System

Abstract

To provide a monitoring system for detecting danger and quickly coping with it.SOLUTION: The monitoring system includes a collection unit, an analysis unit, a control unit, a distribution unit, and a warning unit. The collection unit collects a video of a monitoring camera. The analysis unit analyzes the video collected by the collection unit and detects a danger. The control unit controls the autopilot drone based on the danger detected by the analysis unit. The distribution unit causes the drone controlled by the control unit to perform live distribution of video and audio of the site. The warning unit issues a warning or a call based on the image or the sound distributed by the distribution unit.SELECTED DRAWING: None

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 an instruction sentence related to a description of 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to quickly detect danger using surveillance camera footage and take appropriate action.

[0005] The system according to the embodiment aims to analyze images from a surveillance camera, detect danger, and respond quickly. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a control unit, a distribution unit, and a warning unit. The collection unit collects video footage from surveillance cameras. The analysis unit analyzes the video footage collected by the collection unit and detects danger. The control unit controls an autonomous drone based on the danger detected by the analysis unit. The distribution unit allows the drone controlled by the control unit to live-stream video footage and audio of the scene. The warning unit issues warnings and calls based on the video footage and audio streamed by the distribution unit. [Effects of the Invention]

[0007] The system according to the embodiment can analyze images from a surveillance camera, detect danger, and respond quickly. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 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. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 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. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 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 INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single 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).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] 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.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] 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.

[0020] 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 (for example, 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 indicating 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 indicating the user input.

[0021] 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., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. 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 process 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] 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 generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A surveillance system according to an embodiment of the present invention uses multimodal AI to analyze surveillance camera footage, detect danger, and respond quickly using drones. The surveillance system collects surveillance camera footage and uses multimodal AI to analyze it and detect danger. For example, it can detect violent acts and suspicious behavior. If danger is detected, an AI-powered, autonomous drone rushes to the scene. The drone is equipped with a camera and broadcasts live video and audio of the scene to relevant authorities. Furthermore, relevant authorities can issue warnings, appeals, and guidance through the drone's speaker. For example, a surveillance system collects video from surveillance cameras installed throughout the city. For example, cameras installed around major intersections and public facilities collect video. The collected video is then analyzed using multimodal AI. For example, it can detect violent acts from the video and screams and abnormal sounds from the audio. If danger is detected, an AI-powered, autonomous drone rushes to the scene. For example, the drone uses a location information system to calculate the shortest route and head to the scene. Drones are equipped with cameras and can broadcast live video and audio from the scene to relevant authorities. For example, relevant authorities can grasp the situation at the scene in real time. Furthermore, relevant authorities can issue warnings, calls, and guidance through the drone's speakers. For example, relevant authorities can use the drone to warn criminals and prevent them from escaping. At the scene of an accident, drones can also guide people to safety. This allows surveillance systems to improve city safety and reduce the occurrence of crime and accidents. Surveillance systems can improve city safety and reduce the occurrence of crime and accidents. For example, early detection of violent acts or suspicious behavior and rapid response can minimize damage. Drones can also be used to cover a wide area and conduct efficient surveillance. This improves the safety of the entire city and increases residents' sense of security.

[0029] A surveillance system according to an embodiment includes a collection unit, an analysis unit, a control unit, a distribution unit, and a warning unit. The collection unit collects surveillance camera footage. The surveillance camera footage includes, but is not limited to, footage of major intersections and areas around public facilities. The collection unit collects footage using, for example, surveillance cameras that cover a wide area. The collection unit can also provide footage in real time. For example, the collection unit collects footage from cameras installed at major intersections. The analysis unit analyzes the footage collected by the collection unit to detect danger. The analysis unit analyzes the footage using, for example, multimodal AI. For example, the analysis unit detects violent acts from the footage. The analysis unit can also detect screams or abnormal sounds from audio. For example, the analysis unit analyzes the video and audio to detect danger. The control unit controls an autonomous drone based on the danger detected by the analysis unit. For example, the control unit calculates the shortest route using the drone's positioning information system and heads to the scene. For example, the control unit controls the drone to move at high speed and arrive at the scene quickly. The distribution unit causes the drone controlled by the control unit to live-stream video and audio of the scene. For example, the distribution unit distributes video of the scene using a camera mounted on the drone. The distribution unit can also distribute audio of the scene using a microphone mounted on the drone. For example, the distribution unit enables related agencies to grasp the situation at the scene in real time. The warning unit issues warnings and calls based on the video and audio distributed by the distribution unit. For example, the warning unit issues warnings through a speaker on the drone. For example, the warning unit enables related agencies to warn the perpetrator through the drone and prevent him from escaping. The warning unit can also guide people at the scene of an accident to a safe place. For example, the warning unit calls on people to evacuate through the drone. As a result, the surveillance system according to the embodiment can improve the safety of cities and reduce the occurrence of crimes and accidents.

[0030] The collection unit can collect surveillance camera footage. The collection unit, for example, collects footage using surveillance cameras that cover a wide area. For example, the collection unit collects footage from cameras installed at major intersections. The collection unit can also provide footage in real time. For example, the collection unit collects footage from cameras installed around public facilities. In this way, by collecting surveillance camera footage, the situation in the entire city can be grasped. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input surveillance camera footage into AI and have the AI ​​collect the footage.

[0031] The analysis unit can analyze the collected video and detect danger. The analysis unit, for example, uses multimodal AI to analyze the video. For example, the analysis unit can detect violent acts from the video. The analysis unit can also detect screams or abnormal sounds from the audio. For example, the analysis unit can integrate and analyze video and audio to detect danger. In this way, by analyzing the collected video and detecting danger, it is possible to respond quickly. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the collected video into AI and have the AI ​​detect danger.

[0032] The control unit can control the autonomous drone based on the detected danger. For example, the control unit uses the drone's positioning information system to calculate the shortest route and head to the scene. For example, the control unit moves the drone at high speed to quickly arrive at the scene. This allows the autonomous drone to be controlled based on the detected danger, allowing for a rapid response to the scene. Some or all of the above-described processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input the drone's flight route into AI and have the AI ​​control the drone.

[0033] The distribution unit allows the drone to live-stream video and audio of the scene. For example, the distribution unit distributes video of the scene using a camera mounted on the drone. The distribution unit can also distribute audio of the scene using a microphone mounted on the drone. For example, the distribution unit enables related organizations to grasp the situation at the scene in real time. As a result, by having the drone live-stream video and audio of the scene, related organizations can grasp the situation in real time and respond quickly. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input video from the drone's camera into AI and have the AI ​​perform live streaming.

[0034] The warning unit can issue a warning or call based on the distributed video and audio. The warning unit issues a warning, for example, through the drone's speaker. For example, the warning unit allows relevant authorities to issue a warning to the perpetrator through the drone and prevent them from escaping. The warning unit can also guide people to a safe place at the scene of an accident. For example, the warning unit can call on people to evacuate through the drone. In this way, by issuing warnings and calls based on the distributed video and audio, crimes and accidents can be prevented before they occur. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the drone's speaker into AI and have the AI ​​issue the warning.

[0035] The collection unit can dynamically change the installation locations of the surveillance cameras to ensure an optimal surveillance range. For example, the collection unit can move the cameras to areas with a high flow of people to expand the surveillance range. The collection unit can also install cameras around an event venue when an event is held. The collection unit can also move cameras to areas where crimes are frequent at night. In this way, the installation locations of the surveillance cameras can be dynamically changed to ensure an optimal surveillance range. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input changes in the installation locations of the surveillance cameras into AI and have the AI ​​optimize the installation locations.

