System

Abstract

To provide a system according to an embodiment that improves quality of grasping a situation before arriving at a site.SOLUTION: A system according to an embodiment comprises: a collection unit; an analysis unit; and a generation unit. The collection unit is configured to collect a picture and voice from a smart glass. The analysis unit is configured to analyze the picture and voice collected by the collection unit. The generation unit is configured to generate a summary announcement on the basis of information analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, understanding the on-site status of accidents, incidents, and disasters relied on reports from members of the public and on grasping the situation after arriving at the scene, which had the problem of lacking in reliability and agility.

[0005] The system of the embodiment aims to improve the quality of situational awareness before arriving at the scene. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects video and audio from the smart glasses. The analysis unit analyzes the video and audio collected by the collection unit. The generation unit generates a general announcement based on the information analyzed by the analysis unit. Effect of the Invention

[0007] Embodiments of the system can improve situational awareness before arriving at the scene. [Brief description 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. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

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

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a 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 (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The on-site grasping system according to the embodiment of the present invention is a system for quickly and reliably grasping the on-site of an accident, incident, or disaster. This on-site grasping system accesses the smart glasses equipped with a camera of a bystander near the site, collects video and audio, and generates an analysis and overview announcement of the on-site. This makes it possible to improve the quality of situation grasping before arriving at the site. For example, the camera-equipped smart glasses of a bystander near the site are accessed. In this case, the owner of the smart glasses must give consent in advance. For example, the owner of the smart glasses installs an app and sets it up to agree to the provision of video and audio in the event of an emergency. Next, video and audio are collected from the smart glasses. The collected video and audio are analyzed in real time. For example, the video and audio of the accident site are analyzed to grasp the situation at the site. At this time, the generation AI analyzes the video and audio and extracts important information. Furthermore, an overview announcement of the site is generated based on the analyzed information. The generated announcement is provided to the emergency response team heading to the site. For example, by announcing the situation at the site, the extent of the damage, and necessary responses, the emergency response team can grasp the situation before arriving at the site. This system improves the quality of situational awareness before arriving at the scene, enabling swift and appropriate responses. For example, at the scene of a fire, appropriate firefighting and rescue activities can be carried out by analyzing the video and audio at the scene and grasping the scale of the fire and the extent of the damage. Also, at the scene of a traffic accident, the situation at the scene can be grasped and the necessary emergency response can be carried out quickly. This allows the scene awareness system to improve the quality of situational awareness before arriving at the scene.

[0029] The on-site grasping system according to the embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects video and audio from the smart glasses. The collection unit collects video of the on-site using, for example, a camera of the smart glasses. The collection unit can also collect audio of the on-site using a microphone of the smart glasses. For example, the collection unit collects video of the on-site in real time using a camera of the smart glasses. The collection unit can also collect audio of the on-site in real time using a microphone of the smart glasses. Furthermore, the collection unit can combine a camera and a microphone of the smart glasses to simultaneously collect video and audio. For example, the collection unit collects video and audio of the on-site simultaneously using a camera and a microphone of the smart glasses. The analysis unit analyzes the video and audio collected by the collection unit. For example, the analysis unit analyzes the video using a generation AI to extract important information. The analysis unit can also analyze audio using a generation AI to extract important information. For example, the analysis unit analyzes the situation of the accident from the video using a generation AI. The analysis unit can also analyze the situation at the site from the voice using the generation AI. Furthermore, the analysis unit can also analyze the situation by combining video and voice using the generation AI. For example, the analysis unit uses the generation AI to combine video and voice to analyze the situation at the site. The generation unit generates a general announcement based on the information analyzed by the analysis unit. The generation unit generates an announcement in text format using, for example, the generation AI. The generation unit can also generate an announcement in audio format using the generation AI. For example, the generation unit generates an announcement in text format using the generation AI. The generation unit can also generate an announcement in audio format using the generation AI. As a result, the site grasping system according to the embodiment can improve the quality of grasping the situation before arriving at the site.

[0030] The collection unit collects video and audio from the smart glasses. Specifically, the smart glasses camera is used to collect video of the site. The smart glasses camera can capture high-resolution video in real time and capture the detailed situation of the site. For example, the smart glasses camera is very effective in situations where visual information is important, such as construction sites and disaster sites. The collection unit can also collect audio of the site using the smart glasses microphone. The smart glasses microphone picks up surrounding sounds with high sensitivity and collects audio information of the site in real time. This makes it possible to grasp audio-based information such as the noise level and conversation content of the site. Furthermore, the collection unit can combine the smart glasses camera and microphone to collect video and audio simultaneously. For example, the collection unit uses the smart glasses camera and microphone to collect video and audio of the site simultaneously. This makes it possible to obtain data in which the video and audio are synchronized, and to grasp the situation of the site more accurately. The collected data is transmitted to a central database in real time, making it accessible to the analysis unit and generation unit. This allows the collection unit to quickly and accurately grasp the situation of the site and improve the performance of the entire system.

[0031] The analysis unit analyzes the video and audio collected by the collection unit. For analysis, the generation AI is used to analyze the video and extract important information. Specifically, the generation AI detects specific objects and actions from the video and identifies accidents and abnormal situations. For example, the generation AI can analyze the movements and facial expressions of people in the video to detect emergency situations and dangerous situations. The analysis unit can also use the generation AI to analyze the audio and extract important information. The generation AI detects specific keywords and audio patterns from the audio data to grasp the situation at the scene. For example, the generation AI can detect emergency keywords such as "help" and "fire" from the audio data and respond immediately. In addition, the analysis unit can also use the generation AI to combine and analyze the video and audio. For example, the generation AI synchronizes and analyzes the video and audio to grasp the situation at the scene in more detail. This allows the analysis unit to quickly and accurately analyze the collected data and detect risks and abnormalities at the scene in real time. In addition, the analysis unit can also perform long-term risk assessment and trend analysis by utilizing past data and statistical information. This enables the analysis unit to not only grasp the situation in real time, but also handle long-term risk management and anomaly detection, improving the reliability and safety of the entire system.

[0032] The generation unit generates a general announcement based on the information analyzed by the analysis unit. Specifically, the generation unit generates a text-format announcement using the generation AI. The generation AI generates text that concisely and clearly conveys the situation at the site based on the analyzed information. For example, the generation AI can generate an emergency announcement such as "There is a fire at the site. Please evacuate immediately." The generation unit can also generate an audio-format announcement using the generation AI. The generation AI converts text into audio and conveys the situation at the site by audio. For example, the generation AI can generate an audio announcement such as "There is a fire at the site. Please evacuate immediately." and convey it to workers and related parties at the site. This allows the generation unit to quickly and accurately generate announcements based on the analyzed information and convey the situation at the site to related parties. Furthermore, the generation unit can update the content of the announcement in real time to respond to the latest situation. For example, if the situation at the site changes, the generation unit immediately generates a new announcement and conveys it to related parties. The generation unit can also generate announcements in multiple languages, making it possible to respond to international sites. This enables the generation unit to always provide highly accurate announcements based on the latest information, and to assist in rapid and appropriate responses.

