerial vehicle. The generation means can also convert human oral or text input instructions into digital data using a voice recognition means and a text analysis means and interpret the contents of the digital data. This means includes a voice recognition function and converts the user's oral instructions into text data. The voice recognition means has a function of receiving the user's voice instructions and converting the voice data into text. The text analysis means performs morphological analysis and syntactic analysis to understand the contents of the instructions and grasp the intention. The text analysis means also performs morphological analysis and syntactic analysis to understand the meaning of the input text. The intention analysis means identifies the purpose or task behind the instructions, and the operation program generation means generates a specific operation program based on the analyzed intention. The intention analysis means can also identify specific tasks or purposes from instructions included in the text, and the operation program generation means can create an operation program based on the specified tasks or purposes. The operation program generation means utilizes a probabilistic algorithm or a machine learning model to develop an efficient and safe operation plan for the unmanned aerial vehicle. The operation program generating means can also define an operation sequence to be performed by the unmanned aerial vehicle and calculate the parameters required for that. The unmanned aerial vehicle automatically executes operations based on the generated operating program through the flight control means installed on the vehicle. The unmanned aerial vehicle also has a built-in flight control means, and can autonomously perform operations such as flying and rotating according to the generated operating program. The flight control means controls the attitude and position of the unmanned aerial vehicle in real time based on data from sensors and position information from GPS. The flight control means also functions by combining an attitude control function, a position control function, and a speed control function, which can also adjust the flight state of the unmanned aerial vehicle based on sensor data and GPS information. The obstacle detection means recognizes the surrounding environment, and the collision avoidance means calculates a route to avoid the obstacle. The obstacle detection means also detects surrounding obstacles using sensors such as radar and LiDAR, and the collision avoidance means can calculate an alternative route to avoid the detected obstacle, allowing the vehicle to fly safely. The communication means enables data transmission and reception between the control device and the unmanned aerial vehicle using wireless communication technology. The communication means can also transmit and receive data between the control device and the unmanned aerial vehicle using advanced wireless communication technology. The means include an encoding means for encoding and decoding signals and an error correction means for maintaining the reliability of communication. The encoding means efficiently encodes the data to be transmitted and decodes it at the receiving end to recover the meaning of the data. The error correction means detects and corrects data errors that may occur in the communication process to maintain the reliability of communication. The communication means employs a communication protocol with low latency and high bandwidth to quickly transmit and receive data on the operation program and operation status. The communication protocol can also be optimized to achieve low latency and high bandwidth and transmit the flight status, sensor data, and video feed of the unmanned aerial vehicle in real time. The control device can always grasp the status of the unmanned aerial vehicle and issue additional instructions as necessary. The unmanned aerial vehicle also transmits sensor data and video feeds during flight to the control device in real time for monitoring and analysis. The unmanned aerial vehicle can also transmit data during flight to a control device via communication means, allowing real-time monitoring by an operator and collection of data for later analysis. A variety of additional functions can be incorporated into control systems that utilize unmanned aerial vehicles. For example, an environmental monitoring function can be added to an unmanned aerial vehicle to precisely measure temperature, humidity, and atmospheric pressure from the air and collect meteorological data. In addition, in agricultural applications, it is effective to equip the vehicle with sensors that measure soil moisture and nutritional status to provide functions that support precision agriculture. Unmanned aerial vehicles can also be equipped with functions to support rescue operations. For example, in the event of a disaster, they can grasp the extent of damage to buildings and the locations of victims, and provide information to rescue teams. They can also be equipped with thermal cameras to detect smoke and fire conditions, which can be useful in directing and supporting firefighting operations. Furthermore, to improve their autonomous flight capabilities, swarm functions can be developed that use AI to allow unmanned aerial vehicles to share information with each other and cooperate as a swarm, making it possible to monitor a wider area and carry out multiple tasks simultaneously. In terms of communication, we will consider alternative means of communication such as satellite communication and laser communication to improve communication stability. This will enable us to maintain communication with unmanned aircraft even in remote areas or disaster areas where communication infrastructure has been destroyed. Furthermore, to operate unmanned aircraft more safely and efficiently, we will introduce a system that combines ground radar systems and communications with other aircraft to accurately grasp the position and status of unmanned aircraft in flight and assist in collision avoidance. Surveillance systems using unmanned aerial vehicles can incorporate advances in video analytics technology to identify objects and people from video in real time and analyze behavioral patterns. This will automate security and surveillance tasks, contributing to crime prevention and safety management. In addition, footage captured by unmanned aerial vehicles can be used for virtual reality and augmented reality to provide new experiences in education, training, tourism, and more. Finally, the control device will be equipped with a self-learning function to train machine learning models that utilize the drone's operational logs and sensor data to improve the drone's flight performance, allowing the drone to learn from past experience, select more effective flight routes, and perform tasks more efficiently. It is conceivable that generative AI installed in the control device can be used to automate tasks in other industrial fields. For example, agricultural tasks such as spraying pesticides and sowing seeds can be automated to reduce manual labor. Ultrasonic sensors and near-infrared cameras can be installed in the drones to help with crop growth and early detection of disease. In addition, a precision pesticide spraying system using drones can be developed to optimize the amount of pesticide used and reduce environmental impact. The AI ​​that generates the control device can be applied not only to unmanned aerial vehicles, but also to underwater robots and autonomous vehicles on land. By combining these different platforms, a monitoring network covering land, sea and air can be constructed, which is expected to be used in a wide range of fields such as environmental monitoring, resource exploration, and disaster response. In environmental monitoring using unmanned aerial vehicles, it is also effective to mount a composite gas sensor to monitor air pollution and measure greenhouse gases. In addition to disaster relief, the combination of the control device and unmanned aerial vehicles can also be used for rescue and search operations. Combining high-performance cameras with face recognition technology will help with searches for missing people and early detection of people in distress during coastal surveillance. A system will also be developed that will equip unmanned aerial vehicles with lifesaving kits and quickly drop rescue supplies to people in distress. The strengthening of communication methods will enable use in remote medical care, where real-time data is important, and emergency communications during disasters. By achieving high-resolution video transmission and low-latency communications, it will play a role as infrastructure for doctors to supervise surgery from remote locations and for establishing emergency communications from disaster sites. We will further evolve the AI ​​of the control device and develop algorithms that allow swarms of unmanned aerial vehicles to work together to carry out complex tasks. This will enable multiple unmanned aerial vehicles to share a large task and complete it efficiently. For example, this can be applied to transporting materials at construction sites and extinguishing fires. Ultimately, the combination of control device AI and unmanned aerial vehicles will contribute to the creation of smart cities, such as managing urban infrastructure, monitoring traffic flow, and ensuring public safety. Using real-time data provided by unmanned aerial vehicles, a system will be built to optimize city operations and respond quickly to disasters. Information collected by unmanned aerial vehicles will also be useful in formulating urban plans and transportation policies. This will support the development of sustainable and efficient cities. (Example 2) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a location information acquisition means. The control device receives instructions in natural language, analyzes the instructions using the AI, and then acquires location information of the unmanned aerial vehicles. The location information acquisition means is a means for identifying the location of the unmanned aerial vehicles using a GPS, a sensor, or the like. The control device includes a control means for controlling the unmanned aerial vehicles according to the instructions based on the acquired location information. The location information acquisition means is a means for identifying a location using a GPS or a sensor mounted on the unmanned aerial vehicle, and is realized by a device different from the data processing device 12. The control means is realized by the specific processing unit 290 of the data processing device 12, and controls the unmanned aerial vehicle according to instructions based on the acquired location information. The control means may also be realized by the control unit 46A of the headset terminal 314. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The control device uses an analysis means including a natural language understanding module to analyze instructions from the user and grasp the intention. The control device also includes an instruction receiving means for receiving natural language instructions from the user and a natural language understanding module for analyzing the instructions. The natural language understanding module includes a voice-to-text conversion means for converting voice instructions into text data using voice recognition technology. The voice-to-text conversion function can convert the user's instructions into text information using a voice recognition algorithm. The voice-to-text conversion function includes language processing means such as tokenization, part-of-speech tagging, noun phrase analysis, verb phrase analysis, and dependency analysis for further analyzing the converted text data. The language processing function can also clearly grasp the intention of the instructions using a tokenization means, part-of-speech tagging means, syntactic analysis means, etc. This allows commands, parameters, conditions, etc. included in the user's instructions to be accurately identified. The analyzed instructions are interpreted by the generation AI as commands necessary for controlling the unmanned aerial vehicle and transmitted to the control unit of the unmanned aerial vehicle via a command generation means for generating a corresponding action command. This allows the user's intention to be interpreted as a command and generates an action command to be transmitted to the unmanned aerial vehicle. The location information acquisition means includes a composite location information processing means for tracking the exact location of the unmanned aerial vehicle. The location information acquisition means also includes a GPS module mounted on the unmanned aerial vehicle, which can acquire location information on the earth. This GPS module acquires latitude, longitude, and altitude information of any point on the earth. Furthermore, a GNSS analysis means for analyzing a GNSS (Global Navigation Satellite System) signal can provide higher accuracy and reliability of location information. The GNSS analysis means used in conjunction with this can also improve the accuracy of the position using signals from satellites. Meanwhile, an inertial measurement unit (IMU) such as an integrated acceleration sensor and gyroscope continuously tracks the attitude and movement of the unmanned aerial vehicle, and assists in acquiring stable location information even in an environment where the GPS signal is unstable. In addition, an IMU for detecting the movement of the unmanned aerial vehicle provides information based on inertia, and can maintain the accuracy of the location information even in a situation where the GPS signal is unstable. As an example that does not include a sensor, a communication-based location information acquisition means is considered, in which the unmanned aerial vehicle acquires its own location information by communicating with a beacon or a ground station. Another example of sensor-free location acquisition is a communication-based location acquisition method. In this method, the relative and absolute position is determined through signals transmitted from ground beacons and through communication with other unmanned aircraft. The beacon transmits radio waves of a specific frequency, which is received by a receiving module on the unmanned aircraft and serves as a reference point for calculating the location information. The unmanned aircraft can also calculate its own position based on the received signal. In such a system, the current position of the unmanned aircraft and adjustments to the flight path are exchanged in real time through communication with a ground station. The control means includes a flight path planning means for planning and adjusting the flight path of the unmanned aerial vehicle. The control means also includes a flight path planning