[0036] The collection unit can start collecting video from a surveillance camera when a specific event is triggered. For example, the collection unit can start collecting video when a crowd-gathering event occurs. The collection unit can also start collecting video when a traffic accident occurs. The collection unit can also start collecting video when suspicious movement is detected. In this way, by starting video collection when a specific event is triggered, it is possible to monitor without missing important moments. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input a specific event into AI and have the AI ​​execute a trigger to collect video.

[0037] When collecting video from a surveillance camera, the collection unit can automatically adjust the camera settings according to the weather and time of day. For example, the collection unit collects video using an infrared camera at night. The collection unit can also collect video using a waterproof camera when it is raining. The collection unit can also collect video using a high-resolution camera during the day. This allows the camera settings to be automatically adjusted according to the weather and time of day, making it possible to always collect optimal video. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the weather and time of day into AI and automatically adjust the camera settings.

[0038] When collecting video from a surveillance camera, the collection unit can also use an audio sensor to detect abnormal sounds and strengthen video collection. For example, the collection unit can strengthen video collection when an abnormal sound (e.g., a scream) is detected. The collection unit can also strengthen video collection when the sound of glass breaking is detected. The collection unit can also strengthen video collection when a gunshot is detected. In this way, by also using an audio sensor to detect abnormal sounds, it is possible to quickly grasp abnormal situations and strengthen video collection. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data from the audio sensor into AI and have the AI ​​detect abnormal sounds.

[0039] The collection unit can cover a wide area by auxiliary use of a drone camera when collecting video from a surveillance camera. For example, the collection unit uses a drone to collect video from a wide area. The collection unit can also use a drone to collect video from a high place. The collection unit can also use a drone to collect video of blind spots. In this way, by auxiliary use of the drone camera, a wide area can be covered and blind spots can be reduced. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input video from the drone camera into AI and have the AI ​​collect video from a wide area.

[0040] When collecting surveillance camera footage, the collection unit can prioritize monitoring of high-risk areas by referring to past crime data. For example, the collection unit prioritizes monitoring of areas where crimes have frequently occurred in the past. The collection unit can also identify high-risk areas based on past crime data and strengthen surveillance. The collection unit can also analyze past crime data and strengthen surveillance during times when crimes are likely to occur. In this way, by prioritizing monitoring of high-risk areas by referring to past crime data, it is possible to prevent crimes from occurring. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, AI, for example. For example, the collection unit can input past crime data into AI and have the AI ​​identify high-risk areas.

[0041] During analysis, the analysis unit can integrate video and audio data to perform more accurate danger detection. For example, the analysis unit can integrate video data and audio data to detect violent acts. The analysis unit can also integrate video data and audio data to detect suspicious movements. The analysis unit can also integrate video data and audio data to detect abnormal sounds. In this way, by integrating video and audio data, more accurate danger detection becomes possible. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input video data and audio data into AI and have the AI ​​perform data integration and danger detection.

[0042] During analysis, the analysis unit can optimize the analysis algorithm by referring to past analysis data. The analysis unit, for example, optimizes the analysis algorithm based on past analysis data. The analysis unit can also analyze past analysis data to improve analysis accuracy. The analysis unit can also improve the accuracy of anomaly detection by referring to past analysis data. In this way, by referring to past analysis data, the analysis algorithm can be optimized and the analysis accuracy can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis data into AI and have the AI ​​optimize the analysis algorithm.

[0043] The analysis unit can learn abnormal behavior patterns in real time during analysis, thereby improving the accuracy of the analysis. For example, the analysis unit can learn abnormal behavior patterns in real time, thereby improving the accuracy of the analysis. The analysis unit can also detect danger based on the abnormal behavior patterns learned in real time. The analysis unit can also reflect the abnormal behavior patterns learned in real time in the analysis algorithm. In this way, by learning abnormal behavior patterns in real time, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input abnormal behavior patterns into AI and have the AI ​​learn in real time and improve the accuracy of the analysis.

[0044] During analysis, the analysis unit can improve the accuracy of the analysis by combining detection of abnormal sounds from the audio data. For example, the analysis unit detects abnormal sounds from the audio data to improve the accuracy of the analysis. The analysis unit can also detect screams from the audio data to improve the accuracy of the analysis. The analysis unit can also detect gunshots from the audio data to improve the accuracy of the analysis. In this way, by combining detection of abnormal sounds from the audio data, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the audio data into AI and have the AI ​​detect abnormal sounds and improve the accuracy of the analysis.

[0045] During analysis, the analysis unit can perform anomaly detection by combining data from a temperature sensor and a vibration sensor. For example, the analysis unit can detect fires by combining data from a temperature sensor. The analysis unit can also detect earthquakes by combining data from a vibration sensor. The analysis unit can also detect abnormal situations by combining data from a temperature sensor and a vibration sensor. In this way, by combining data from a temperature sensor and a vibration sensor, the accuracy of anomaly detection can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data from a temperature sensor and a vibration sensor to AI and have the AI ​​perform anomaly detection.

[0046] During analysis, the analysis unit can visualize the analysis results on a map, allowing the user to intuitively grasp dangerous areas. The analysis unit, for example, displays the analysis results on a map, allowing the user to intuitively grasp dangerous areas. The analysis unit can also visualize the analysis results on a map and identify dangerous areas. The analysis unit can also display the analysis results on a map and grasp the extent of dangerous areas. In this way, by visualizing the analysis results on a map, the user can intuitively grasp dangerous areas. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data for displaying the analysis results on a map to AI and have the AI ​​perform the visualization.

[0047] The control unit can add a function to automatically avoid obstacles during drone flight. For example, the control unit detects obstacles while the drone is flying and automatically avoids them. The control unit can also detect buildings while the drone is flying and automatically avoid them. The control unit can also detect trees while the drone is flying and automatically avoid them. This allows the drone to automatically avoid obstacles during flight, thereby ensuring safe flight. Some or all of the above-mentioned processing in the control unit may be performed using, or without, AI, for example. For example, the control unit can input obstacle data into AI and have the AI ​​execute obstacle avoidance control.

[0048] The control unit can automatically adjust flight parameters during drone flight, taking into account wind speed and weather conditions. For example, when wind speed is strong, the control unit adjusts the flight parameters to ensure stable flight. The control unit can also activate the waterproof function to fly in rainy weather. The control unit can also adjust the flight parameters to ensure safe flight on snowy days. This allows for stable flight by automatically adjusting flight parameters taking into account wind speed and weather conditions. Some or all of the above-described processing in the control unit may be performed using AI, for example, or may be performed without using AI. For example, the control unit can input data on wind speed and weather conditions into AI and have the AI ​​adjust the flight parameters.

[0049] The control unit can cooperatively control multiple drones during drone flight to efficiently monitor a wide area. For example, the control unit can cooperatively control multiple drones to efficiently monitor a wide area. The control unit can also cooperatively control multiple drones to eliminate blind spots and perform monitoring. The control unit can also cooperatively control multiple drones to arrive at the scene quickly. This allows for efficient monitoring of a wide area by cooperatively controlling multiple drones. Some or all of the above-described processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input data from multiple drones into AI and have the AI ​​perform cooperative control.

[0050] The control unit can calculate the optimal flight route using a geographic information system (GIS) when flying the drone. The control unit, for example, uses the GIS to calculate the shortest route and flies the drone. The control unit can also use the GIS to calculate the optimal route that avoids obstacles. The control unit can also use the GIS to calculate the optimal route that takes weather conditions into consideration. This enables efficient flight by calculating the optimal flight route using the geographic information system. Some or all of the above-mentioned processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input GIS data into AI and have the AI ​​calculate the optimal flight route.