[0033] The on-site awareness system includes a consent unit that manages the consent process. The consent unit appropriately manages the consent of bystanders. For example, the consent unit configures the smart glasses owner to install an app and consent to the provision of video and audio in an emergency. The consent unit manages the method of obtaining and recording consent. For example, the consent unit manages the process by which the smart glasses owner gives consent through the app. The consent unit also includes a function of recording consent. For example, the consent unit records the date and time consent was obtained and the content of consent. This enables the on-site awareness system to appropriately manage bystanders' consent.

[0034] The on-site grasping system includes a providing unit that provides the generated announcement. The providing unit provides the generated announcement to an emergency response team. The providing unit includes, for example, a function of notifying the generated announcement. The providing unit manages a method of notifying the announcement and a format of the information to be provided. For example, the providing unit notifies the generated announcement as a text message. The providing unit can also notify the generated announcement as a voice message. For example, the providing unit notifies the emergency response team of the generated announcement as a text message. The providing unit can also notify the emergency response team of the generated announcement as a voice message. This allows the on-site grasping system to quickly provide information to the emergency response team.

[0035] The analysis unit can analyze the video and audio in real time and extract information based on specific criteria. The analysis unit can, for example, use a generation AI to analyze the video in real time and extract important information. For example, the analysis unit can use a generation AI to analyze the situation of the accident from the video in real time. The analysis unit can also analyze the audio in real time and extract important information using a generation AI. For example, the analysis unit can use a generation AI to analyze the situation at the scene from the audio in real time. Furthermore, the analysis unit can also use a generation AI to combine the video and audio and analyze it in real time. For example, the analysis unit can use a generation AI to combine the video and audio and analyze the situation at the scene in real time. This allows the analysis unit to extract important information in real time.

[0036] The generation unit can perform a process of generating an announcement in text format or audio format based on the analysis result. The generation unit generates an announcement in text format using, for example, a generation AI. For example, the generation unit generates an announcement in text format based on the analysis result using the generation AI. The generation unit can also generate an announcement in audio format using the generation AI. For example, the generation unit generates an announcement in audio format based on the analysis result using the generation AI. This allows the generation unit to generate an announcement in an appropriate format.

[0037] The providing unit can provide the generated announcement to the emergency response team. For example, the providing unit notifies the emergency response team of the generated announcement as a text message. For example, the providing unit notifies the emergency response team of the generated announcement as a text message. The providing unit can also notify the emergency response team of the generated announcement as a voice message. For example, the providing unit notifies the emergency response team of the generated announcement as a voice message. This allows the providing unit to quickly provide information to the emergency response team.

[0038] The collection unit can analyze the bystander's past behavior history and select an appropriate collection method. The collection unit, for example, analyzes how the bystander has behaved in a similar situation in the past and selects the optimal collection method. For example, the collection unit analyzes how the bystander has behaved in a similar situation in the past and selects the optimal collection method. The collection unit can also select the optimal collection method based on the quality of video and audio collected by the bystander in the past. For example, the collection unit selects the optimal collection method based on the quality of video and audio collected by the bystander in the past. The collection unit can also analyze the bystander's past behavior patterns and select the optimal collection timing. For example, the collection unit analyzes the bystander's past behavior patterns and selects the optimal collection timing. This allows the collection unit to select the optimal collection method based on the past behavior history.

[0039] The collection unit can dynamically adjust the collection range based on the situation at the site when collecting video and audio. For example, when the situation at the site changes, the collection unit automatically adjusts the collection range. For example, when the situation at the site changes, the collection unit automatically adjusts the collection range. The collection unit can also widen or narrow the collection range according to the situation at the site. For example, the collection unit widens or narrows the collection range according to the situation at the site. The collection unit can also fix the collection range when the situation at the site is stable. For example, the collection unit fixes the collection range when the situation at the site is stable. This allows the collection unit to dynamically adjust the collection range according to the situation at the site.

[0040] When collecting video and audio, the collection unit can preferentially collect information with high relevance based on the geographical location information of the bystander. For example, when a bystander is close to the scene, the collection unit preferentially collects the video and audio. For example, when a bystander is close to the scene, the collection unit preferentially collects the video and audio. In addition, when a bystander is far from the scene, the collection unit can also prioritize the video and audio of other bystanders. For example, when a bystander is far from the scene, the collection unit prioritizes the video and audio of other bystanders. In addition, when a bystander is moving, the collection unit can also collect video and audio along the moving route. For example, when a bystander is moving, the collection unit collects video and audio along the moving route. This allows the collection unit to preferentially collect information with high relevance based on the geographical location information.

[0041] The collection unit can collect related information based on the social media activities of bystanders when collecting video and audio. For example, when a bystander posts the situation at the scene on social media, the collection unit collects the information. For example, when a bystander posts the situation at the scene on social media, the collection unit collects the information. In addition, when a bystander interacts with other users on social media, the collection unit can also collect the interactions. For example, when a bystander interacts with other users on social media, the collection unit collects the interactions. In addition, when a bystander posts photos or videos of the scene on social media, the collection unit can also collect the media. For example, when a bystander posts photos or videos of the scene on social media, the collection unit collects the media. This allows the collection unit to collect related information based on social media activities.

[0042] The analysis unit can adjust the level of detail of the analysis based on the importance of the video and audio during analysis. For example, in the case of important video and audio, the analysis unit performs a detailed analysis. For example, in the case of important video and audio, the analysis unit performs a detailed analysis. In addition, the analysis unit can also perform a simplified analysis in the case of video and audio with low importance. For example, the analysis unit performs a simplified analysis in the case of video and audio with low importance. In addition, the analysis unit can also perform a standard analysis in the case of video and audio with medium importance. For example, the analysis unit performs a standard analysis in the case of video and audio with medium importance. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the video and audio.

[0043] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the scene. For example, in the case of a traffic accident, the analysis unit applies an algorithm dedicated to traffic accidents. For example, in the case of a traffic accident, the analysis unit applies an algorithm dedicated to traffic accidents. Furthermore, in the case of a fire, the analysis unit can also apply an algorithm dedicated to fires. For example, in the case of a fire, the analysis unit applies an algorithm dedicated to fires. Furthermore, in the case of a natural disaster, the analysis unit can also apply an algorithm dedicated to natural disasters. For example, in the case of a natural disaster, the analysis unit applies an algorithm dedicated to natural disasters. This allows the analysis unit to apply an appropriate analysis algorithm depending on the category of the scene.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the time when the video and audio were collected. For example, the analysis unit gives priority to analyzing the most recent video and audio. For example, the analysis unit gives priority to analyzing the most recent video and audio. The analysis unit can also postpone video and audio that was collected a long time ago. For example, the analysis unit postpones video and audio that was collected a long time ago. The analysis unit can also analyze video and audio that was collected at a medium time with standard priority. For example, the analysis unit analyzes video and audio that was collected at a medium time with standard priority. This allows the analysis unit to determine the priority of analysis based on the time of collection.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the video and audio during analysis. For example, the analysis unit gives priority to analyzing video and audio with important relevance. For example, the analysis unit gives priority to analyzing video and audio with important relevance. The analysis unit can also postpone video and audio with low relevance. For example, the analysis unit postpones video and audio with low relevance. The analysis unit can also analyze video and audio with medium relevance in a standard order. For example, the analysis unit analyzes video and audio with medium relevance in a standard order. This allows the analysis unit to adjust the order of analysis based on relevance.