function for planning and adjusting the flight path of the unmanned aerial vehicle. This incorporates a simulation means for simulating the operation of the unmanned aerial vehicle and calculating an optimal flight path, taking into account obstacles and safety constraints on the flight path. This function can also simulate the flight path using the simulation means and calculate the optimal path, taking into account obstacle avoidance means and safety constraints. Furthermore, it also includes an emergency avoidance means for quickly responding to an emergency that the unmanned aerial vehicle may encounter, and a group control means for cooperatively controlling multiple unmanned aerial vehicles. It also includes an emergency avoidance function for responding to an emergency, and a group control function for centrally controlling multiple unmanned aerial vehicles. The control device of this embodiment can incorporate an advanced obstacle detection system to improve flight capabilities in more complex environments. For example, a function is added that utilizes 3D mapping technology using a laser scanner or ultrasonic sensor to precisely recognize the surrounding environment during flight and quickly and autonomously respond to dynamically changing obstacles. In addition, by analyzing satellite images and geographic information system (GIS) data, it is possible to take into account terrain features and obstacle information in more detail in the flight plan, enabling advanced optimization of the flight path. In controlling a group of unmanned aerial vehicles, a coordinated flight algorithm based on swarm intelligence using AI can be introduced, allowing multiple unmanned aerial vehicles to work together efficiently. For example, when multiple unmanned aerial vehicles are dispersed to perform tasks in pesticide spraying or search and rescue operations, dynamic flight path adjustments are made to maximize the overall work efficiency. This allows unmanned aerial vehicles to share roles and cooperate according to individual situations. The control device's natural language understanding module will be equipped with a specialized dictionary and context analysis function to understand technical terms and industry-specific language used by users, improving its ability to accurately analyze instructions specialized for specific industries and applications and convert them into specific operation commands. In addition, to improve the unmanned aerial vehicle's environmental awareness, a function will be added to analyze social media and internet information in addition to sensor data to grasp people's activity patterns and the occurrence of events. In terms of location information acquisition means, it is possible to introduce a differential GPS (DGPS) system that provides more accurate location information by incorporating a network of ground reference stations that provide correction signals to the GPS module used by the unmanned aircraft. Furthermore, in order to enable operation and monitoring from remote locations, a real-time data link system using satellite communications can be incorporated, allowing the unmanned aircraft to be controlled from anywhere on Earth. By integrating these functions, unmanned aerial vehicles will be able to handle more complex missions and realize flexible and advanced operations tailored to user needs, providing advanced solutions using unmanned aerial vehicles in fields such as disaster relief, environmental monitoring, and security surveillance. The control device can be equipped with a context recognition function to interpret user instructions more precisely, allowing it to take the optimal action depending on different circumstances, even with the same command. It can also have a function to ask questions to the user in response to unclear instructions through dialogue, improving the accuracy of communication and preventing misunderstandings. Furthermore, it can have a multitasking capability to process instructions from multiple users simultaneously, achieving high flexibility in large-scale operations. The location information acquisition method will add a LiDAR sensor that performs 3D scanning of the drone's surroundings in real time, achieving more advanced environmental recognition and accurate positioning. In addition, visual odometry will be used to estimate the drone's movement from images captured by the camera, providing stable location information even in environments where GPS is not available. This will enable activities in places where it is difficult to receive GPS signals, such as between high-rise buildings in urban areas or in dense forests. The control method will employ a self-learning obstacle avoidance algorithm that allows the drone to autonomously avoid obstacles and adjust its flight path. In addition, a cooperative avoidance algorithm will be introduced that allows drones to communicate with each other to share the status of surrounding drones in real time, enabling them to fly efficiently while avoiding collisions. This will enable drones to carry out their missions safely even in situations where multiple drones are flying close together. The AI ​​of the control device can continuously update the environmental model based on the data collected by the unmanned aircraft and perform predictive control based on that environmental model. This allows the unmanned aircraft to realize autonomous flight that can respond not only to the current situation but also to future changes. The unmanned aircraft can also make optimal decisions according to the situation at hand, going beyond pre-set behavior patterns. Finally, the system proposed in this embodiment is applicable to various applications such as advanced monitoring, investigation, and disaster response using unmanned aerial vehicles, and is a next-generation unmanned aerial vehicle control system that combines high autonomy and usability. It is expected that this will promote the effective use of unmanned aerial vehicles in activities in areas where human access is difficult or dangerous, and in emergency missions with time constraints. (Example 3) An embodiment of the present invention is a system including a control device equipped with a generating AI, a plurality of unmanned aerial vehicles, and a video processing means. The control device receives instructions in natural language, which are analyzed by the AI, and then processes the video of the unmanned aerial vehicle. The video processing means is a means for analyzing the video of the unmanned aerial vehicle using a camera or image recognition technology. The control device includes a control means for controlling the unmanned aerial vehicle according to the instructions based on the analyzed video information. The image processing means is a means for analyzing images using a camera mounted on the unmanned aerial vehicle and image recognition technology, and is realized by a device different from the data processing device 12. The control means is realized by a specific processing unit 290 of the data processing device 12, and controls the unmanned aerial vehicle according to instructions based on the analyzed image information. The control means may also be realized by the control unit 46A of the headset terminal 314. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The control device includes an instruction analysis means using a natural language processing model, and has a function of receiving instructions from a user in text or voice format and understanding the intention. The instruction analysis means understands natural language sentences through morphological analysis and syntactic analysis, and accurately understands the intention of the instructions through semantic analysis. The natural language processing model mounted on the control device can receive the user's voice or text instructions and divide the data into basic units of language through a morpheme division function. Next, the syntactic analysis function can clarify the structure of the sentence, and the semantic analysis function can also identify the intention of the instructions according to the context. Based on these analysis results, a language understanding model built by machine learning accurately understands the user's intention and generates a corresponding action. In this process, a language model based on machine learning learns from training data to improve the accuracy of responses to user instructions. The image processing means installed in the unmanned aerial vehicle includes a real-time image analysis function, which instantly processes the image data captured by the unmanned aerial vehicle and identifies specific objects and scenery. This function uses an object detection model and a semantic segmentation model based on deep learning to recognize the type and location of objects and extract the characteristics of the environment captured by the unmanned aerial vehicle. The image processing means installed in the unmanned aerial vehicle can also analyze the image data in real time and identify specific objects in the screen using the object identification function. The object detection model and the semantic segmentation model can also be fused to identify the type and location of objects in the image. Pre-processing of the image data includes noise reduction and contrast adjustment, which contributes to improving the recognition accuracy. Furthermore, the image pre-processing function can perform noise reduction and contrast adjustment to improve the accuracy of the image analysis. The control means includes a flight path calculation function for the unmanned aerial vehicle, which calculates an optimal flight path to the destination based on the analyzed image information, and efficiently guides the unmanned aerial vehicle. This flight path calculation function integrates terrain data and weather information to avoid obstacles and maximize energy efficiency. In addition, as a control means, the unmanned aerial vehicle uses a flight path calculation function to calculate an efficient path to the destination. This function can combine a terrain data integration function and a weather information integration function to ensure flight safety and efficiency. In addition, the flight operation control function of the unmanned aerial vehicle precisely adjusts basic flight operations such as speed, altitude, and attitude control, and performs operations according to user instructions. In addition, the flight operation control function can also appropriately adjust the speed, altitude, and attitude of the unmanned aerial vehicle to realize operations according to user instructions. As part of the image processing means, an environmental monitoring function using an unmanned aerial vehicle is also considered. This uses an environmental change detection model to detect natural disasters and abnormal situations, enabling appropriate responses to the situation. The environmental monitoring function using an unmanned aerial vehicle can also use an environmental change detection model to quickly capture natural disasters and abnormal situations, enabling appropriate responses to the situation. This monitoring function effectively detects environmental changes over a wide area, enabling information collection and rapid response. An example of data collection that does not include sensors is a manual selection means where a user manually selects video data through a camera mounted on the unmanned aerial vehicle and transmits the data to the control device. This manual selection means is useful when a user is interested in a specific video or when video analysis is required under a specific situation. The user selects video data through an interface and transmits it to the control device, where it is analyzed by the video analysis means and handled by the control means. Alternatively, as a manual selection means, a user can select video data captured by the camera of the unmanned aerial vehicle through an interface and transmit it to the control device. This selection process allows video data to be selected based on a specific request from the user, and detailed analysis by the video processing means and appropriate flight control by the control means are performed. The control device can incorporate a reinforcement learning algorithm to learn behavioral patterns according to various situations. This algorithm enhances the adaptability of the unmanned aerial vehicle to respond to different environments and missions. The control device can also be equipped with a multi-agent system to manage the coordinated flight of multiple unmanned aerial vehicles. This allows multiple unmanned aerial vehicles to take action simultaneously and cooperate efficiently toward a single goal. Furthermore, the control device can be equipped with safety functions, including an automatic return function for the unmanned aerial vehicle in an emergency and an automatic obstacle avoidance function. This allows the unmanned aerial vehicle to complete its mission while ensuring its own safety. The image processing means may incorporate infrared cameras and heat sensing technology for high-precision image analysis even at night or in bad weather conditions, allowing the UAV to collect and analyze image data in any environment, day or night. In addition, the image processing means may also enable tracking of moving targets using object tracking algorithms in dynamic scenes. This capability allows the UAV to continuously monitor moving objects and provide critical information. The control means can be equipped with a swarm intelligence function that controls a swarm of unmanned aerial vehicles based on user instructions. This allows a swarm of unmanned aerial vehicles to fly together and perform missions more effectively in complex environments. The control means can also be equipped with a dynamic flight path recalculation function in response to real-time traffic information and weather changes. This allows the unmanned aerial vehicles to quickly respond even when information is updated mid-flight, improving the efficiency of mission execution. As part of the video processing means, a function can be included for uploading the video data collected by the unmanned aerial vehicle to a cloud service in real time for wide-ranging data analysis and sharing. This allows the video data captured by the unmanned aerial vehicle to be shared with a wide range of users for quick decision-making and information sharing. The video processing means can also have a detailed mapping function for the damage situation when a disaster occurs. This allows the unmanned aerial vehicle to get a detailed understanding of the situation immediately after the disaster occurs and provide important information for rescue teams and recovery efforts. As an example of sensor-free data collection, video data acquired by users through drones can be automatically posted to social