[0051] The control unit can optimize the flight plan by taking into account the remaining battery level when flying the drone. For example, when the remaining battery level is low, the control unit heads to the site via the shortest route. The control unit can also set a charging point along the way by taking into account the remaining battery level. Furthermore, when the remaining battery level is sufficient, the control unit can head to the site using a normal flight plan. This enables efficient flight by optimizing the flight plan by taking into account the remaining battery level. Some or all of the above-described processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input remaining battery level data into AI and have the AI ​​optimize the flight plan.

[0052] The control unit can cooperate with other monitoring systems to share information and perform comprehensive monitoring when the drone is flying. For example, the control unit cooperates with other monitoring systems to share information and perform comprehensive monitoring. The control unit can also adjust the drone's flight route based on information from other monitoring systems. The control unit can also cooperate with other monitoring systems to perform efficient monitoring. This enables comprehensive monitoring by cooperating with other monitoring systems and sharing information. Some or all of the above-mentioned processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input data from other monitoring systems into AI and have the AI ​​share information and adjust monitoring.

[0053] The distribution unit can synchronize video and audio during live streaming. For example, the distribution unit synchronizes video and audio in real time to perform live streaming. The distribution unit can also perform live streaming while minimizing delay between video and audio. The distribution unit can also automatically adjust the synchronization between video and audio to perform live streaming. This allows for synchronized video and audio distribution, thereby providing more accurate information to viewers. Some or all of the above-described processing in the distribution unit may be performed using, or without, AI, for example. For example, the distribution unit can input video and audio data into AI and have the AI ​​adjust the synchronization.

[0054] During live streaming, the streaming unit can simultaneously stream footage from multiple cameras, allowing viewers to freely switch between them. For example, the streaming unit can simultaneously stream footage from multiple cameras, allowing viewers to freely switch between them. The streaming unit can also enable viewers to simultaneously watch footage from multiple cameras. The streaming unit can also minimize video delays when viewers switch between camera footage. This allows viewers to freely switch perspectives by simultaneously streaming footage from multiple cameras. Some or all of the above-described processing in the streaming unit may be performed using, or without, AI, for example. For example, the streaming unit can input data from multiple camera footage into AI and have the AI ​​adjust the simultaneous streaming and switching.

[0055] The distribution unit can automatically save the distribution data during live distribution so that it can be analyzed later. For example, the distribution unit can automatically save the live distribution data so that it can be analyzed later. The distribution unit can also analyze the saved distribution data and extract important information. The distribution unit can also perform detailed analysis later based on the saved distribution data. In this way, by automatically saving the distribution data, detailed analysis can be performed later. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input the distribution data into AI and have the AI ​​perform automatic saving and analysis.

[0056] During live streaming, the distribution unit can receive feedback from viewers in real time and adjust the content of the stream. For example, the distribution unit can receive feedback from viewers in real time and adjust the content of the stream. The distribution unit can also optimize the content of the stream based on the viewer feedback. The distribution unit can also analyze the viewer feedback and improve the content of the stream. In this way, the content of the stream can be optimized by receiving feedback from viewers in real time. Some or all of the above-described processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input viewer feedback data into AI and have the AI ​​receive the data in real time and adjust the content of the stream.

[0057] The distribution unit can add annotations to video in real time during live streaming to emphasize important information. For example, the distribution unit can add annotations to live streaming video in real time to emphasize important information. The distribution unit can also minimize video delay when adding annotations. The distribution unit can also allow viewers to freely display or hide annotations when adding annotations. In this way, adding annotations to video in real time can emphasize and convey important information to viewers. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input annotation data to AI and have the AI ​​add annotations in real time.

[0058] The distribution unit can enhance security by encrypting distribution data during live distribution. For example, the distribution unit encrypts live distribution data to enhance security. The distribution unit can also minimize delays when decrypting encrypted distribution data. The distribution unit can also automatically encrypt and decrypt distribution data to ensure security. In this way, encrypting distribution data enhances security and prevents unauthorized access to data. Some or all of the above-described processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input distribution data to AI and have the AI ​​perform encryption and decryption.

[0059] The warning unit can issue a warning by both voice and text when issuing a warning. For example, the warning unit can issue a warning by both voice and text, thereby communicating the warning both visually and audibly. The warning unit can also automatically adjust the synchronization between voice and text when issuing a warning. The warning unit can also simultaneously issue a warning by voice and text, thereby enhancing the effectiveness of the warning. In this way, by issuing a warning by both voice and text, the warning can be communicated both visually and audibly. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input voice and text data into AI and have the AI ​​adjust the synchronization and issue the warning.

[0060] When issuing a warning, the warning unit can make the warning message multilingual and issue the warning in different languages. For example, the warning unit can make the warning message multilingual and issue the warning in different languages. The warning unit can also automatically translate the warning message based on the user's language setting. The warning unit can also issue the warning message in multiple languages ​​to accommodate users who speak different languages. In this way, by making the warning message multilingual, it is possible to accommodate users who speak different languages. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input data of the warning message into AI and have the AI ​​perform multilingual support and translation.

[0061] The warning unit can adjust the frequency of issuing a warning message depending on the situation when issuing a warning. For example, in the case of an emergency, the warning unit can increase the frequency of issuing a warning message. The warning unit can also return the frequency of issuing a warning message to normal under normal circumstances. The warning unit can also automatically adjust the frequency of issuing a warning message depending on the situation. In this way, by adjusting the frequency of issuing a warning message depending on the situation, a more effective warning can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input situation data into AI and have the AI ​​adjust the frequency of issuing the warning message.

[0062] The warning unit visually displays a warning message when issuing a warning, making it possible to accommodate hearing-impaired persons. The warning unit, for example, visually displays a warning message to accommodate hearing-impaired persons. The warning unit can also employ a design that enhances visibility when displaying a visual warning message. The warning unit can also emphasize important information when displaying a visual warning message. In this way, by visually displaying the warning message, it is possible to convey the warning to hearing-impaired persons as well. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input data of the visual warning message into AI and have the AI ​​perform the display and emphasis.

[0063] When issuing a warning, the warning unit can notify relevant organizations of the warning message via social media or email. The warning unit can, for example, notify relevant organizations of the warning message via social media or email, encouraging them to take prompt action. The warning unit can also emphasize important information when notifying via social media or email. The warning unit can also minimize notification delays when notifying via social media or email. This makes it possible to notify relevant organizations of the warning message via social media or email, encouraging them to take prompt action. Some or all of the above-mentioned processing in the warning unit can be performed, for example, using AI, or can be performed without using AI. For example, the warning unit can input warning message data into AI and have the AI ​​execute notification via social media or email.

[0064] The warning unit can optimize the content of the warning message based on past cases when issuing a warning. The warning unit can optimize the content of the warning message based on past cases, for example. The warning unit can also analyze past cases to improve the effectiveness of the warning message. The warning unit can also refer to past cases to improve the content of the warning message. In this way, by optimizing the content of the warning message based on past cases, a more effective warning can be provided. Some or all of the above-mentioned processing in the warning unit can be performed using, for example, AI, or can be performed without using AI. For example, the warning unit can input past case data into AI and have the AI ​​optimize the warning message.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The collection unit can add a function to track a specific person when collecting video from a surveillance camera. For example, the collection unit can automatically track a specific person when that person enters the field of view of a surveillance camera. The collection unit can also continue tracking a specific person as they move by coordinating across multiple cameras. Furthermore, the collection unit can record the behavior of a specific person in real time and analyze it later. This allows for more detailed monitoring by tracking specific people.

[0067] The control unit can collect ambient sounds while the drone is flying and optimize the flight route. For example, the control unit can estimate traffic volume from the ambient sounds and select a route that avoids congested areas. The control unit can also detect changes in the weather from the ambient sounds and select a safe route. Furthermore, the control unit can detect an emergency from the ambient sounds and rush to the scene via the shortest route. This allows for safer and more efficient flight by optimizing the flight route using ambient sounds.