[0046] When generating an announcement, the generation unit can adjust the level of detail of the announcement based on the importance of the analysis result. For example, in the case of an important analysis result, the generation unit generates a detailed announcement. For example, in the case of an important analysis result, the generation unit generates a detailed announcement. In addition, the generation unit can also generate a concise announcement in the case of an analysis result with low importance. For example, the generation unit generates a concise announcement in the case of an analysis result with low importance. In addition, the generation unit can also generate a standard announcement in the case of an analysis result with medium importance. For example, the generation unit generates a standard announcement in the case of an analysis result with medium importance. This allows the generation unit to adjust the level of detail of the announcement based on the importance of the analysis result.

[0047] When generating an announcement, the generation unit can apply different generation algorithms depending on the category of the site. For example, in the case of a traffic accident, the generation unit applies an announcement generation algorithm dedicated to traffic accidents. For example, in the case of a traffic accident, the generation unit applies an announcement generation algorithm dedicated to traffic accidents. In addition, the generation unit can also apply an announcement generation algorithm dedicated to fires in the case of a fire. For example, in the case of a fire, the generation unit applies an announcement generation algorithm dedicated to fires. In addition, the generation unit can also apply an announcement generation algorithm dedicated to natural disasters in the case of a natural disaster. For example, in the case of a natural disaster, the generation unit applies an announcement generation algorithm dedicated to natural disasters. This allows the generation unit to apply an appropriate generation algorithm depending on the category of the site.

[0048] When generating an announcement, the generation unit can determine the priority of the announcement based on the submission time of the analysis result. For example, the generation unit preferentially generates an announcement based on the latest analysis result. For example, the generation unit preferentially generates an announcement based on the latest analysis result. The generation unit can also postpone analysis results submitted earlier. For example, the generation unit postpones analysis results submitted earlier. The generation unit can also generate an announcement with standard priority for analysis results submitted at a medium time. For example, the generation unit generates an announcement with standard priority for analysis results submitted at a medium time. This allows the generation unit to determine the priority of the announcement based on the submission time.

[0049] The generation unit can adjust the order of announcements based on the relevance of the analysis results when generating announcements. For example, the generation unit preferentially generates announcements based on analysis results having important relevance. For example, the generation unit preferentially generates announcements based on analysis results having important relevance. The generation unit can also postpone analysis results with low relevance. For example, the generation unit postpones analysis results with low relevance. The generation unit can also generate announcements in a standard order for analysis results with medium relevance. For example, the generation unit generates announcements in a standard order for analysis results with medium relevance. This allows the generation unit to adjust the order of announcements based on relevance.

[0050] During the consent process, the consent unit can select an appropriate consent method by referring to the bystander's past consent history. The consent unit selects the optimal consent method, for example, based on the method by which the bystander has consented in the past. For example, the consent unit selects the optimal consent method based on the method by which the bystander has consented in the past. The consent unit can also select a method by which consent can be obtained most quickly from the bystander's past consent history. For example, the consent unit selects a method by which consent can be obtained most quickly from the bystander's past consent history. The consent unit can also analyze the bystander's past consent history and propose an optimal consent process. For example, the consent unit analyzes the bystander's past consent history and propose an optimal consent process. This allows the consent unit to select the optimal consent method based on the past consent history.

[0051] The consent unit can select an appropriate consent method in consideration of the device information of the bystander during the consent process. For example, if the bystander is using a smartphone, the consent unit provides a consent method optimized for the smartphone. For example, if the bystander is using a smartphone, the consent unit provides a consent method optimized for the smartphone. In addition, if the bystander is using a tablet, the consent unit can also provide a consent method optimized for the tablet. For example, if the bystander is using a tablet, the consent unit provides a consent method optimized for the tablet. In addition, if the bystander is using smart glasses, the consent unit can also provide a consent method optimized for the smart glasses. For example, if the bystander is using smart glasses, the consent unit provides a consent method optimized for the smart glasses. This allows the consent unit to select the optimal consent method based on the device information.

[0052] The providing unit can select an appropriate providing method by referring to the past response history of the emergency response team when providing an announcement. The providing unit selects an optimal providing method, for example, based on the announcement method used in the past by the emergency response team. For example, the providing unit selects an optimal providing method based on the announcement method used in the past by the emergency response team. The providing unit can also select the most effective announcement method from the past response history of the emergency response team. For example, the providing unit selects the most effective announcement method from the past response history of the emergency response team. The providing unit can also analyze the past response history of the emergency response team and propose an optimal announcement providing method. For example, the providing unit analyzes the past response history of the emergency response team and proposes an optimal announcement providing method. This allows the providing unit to select an optimal providing method based on the past response history.

[0053] The providing unit can select an appropriate providing method in consideration of device information of the emergency response team when providing an announcement. For example, when the emergency response team uses a smartphone, the providing unit provides an announcement method optimized for the smartphone. For example, when the emergency response team uses a smartphone, the providing unit provides an announcement method optimized for the smartphone. In addition, when the emergency response team uses a tablet, the providing unit can also provide an announcement method optimized for the tablet. For example, when the emergency response team uses a tablet, the providing unit provides an announcement method optimized for the tablet. In addition, when the emergency response team uses a smartwatch, the providing unit can also provide an announcement method optimized for the smartwatch. For example, when the emergency response team uses a smartwatch, the providing unit provides an announcement method optimized for the smartwatch. This allows the providing unit to select an optimal providing method based on the device information.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The scene recognition system may further include a location information acquisition unit. The location information acquisition unit acquires location information from the bystander's smart glasses or smartphone and provides it to the collection unit. For example, the location information acquisition unit may identify the location of the bystander using GPS and provide it to the collection unit. The location information acquisition unit may also acquire indoor location information using Wi-Fi or Bluetooth (registered trademark). This allows the collection unit to optimally collect video and audio based on the location of the bystander. Furthermore, the location information acquisition unit may track the movement path of the bystander and provide it to the collection unit. For example, when the bystander is moving, the location information acquisition unit collects video and audio along the movement path. This allows the scene recognition system to collect information more effectively based on the bystander's location information.