media and news sites through AI-assisted automated analysis. This allows social events and unusual natural phenomena to be widely publicized, attracting interest and raising awareness. In addition, by including a data anonymization function to protect user privacy, video data collected by drones can be shared safely. The generation AI installed in the control device can be added with a function to analyze the video captured by the unmanned aerial vehicle in real time and identify the damage situation and the location of survivors during a disaster. This will contribute to the speed and efficiency of rescue operations. In addition, 3D mapping technology using the video data from the unmanned aerial vehicle can be integrated to create a three-dimensional map of the disaster area, enabling a more detailed understanding of the situation. The image processing means will incorporate highly sensitive sensors and image enhancement technology that are not affected by day and night or weather changes, allowing the drone to capture clear images even in low-light environments. It will also be able to recognize specific patterns and symbols in the image data, for example, to detect signs requesting help or specific obstacles. The control means has the function of automatically adjusting the formation and timing when the drones fly in a group. This allows multiple drones to cooperate to cover a wide area and efficiently collect data. In addition, the drones can be equipped with an autonomous avoidance function based on environmental recognition to quickly avoid unexpected obstacles they encounter. The video processing means may include the ability to detect motion within the video data and automatically track the camera of the unmanned aerial vehicle accordingly, allowing for uninterrupted monitoring of dynamic scenes or objects that need to be tracked. The control means is equipped with an algorithm that optimizes the energy consumption of the drone, contributing to extending mission time and reducing operating costs. In addition, the drone's flight path can be optimized in real time to flexibly respond to sudden changes in conditions. As an extension of the image processing means, it will be equipped with a function that enables multifaceted analysis of the image data collected by the unmanned aerial vehicle, enabling applications in different fields, such as evaluating the health of crops in the agricultural sector and detecting changes in ecosystems in environmental monitoring. The control device can be equipped with a function to further improve its natural language understanding capability in order to realize interactive communication with users. This will enable users to intuitively operate the unmanned aerial vehicle, enabling a wider range of users to utilize unmanned aerial vehicles. The video processing means can be equipped with a function that allows the insertion of text and annotations into live video in real time to make the content of the video easier to understand. This makes it possible, for example, to instantly provide rescue information to rescue workers and commanders on the scene during a disaster. The control means can be equipped with features to enable the UAS to self-heal and provide periodic maintenance reminders, thereby increasing the availability and reliability of the UAS for long-term, stable operation. These additional functions will dramatically improve the capabilities of unmanned aerial vehicles for surveillance, disaster response, and information gathering, making it possible to create a flexible system that can respond to a variety of situations. (Example 4) An embodiment of the present invention is a system including a control device equipped with a generating AI, a plurality of unmanned aerial vehicles, and a distance measurement means. The control device receives instructions in natural language, analyzes them using the AI, and then measures the distance to the unmanned aerial vehicles. The distance measurement means measures the distance between the unmanned aerial vehicles and obstacles using an ultrasonic sensor, a laser range finder, or the like. The control device includes a control means for controlling the unmanned aerial vehicles according to the instructions based on the measured distance information. The distance measurement means is a means for measuring the distance between the unmanned aerial vehicle and an obstacle using an ultrasonic sensor or a laser range finder mounted on the unmanned aerial vehicle, and is realized by a device different from the data processing device 12. The control means is realized by a specific processing unit 290 of the data processing device 12, and controls the unmanned aerial vehicle according to instructions based on the measured distance information. The control means may also be realized by the control unit 46A of the headset terminal 314. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The generation AI built into the control device has a function of understanding human instructions using natural language analysis means, and generates commands necessary for operating the unmanned aerial vehicle using this function. In addition, the generation AI mounted on the control device can understand user instructions and generate commands necessary for operating the unmanned aerial vehicle by combining a voice recognition means having a voice-to-text conversion function with a grammar analysis means and a semantic analysis means for interpreting the meaning of a sentence. The generated commands include specific instructions for planning the flight path and the operation of the unmanned aerial vehicle, which are executed by the control algorithm of the unmanned aerial vehicle. In addition, the generated commands include detailed instructions regarding the flight path and operation of the unmanned aerial vehicle, and can be executed by the control algorithm means. The ultrasonic sensor as a distance measuring means is installed on the front or side of the unmanned aerial vehicle and measures the distance by detecting the reflected sound waves from surrounding obstacles. This sensor has an echo cancellation function to adapt to the environment and a filtering function to remove interference waves, and provides accurate distance information. In addition, the ultrasonic sensor can detect the reflected waves from surrounding obstacles using the echolocation function and obtain distance information. This sensor can provide accurate distance information without being affected by environmental noise due to the interference sound wave removal function and echo cancellation function. On the other hand, the laser rangefinder can measure distance with high accuracy and is particularly suitable for measuring long distances and detecting subtle obstacles. The laser rangefinder emits a laser beam to the target and calculates the distance using the time difference of the reflected light. In addition, the laser rangefinder has a function of emitting a laser beam to the target and a function of detecting the reflected light, and can measure the distance by the reflection time difference calculation function. The laser rangefinder enables precise distance measurement and can be particularly suitable for detecting long distances and subtle obstacles. The control means has a function of adjusting the operation of the unmanned aerial vehicle based on information from the distance measurement means, and this function is realized by a flight control algorithm of the unmanned aerial vehicle. The flight control algorithm is designed based on control theories such as PID control and feedforward control, and enables the unmanned aerial vehicle to accurately execute instructed operations while maintaining stable flight. The control means adjusts the attitude and speed of the unmanned aerial vehicle in real time, and optimizes a route to reach the destination while avoiding obstacles. The control means can also have a route control function that uses information provided by the distance measurement means to adjust the attitude and speed of the unmanned aerial vehicle and avoid obstacles. The flight control algorithm means can utilize a PID control function and a feedforward control function to adjust the operation of the unmanned aerial vehicle so that the unmanned aerial vehicle flies stably and accurately according to instructions. An example of distance measurement that does not include a sensor is a positioning means using GPS. A GPS receiver mounted on an unmanned aerial vehicle receives signals transmitted from satellites and calculates the current position of the unmanned aerial vehicle based on the information. The positioning means provides wide-area position information of the environment in which the unmanned aerial vehicle flies, and is used to plan larger-scale flight plans. In addition, in order to grasp the relative positional relationship between unmanned aerial vehicles, multiple unmanned aerial vehicles share their respective GPS information and function as a means for adjusting the flight formation as a whole. Furthermore, the positioning means using GPS can determine the current location of the unmanned aerial vehicle via a GPS receiver equipped with a satellite signal receiving function. The position information calculation function can calculate the position of the unmanned aerial vehicle from the received satellite signals and contribute to the planning of a wide-area flight plan. Furthermore, by sharing position information between unmanned aerial vehicles, it can also function as a flight formation adjustment function, and flight coordination as a whole can be realized. The control device further includes an image processing means for improving the accuracy of obstacle detection. For example, an object recognition algorithm based on machine learning can be used to automatically detect obstacles from the video captured by the unmanned aerial vehicle and recognize their size and shape. This allows the unmanned aerial vehicle to fly safely in more complex environments. The control device also has the ability to analyze the video data captured by the unmanned aerial vehicle in real time and adjust the flight path according to dynamic environmental changes. Furthermore, the control device is equipped with a communication control means for adjusting communication between unmanned aerial vehicles, enabling multiple unmanned aerial vehicles to share information and fly cooperatively. The communication control means has a function of optimizing cooperative operations during formation flight and specific mission execution. The AI ​​of the control device has a self-learning function that learns from the actual flight environment, and automatically generates the optimal flight path when it encounters new obstacles or unknown situations. The AI ​​accumulates the drone's experience and improves the flight pattern by referring to past data. This learning process allows the drone to better adapt to the environment and perform its missions more effectively. The control device also has a collision avoidance algorithm when multiple drones are operating at the same time, realizing safe and efficient swarm movements. Distance measurement sensors will be supplemented with infrared sensors and thermal imaging cameras for accurate distance measurements even at night and in bad weather. These will compensate for the limitations of conventional ultrasonic sensors and laser range finders, allowing the drone to operate in more challenging environments. These sensors will also provide additional information to detect obstacle types and temperature distributions and select flight paths accordingly. The control vehicle will incorporate an advanced collision avoidance system that combines real-time environmental awareness and predictive modeling to enable the unmanned aerial vehicle to respond quickly and effectively to unexpected obstacles. The collision avoidance system will allow the unmanned aerial vehicle to automatically change its flight path to ensure safe and continuous mission completion. In addition, the control vehicle will also be capable of optimizing the unmanned aerial vehicle's energy management to extend flight time and improve mission efficiency. The generative AI installed in the control device has the ability to simultaneously monitor multiple unmanned aerial vehicles and coordinate the operation of each aircraft, enabling them to operate in a swarm-like coordinated manner. The unmanned aerial vehicles share information with each other and are aware of the surrounding environment and the positions of other aircraft, allowing them to carry out their missions efficiently and safely. This coordinated operation is particularly effective in environments with complex terrain and many obstacles, and can be applied to search and rescue operations and situational awareness during disasters. In addition, the drone's distance measurement means will use a new sensor fusion technology to reduce the risk of collision with obstacles. By integrating information from different types of sensors, the drone will achieve more accurate and reliable environmental recognition. For example, by combining distance information from an ultrasonic sensor with the precise measurement results of a laser rangefinder, the drone will be able to more precisely recognize obstacles and fly around them safely. The controller can also upload the drone's flight data to the cloud and perform large-scale data analysis based on the data. This can help discover new flight patterns that can improve the drone's flight efficiency and provide insights that can help improve future flight plans. Additionally, cloud-based simulation can be used to test flight drones in virtual environments, allowing them to learn how to respond to various scenarios before flying them in real life. The control device will also be equipped with an interface that allows users to operate intuitively. Using a touchscreen display and gesture recognition technology, users can direct the flight of the drone with simple actions. In addition, by combining virtual reality (VR) and augmented reality (AR) technologies, users can have a more intuitive experience in monitoring and controlling the flight of the drone. Furthermore, the drone will be equipped with a predictive maintenance function based on machine learning, which will identify the risk of aircraft failure in advance and perform preventative maintenance, thereby increasing the drone's uptime and contributing to maintaining its reliability over the long term. Finally, to expand the range of applications for unmanned aerial vehicles, the development of models with waterproof and dustproof functions that can be used underwater and underground will be considered. This will enable applications in areas where conventional unmanned aerial vehicles have been difficult, such as marine surveys and underground resource exploration.