[0068] When issuing a warning message, the warning unit can select the optimal warning means taking into account the user's location information. For example, when the user is indoors, the warning unit prioritizes audio warnings. When the user is outdoors, the warning unit can also prioritize visual warning messages. Furthermore, when the user is moving, the warning unit can also issue warnings using means such as vibration or flashing lights. This allows for more effective warnings to be provided by selecting the optimal warning means according to the user's location information.

[0069] The collection unit can detect specific objects when collecting video from a surveillance camera and collect information about the objects. For example, the collection unit can detect a vehicle's license plate and obtain the vehicle's registration information. The collection unit can also detect a specific brand logo and obtain information about the brand. Furthermore, the collection unit can detect a specific product's barcode and obtain detailed information about the product. This allows for more detailed monitoring by detecting specific objects and collecting information about the objects.

[0070] When a drone flies, the control unit can communicate with other drones and cooperate to optimize the flight route. For example, when multiple drones are monitoring the same area, the control unit can adjust the flight route to avoid overlapping. In addition, when multiple drones are monitoring different areas, the control unit can also adjust the flight route to efficiently cover the area. Furthermore, when multiple drones are responding to an emergency, the control unit can calculate the optimal placement and respond quickly. This allows for more efficient monitoring by communicating with other drones and cooperating to optimize the flight route.

[0071] When issuing a warning message, the warning unit can determine the optimal warning content by referring to the user's past behavior history. For example, if the user has previously felt unsafe in a specific area, the warning unit can provide a detailed warning about that area. Also, if the user has previously felt uneasy in a specific situation, the warning unit can provide a warning including specific countermeasures for that situation. Furthermore, if the user has previously taken a specific action, the warning unit can provide an appropriate warning based on that action. In this way, by determining the optimal warning content by referring to the user's past behavior history, more effective warnings can be provided.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The collection unit collects surveillance camera footage. The surveillance camera footage includes footage of major intersections and areas around public facilities. The collection unit collects footage using surveillance cameras that cover a wide area and can provide the footage in real time. Step 2: The analysis unit analyzes the video collected by the collection unit and detects danger. The analysis unit uses multimodal AI to analyze the video and detect, for example, violent acts, screams, and abnormal sounds. It can also analyze video and audio together. Step 3: The control unit controls the autonomous drone based on the danger detected by the analysis unit. The control unit uses the drone's positioning information system to calculate the shortest route to the scene, and moves the drone at high speed to arrive at the scene quickly. Step 4: The broadcasting unit, under the control of the control unit, broadcasts live video and audio from the scene using the drone's on-board camera and microphone, allowing related agencies to grasp the situation on-site in real time. Step 5: The warning unit issues a warning or calls based on the video and audio delivered by the distribution unit. The warning unit issues a warning through the drone's speaker, for example, to warn the perpetrator and prevent them from escaping. It also calls for evacuation to guide people to a safe place at the accident site.

[0074] (Example 2) A surveillance system according to an embodiment of the present invention uses multimodal AI to analyze surveillance camera footage, detect danger, and respond quickly using drones. The surveillance system collects surveillance camera footage and uses multimodal AI to analyze it and detect danger. For example, it can detect violent acts and suspicious behavior. If danger is detected, an AI-powered, autonomous drone rushes to the scene. The drone is equipped with a camera and broadcasts live video and audio of the scene to relevant authorities. Furthermore, relevant authorities can issue warnings, appeals, and guidance through the drone's speaker. For example, a surveillance system collects video from surveillance cameras installed throughout the city. For example, cameras installed around major intersections and public facilities collect video. The collected video is then analyzed using multimodal AI. For example, it can detect violent acts from the video and screams and abnormal sounds from the audio. If danger is detected, an AI-powered, autonomous drone rushes to the scene. For example, the drone uses a location information system to calculate the shortest route and head to the scene. Drones are equipped with cameras and can broadcast live video and audio from the scene to relevant authorities. For example, relevant authorities can grasp the situation at the scene in real time. Furthermore, relevant authorities can issue warnings, calls, and guidance through the drone's speakers. For example, relevant authorities can use the drone to warn criminals and prevent them from escaping. At the scene of an accident, drones can also guide people to safety. This allows surveillance systems to improve city safety and reduce the occurrence of crime and accidents. Surveillance systems can improve city safety and reduce the occurrence of crime and accidents. For example, early detection of violent acts or suspicious behavior and rapid response can minimize damage. Drones can also be used to cover a wide area and conduct efficient surveillance. This improves the safety of the entire city and increases residents' sense of security.

[0075] A surveillance system according to an embodiment includes a collection unit, an analysis unit, a control unit, a distribution unit, and a warning unit. The collection unit collects surveillance camera footage. The surveillance camera footage includes, but is not limited to, footage of major intersections and areas around public facilities. The collection unit collects footage using, for example, surveillance cameras that cover a wide area. The collection unit can also provide footage in real time. For example, the collection unit collects footage from cameras installed at major intersections. The analysis unit analyzes the footage collected by the collection unit to detect danger. The analysis unit analyzes the footage using, for example, multimodal AI. For example, the analysis unit detects violent acts from the footage. The analysis unit can also detect screams or abnormal sounds from audio. For example, the analysis unit analyzes the video and audio to detect danger. The control unit controls an autonomous drone based on the danger detected by the analysis unit. For example, the control unit calculates the shortest route using the drone's positioning information system and heads to the scene. For example, the control unit controls the drone to move at high speed and arrive at the scene quickly. The distribution unit causes the drone controlled by the control unit to live-stream video and audio of the scene. For example, the distribution unit distributes video of the scene using a camera mounted on the drone. The distribution unit can also distribute audio of the scene using a microphone mounted on the drone. For example, the distribution unit enables related agencies to grasp the situation at the scene in real time. The warning unit issues warnings and calls based on the video and audio distributed by the distribution unit. For example, the warning unit issues warnings through a speaker on the drone. For example, the warning unit enables related agencies to warn the perpetrator through the drone and prevent him from escaping. The warning unit can also guide people at the scene of an accident to a safe place. For example, the warning unit calls on people to evacuate through the drone. As a result, the surveillance system according to the embodiment can improve the safety of cities and reduce the occurrence of crimes and accidents.

[0076] The collection unit can collect surveillance camera footage. The collection unit, for example, collects footage using surveillance cameras that cover a wide area. For example, the collection unit collects footage from cameras installed at major intersections. The collection unit can also provide footage in real time. For example, the collection unit collects footage from cameras installed around public facilities. In this way, by collecting surveillance camera footage, the situation in the entire city can be grasped. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input surveillance camera footage into AI and have the AI ​​collect the footage.

[0077] The analysis unit can analyze the collected video and detect danger. The analysis unit, for example, uses multimodal AI to analyze the video. For example, the analysis unit can detect violent acts from the video. The analysis unit can also detect screams or abnormal sounds from the audio. For example, the analysis unit can integrate and analyze video and audio to detect danger. In this way, by analyzing the collected video and detecting danger, it is possible to respond quickly. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the collected video into AI and have the AI ​​detect danger.

[0078] The control unit can control the autonomous drone based on the detected danger. For example, the control unit uses the drone's positioning information system to calculate the shortest route and head to the scene. For example, the control unit moves the drone at high speed to quickly arrive at the scene. This allows the autonomous drone to be controlled based on the detected danger, allowing for a rapid response to the scene. Some or all of the above-described processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input the drone's flight route into AI and have the AI ​​control the drone.