[0056] The on-site grasping system may further include a data filtering unit. The data filtering unit filters the collected video and audio data and provides only important information to the analysis unit. For example, the data filtering unit removes noise and unnecessary information and provides clear video and audio to the analysis unit. The data filtering unit may also extract important information based on specific keywords or audio patterns. For example, the data filtering unit may preferentially provide audio containing keywords related to an emergency to the analysis unit. This allows the analysis unit to analyze important information more efficiently. Furthermore, the data filtering unit may perform image processing to improve the quality of the video. For example, the data filtering unit may adjust the brightness and contrast of the video to improve visibility. This allows the on-site grasping system to grasp the situation at the site based on higher quality data.

[0057] The on-site grasping system may further include an emergency notification unit. The emergency notification unit immediately notifies the emergency response team when an emergency response is required based on the collected information. For example, the emergency notification unit notifies the emergency response team in real time when a serious incident such as a fire or a traffic accident occurs. The emergency notification unit may also set a priority order for notifications and quickly convey the most important information. For example, the emergency notification unit may notify the occurrence of a fire as a top priority, and then notify information about a traffic accident. This allows the emergency response team to respond quickly and appropriately. Furthermore, the emergency notification unit may also select the form of notification. For example, the emergency notification unit may notify the emergency response team as a text message, a voice message, or even a video message. This allows the on-site grasping system to quickly and effectively notify the emergency response team.

[0058] The on-site understanding system can further include a data storage unit. The data storage unit securely stores the collected video and audio data so that it can be used for analysis and verification later. For example, the data storage unit uses cloud storage to store the data and make it accessible as needed. The data storage unit can also encrypt the data to ensure security. For example, the data storage unit encrypts the collected data and protects it from unauthorized access. This allows the on-site understanding system to safely manage the collected data and quickly obtain necessary information later. Furthermore, the data storage unit can also periodically back up the data. For example, the data storage unit periodically creates a backup of the data to prevent data loss. This allows the on-site understanding system to ensure the reliability and availability of the data.

[0059] The on-site grasping system may further include a user interface unit. The user interface unit provides an interface that allows the emergency response team to intuitively understand the collected information. For example, the user interface unit provides a dashboard that displays the collected video and audio data in real time. The user interface unit may also highlight important information to enable the emergency response team to respond quickly. For example, the user interface unit visually displays the location of the fire and the extent of the damage. This allows the emergency response team to quickly grasp the situation at the site and take appropriate action. Furthermore, the user interface unit may respond to voice commands and touch operations to improve the convenience of operation. For example, the user interface unit may search for specific information using voice commands and zoom in and out of a map using touch operations. This allows the on-site grasping system to provide an interface that is easy for the emergency response team to use.

[0060] The process flow of the first embodiment will be briefly described below.

[0061] Step 1: The collection unit collects video and audio from the smart glasses. For example, the collection unit uses the smart glasses' camera to collect on-site video in real time and the smart glasses' microphone to collect on-site audio in real time. The collection unit can also collect video and audio simultaneously by combining a camera and microphone. Step 2: The analysis unit analyzes the video and audio collected by the collection unit. For example, the analysis unit uses a generative AI to analyze the video and extract important information. It can also use a generative AI to analyze audio and extract important information. Furthermore, the analysis unit combines and analyzes the video and audio to grasp the situation at the scene. Step 3: The generator generates a summary announcement based on the information analyzed by the analyzer. For example, the generator can generate a text-format announcement using a generation AI, and can also generate a voice-format announcement.

[0062] (Example 2) The on-site grasping system according to the embodiment of the present invention is a system for quickly and reliably grasping the on-site of an accident, incident, or disaster. This on-site grasping system accesses the smart glasses equipped with a camera of a bystander near the site, collects video and audio, and generates an analysis and overview announcement of the on-site. This makes it possible to improve the quality of situation grasping before arriving at the site. For example, the camera-equipped smart glasses of a bystander near the site are accessed. In this case, the owner of the smart glasses must give consent in advance. For example, the owner of the smart glasses installs an app and sets it up to agree to the provision of video and audio in the event of an emergency. Next, video and audio are collected from the smart glasses. The collected video and audio are analyzed in real time. For example, the video and audio of the accident site are analyzed to grasp the situation at the site. At this time, the generation AI analyzes the video and audio and extracts important information. Furthermore, an overview announcement of the site is generated based on the analyzed information. The generated announcement is provided to the emergency response team heading to the site. For example, by announcing the situation at the site, the extent of the damage, and necessary responses, the emergency response team can grasp the situation before arriving at the site. This system improves the quality of situational awareness before arriving at the scene, enabling swift and appropriate responses. For example, at the scene of a fire, appropriate firefighting and rescue activities can be carried out by analyzing the video and audio at the scene and grasping the scale of the fire and the extent of the damage. Also, at the scene of a traffic accident, the situation at the scene can be grasped and the necessary emergency response can be carried out quickly. This allows the scene awareness system to improve the quality of situational awareness before arriving at the scene.

[0063] The on-site grasping system according to the embodiment includes a collection unit, an analysis unit, and a generation unit. The collection unit collects video and audio from the smart glasses. The collection unit collects video of the on-site using, for example, a camera of the smart glasses. The collection unit can also collect audio of the on-site using a microphone of the smart glasses. For example, the collection unit collects video of the on-site in real time using a camera of the smart glasses. The collection unit can also collect audio of the on-site in real time using a microphone of the smart glasses. Furthermore, the collection unit can combine a camera and a microphone of the smart glasses to simultaneously collect video and audio. For example, the collection unit collects video and audio of the on-site simultaneously using a camera and a microphone of the smart glasses. The analysis unit analyzes the video and audio collected by the collection unit. For example, the analysis unit analyzes the video using a generation AI to extract important information. The analysis unit can also analyze audio using a generation AI to extract important information. For example, the analysis unit analyzes the situation of the accident from the video using a generation AI. The analysis unit can also analyze the situation at the site from the voice using the generation AI. Furthermore, the analysis unit can also analyze the situation by combining video and voice using the generation AI. For example, the analysis unit uses the generation AI to combine video and voice to analyze the situation at the site. The generation unit generates a general announcement based on the information analyzed by the analysis unit. The generation unit generates an announcement in text format using, for example, the generation AI. The generation unit can also generate an announcement in audio format using the generation AI. For example, the generation unit generates an announcement in text format using the generation AI. The generation unit can also generate an announcement in audio format using the generation AI. As a result, the site grasping system according to the embodiment can improve the quality of grasping the situation before arriving at the site.

[0064] The collection unit collects video and audio from the smart glasses. Specifically, the smart glasses camera is used to collect video of the site. The smart glasses camera can capture high-resolution video in real time and capture the detailed situation of the site. For example, the smart glasses camera is very effective in situations where visual information is important, such as construction sites and disaster sites. The collection unit can also collect audio of the site using the smart glasses microphone. The smart glasses microphone picks up surrounding sounds with high sensitivity and collects audio information of the site in real time. This makes it possible to grasp audio-based information such as the noise level and conversation content of the site. Furthermore, the collection unit can combine the smart glasses camera and microphone to collect video and audio simultaneously. For example, the collection unit uses the smart glasses camera and microphone to collect video and audio of the site simultaneously. This makes it possible to obtain data in which the video and audio are synchronized, and to grasp the situation of the site more accurately. The collected data is transmitted to a central database in real time, making it accessible to the analysis unit and generation unit. This allows the collection unit to quickly and accurately grasp the situation of the site and improve the performance of the entire system.