[0073] The process flow of each embodiment will be described below.

[0074] (Example 1) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program based on the instructions analyzed by the AI. Step 3: The generated operation program is sent to the unmanned aerial vehicle, which then performs operations such as moving and rotating according to the instructions. (Example 2) Step 1: The controller receives a natural language instruction. Step 2: Obtain the drone's location information based on the instructions analyzed by AI. Step 3: Based on the acquired position information, the control device controls the unmanned aerial vehicle. (Example 3) Step 1: The controller receives a natural language instruction. Step 2: Process the drone footage based on instructions analyzed by AI. Step 3: Using the video processing means, the control device analyzes the video of the unmanned aerial vehicle. Step 4: Based on the analyzed video information, the control device controls the unmanned aerial vehicle. (Example 4) Step 1: The controller receives a natural language instruction. Step 2: Based on the instructions analyzed by the AI, measure the distance between the drone and the obstacle. Step 3: Using the distance measurement means, the control device measures the distance between the unmanned aerial vehicle and the obstacle. Step 4: Based on the measured distance information, the control device controls the unmanned aerial vehicle.

[0075] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0076] (Example 1) The embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device has a generation means for receiving instructions in natural language, analyzing them by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine has a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is happy, the flight speed of the unmanned aerial vehicle is increased and the viewpoint of the camera is set to a wide range. The generating means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and generates an operation program for the unmanned aerial vehicle. The recognizing means captures the user's voice using the microphone 238 of the headset type terminal 314, and recognizes the user's emotions by an emotion engine. The reflecting means is realized by the control unit 46A of the headset type terminal 314, and increases the flight speed of the unmanned aerial vehicle or sets the camera's viewpoint to a wide range in response to the user's emotions. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The control device includes an analysis means using natural language understanding (NLU) technology, which interprets the instructions given by the user according to their intention. The analysis means tokenizes the user's speech and performs part-of-speech tagging and syntactic analysis. The analysis means also includes a program generation means that functions by combining a tokenization means for tokenizing the contents of the speech, a part-of-speech tagging means for identifying parts of speech, and a syntactic analysis means for analyzing the structure of a sentence, and generates an operation program according to the user's command. Furthermore, the intention recognition means identifies the purpose of the utterance and extracts information for generating an appropriate operation program. The operation program generation means generates specific operation commands such as the flight path, speed, and camera operation of the unmanned aerial vehicle based on the analyzed instructions. The operation program generation means also forms instructions for controlling the flight path, camera operation, etc. of the unmanned aerial vehicle, and sets parameters necessary for the unmanned aerial vehicle to perform its mission. The emotion recognition means includes a function for grasping the emotional state of the user using voice analysis and facial expression analysis techniques. The voice analysis means reads emotions from changes in tone and pitch of the speech. The voice analysis means estimates emotions from the speech. The facial expression analysis means identifies emotions such as happiness and sadness from the facial expressions of the user captured by the camera. The facial expression analysis means identifies emotions based on visual information. These means are trained using machine learning models to recognize emotions with high accuracy. The emotion reflection means adjusts the flight pattern and camera settings of the unmanned aerial vehicle according to the recognized emotion. For example, if the user shows joy, the unmanned aerial vehicle will take a more dynamic flight pattern and widen the viewing angle of the camera to capture a wider range of scenery. The emotion reflection means also changes the behavior of the unmanned aerial vehicle based on the recognized emotion, for example, responding to a user who is feeling joy by increasing the flight speed. The flight control means of the unmanned aerial vehicle understands the control characteristics of each model of the unmanned aerial vehicle and calculates the optimal flight path based on the characteristics. The unmanned aerial vehicle also has a flight control means that understands the characteristics of each aircraft and calculates the optimal flight path. The obstacle avoidance means analyzes the surrounding environment information obtained by the sensor and plans a safe flight path in real time. The unmanned aerial vehicle also has an obstacle avoidance means that detects obstacles and calculates a path to avoid them. This obstacle avoidance means combines a predictive model based on machine learning and sensor fusion technology to flexibly respond to environmental changes. The camera control means automatically performs pan, tilt, and zoom operations of the camera based on the user's instructions and emotional state. This makes it possible to capture images and videos that the user desires. The camera control means also remotely controls the camera of the unmanned aerial vehicle based on the user's instructions to capture the desired video. The overall configuration of the system is modular and can be flexibly customized to suit the type of unmanned aerial vehicle and the operating environment. In addition, the system is designed so that each module has an independent function and can be customized to suit the type of unmanned aerial vehicle and the operating environment, and the cloud-based infrastructure allows centralized management of data and remote updating of control logic. This improves the scalability and adaptability of the system and enables the provision of services according to the needs of users. In addition, the system adopts a cloud-based architecture, and data processing and updating of the control logic of the unmanned aerial vehicle can be performed remotely. This makes it easy to maintain and upgrade the system and enables the latest technology to be introduced quickly. In addition, as a means of collecting data that does not include sensors, there is a method of registering instructions and emotional expressions directly entered by the user into the system, which customizes the operation of the unmanned aerial vehicle and camera control. The control device equipped with the generation AI of the present invention can add context recognition capabilities to better understand user instructions and refine the drone's operating program. This allows the user's instructions to be optimized for specific situations and environments, for example, adjusting the drone's flight pattern based on outdoor weather conditions and ambient noise levels. In addition, real-time environmental recognition using sensor data allows the drone to automatically adapt to weather changes and generate operating programs that maintain safe flight. As for the emotion engine, the integration of biosensors that analyze the user's physiological signals makes it possible to read the user's emotional state more accurately from heart rate, skin activity, etc. This allows the drone to fly calmly and adjust the camera to capture a tranquil landscape if the user is feeling stressed. In addition, the drone can provide entertainment functions such as playing music in response to changes in the user's emotions. A group flight function will be added to the unmanned aerial vehicle, allowing multiple unmanned aerial vehicles to cooperate with each other to realize complex flight patterns and shooting. With this function, for example, one unmanned aerial vehicle will be able to track a subject while other unmanned aerial vehicles will take auxiliary images from different angles, generating images from multiple angles. By incorporating augmented reality (AR) and virtual reality (VR) technologies into the camera control means, it is possible to overlay digital information on the captured image in real time, providing the user with an immersive visual experience. For example, map information and annotations can be added to images captured by unmanned aerial vehicles, and used as tourist guides or educational content. The controller also allows users to add trigger functions that allow the drone to preprogram its behavior and execute automatically when certain events or conditions are met, allowing users to set up scenarios where a certain flight pattern is triggered when the user displays a certain emotion, for example. The system as a whole is designed to allow each module to be easily replaced or upgraded, and a mechanism is provided to reflect user feedback in the system. This allows the system to continue to evolve in response to user usage and requests, and continue to provide value over the long term. In addition, in the event of a breakdown or damage to the unmanned aerial vehicle, the self-diagnosis function can identify the problem and notify the user or maintenance personnel. In this way, the present invention provides a user-centered interactive experience using an unmanned aerial vehicle, and is expected to be used in a variety of application fields. The control unit can be equipped with the ability to have the drone generate specific lighting effects in response to the user's emotions. For example, when the user is excited, the drone could create an aerial light show using brightly colored LED lights. The drone could also emit scents tailored to the situation as it flies around the user, providing a multi-sensory experience. To improve the accuracy of user emotion recognition, the emotion engine will build an emotion prediction model by analyzing data from social media posts and daily behavior patterns, allowing the drone to predict changes in user emotions in advance and respond in a more timely manner. The drone's flight control means will be equipped with a function to analyze environmental sounds to grasp the surrounding situation, automatically adjusting the flight altitude in noisy areas to reduce the impact of noise, and a function to recognize the brightness of the surroundings and provide appropriate lighting during night flights. The camera