[0079] The distribution unit allows the drone to live-stream video and audio of the scene. For example, the distribution unit distributes video of the scene using a camera mounted on the drone. The distribution unit can also distribute audio of the scene using a microphone mounted on the drone. For example, the distribution unit enables related organizations to grasp the situation at the scene in real time. As a result, by having the drone live-stream video and audio of the scene, related organizations can grasp the situation in real time and respond quickly. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input video from the drone's camera into AI and have the AI ​​perform live streaming.

[0080] The warning unit can issue a warning or call based on the distributed video and audio. The warning unit issues a warning, for example, through the drone's speaker. For example, the warning unit allows relevant authorities to issue a warning to the perpetrator through the drone and prevent them from escaping. The warning unit can also guide people to a safe place at the scene of an accident. For example, the warning unit can call on people to evacuate through the drone. In this way, by issuing warnings and calls based on the distributed video and audio, crimes and accidents can be prevented before they occur. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input the drone's speaker into AI and have the AI ​​issue the warning.

[0081] The collection unit can estimate the user's emotions and adjust the timing of video collection by the surveillance camera based on the estimated user emotions. For example, if the user feels anxious, the collection unit can increase the frequency of video collection by the surveillance camera. Furthermore, if the user feels relaxed, the collection unit can also return the frequency of video collection to normal. Furthermore, if the user feels an emergency, the collection unit can immediately start video collection. This enables more appropriate monitoring by adjusting the video collection timing according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0082] The collection unit can dynamically change the installation locations of the surveillance cameras to ensure an optimal surveillance range. For example, the collection unit can move the cameras to areas with a high flow of people to expand the surveillance range. The collection unit can also install cameras around an event venue when an event is held. The collection unit can also move cameras to areas where crimes are frequent at night. In this way, the installation locations of the surveillance cameras can be dynamically changed to ensure an optimal surveillance range. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input changes in the installation locations of the surveillance cameras into AI and have the AI ​​optimize the installation locations.

[0083] The collection unit can start collecting video from a surveillance camera when a specific event is triggered. For example, the collection unit can start collecting video when a crowd-gathering event occurs. The collection unit can also start collecting video when a traffic accident occurs. The collection unit can also start collecting video when suspicious movement is detected. In this way, by starting video collection when a specific event is triggered, it is possible to monitor without missing important moments. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input a specific event into AI and have the AI ​​execute a trigger to collect video.

[0084] When collecting video from a surveillance camera, the collection unit can automatically adjust the camera settings according to the weather and time of day. For example, the collection unit collects video using an infrared camera at night. The collection unit can also collect video using a waterproof camera when it is raining. The collection unit can also collect video using a high-resolution camera during the day. This allows the camera settings to be automatically adjusted according to the weather and time of day, making it possible to always collect optimal video. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data on the weather and time of day into AI and automatically adjust the camera settings.

[0085] The collection unit can estimate the user's emotions and determine the priority of the videos to be collected based on the estimated user emotions. For example, if the user is feeling anxious, the collection unit can prioritize collecting videos of important areas. Furthermore, if the user is relaxed, the collection unit can also collect videos of normal areas. Furthermore, if the user is feeling an emergency, the collection unit can also prioritize collecting videos of dangerous areas. This allows for enhanced monitoring of important areas by determining the priority of the videos to be collected according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0086] When collecting video from a surveillance camera, the collection unit can also use an audio sensor to detect abnormal sounds and strengthen video collection. For example, the collection unit can strengthen video collection when an abnormal sound (e.g., a scream) is detected. The collection unit can also strengthen video collection when the sound of glass breaking is detected. The collection unit can also strengthen video collection when a gunshot is detected. In this way, by also using an audio sensor to detect abnormal sounds, it is possible to quickly grasp abnormal situations and strengthen video collection. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input data from the audio sensor into AI and have the AI ​​detect abnormal sounds.

[0087] The collection unit can cover a wide area by auxiliary use of a drone camera when collecting video from a surveillance camera. For example, the collection unit uses a drone to collect video from a wide area. The collection unit can also use a drone to collect video from a high place. The collection unit can also use a drone to collect video of blind spots. In this way, by auxiliary use of the drone camera, a wide area can be covered and blind spots can be reduced. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input video from the drone camera into AI and have the AI ​​collect video from a wide area.

[0088] When collecting surveillance camera footage, the collection unit can prioritize monitoring of high-risk areas by referring to past crime data. For example, the collection unit prioritizes monitoring of areas where crimes have frequently occurred in the past. The collection unit can also identify high-risk areas based on past crime data and strengthen surveillance. The collection unit can also analyze past crime data and strengthen surveillance during times when crimes are likely to occur. In this way, by prioritizing monitoring of high-risk areas by referring to past crime data, it is possible to prevent crimes from occurring. Some or all of the above-mentioned processing in the collection unit may be performed using, or without, AI, for example. For example, the collection unit can input past crime data into AI and have the AI ​​identify high-risk areas.

[0089] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This allows for more appropriate information provision by adjusting the display method of the analysis results according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0090] During analysis, the analysis unit can integrate video and audio data to perform more accurate danger detection. For example, the analysis unit can integrate video data and audio data to detect violent acts. The analysis unit can also integrate video data and audio data to detect suspicious movements. The analysis unit can also integrate video data and audio data to detect abnormal sounds. In this way, by integrating video and audio data, more accurate danger detection becomes possible. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input video data and audio data into AI and have the AI ​​perform data integration and danger detection.

[0091] During analysis, the analysis unit can optimize the analysis algorithm by referring to past analysis data. The analysis unit, for example, optimizes the analysis algorithm based on past analysis data. The analysis unit can also analyze past analysis data to improve analysis accuracy. The analysis unit can also improve the accuracy of anomaly detection by referring to past analysis data. In this way, by referring to past analysis data, the analysis algorithm can be optimized and the analysis accuracy can be improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past analysis data into AI and have the AI ​​optimize the analysis algorithm.

[0092] The analysis unit can learn abnormal behavior patterns in real time during analysis, thereby improving the accuracy of the analysis. For example, the analysis unit can learn abnormal behavior patterns in real time, thereby improving the accuracy of the analysis. The analysis unit can also detect danger based on the abnormal behavior patterns learned in real time. The analysis unit can also reflect the abnormal behavior patterns learned in real time in the analysis algorithm. In this way, by learning abnormal behavior patterns in real time, the accuracy of the analysis can be improved. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input abnormal behavior patterns into AI and have the AI ​​learn in real time and improve the accuracy of the analysis.

[0093] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated user emotions. For example, if the user is feeling anxious, the analysis unit can prioritize displaying important analysis results. Furthermore, if the user is relaxed, the analysis unit can also display normal analysis results. Furthermore, if the user is feeling an emergency, the analysis unit can also prioritize displaying dangerous analysis results. This allows important information to be provided quickly by prioritizing the analysis results according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0094] During analysis, the analysis unit can improve the accuracy of the analysis by combining detection of abnormal sounds from the audio data. For example, the analysis unit detects abnormal sounds from the audio data to improve the accuracy of the analysis. The analysis unit can also detect screams from the audio data to improve the accuracy of the analysis. The analysis unit can also detect gunshots from the audio data to improve the accuracy of the analysis. In this way, by combining detection of abnormal sounds from the audio data, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the audio data into AI and have the AI ​​detect abnormal sounds and improve the accuracy of the analysis.

[0095] During analysis, the analysis unit can perform anomaly detection by combining data from a temperature sensor and a vibration sensor. For example, the analysis unit can detect fires by combining data from a temperature sensor. The analysis unit can also detect earthquakes by combining data from a vibration sensor. The analysis unit can also detect abnormal situations by combining data from a temperature sensor and a vibration sensor. In this way, by combining data from a temperature sensor and a vibration sensor, the accuracy of anomaly detection can be improved. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data from a temperature sensor and a vibration sensor to AI and have the AI ​​perform anomaly detection.