[0065] The analysis unit analyzes the video and audio collected by the collection unit. For analysis, the generation AI is used to analyze the video and extract important information. Specifically, the generation AI detects specific objects and actions from the video and identifies accidents and abnormal situations. For example, the generation AI can analyze the movements and facial expressions of people in the video to detect emergency situations and dangerous situations. The analysis unit can also use the generation AI to analyze the audio and extract important information. The generation AI detects specific keywords and audio patterns from the audio data to grasp the situation at the scene. For example, the generation AI can detect emergency keywords such as "help" and "fire" from the audio data and respond immediately. In addition, the analysis unit can also use the generation AI to combine and analyze the video and audio. For example, the generation AI synchronizes and analyzes the video and audio to grasp the situation at the scene in more detail. This allows the analysis unit to quickly and accurately analyze the collected data and detect risks and abnormalities at the scene in real time. In addition, the analysis unit can also perform long-term risk assessment and trend analysis by utilizing past data and statistical information. This enables the analysis unit to not only grasp the situation in real time, but also handle long-term risk management and anomaly detection, improving the reliability and safety of the entire system.

[0066] The generation unit generates a general announcement based on the information analyzed by the analysis unit. Specifically, the generation unit generates a text-format announcement using the generation AI. The generation AI generates text that concisely and clearly conveys the situation at the site based on the analyzed information. For example, the generation AI can generate an emergency announcement such as "There is a fire at the site. Please evacuate immediately." The generation unit can also generate an audio-format announcement using the generation AI. The generation AI converts text into audio and conveys the situation at the site by audio. For example, the generation AI can generate an audio announcement such as "There is a fire at the site. Please evacuate immediately." and convey it to workers and related parties at the site. This allows the generation unit to quickly and accurately generate announcements based on the analyzed information and convey the situation at the site to related parties. Furthermore, the generation unit can update the content of the announcement in real time to respond to the latest situation. For example, if the situation at the site changes, the generation unit immediately generates a new announcement and conveys it to related parties. The generation unit can also generate announcements in multiple languages, making it possible to respond to international sites. This enables the generation unit to always provide highly accurate announcements based on the latest information, and to assist in rapid and appropriate responses.

[0067] The on-site awareness system includes a consent unit that manages the consent process. The consent unit appropriately manages the consent of bystanders. For example, the consent unit configures the smart glasses owner to install an app and consent to the provision of video and audio in an emergency. The consent unit manages the method of obtaining and recording consent. For example, the consent unit manages the process by which the smart glasses owner gives consent through the app. The consent unit also includes a function of recording consent. For example, the consent unit records the date and time consent was obtained and the content of consent. This enables the on-site awareness system to appropriately manage bystanders' consent.

[0068] The on-site grasping system includes a providing unit that provides the generated announcement. The providing unit provides the generated announcement to an emergency response team. The providing unit includes, for example, a function of notifying the generated announcement. The providing unit manages a method of notifying the announcement and a format of the information to be provided. For example, the providing unit notifies the generated announcement as a text message. The providing unit can also notify the generated announcement as a voice message. For example, the providing unit notifies the emergency response team of the generated announcement as a text message. The providing unit can also notify the emergency response team of the generated announcement as a voice message. This allows the on-site grasping system to quickly provide information to the emergency response team.

[0069] The analysis unit can analyze the video and audio in real time and extract information based on specific criteria. The analysis unit can, for example, use a generation AI to analyze the video in real time and extract important information. For example, the analysis unit can use a generation AI to analyze the situation of the accident from the video in real time. The analysis unit can also analyze the audio in real time and extract important information using a generation AI. For example, the analysis unit can use a generation AI to analyze the situation at the scene from the audio in real time. Furthermore, the analysis unit can also use a generation AI to combine the video and audio and analyze it in real time. For example, the analysis unit can use a generation AI to combine the video and audio and analyze the situation at the scene in real time. This allows the analysis unit to extract important information in real time.

[0070] The generation unit can perform a process of generating an announcement in text format or audio format based on the analysis result. The generation unit generates an announcement in text format using, for example, a generation AI. For example, the generation unit generates an announcement in text format based on the analysis result using the generation AI. The generation unit can also generate an announcement in audio format using the generation AI. For example, the generation unit generates an announcement in audio format based on the analysis result using the generation AI. This allows the generation unit to generate an announcement in an appropriate format.

[0071] The providing unit can provide the generated announcement to the emergency response team. For example, the providing unit notifies the emergency response team of the generated announcement as a text message. For example, the providing unit notifies the emergency response team of the generated announcement as a text message. The providing unit can also notify the emergency response team of the generated announcement as a voice message. For example, the providing unit notifies the emergency response team of the generated announcement as a voice message. This allows the providing unit to quickly provide information to the emergency response team.

[0072] The collection unit can estimate the emotion of the bystander and adjust the timing of collecting the video and audio based on the estimated emotion. For example, when the bystander is surprised, the collection unit immediately starts collecting the video and audio. For example, when the bystander is surprised, the collection unit immediately starts collecting the video and audio. In addition, the collection unit can also collect the video and audio at regular intervals when the bystander is calm. For example, when the bystander is calm, the collection unit collects the video and audio at regular intervals. In addition, the collection unit can also collect the video and audio frequently when the bystander is upset. For example, when the bystander is upset, the collection unit collects the video and audio frequently. This allows the collection unit to adjust the collection timing according to the emotion of the bystander. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0073] The collection unit can analyze the bystander's past behavior history and select an appropriate collection method. The collection unit, for example, analyzes how the bystander has behaved in a similar situation in the past and selects the optimal collection method. For example, the collection unit analyzes how the bystander has behaved in a similar situation in the past and selects the optimal collection method. The collection unit can also select the optimal collection method based on the quality of video and audio collected by the bystander in the past. For example, the collection unit selects the optimal collection method based on the quality of video and audio collected by the bystander in the past. The collection unit can also analyze the bystander's past behavior patterns and select the optimal collection timing. For example, the collection unit analyzes the bystander's past behavior patterns and selects the optimal collection timing. This allows the collection unit to select the optimal collection method based on the past behavior history.

[0074] The collection unit can dynamically adjust the collection range based on the situation at the site when collecting video and audio. For example, when the situation at the site changes, the collection unit automatically adjusts the collection range. For example, when the situation at the site changes, the collection unit automatically adjusts the collection range. The collection unit can also widen or narrow the collection range according to the situation at the site. For example, the collection unit widens or narrows the collection range according to the situation at the site. The collection unit can also fix the collection range when the situation at the site is stable. For example, the collection unit fixes the collection range when the situation at the site is stable. This allows the collection unit to dynamically adjust the collection range according to the situation at the site.