control means will be equipped with a function to apply effects and filters to the captured images in real time, helping to create beautiful images, and will also add a function to automatically post the images captured by the drone to the user's social media accounts. The system as a whole takes user privacy into consideration, setting up a privacy policy for the collection and use of emotion and behavioral data, allowing users to easily control it. In addition, communication between drones is encrypted to strengthen security, ensuring thorough protection of user data. The drones will be able to send SOS signals and contact nearby rescue agencies so that users can respond quickly in emergencies, and they will also be able to pinpoint the location of survivors and provide information to rescue teams during search and rescue operations after disasters. With these functions, the unmanned aircraft system of the present invention is expected to enrich users' lives by providing convenience and safety in a wide range of situations, such as entertainment, daily companion, and emergency assistance. (Example 2) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device includes a generation means for receiving instructions in natural language, analyzing the instructions by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine includes a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is angry, the flight speed of the unmanned aerial vehicle is reduced and the viewpoint of the camera is stabilized. The generating means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and generates an operation program for the unmanned aerial vehicle. The recognizing means captures the user's voice using the microphone 238 of the headset type terminal 314, and recognizes the user's emotions by an emotion engine. The reflecting means is realized by the control unit 46A of the headset type terminal 314, and reduces the flight speed of the unmanned aerial vehicle and stabilizes the viewpoint of the camera according to the user's emotions. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The generating means mounted on the control device includes a receiving means for receiving instructions in natural language from the user, and the receiving means extracts text information from the user's speech using voice recognition technology. The received text information has an analyzing means for analyzing the natural language information using natural language processing technology and understanding the intention and content of the instruction. Based on the analysis result, the AI ​​has a generating means for generating an operation program for the unmanned aerial vehicle, and the generating means incorporates a machine learning algorithm and a rule-based algorithm. In addition, the generating AI incorporated in the control device has a voice recognition means for converting a command in natural language issued by the user into text, and the voice recognition means utilizes a voice analysis algorithm for converting the user's speech into text data. The textual instructions are then examined by the intention analysis means and processed by an AI algorithm for generating an operation program for the unmanned aerial vehicle. The AI ​​algorithm has a conditional branching function and a parameter adjustment function, and determines the flight path and behavior pattern of the unmanned aerial vehicle based on the user's instructions. The emotion recognition means includes sensors and cameras for analyzing the user's tone of voice, facial expressions, body language, etc., and uses data obtained from these to determine the user's emotional state. This determination is made through a means for estimating emotions from the pitch, strength, and speed of voice using voice analysis technology, and a means for reading emotions from the user's facial expressions using face recognition technology. The emotion engine includes a composite sensing means for identifying the user's emotional state, which integrates and processes information from the voice sensor and the visual sensor. The voice sensor estimates emotions from the user's tone of voice and speech rhythm using an emotion analysis algorithm. The visual sensor detects changes in facial expressions using face recognition technology to analyze the emotional state. The emotion data obtained by these sensors is processed by an emotion reflection algorithm to affect the operation of the unmanned aerial vehicle. The operation program of the unmanned aerial vehicle includes, for example, a navigation route calculation means for making a flight plan and a sensor data processing means for avoiding obstacles. The navigation route calculation means calculates the optimal flight route using GPS data and map information. The flight program of the unmanned aerial vehicle also includes a navigation route calculation means, which plans a flight route by referring to geographic information system (GIS) data and weather information. The sensor data processing means processes information obtained from a lidar or ultrasonic sensor, and instructs the unmanned aerial vehicle to detect and avoid obstacles in the vicinity. In addition, as an obstacle avoidance means, data from a sensor array mounted on the unmanned aerial vehicle is analyzed to grasp the surrounding environment and avoid the risk of collision. The communication means is responsible for transferring data and sending commands between the control device and the unmanned aerial vehicle, enabling real-time flight control. In addition, the unmanned aerial vehicle constantly exchanges data with the control device via the communication means during flight, and adjusts its operation according to the situation in real time. The system also has a user interface that is intuitively designed to allow users to easily control the drone, and some systems incorporate touch screen input means and gesture recognition means to enhance operability. Sensor-free data collection includes interactive input that is operated directly by the user, allowing the user to manually communicate emotion and behavior preferences to the system. Another example of sensor-free data collection is data based on emotional states and situations manually input by the user. In this case, the user directly specifies their emotions and desired drone behavior through an application or web interface. The drone then executes a program that operates based on the user's manual input. The implementation of each means utilizes hardware components such as a microprocessor, memory, and communication interfaces, which support the efficient operation of the entire system. The system of the present invention can be enhanced with additional capabilities to operate the drone based on the user's emotions and intent. For example, a generative AI built into the controller can learn from the user's past commands and reaction patterns to generate more personalized responses and behavioral programs. This learning capability allows the system to predict the user's behavior and preferences and automatically adjust the drone's behavior accordingly. Additionally, drones can be equipped with acoustic sensing capabilities to identify environmental sounds and use that information to estimate the user's emotional state, allowing the system to analyze surrounding noise, music, animal sounds, etc. to get a more detailed picture of the atmosphere in the user's environment. The emotion engine can also be integrated with wearable devices to track the user's bio-signals, collecting vital information such as heart rate, electrodermal activity, and body temperature, and incorporating this data into emotion estimation to more accurately identify the user's emotional state. The flight program of the drone can also incorporate an automatic return function in case of an emergency and an evasive maneuver function to ensure the safety of the user, allowing the drone to autonomously take safe action in the face of unexpected obstacles or changing weather conditions. Furthermore, facial expression recognition and gesture analysis functions can be added to the drone to realize interactive communication with the user, allowing the drone to recognize the gestures and facial expressions made by the user toward the drone and take action accordingly. The communication method uses a low-latency, high-bandwidth communication protocol, which allows faster and more stable data transfer between the control device and the unmanned aerial vehicle. This advanced communication technology enables the system to exchange information in real time, enabling precise flight control without delays. With the addition of such functions, the system of the present invention can better understand the user's emotions and intentions and provide more advanced and flexible services using unmanned aerial vehicles. User-system interactions can bring a more intuitive and richer experience, helping users complete their desired tasks more efficiently and safely. The generative AI installed in the control device can be equipped with a predictive function to improve the response speed to user instructions. This function analyzes the user's instruction patterns and habits to predict the next command that will be issued, allowing the drone to respond immediately. By anticipating the user's intentions and initiating actions, the drone can reduce reaction time and achieve more fluid operation. The flight program of the drones can also incorporate swarm intelligence capabilities that allow multiple drones to work together in a coordinated manner, allowing them to form a swarm to efficiently cover an area and share complex tasks based on user instructions. As for the emotion engine, a function can be added to control the lighting and sounds of the drone according to the user's emotions. For example, when the user is relaxing, the drone can play soft lighting and calming music to make the surrounding atmosphere more pleasant. Additionally, drones can be equipped with a projection mapping function to visually communicate user instructions, allowing the drone to project information onto the ground or walls, providing intuitive feedback to the user. The communications means can also be enhanced with the ability to link with a global communications network using satellite communications, allowing the drone to receive commands from a control device anywhere on Earth and handle a wide range of tasks. The drone's sensor array will be equipped with an environmental monitoring function, capable of measuring air pollution and greenhouse gas concentrations and transmitting the data to a control system in real time, making the system part of an environmental monitoring system. These additional features allow the system of the present invention to more intelligently control the drone in a way that reflects the user's emotions and intentions, and adapts to a wide variety of application scenarios, providing the user with a more comfortable and satisfying experience and greatly improving the usability of the system. (Example 3) The embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and an emotion engine. The control device includes a generation means for receiving instructions in natural language, analyzing the instructions by the AI, and then generating an operation program for the unmanned aerial vehicle. The emotion engine includes a recognition means for recognizing the user's emotion and a reflection means for reflecting the emotion in the operation of the unmanned aerial vehicle. For example, if the user is surprised, the flight route of the unmanned aerial vehicle is changed, or the viewpoint of the camera is directed to a specific target. The generating means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and generates an operation program for the unmanned aerial vehicle. The recognizing means captures the user's voice using the microphone 238 of the headset type terminal 314, and recognizes the user's emotions by an emotion engine. The reflecting means is realized by the control unit 46A of the headset type terminal 314, and changes the flight route of the unmanned aerial vehicle or directs the viewpoint of the camera to a specific target according to the user's emotions. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various changes are possible. The generating means includes an analyzing means for analyzing instructions from a user using natural language processing (NLP) technology, and a program generating means for creating an operation program for the unmanned aerial vehicle based on the analyzed instructions. The generating means also has a function for analyzing the natural language instructions of the user and generating an operation program for the unmanned aerial vehicle. The generating means is integrated as a modularized software component in a data processing device or a smart device, and is also provided as a cloud-based service as necessary. The analyzing means converts the user's utterance into text using a voice recognition technology, and grasps the purpose and content of the instruction using an intention analysis function. The analyzing means also converts the user's voice instructions into text, and utilizes a voice recognition technology and an intention analysis function to understand the content. The program generating means automatically generates an operation program such as a flight path, speed, altitude, and camera operation of the unmanned aerial vehicle according to the analyzed user's instructions. The program generating means also automatically creates a specific operation program such as a flight path and camera operation of the unmanned aerial vehicle based on the analyzed instruction content. In this process, an algorithm that takes into account flight safety regulations and physical constraints is used so that the unmanned aerial vehicle is operated safely. In addition, the generation process applies algorithms that comply with flight safety regulations and take physical constraints into account to ensure the safe operation of the unmanned aerial vehicle. The recognition means includes an emotion analysis function that estimates emotions from the user's facial expressions, tone of voice, choice of words, etc. The emotion engine also includes a recognition means for capturing the user's emotions in real time. This function estimates the user's emotional state in real time using an emotion recognition model trained by machine learning. The emotion recognition model is trained to analyze a large amount of facial expression images and voice data and identify specific emotion patterns. The recognition means includes an emotion analysis function that estimates emotions from the user's facial expressions, tone of voice, choice of words, etc., and instantaneously estimates the user's emotional state using an emotion recognition model based on machine learning. The model is trained to identify various emotion patterns by analyzing a large amount of facial expression images and voice data. The reflecting means includes an operation change function that changes the operation of the unmanned aerial vehicle according to the recognized user's emotion. For example, when the user shows an emotion of surprise, the flight path of the unmanned aerial vehicle is immediately changed to respond according to the emotion, such as pointing the camera at an object of the user's interest. This function is for adjusting the operation program of the unmanned aerial vehicle in real time to improve the user's experience. In addition, when the user's emotion is recognized, the reflecting means reflects the emotion in the operation of the unmanned aerial vehicle. The operation change function responds according to the emotion, such as changing the flight path of the unmanned aerial vehicle or adjusting the viewpoint of the camera, according to the user's emotion. This function improves the user's experience and makes the operation of the unmanned aerial vehicle more dynamic and attractive. In addition, the input emotion data is reflected in the operation program of the unmanned aerial vehicle by the reflecting means. In this case, sensor technology is not required for emotion recognition, and the system operates based on user-driven information provision. In addition, when the user provides information by directly inputting his / her own emotional state, this does not require emotion recognition by a sensor, but is performed by manual input through an interface. The input emotion data is provided to the system at the user's initiative and reflected in the unmanned aerial vehicle's operating program, enabling it to be operated in accordance with the user's intentions. Further functional expansion is possible for the system of this embodiment. A function for dynamically controlling a swarm of unmanned aerial vehicles and realizing a complex aerial show can be added. This is expected to be used in events and entertainment fields. The emotion engine also has a function for measuring the user's stress level and providing specific flight patterns and images to promote relaxation. Music and images for the user to relax are played simultaneously, providing a whole-body relaxation experience based on emotions. Furthermore, the control device can also incorporate a prediction means that predicts user behavior and environmental changes and anticipates the behavior of the unmanned aerial vehicle. The prediction means utilizes past flight data and information from environmental sensors to optimize future flight patterns. This allows the unmanned aerial vehicle to automatically change its flight route according to the situation, achieving efficient flight. In addition, by having a function to automatically adjust the flight route according to environmental changes, it can quickly respond to sudden weather changes and the appearance of obstacles. To strengthen security, encryption technology will be used for the means of communication between the control device and the unmanned aerial vehicle. This will prevent unauthorized access from outside and ensure secure communication. As for the emotion engine, the user's emotion data will be anonymized and data processing will be performed with an emphasis on privacy protection. The anonymized emotion data can be used for research purposes and to develop more advanced emotion recognition models. The drone will be equipped with sensors that map the surrounding environment in 3D, enhancing its real-time environmental awareness. The 3D mapping data will be sent to the control device and used as information for flight safety. This data will also contribute to rescue operations in emergencies and understanding of the situation during disasters. The generator evolves the drone's motion program by learning from user feedback. This learning function improves the drone's performance and enables more sophisticated operation. The feedback-based learning function enables customization to suit the user's preferences and needs. Finally, the system provides a more intuitive and user-friendly operation experience by improving the user interface. The interface is automatically optimized based on the user's operation history and preferences, and provides a guide to simplify the operation of the drone. This makes drones more comfortable for users of all ages. Systems using unmanned aerial vehicles can be equipped with features to further enhance the capabilities of the emotion engine. For example, sensors that measure the user's biosignals in real time can be incorporated to more accurately grasp changes in emotions from heart rate and electrical resistance of the skin. In addition, the accuracy of user emotion recognition can be improved by having the unmanned aerial vehicle's camera capture the user's facial expressions and having the emotion engine analyze the video data. Regarding the generation means of the control device, a multitasking function can be added that processes instructions from multiple users simultaneously and assigns appropriate operation programs to each unmanned aerial vehicle. This makes it possible to operate the unmanned aerial vehicle according to each user's request, even if multiple users have different requests at one event. In addition, it is possible to implement an environmental adaptation function that uses data from sensors possessed by the unmanned aerial vehicle to detect changes in the environment and automatically adjust the flight program. This allows the unmanned aerial vehicle to take appropriate actions more autonomously, for example, to avoid people at a crowded event or to select the optimal angle to photograph a particular landscape. Regarding communication, it is possible to build a network where drones can share information with each other, enabling them to move intelligently as a swarm. Drones can grasp each other's positions and status in real time, and cooperate to efficiently carry out multiple tasks. In addition, by flexibly changing the formation formed by drones according to user instructions, new applications such as visual art and advertising are expected. The emotion engine can also be equipped with an automatic music and lighting adjustment function according to the user's emotions. It can enhance the emotion-based experience via the drone by providing bright and active music and lighting when the user is feeling joyful, and calm music and lighting when the user is feeling calm. In addition, the drone can add a health monitoring function to support the user's health and wellness, providing regular health checks and relaxation activities. With these expansions, systems using unmanned aerial vehicles are expected to be used in a wide range of fields, not only for entertainment, but also for health management, improving personal wellness, emergency response, etc. In addition, improvements to the user interface will enable more people to intuitively operate unmanned aerial vehicles, and their convenience will be widely recognized.