[0096] During analysis, the analysis unit can visualize the analysis results on a map, allowing the user to intuitively grasp dangerous areas. The analysis unit, for example, displays the analysis results on a map, allowing the user to intuitively grasp dangerous areas. The analysis unit can also visualize the analysis results on a map and identify dangerous areas. The analysis unit can also display the analysis results on a map and grasp the extent of dangerous areas. In this way, by visualizing the analysis results on a map, the user can intuitively grasp dangerous areas. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data for displaying the analysis results on a map to AI and have the AI ​​perform the visualization.

[0097] The control unit can estimate the user's emotions and adjust the drone's flight route based on the estimated user's emotions. For example, if the user is feeling anxious, the control unit can rush to the scene via the shortest route. Alternatively, if the user is relaxed, the control unit can also head to the scene via a normal route. Alternatively, if the user feels an emergency, the control unit can also rush to the scene via the fastest route. This allows for a faster and more appropriate response by adjusting the drone's flight route according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0098] The control unit can add a function to automatically avoid obstacles during drone flight. For example, the control unit detects obstacles while the drone is flying and automatically avoids them. The control unit can also detect buildings while the drone is flying and automatically avoid them. The control unit can also detect trees while the drone is flying and automatically avoid them. This allows the drone to automatically avoid obstacles during flight, thereby ensuring safe flight. Some or all of the above-mentioned processing in the control unit may be performed using, or without, AI, for example. For example, the control unit can input obstacle data into AI and have the AI ​​execute obstacle avoidance control.

[0099] The control unit can automatically adjust flight parameters during drone flight, taking into account wind speed and weather conditions. For example, when wind speed is strong, the control unit adjusts the flight parameters to ensure stable flight. The control unit can also activate the waterproof function to fly in rainy weather. The control unit can also adjust the flight parameters to ensure safe flight on snowy days. This allows for stable flight by automatically adjusting flight parameters taking into account wind speed and weather conditions. Some or all of the above-described processing in the control unit may be performed using AI, for example, or may be performed without using AI. For example, the control unit can input data on wind speed and weather conditions into AI and have the AI ​​adjust the flight parameters.

[0100] The control unit can cooperatively control multiple drones during drone flight to efficiently monitor a wide area. For example, the control unit can cooperatively control multiple drones to efficiently monitor a wide area. The control unit can also cooperatively control multiple drones to eliminate blind spots and perform monitoring. The control unit can also cooperatively control multiple drones to arrive at the scene quickly. This allows for efficient monitoring of a wide area by cooperatively controlling multiple drones. Some or all of the above-described processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input data from multiple drones into AI and have the AI ​​perform cooperative control.

[0101] The control unit can estimate the user's emotions and adjust the drone's flight speed based on the estimated user's emotions. For example, if the user feels anxious, the control unit can increase the flight speed and rush to the scene. Alternatively, if the user feels relaxed, the control unit can head to the scene at a normal flight speed. Alternatively, if the user feels an emergency, the control unit can rush to the scene at maximum speed. This allows for a prompt and appropriate response by adjusting the drone's flight speed according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the control unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the control unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0102] The control unit can calculate the optimal flight route using a geographic information system (GIS) when flying the drone. The control unit, for example, uses the GIS to calculate the shortest route and flies the drone. The control unit can also use the GIS to calculate the optimal route that avoids obstacles. The control unit can also use the GIS to calculate the optimal route that takes weather conditions into consideration. This enables efficient flight by calculating the optimal flight route using the geographic information system. Some or all of the above-mentioned processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input GIS data into AI and have the AI ​​calculate the optimal flight route.

[0103] The control unit can optimize the flight plan by taking into account the remaining battery level when flying the drone. For example, when the remaining battery level is low, the control unit heads to the site via the shortest route. The control unit can also set a charging point along the way by taking into account the remaining battery level. Furthermore, when the remaining battery level is sufficient, the control unit can head to the site using a normal flight plan. This enables efficient flight by optimizing the flight plan by taking into account the remaining battery level. Some or all of the above-described processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input remaining battery level data into AI and have the AI ​​optimize the flight plan.

[0104] The control unit can cooperate with other monitoring systems to share information and perform comprehensive monitoring when the drone is flying. For example, the control unit cooperates with other monitoring systems to share information and perform comprehensive monitoring. The control unit can also adjust the drone's flight route based on information from other monitoring systems. The control unit can also cooperate with other monitoring systems to perform efficient monitoring. This enables comprehensive monitoring by cooperating with other monitoring systems and sharing information. Some or all of the above-mentioned processing in the control unit may be performed using, for example, AI, or may be performed without using AI. For example, the control unit can input data from other monitoring systems into AI and have the AI ​​share information and adjust monitoring.

[0105] The distribution unit can estimate the user's emotions and adjust the image quality of the live broadcast based on the estimated user emotions. For example, if the user is feeling anxious, the distribution unit can perform the live broadcast at high image quality. Furthermore, if the user is feeling relaxed, the distribution unit can also perform the live broadcast at normal image quality. Furthermore, if the user is feeling an emergency, the distribution unit can also perform the live broadcast at the highest image quality. This allows for more appropriate information provision by adjusting the image quality of the live broadcast according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the distribution unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the distribution unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0106] The distribution unit can synchronize video and audio during live streaming. For example, the distribution unit synchronizes video and audio in real time to perform live streaming. The distribution unit can also perform live streaming while minimizing delay between video and audio. The distribution unit can also automatically adjust the synchronization between video and audio to perform live streaming. This allows for synchronized video and audio distribution, thereby providing more accurate information to viewers. Some or all of the above-described processing in the distribution unit may be performed using, or without, AI, for example. For example, the distribution unit can input video and audio data into AI and have the AI ​​adjust the synchronization.

[0107] During live streaming, the streaming unit can simultaneously stream footage from multiple cameras, allowing viewers to freely switch between them. For example, the streaming unit can simultaneously stream footage from multiple cameras, allowing viewers to freely switch between them. The streaming unit can also enable viewers to simultaneously watch footage from multiple cameras. The streaming unit can also minimize video delays when viewers switch between camera footage. This allows viewers to freely switch perspectives by simultaneously streaming footage from multiple cameras. Some or all of the above-described processing in the streaming unit may be performed using, or without, AI, for example. For example, the streaming unit can input data from multiple camera footage into AI and have the AI ​​adjust the simultaneous streaming and switching.

[0108] The distribution unit can automatically save the distribution data during live distribution so that it can be analyzed later. For example, the distribution unit can automatically save the live distribution data so that it can be analyzed later. The distribution unit can also analyze the saved distribution data and extract important information. The distribution unit can also perform detailed analysis later based on the saved distribution data. In this way, by automatically saving the distribution data, detailed analysis can be performed later. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input the distribution data into AI and have the AI ​​perform automatic saving and analysis.

[0109] The distribution unit can estimate the user's emotions and adjust the volume of the live broadcast based on the estimated user's emotions. For example, if the user is feeling anxious, the distribution unit can increase the volume of the live broadcast. Furthermore, if the user is relaxed, the distribution unit can also perform the live broadcast at a normal volume. Furthermore, if the user feels an emergency, the distribution unit can also perform the live broadcast at maximum volume. This allows for more appropriate information provision by adjusting the volume of the live broadcast according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, with an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the distribution unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the distribution unit can input the user's emotion data into the generation AI and have the generation AI perform emotion estimation.