[0075] The collection unit can estimate the emotion of the bystander and determine the priority of the video and audio to be collected based on the estimated emotion. For example, when the bystander is surprised, the collection unit prioritizes the collection of video. For example, when the bystander is surprised, the collection unit prioritizes the collection of video. The collection unit can also prioritize the collection of audio when the bystander is calm. For example, when the bystander is calm, the collection unit prioritizes the collection of audio. The collection unit can also simultaneously collect both video and audio when the bystander is upset. For example, when the bystander is upset, the collection unit simultaneously collects both video and audio. This allows the collection unit to determine the priority of the video and audio to be collected according to the emotion of the bystander. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0076] When collecting video and audio, the collection unit can preferentially collect information with high relevance based on the geographical location information of the bystander. For example, when a bystander is close to the scene, the collection unit preferentially collects the video and audio. For example, when a bystander is close to the scene, the collection unit preferentially collects the video and audio. In addition, when a bystander is far from the scene, the collection unit can also prioritize the video and audio of other bystanders. For example, when a bystander is far from the scene, the collection unit prioritizes the video and audio of other bystanders. In addition, when a bystander is moving, the collection unit can also collect video and audio along the moving route. For example, when a bystander is moving, the collection unit collects video and audio along the moving route. This allows the collection unit to preferentially collect information with high relevance based on the geographical location information.

[0077] The collection unit can collect related information based on the social media activities of bystanders when collecting video and audio. For example, when a bystander posts the situation at the scene on social media, the collection unit collects the information. For example, when a bystander posts the situation at the scene on social media, the collection unit collects the information. In addition, when a bystander interacts with other users on social media, the collection unit can also collect the interactions. For example, when a bystander interacts with other users on social media, the collection unit collects the interactions. In addition, when a bystander posts photos or videos of the scene on social media, the collection unit can also collect the media. For example, when a bystander posts photos or videos of the scene on social media, the collection unit collects the media. This allows the collection unit to collect related information based on social media activities.

[0078] The analysis unit can estimate the emotion of the bystander and adjust the accuracy of the analysis based on the estimated emotion. For example, when the bystander is surprised, the analysis unit performs a highly accurate analysis. For example, when the bystander is surprised, the analysis unit performs a highly accurate analysis. In addition, the analysis unit can also perform an analysis with standard accuracy when the bystander is calm. For example, when the bystander is calm, the analysis unit performs an analysis with standard accuracy. In addition, the analysis unit can also perform an analysis quickly when the bystander is upset. For example, when the bystander is upset, the analysis unit performs an analysis quickly. This allows the analysis unit to adjust the accuracy of the analysis according to the emotion of the bystander. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0079] The analysis unit can adjust the level of detail of the analysis based on the importance of the video and audio during analysis. For example, in the case of important video and audio, the analysis unit performs a detailed analysis. For example, in the case of important video and audio, the analysis unit performs a detailed analysis. In addition, the analysis unit can also perform a simplified analysis in the case of video and audio with low importance. For example, the analysis unit performs a simplified analysis in the case of video and audio with low importance. In addition, the analysis unit can also perform a standard analysis in the case of video and audio with medium importance. For example, the analysis unit performs a standard analysis in the case of video and audio with medium importance. This allows the analysis unit to adjust the level of detail of the analysis based on the importance of the video and audio.

[0080] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the scene. For example, in the case of a traffic accident, the analysis unit applies an algorithm dedicated to traffic accidents. For example, in the case of a traffic accident, the analysis unit applies an algorithm dedicated to traffic accidents. Furthermore, in the case of a fire, the analysis unit can also apply an algorithm dedicated to fires. For example, in the case of a fire, the analysis unit applies an algorithm dedicated to fires. Furthermore, in the case of a natural disaster, the analysis unit can also apply an algorithm dedicated to natural disasters. For example, in the case of a natural disaster, the analysis unit applies an algorithm dedicated to natural disasters. This allows the analysis unit to apply an appropriate analysis algorithm depending on the category of the scene.

[0081] The analysis unit can estimate the emotion of the bystander and adjust the display method of the analysis result based on the estimated emotion. For example, when the bystander is surprised, the analysis unit displays the analysis result briefly. For example, when the bystander is surprised, the analysis unit displays the analysis result briefly. In addition, the analysis unit can also display the analysis result in detail when the bystander is calm. For example, when the bystander is calm, the analysis unit displays the analysis result in detail. In addition, the analysis unit can also quickly display the analysis result when the bystander is upset. For example, when the bystander is upset, the analysis unit displays the analysis result quickly. This allows the analysis unit to adjust the display method of the analysis result according to the emotion of the bystander. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0082] During analysis, the analysis unit can determine the priority of analysis based on the time when the video and audio were collected. For example, the analysis unit gives priority to analyzing the most recent video and audio. For example, the analysis unit gives priority to analyzing the most recent video and audio. The analysis unit can also postpone video and audio that was collected a long time ago. For example, the analysis unit postpones video and audio that was collected a long time ago. The analysis unit can also analyze video and audio that was collected at a medium time with standard priority. For example, the analysis unit analyzes video and audio that was collected at a medium time with standard priority. This allows the analysis unit to determine the priority of analysis based on the time of collection.

[0083] The analysis unit can adjust the order of analysis based on the relevance of the video and audio during analysis. For example, the analysis unit gives priority to analyzing video and audio with important relevance. For example, the analysis unit gives priority to analyzing video and audio with important relevance. The analysis unit can also postpone video and audio with low relevance. For example, the analysis unit postpones video and audio with low relevance. The analysis unit can also analyze video and audio with medium relevance in a standard order. For example, the analysis unit analyzes video and audio with medium relevance in a standard order. This allows the analysis unit to adjust the order of analysis based on relevance.

[0084] The generation unit can estimate the emotion of the bystander and adjust the expression method of the announcement based on the estimated emotion. For example, when the bystander is surprised, the generation unit generates a concise and clear announcement. For example, when the bystander is surprised, the generation unit generates a concise and clear announcement. In addition, the generation unit can also generate a detailed announcement when the bystander is calm. For example, when the bystander is calm, the generation unit generates a detailed announcement. In addition, the generation unit can also generate a quick announcement when the bystander is upset. For example, when the bystander is upset, the generation unit generates a quick announcement. This allows the generation unit to adjust the expression method of the announcement according to the emotion of the bystander. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0085] When generating an announcement, the generation unit can adjust the level of detail of the announcement based on the importance of the analysis result. For example, in the case of an important analysis result, the generation unit generates a detailed announcement. For example, in the case of an important analysis result, the generation unit generates a detailed announcement. In addition, the generation unit can also generate a concise announcement in the case of an analysis result with low importance. For example, the generation unit generates a concise announcement in the case of an analysis result with low importance. In addition, the generation unit can also generate a standard announcement in the case of an analysis result with medium importance. For example, the generation unit generates a standard announcement in the case of an analysis result with medium importance. This allows the generation unit to adjust the level of detail of the announcement based on the importance of the analysis result.