[0077] The process flow of each embodiment will be described below.

[0078] (Example 1) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone will move, rotate, and perform other operations according to instructions. (Example 2) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program for the unmanned aircraft based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone will move, rotate, and perform other operations according to instructions. (Example 3) Step 1: The controller receives a natural language instruction. Step 2: Generate an operating program for the unmanned aircraft based on the instructions analyzed by the AI. Step 3: The emotion engine recognizes the user's emotions and reflects them in the operation of the drone. Step 4: Using the generated motion program and emotion engine, the drone performs operations such as moving and rotating according to the instructions. For example, if the user is happy, the drone will move more aggressively. Conversely, if the user is angry, the drone will move more cautiously.

[0079] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0080] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing while using the data generation model 58.

[0081] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314. [Fourth embodiment]

[0082] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0083] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0084] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a wide area network (WAN) and / or a local area network (LAN).

[0085] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0086] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0087] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0088] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0089] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0090] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0091] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0092] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0093] In the robot 414, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0094] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a ChatGPT server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, or a home appliance) owned by a user. Next, the identification process by the identification processing unit 290 of the data processing device 12 will be described.

[0095] (Example 1) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a communication means. The control device is equipped with a generation means that receives instructions in natural language, analyzes the instructions by the AI, and then generates an operation program for the unmanned aerial vehicle. The unmanned aerial vehicle performs operations such as movement and rotation according to the instructions based on the generated operation program. The communication means is a means for transmitting and receiving instructions and data between the control device and the unmanned aerial vehicle. The generation means is realized by the specific processing unit 290 of the data processing device 12, receives instructions in natural language, analyzes them by AI, and then generates an operation program for the unmanned aerial vehicle. The communication means is realized as a means for transmitting and receiving instructions and data between the control device and the unmanned aerial vehicle via the communication I / F 26 of the data processing device 12 and the communication I / F 44 of the robot 414. The correspondence between each means and the device or control unit is not limited to the above-mentioned example, and various modifications are possible. The generation means utilizes natural language processing technology to analyze instructions from a user and generate an operation program for the unmanned aerial vehicle. The generation means can also convert human oral or text input instructions into digital data using a voice recognition means and a text analysis means and interpret the contents of the digital data. This means includes a voice recognition function and converts the user's oral instructions into text data. The voice recognition means has a function of receiving the user's voice instructions and converting the voice data into text. The text analysis means performs morphological analysis and syntactic analysis to understand the contents of the instructions and grasp the intention. The text analysis means also performs morphological analysis and syntactic analysis to understand the meaning of the input text. The intention analysis means identifies the purpose or task behind the instructions, and the operation program generation means generates a specific operation program based on the analyzed intention. The intention analysis means can also identify specific tasks or purposes from instructions included in the text, and the operation program generation means can create an operation program based on the specified tasks or purposes. The operation program generation means utilizes a probabilistic algorithm or a machine learning model to develop an efficient and safe operation plan for the unmanned aerial vehicle. The operation program generating means can also define an operation sequence to be performed by the unmanned aerial vehicle and calculate the parameters required for that. The unmanned aerial vehicle automatically executes operations based on the generated operating program through the flight control means installed on the vehicle. The unmanned aerial vehicle also has a built-in flight control means, and can autonomously perform operations such as flying and rotating according to the generated operating program. The flight control means controls the attitude and position of the unmanned aerial vehicle in real time based on data from sensors and position information from GPS. The flight control means also functions by combining an attitude control function, a position control function, and a speed control function, which can also adjust the flight state of the unmanned aerial vehicle based on sensor data and GPS information. The obstacle detection means recognizes the surrounding environment, and the collision avoidance means calculates a route to avoid the obstacle. The obstacle detection means also detects surrounding obstacles using sensors such as radar and LiDAR, and the collision avoidance means can calculate an alternative route to avoid the detected obstacle, allowing the vehicle to fly safely. The communication means enables data transmission and reception between the control device and the unmanned aerial vehicle using wireless communication technology. The communication means can also transmit and receive data between the control device and the unmanned aerial vehicle using advanced wireless communication technology. The means include an encoding means for encoding and decoding signals and an error correction means for maintaining the reliability of communication. The encoding means efficiently encodes the data to be transmitted and decodes it at the receiving end to recover the meaning of the data. The error correction means detects and corrects data errors that may occur in the communication process to maintain the reliability of communication. The communication means employs a communication protocol with low latency and high bandwidth to quickly transmit and receive data on the operation program and operation status. The communication protocol can also be optimized to achieve low latency and high bandwidth and transmit the flight status, sensor data, and video feed of the unmanned aerial vehicle in real time. The control device can always grasp the status of the unmanned aerial vehicle and issue additional instructions as necessary. The unmanned aerial vehicle also transmits sensor data and video feeds during flight to the control device in real time for monitoring and analysis. The unmanned aerial vehicle can also transmit data during flight to a control device via communication means, allowing real-time monitoring by an operator and collection of data for later analysis. A variety of additional functions can be incorporated into control systems that utilize unmanned aerial vehicles. For example, an environmental monitoring function can be added to an unmanned aerial vehicle to precisely measure temperature, humidity, and atmospheric pressure from the air and collect meteorological data. In addition, in agricultural applications, it is effective to equip the vehicle with sensors that measure soil moisture and nutritional status to provide functions that support precision agriculture. Unmanned aerial vehicles can also be equipped with functions to support rescue operations. For example, in the event of a disaster, they can grasp the extent of damage to buildings and the locations of victims, and provide information to rescue teams. They can also be equipped with thermal cameras to detect smoke and fire conditions, which can be useful in directing and supporting firefighting operations. Furthermore, to improve their autonomous flight capabilities, swarm functions can be developed that use AI to allow unmanned aerial vehicles to share information with each other and cooperate as a swarm, making it possible to monitor a wider area and carry out multiple tasks simultaneously. In terms of communication, we will consider alternative means of communication such as satellite communication and laser communication to improve communication stability. This will enable us to maintain communication with unmanned aircraft even in remote areas or disaster areas where communication infrastructure has been destroyed. Furthermore, to operate unmanned aircraft more safely and efficiently, we will introduce a system that combines ground radar systems and communications with other aircraft to accurately grasp the position and status of unmanned aircraft in flight and assist in collision avoidance. Surveillance systems using unmanned aerial vehicles can incorporate advances in video analytics technology to identify objects and people from video in real time and analyze behavioral patterns. This will automate security and surveillance tasks, contributing to crime prevention and safety management. In addition, footage captured by unmanned aerial vehicles can be used for virtual reality and augmented reality to provide new experiences in education, training, tourism, and more. Finally, the control device will be equipped with a self-learning function to train machine learning models that utilize the drone's operational logs and sensor data to improve the drone's flight performance, allowing the drone to learn from past experience, select more effective flight routes, and perform tasks more efficiently. It is conceivable that generative AI installed in the control device can be used to automate tasks in other industrial fields. For example, agricultural tasks such as spraying pesticides and sowing seeds can be automated to reduce manual labor. Ultrasonic sensors and near-infrared cameras can be installed in the drones to help with crop growth and early detection of disease. In addition, a precision pesticide spraying system using drones can be developed to optimize the amount of pesticide used and reduce environmental impact. The AI ​​that generates the control device can be applied not only to unmanned aerial vehicles, but also to underwater robots and autonomous vehicles on land. By combining these different platforms, a monitoring network covering land, sea and air can be constructed, which is expected to be used in a wide range of fields such as environmental monitoring, resource exploration, and disaster response. In environmental monitoring using unmanned aerial vehicles, it is also effective to mount a composite gas sensor to monitor air pollution and measure greenhouse gases. In addition to disaster relief, the combination of the control device and unmanned aerial vehicles can also be used for rescue and search operations. Combining high-performance cameras with face