[0110] During live streaming, the distribution unit can receive feedback from viewers in real time and adjust the content of the stream. For example, the distribution unit can receive feedback from viewers in real time and adjust the content of the stream. The distribution unit can also optimize the content of the stream based on the viewer feedback. The distribution unit can also analyze the viewer feedback and improve the content of the stream. In this way, the content of the stream can be optimized by receiving feedback from viewers in real time. Some or all of the above-described processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input viewer feedback data into AI and have the AI ​​receive the data in real time and adjust the content of the stream.

[0111] The distribution unit can add annotations to video in real time during live streaming to emphasize important information. For example, the distribution unit can add annotations to live streaming video in real time to emphasize important information. The distribution unit can also minimize video delay when adding annotations. The distribution unit can also allow viewers to freely display or hide annotations when adding annotations. In this way, adding annotations to video in real time can emphasize and convey important information to viewers. Some or all of the above-mentioned processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input annotation data to AI and have the AI ​​add annotations in real time.

[0112] The distribution unit can enhance security by encrypting distribution data during live distribution. For example, the distribution unit encrypts live distribution data to enhance security. The distribution unit can also minimize delays when decrypting encrypted distribution data. The distribution unit can also automatically encrypt and decrypt distribution data to ensure security. In this way, encrypting distribution data enhances security and prevents unauthorized access to data. Some or all of the above-described processing in the distribution unit may be performed using, for example, AI, or may be performed without using AI. For example, the distribution unit can input distribution data to AI and have the AI ​​perform encryption and decryption.

[0113] The warning unit can estimate the user's emotions and adjust the content of the warning message based on the estimated user emotions. For example, if the user feels anxious, the warning unit can provide a detailed warning message. Furthermore, if the user feels relaxed, the warning unit can also provide a normal warning message. Furthermore, if the user feels an emergency, the warning unit can also provide a high-urgency warning message. By adjusting the content of the warning message according to the user's emotions, a more appropriate warning can be provided. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the warning unit can be performed using, for example, AI, or without AI. For example, the warning unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0114] The warning unit can issue a warning by both voice and text when issuing a warning. For example, the warning unit can issue a warning by both voice and text, thereby communicating the warning both visually and audibly. The warning unit can also automatically adjust the synchronization between voice and text when issuing a warning. The warning unit can also simultaneously issue a warning by voice and text, thereby enhancing the effectiveness of the warning. In this way, by issuing a warning by both voice and text, the warning can be communicated both visually and audibly. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input voice and text data into AI and have the AI ​​adjust the synchronization and issue the warning.

[0115] When issuing a warning, the warning unit can make the warning message multilingual and issue the warning in different languages. For example, the warning unit can make the warning message multilingual and issue the warning in different languages. The warning unit can also automatically translate the warning message based on the user's language setting. The warning unit can also issue the warning message in multiple languages ​​to accommodate users who speak different languages. In this way, by making the warning message multilingual, it is possible to accommodate users who speak different languages. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input data of the warning message into AI and have the AI ​​perform multilingual support and translation.

[0116] The warning unit can adjust the frequency of issuing a warning message depending on the situation when issuing a warning. For example, in the case of an emergency, the warning unit can increase the frequency of issuing a warning message. The warning unit can also return the frequency of issuing a warning message to normal under normal circumstances. The warning unit can also automatically adjust the frequency of issuing a warning message depending on the situation. In this way, by adjusting the frequency of issuing a warning message depending on the situation, a more effective warning can be provided. Some or all of the above-mentioned processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input situation data into AI and have the AI ​​adjust the frequency of issuing the warning message.

[0117] The warning unit can estimate the user's emotions and determine the priority of warning messages based on the estimated user emotions. For example, if the user feels anxious, the warning unit can prioritize issuing an important warning message. Furthermore, if the user feels relaxed, the warning unit can also prioritize issuing a high-urgency warning message. Thus, by determining the priority of warning messages according to the user's emotions, important warnings can be provided promptly. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the warning unit can be performed using, for example, AI, or without AI. For example, the warning unit can input the user's emotion data into the generation AI and cause the generation AI to estimate the emotion.

[0118] The warning unit visually displays a warning message when issuing a warning, making it possible to accommodate hearing-impaired persons. The warning unit, for example, visually displays a warning message to accommodate hearing-impaired persons. The warning unit can also employ a design that enhances visibility when displaying a visual warning message. The warning unit can also emphasize important information when displaying a visual warning message. In this way, by visually displaying the warning message, it is possible to convey the warning to hearing-impaired persons as well. Some or all of the above-described processing in the warning unit may be performed using, for example, AI, or may be performed without using AI. For example, the warning unit can input data of the visual warning message into AI and have the AI ​​perform the display and emphasis.

[0119] When issuing a warning, the warning unit can notify relevant organizations of the warning message via social media or email. The warning unit can, for example, notify relevant organizations of the warning message via social media or email, encouraging them to take prompt action. The warning unit can also emphasize important information when notifying via social media or email. The warning unit can also minimize notification delays when notifying via social media or email. This makes it possible to notify relevant organizations of the warning message via social media or email, encouraging them to take prompt action. Some or all of the above-mentioned processing in the warning unit can be performed, for example, using AI, or can be performed without using AI. For example, the warning unit can input warning message data into AI and have the AI ​​execute notification via social media or email.

[0120] The warning unit can optimize the content of the warning message based on past cases when issuing a warning. The warning unit can optimize the content of the warning message based on past cases, for example. The warning unit can also analyze past cases to improve the effectiveness of the warning message. The warning unit can also refer to past cases to improve the content of the warning message. In this way, by optimizing the content of the warning message based on past cases, a more effective warning can be provided. Some or all of the above-mentioned processing in the warning unit can be performed using, for example, AI, or can be performed without using AI. For example, the warning unit can input past case data into AI and have the AI ​​optimize the warning message. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, control unit, distribution unit, and warning unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit can collect surveillance camera footage via the camera 42 of the smart device 14 or the communication I / F 26 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the footage using multimodal AI and detects danger. The control unit, realized, for example, by the specific processing unit 290 of the data processing device 12, calculates the shortest route using a drone's positioning information system and heads to the scene. The distribution unit, for example, live-streams video and audio of the scene using the camera 42 and microphone 38B of the smart device 14. The warning unit, for example, issues a warning through the speaker 40B of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, control unit, distribution unit, and warning unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit can collect surveillance camera footage via the camera 42 of the smart glasses 214 or the communication I / F 26 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the footage using multimodal AI and detects danger. The control unit, realized, for example, by the specific processing unit 290 of the data processing device 12, calculates the shortest route using the drone's positioning information system and heads to the scene. The distribution unit, for example, uses the camera 42 and microphone 238 of the smart glasses 214 to live-stream video and audio of the scene. The warning unit, for example, issues a warning through the speaker 240 of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, control unit, distribution unit, and warning unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit can collect surveillance camera footage via the camera 42 of the headset-type terminal 314 or the communication I / F 26 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the footage using multimodal AI and detects danger. The control unit, realized, for example, by the specific processing unit 290 of the data processing device 12, calculates the shortest route using the drone's positioning information system and heads to the scene. The distribution unit, for example, uses the camera 42 and microphone 238 of the headset-type terminal 314 to live-stream video and audio of the scene. The warning unit, for example, issues a warning through the speaker 240 of the headset-type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, control unit, distribution unit, and warning unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit can collect surveillance camera footage via the camera 42 of the robot 414 or the communication I / F 26 of the data processing device 12. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the footage using multimodal AI and detects danger. The control unit, realized, for example, by the specific processing unit 290 of the data processing device 12, calculates the shortest route using the drone's positioning information system and heads to the scene. The distribution unit, for example, uses the camera 42 and microphone 238 of the robot 414 to live-stream video and audio of the scene. The warning unit, for example, issues a warning through the speaker 240 of the robot 414.