[0086] When generating an announcement, the generation unit can apply different generation algorithms depending on the category of the site. For example, in the case of a traffic accident, the generation unit applies an announcement generation algorithm dedicated to traffic accidents. For example, in the case of a traffic accident, the generation unit applies an announcement generation algorithm dedicated to traffic accidents. In addition, the generation unit can also apply an announcement generation algorithm dedicated to fires in the case of a fire. For example, in the case of a fire, the generation unit applies an announcement generation algorithm dedicated to fires. In addition, the generation unit can also apply an announcement generation algorithm dedicated to natural disasters in the case of a natural disaster. For example, in the case of a natural disaster, the generation unit applies an announcement generation algorithm dedicated to natural disasters. This allows the generation unit to apply an appropriate generation algorithm depending on the category of the site.

[0087] The generation unit can estimate the emotion of the bystander and adjust the length of the announcement based on the estimated emotion. For example, when the bystander is surprised, the generation unit generates a short and to the point announcement. For example, when the bystander is surprised, the generation unit generates a short and to the point announcement. In addition, the generation unit can also generate a detailed announcement when the bystander is calm. For example, when the bystander is calm, the generation unit generates a detailed announcement. In addition, the generation unit can also generate a quick announcement when the bystander is upset. For example, when the bystander is upset, the generation unit generates a quick announcement. This allows the generation unit to adjust the length of the announcement according to the emotion of the bystander. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0088] When generating an announcement, the generation unit can determine the priority of the announcement based on the submission time of the analysis result. For example, the generation unit preferentially generates an announcement based on the latest analysis result. For example, the generation unit preferentially generates an announcement based on the latest analysis result. The generation unit can also postpone analysis results submitted earlier. For example, the generation unit postpones analysis results submitted earlier. The generation unit can also generate an announcement with standard priority for analysis results submitted at a medium time. For example, the generation unit generates an announcement with standard priority for analysis results submitted at a medium time. This allows the generation unit to determine the priority of the announcement based on the submission time.

[0089] The generation unit can adjust the order of announcements based on the relevance of the analysis results when generating announcements. For example, the generation unit preferentially generates announcements based on analysis results having important relevance. For example, the generation unit preferentially generates announcements based on analysis results having important relevance. The generation unit can also postpone analysis results with low relevance. For example, the generation unit postpones analysis results with low relevance. The generation unit can also generate announcements in a standard order for analysis results with medium relevance. For example, the generation unit generates announcements in a standard order for analysis results with medium relevance. This allows the generation unit to adjust the order of announcements based on relevance.

[0090] The consent unit can estimate the emotion of the bystander and adjust the method of the consent process based on the estimated emotion. For example, the consent unit provides a concise and clear consent process when the bystander is surprised. For example, the consent unit provides a concise and clear consent process when the bystander is surprised. The consent unit can also provide a detailed consent process when the bystander is calm. For example, the consent unit provides a detailed consent process when the bystander is calm. The consent unit can also provide a quick consent process when the bystander is upset. For example, the consent unit provides a quick consent process when the bystander is upset. This allows the consent unit to adjust the method of the consent process according to the emotion of the bystander. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0091] During the consent process, the consent unit can select an appropriate consent method by referring to the bystander's past consent history. The consent unit selects the optimal consent method, for example, based on the method by which the bystander has consented in the past. For example, the consent unit selects the optimal consent method based on the method by which the bystander has consented in the past. The consent unit can also select a method by which consent can be obtained most quickly from the bystander's past consent history. For example, the consent unit selects a method by which consent can be obtained most quickly from the bystander's past consent history. The consent unit can also analyze the bystander's past consent history and propose an optimal consent process. For example, the consent unit analyzes the bystander's past consent history and propose an optimal consent process. This allows the consent unit to select the optimal consent method based on the past consent history.

[0092] The consent unit can estimate the emotion of the bystander and determine the priority of the consent process based on the estimated emotion. For example, when the bystander is surprised, the consent unit performs the consent process quickly. For example, when the bystander is surprised, the consent unit performs the consent process quickly. In addition, the consent unit can perform a detailed consent process when the bystander is calm. For example, when the bystander is calm, the consent unit performs a detailed consent process. In addition, the consent unit can perform a brief consent process when the bystander is upset. For example, when the bystander is upset, the consent unit performs a brief consent process. This allows the consent unit to determine the priority of the consent process according to the emotion of the bystander. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0093] The consent unit can select an appropriate consent method in consideration of the device information of the bystander during the consent process. For example, if the bystander is using a smartphone, the consent unit provides a consent method optimized for the smartphone. For example, if the bystander is using a smartphone, the consent unit provides a consent method optimized for the smartphone. In addition, if the bystander is using a tablet, the consent unit can also provide a consent method optimized for the tablet. For example, if the bystander is using a tablet, the consent unit provides a consent method optimized for the tablet. In addition, if the bystander is using smart glasses, the consent unit can also provide a consent method optimized for the smart glasses. For example, if the bystander is using smart glasses, the consent unit provides a consent method optimized for the smart glasses. This allows the consent unit to select the optimal consent method based on the device information.

[0094] The providing unit can estimate the emotion of the bystander and adjust the method of providing the announcement based on the estimated emotion. For example, when the bystander is surprised, the providing unit provides a concise and clear announcement. For example, when the bystander is surprised, the providing unit provides a concise and clear announcement. In addition, the providing unit can also provide a detailed announcement when the bystander is calm. For example, when the bystander is calm, the providing unit provides a detailed announcement. In addition, the providing unit can also provide a quick announcement when the bystander is upset. For example, when the bystander is upset, the providing unit provides a quick announcement. This allows the providing unit to adjust the method of providing the announcement according to the emotion of the bystander. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0095] The providing unit can select an appropriate providing method by referring to the past response history of the emergency response team when providing an announcement. The providing unit selects an optimal providing method, for example, based on the announcement method used in the past by the emergency response team. For example, the providing unit selects an optimal providing method based on the announcement method used in the past by the emergency response team. The providing unit can also select the most effective announcement method from the past response history of the emergency response team. For example, the providing unit selects the most effective announcement method from the past response history of the emergency response team. The providing unit can also analyze the past response history of the emergency response team and propose an optimal announcement providing method. For example, the providing unit analyzes the past response history of the emergency response team and proposes an optimal announcement providing method. This allows the providing unit to select an optimal providing method based on the past response history.