recognition technology will help with searches for missing people and early detection of people in distress during coastal surveillance. A system will also be developed that will equip unmanned aerial vehicles with lifesaving kits and quickly drop rescue supplies to people in distress. The strengthening of communication methods will enable use in remote medical care, where real-time data is important, and emergency communications during disasters. By achieving high-resolution video transmission and low-latency communications, it will play a role as infrastructure for doctors to supervise surgery from remote locations and for establishing emergency communications from disaster sites. We will further evolve the AI ​​of the control device and develop algorithms that allow swarms of unmanned aerial vehicles to work together to carry out complex tasks. This will enable multiple unmanned aerial vehicles to share a large task and complete it efficiently. For example, this can be applied to transporting materials at construction sites and extinguishing fires. Ultimately, the combination of control device AI and unmanned aerial vehicles will contribute to the creation of smart cities, such as managing urban infrastructure, monitoring traffic flow, and ensuring public safety. Using real-time data provided by unmanned aerial vehicles, a system will be built to optimize city operations and respond quickly to disasters. Information collected by unmanned aerial vehicles will also be useful in formulating urban plans and transportation policies. This will support the development of sustainable and efficient cities. (Example 2) An embodiment of the present invention is a system including a control device equipped with a generation AI, a plurality of unmanned aerial vehicles, and a location information acquisition means. The control device receives instructions in natural language, analyzes the instructions using the AI, and then acquires location information of the unmanned aerial vehicles. The location information acquisition means is a means for identifying the location of the unmanned aerial vehicles using a GPS, a sensor, or the like. The control device includes a control means for controlling the unmanned aerial vehicles according to the instructions based on the acquired location information. The location information acquisition means is implemented in the robot 414 as a means for identifying the location of the unmanned aerial vehicle using, for example, a GPS or a sensor. The control means is realized by the specific processing unit 290 of the data processing device 12, and controls the unmanned aerial vehicle according to instructions based on the acquired location information. The correspondence between each means and the device or control unit is not limited to the above example, and various modifications are possible. The control device uses an analysis means including a natural language understanding module to analyze instructions from the user and grasp the intention. The control device also includes an instruction receiving means for receiving natural language instructions from the user and a natural language understanding module for analyzing the instructions. The natural language understanding module includes a voice-to-text conversion means for converting voice instructions into text data using voice recognition technology. The voice-to-text conversion function can convert the user's instructions into text information using a voice recognition algorithm. The voice-to-text conversion function includes language processing means such as tokenization, part-of-speech tagging, noun phrase analysis, verb phrase analysis, and dependency analysis for further analyzing the converted text data. The language processing function can also clearly grasp the intention of the instructions using a tokenization means, part-of-speech tagging means, syntactic analysis means, etc. This allows commands, parameters, conditions, etc. included in the user's instructions to be accurately identified. The analyzed instructions are interpreted by the generation AI as commands necessary for controlling the unmanned aerial vehicle and transmitted to the control unit of the unmanned aerial vehicle via a command generation means for generating a corresponding action command. This allows the user's intention to be interpreted as a command and generates an action command to be transmitted to the unmanned aerial vehicle. The location information acquisition means includes a composite location information processing means for tracking the exact location of the unmanned aerial vehicle. The location information acquisition means also includes a GPS module mounted on the unmanned aerial vehicle, which can acquire location information on the earth. This GPS module acquires latitude, longitude, and altitude information of any point on the earth. Furthermore, a GNSS analysis means for analyzing a GNSS (Global Navigation Satellite System) signal can provide higher accuracy and reliability of location information. The GNSS analysis means used in conjunction with this can also improve the accuracy of the position using signals from satellites. Meanwhile, an inertial measurement unit (IMU) such as an integrated acceleration sensor and gyroscope continuously tracks the attitude and movement of the unmanned aerial vehicle, and assists in acquiring stable location information even in an environment where the GPS signal is unstable. In addition, an IMU for detecting the movement of the unmanned aerial vehicle provides information based on inertia, and can maintain the accuracy of the location information even in a situation where the GPS signal is unstable. As an example that does not include a sensor, a communication-based location information acquisition means is considered, in which the unmanned aerial vehicle acquires its own location information by communicating with a beacon or a ground station. Another example of sensor-free location acquisition is a communication-based location acquisition method. In this method, the relative and absolute position is determined through signals transmitted from ground beacons and through communication with other unmanned aircraft. The beacon transmits radio waves of a specific frequency, which is received by a receiving module on the unmanned aircraft and serves as a reference point for calculating the location information. The unmanned aircraft can also calculate its own position based on the received signal. In such a system, the current position of the unmanned aircraft and adjustments to the flight path are exchanged in real time through communication with a ground station. The control means includes a flight path planning means for planning and adjusting the flight path of the unmanned aerial vehicle. The control means also includes a flight path planning function for planning and adjusting the flight path of the unmanned aerial vehicle. This incorporates a simulation means for simulating the operation of the unmanned aerial vehicle and calculating an optimal flight path, taking into account obstacles and safety constraints on the flight path. This function can also simulate the flight path using the simulation means and calculate the optimal path, taking into account obstacle avoidance means and safety constraints. Furthermore, it also includes an emergency avoidance means for quickly responding to an emergency that the unmanned aerial vehicle may encounter, and a group control means for cooperatively controlling multiple unmanned aerial vehicles. It also includes an emergency avoidance function for responding to an emergency, and a group control function for centrally controlling multiple unmanned aerial vehicles. The control device of this embodiment can incorporate an advanced obstacle detection system to improve flight capabilities in more complex environments. For example, a function is added that utilizes 3D mapping technology using a laser scanner or ultrasonic sensor to precisely recognize the surrounding environment during flight and quickly and autonomously respond to dynamically changing obstacles. In addition, by analyzing satellite images and geographic information system (GIS) data, it is possible to take into account terrain features and obstacle information in more detail in the flight plan, enabling advanced optimization of the flight path. In controlling a group of unmanned aerial vehicles, a coordinated flight algorithm based on swarm intelligence using AI can be introduced, allowing multiple unmanned aerial vehicles to work together efficiently. For example, when multiple unmanned aerial vehicles are dispersed to perform tasks in pesticide spraying or search and rescue operations, dynamic flight path adjustments are made to maximize the overall work efficiency. This allows unmanned aerial vehicles to share roles and cooperate according to individual situations. The control device's natural language understanding module will be equipped with a specialized dictionary and context analysis function to understand technical terms and industry-specific language used by users, improving its ability to accurately analyze instructions specialized for specific industries and applications and convert them into specific operation commands. In addition, to improve the unmanned aerial vehicle's environmental awareness, a function will be added to analyze social media and internet information in addition to sensor data to grasp people's activity patterns and the occurrence of events. In terms of location information acquisition means, it is possible to introduce a differential GPS (DGPS) system that provides more accurate location information by incorporating a network of ground reference stations that provide correction signals to the GPS module used by the unmanned aircraft. Furthermore, in order to enable operation and monitoring from remote locations, a real-time data link system using satellite communications can be incorporated, allowing the unmanned aircraft to be controlled from anywhere on Earth. By integrating these functions, unmanned aerial vehicles will be able to handle more complex missions and realize flexible and advanced operations tailored to user needs, providing advanced solutions using unmanned aerial vehicles in fields such as disaster relief, environmental monitoring, and security surveillance. The control device can be equipped with a context recognition function to interpret user instructions more precisely, allowing it to take the optimal action depending on different circumstances, even with the same command. It can also have a function to ask questions to the user in response to unclear instru...

Claims

1. A system for simultaneously controlling multiple unmanned aerial vehicles using a generating AI, the system including: a generating means for receiving instructions in natural language, analyzing them by the AI, and then generating an operating program for the unmanned aerial vehicles.

2. 2. The system of claim 1, An analysis means for analyzing natural language that is an instruction from a user; and an intent analysis means for identifying a purpose or task of the instruction, The system is characterized in that the generating means generates the operation program based on the analyzed intention.

3. 2. The system according to claim 1, wherein the unmanned aerial vehicle includes a flight control means for autonomously performing operations such as flying and rotating based on the operating program.

4. 2. The system of claim 1, wherein the unmanned aerial vehicle includes a collection means for measuring temperature, humidity, and atmospheric pressure from the air to collect meteorological data, and a sensor for measuring soil moisture and nutrient status.

5. 2. The system according to claim 1, wherein the plurality of unmanned aerial vehicles have a swarm function in which the unmanned aerial vehicles share information with each other and cooperate as a flock.

Images