[0121] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0122] The analysis unit can estimate the user's emotions and dynamically adjust the analysis algorithm based on the estimated user emotions. For example, if the user feels anxious, the analysis unit can increase the sensitivity of the algorithm to detect danger more quickly. Alternatively, if the user feels relaxed, the analysis unit can perform analysis at normal sensitivity. Furthermore, if the user feels an emergency, the analysis unit can perform analysis at the highest sensitivity and immediately detect danger. This allows for more appropriate danger detection by dynamically adjusting the analysis algorithm according to the user's emotions.

[0123] The collection unit can add a function to track a specific person when collecting video from a surveillance camera. For example, the collection unit can automatically track a specific person when that person enters the field of view of a surveillance camera. The collection unit can also continue tracking a specific person as they move by coordinating across multiple cameras. Furthermore, the collection unit can record the behavior of a specific person in real time and analyze it later. This allows for more detailed monitoring by tracking specific people.

[0124] The control unit can collect ambient sounds while the drone is flying and optimize the flight route. For example, the control unit can estimate traffic volume from the ambient sounds and select a route that avoids congested areas. The control unit can also detect changes in the weather from the ambient sounds and select a safe route. Furthermore, the control unit can detect an emergency from the ambient sounds and rush to the scene via the shortest route. This allows for safer and more efficient flight by optimizing the flight route using ambient sounds.

[0125] During live streaming, the streamer can analyze viewer emotions in real time and adjust the content of the stream. For example, if a viewer is excited, the streamer can repeatedly play important scenes. Also, if a viewer is feeling anxious, the streamer can display reassuring comments. Furthermore, if a viewer is losing interest, the streamer can recapture their interest by providing new perspectives or information. This allows for more effective information provision by adjusting the content of the stream according to the viewer's emotions.

[0126] When issuing a warning message, the warning unit can select the optimal warning means taking into account the user's location information. For example, when the user is indoors, the warning unit prioritizes audio warnings. When the user is outdoors, the warning unit can also prioritize visual warning messages. Furthermore, when the user is moving, the warning unit can also issue warnings using means such as vibration or flashing lights. This allows for more effective warnings to be provided by selecting the optimal warning means according to the user's location information.

[0127] The collection unit can detect specific objects when collecting video from a surveillance camera and collect information about the objects. For example, the collection unit can detect a vehicle's license plate and obtain the vehicle's registration information. The collection unit can also detect a specific brand logo and obtain information about the brand. Furthermore, the collection unit can detect a specific product's barcode and obtain detailed information about the product. This allows for more detailed monitoring by detecting specific objects and collecting information about the objects.

[0128] The analysis unit can estimate the user's emotions and adjust the notification method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible notification method. If the user is relaxed, the analysis unit can provide a notification method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a notification method that focuses on the main points. In this way, by adjusting the notification method of the analysis results according to the user's emotions, it is possible to provide more appropriate information.

[0129] When a drone flies, the control unit can communicate with other drones and cooperate to optimize the flight route. For example, when multiple drones are monitoring the same area, the control unit can adjust the flight route to avoid overlapping. In addition, when multiple drones are monitoring different areas, the control unit can also adjust the flight route to efficiently cover the area. Furthermore, when multiple drones are responding to an emergency, the control unit can calculate the optimal placement and respond quickly. This allows for more efficient monitoring by communicating with other drones and cooperating to optimize the flight route.

[0130] During live streaming, the streaming unit can estimate the viewer's emotions and adjust the order of the content to be streamed based on the estimated emotions. For example, if the viewer is excited, the streaming unit can stream important scenes first. Alternatively, if the viewer is relaxed, the streaming unit can stream in the normal order. Furthermore, if the viewer is feeling anxious, the streaming unit can stream scenes that will give a sense of security first. This allows for more effective information provision by adjusting the order of the content to be streamed based on the viewer's emotions.

[0131] When issuing a warning message, the warning unit can determine the optimal warning content by referring to the user's past behavior history. For example, if the user has previously felt unsafe in a specific area, the warning unit can provide a detailed warning about that area. Also, if the user has previously felt uneasy in a specific situation, the warning unit can provide a warning including specific countermeasures for that situation. Furthermore, if the user has previously taken a specific action, the warning unit can provide an appropriate warning based on that action. In this way, by determining the optimal warning content by referring to the user's past behavior history, more effective warnings can be provided.

[0132] The processing flow of the second embodiment will be briefly explained below.

[0133] Step 1: The collection unit collects surveillance camera footage. The surveillance camera footage includes footage of major intersections and areas around public facilities. The collection unit collects footage using surveillance cameras that cover a wide area and can provide the footage in real time. Step 2: The analysis unit analyzes the video collected by the collection unit and detects danger. The analysis unit uses multimodal AI to analyze the video and detect, for example, violent acts, screams, and abnormal sounds. It can also analyze video and audio together. Step 3: The control unit controls the autonomous drone based on the danger detected by the analysis unit. The control unit uses the drone's positioning information system to calculate the shortest route to the scene, moving the drone at high speed to quickly arrive at the scene. Step 4: The broadcasting unit broadcasts live video and audio from the scene using a drone controlled by the control unit. The broadcasting unit broadcasts video and audio from the scene using the camera and microphone mounted on the drone, allowing related agencies to grasp the situation at the scene in real time. Step 5: The warning unit issues a warning or calls based on the video and audio delivered by the distribution unit. The warning unit issues a warning through the drone's speaker, for example, to warn the perpetrator and prevent them from escaping. It also calls for evacuation to guide people to a safe place at the scene of an accident.

[0134] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0135] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with 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 specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, etc., and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device, etc.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0139] 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.

[0140] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN and / or a LAN.

[0141] 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.

[0142] 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 audio according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0145] Fig. 4 shows an example of the 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.

[0146] 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.

[0147] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with 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 using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0155] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0156] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN and / or a LAN.

[0157] 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.

[0158] 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 audio according to instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and 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 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0160] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0161] Fig. 6 shows an example of the 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.

[0162] 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.

[0163] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0166] 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 audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio 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 audio data.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with 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 using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0171] 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.

[0172] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 WAN and / or a LAN.

[0173] 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. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0174] 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 audio according to instructions from the processor 46.

[0175] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0176] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0177] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. 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.

[0178] Fig. 8 shows an example of the 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.

[0179] 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.

[0180] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0181] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0182] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0183] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding 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.

[0184] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with 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 using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0185] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0186] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0188] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0189] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0190] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0191] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0192] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0193] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0194] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0195] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0196] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0197] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0198] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0199] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0200] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0201] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0202] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0203] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0204] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0205] [Explanation of symbols]

[0206] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects images from surveillance cameras; an analysis unit that analyzes the video collected by the collection unit and detects danger; a control unit that controls an autonomous drone based on the danger detected by the analysis unit; a distribution unit that uses a drone controlled by the control unit to live-stream video and audio from the scene; a warning unit that issues a warning or calls based on the video and audio distributed by the distribution unit; A system characterized by:

2. The collecting unit Collecting surveillance camera footage 2. The system of claim 1.

3. The analysis unit Analyzing collected video and detecting danger 2. The system of claim 1.

4. The control unit Controlling autonomous drones based on detected dangers 2. The system of claim 1.

5. The distribution unit Drones broadcast live video and audio from the scene 2. The system of claim 1.

6. The warning unit Sending warnings and appeals based on distributed video and audio 2. The system of claim 1.

7. The collecting unit A system that estimates a user's emotions and adjusts the timing of video collection by a surveillance camera based on the estimated user's emotions.

2. The system of claim 1.

8. The collecting unit Dynamically change the location of surveillance cameras to ensure optimal surveillance coverage 2. The system of claim 1.

Images