[0096] The providing unit can estimate the emotion of the bystander and determine the priority of providing the announcement based on the estimated emotion. For example, when the bystander is surprised, the providing unit quickly provides an announcement. For example, when the bystander is surprised, the providing unit quickly provides an announcement. In addition, the providing unit can also provide a detailed announcement when the bystander is calm. For example, when the bystander is calm, the providing unit provides a detailed announcement. In addition, the providing unit can also provide a concise announcement when the bystander is upset. For example, when the bystander is upset, the providing unit provides a concise announcement. Thereby, the providing unit can determine the priority of providing the announcement according to the emotion of the bystander. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0097] The providing unit can select an appropriate providing method in consideration of device information of the emergency response team when providing an announcement. For example, when the emergency response team uses a smartphone, the providing unit provides an announcement method optimized for the smartphone. For example, when the emergency response team uses a smartphone, the providing unit provides an announcement method optimized for the smartphone. In addition, when the emergency response team uses a tablet, the providing unit can also provide an announcement method optimized for the tablet. For example, when the emergency response team uses a tablet, the providing unit provides an announcement method optimized for the tablet. In addition, when the emergency response team uses a smartwatch, the providing unit can also provide an announcement method optimized for the smartwatch. For example, when the emergency response team uses a smartwatch, the providing unit provides an announcement method optimized for the smartwatch. This allows the providing unit to select an optimal providing method based on the device information.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The scene recognition system may further include a location information acquisition unit. The location information acquisition unit acquires location information from the bystander's smart glasses or smartphone and provides it to the collection unit. For example, the location information acquisition unit may identify the location of the bystander using GPS and provide it to the collection unit. The location information acquisition unit may also acquire indoor location information using Wi-Fi or Bluetooth. This allows the collection unit to optimally collect video and audio based on the location of the bystander. Furthermore, the location information acquisition unit may track the movement path of the bystander and provide it to the collection unit. For example, when the bystander is moving, the location information acquisition unit collects video and audio along the movement path. This allows the scene recognition system to collect information more effectively based on the bystander's location information.

[0100] The on-site grasping system may further include a data filtering unit. The data filtering unit filters the collected video and audio data and provides only important information to the analysis unit. For example, the data filtering unit removes noise and unnecessary information and provides clear video and audio to the analysis unit. The data filtering unit may also extract important information based on specific keywords or audio patterns. For example, the data filtering unit may preferentially provide audio containing keywords related to an emergency to the analysis unit. This allows the analysis unit to analyze important information more efficiently. Furthermore, the data filtering unit may perform image processing to improve the quality of the video. For example, the data filtering unit may adjust the brightness and contrast of the video to improve visibility. This allows the on-site grasping system to grasp the situation at the site based on higher quality data.

[0101] The on-site grasping system may further include an emergency notification unit. The emergency notification unit immediately notifies the emergency response team when an emergency response is required based on the collected information. For example, the emergency notification unit notifies the emergency response team in real time when a serious incident such as a fire or a traffic accident occurs. The emergency notification unit may also set a priority order for notifications and quickly convey the most important information. For example, the emergency notification unit may notify the occurrence of a fire as a top priority, and then notify information about a traffic accident. This allows the emergency response team to respond quickly and appropriately. Furthermore, the emergency notification unit may also select the form of notification. For example, the emergency notification unit may notify the emergency response team as a text message, a voice message, or even a video message. This allows the on-site grasping system to quickly and effectively notify the emergency response team.

[0102] The on-site understanding system can further include a data storage unit. The data storage unit securely stores the collected video and audio data so that it can be used for analysis and verification later. For example, the data storage unit uses cloud storage to store the data and make it accessible as needed. The data storage unit can also encrypt the data to ensure security. For example, the data storage unit encrypts the collected data and protects it from unauthorized access. This allows the on-site understanding system to safely manage the collected data and quickly obtain necessary information later. Furthermore, the data storage unit can also periodically back up the data. For example, the data storage unit periodically creates a backup of the data to prevent data loss. This allows the on-site understanding system to ensure the reliability and availability of the data.

[0103] The on-site grasping system may further include a user interface unit. The user interface unit provides an interface that allows the emergency response team to intuitively understand the collected information. For example, the user interface unit provides a dashboard that displays the collected video and audio data in real time. The user interface unit may also highlight important information to enable the emergency response team to respond quickly. For example, the user interface unit visually displays the location of the fire and the extent of the damage. This allows the emergency response team to quickly grasp the situation at the site and take appropriate action. Furthermore, the user interface unit may respond to voice commands and touch operations to improve the convenience of operation. For example, the user interface unit may search for specific information using voice commands and zoom in and out of a map using touch operations. This allows the on-site grasping system to provide an interface that is easy for the emergency response team to use.

[0104] The scene grasping system may further include an emotion feedback unit. The emotion feedback unit monitors the emotion of the bystander in real time and provides feedback to the collection unit and the analysis unit. For example, when the bystander is surprised, the emotion feedback unit provides the information to the collection unit and adjusts the collection timing. Also, when the bystander is upset, the emotion feedback unit can provide the information to the analysis unit and adjust the accuracy of the analysis. This allows the scene grasping system to flexibly respond based on the emotion of the bystander. Furthermore, the emotion feedback unit can accumulate emotion data of the bystander and use it for future analysis. For example, the emotion feedback unit analyzes the emotion pattern of the bystander based on the past emotion data and performs more accurate emotion estimation. This allows the scene grasping system to realize advanced information collection and analysis based on the emotion of the bystander.

[0105] The scene recognition system may further include an emotion analysis unit. The emotion analysis unit analyzes the emotions of bystanders from the collected video and audio data and provides the results to other elements. For example, the emotion analysis unit may analyze the facial expressions of bystanders from the video data and estimate emotions such as surprise and fear. The emotion analysis unit may also analyze the tone and speed of the bystanders' voices from the audio data and estimate their emotions. This allows the collection unit and analysis unit to respond flexibly based on the emotions of bystanders. Furthermore, the emotion analysis unit may also integrate multiple pieces of emotion data and perform comprehensive emotion evaluation. For example, the emotion analysis unit may integrate emotion data obtained from both video and audio to perform more accurate emotion estimation. This allows the scene recognition system to realize advanced information collection and analysis based on the emotions of bystanders.

[0106] The scene recognition system may further include an emotion notification unit. The emotion notification unit provides an appropriate notification to the emergency response team based on the emotion of the bystander. For example, if the bystander is surprised, the emotion notification unit notifies the emergency response team of the information and prompts a quick response. In addition, if the bystander is calm, the emotion notification unit may also notify the information and perform a normal response. This allows the emergency response team to perform an appropriate response based on the emotion of the bystander. Furthermore, the emotion notification unit may also select the form of the notification. For example, the emotion notification unit may provide a notification as a text message, a voice message, or even a video message. This allows the scene recognition system to flexibly respond based on the emotion of the bystander.

[0107] The on-site assessment system may further include an emotion data storage unit. The emotion data storage unit safely stores the collected emotion data so that it can be used for analysis and verification later. For example, the emotion data storage unit may use cloud storage to store the emotion data so that it can be accessed as needed. The emotion data storage unit may also encrypt the data to ensure security. This allows the on-site assessment system to safely manage the collected emotion data and quickly obtain information that will be required later. Furthermore, the emotion data storage unit may also periodically back up the data. For example, the emotion data storage unit may periodically create a backup of the data to prevent data loss. This allows the on-site assessment system to ensure the reliability and availability of the emotion data.

[0108] The scene grasping system may further include an emotion data analysis unit. The emotion data analysis unit analyzes the collected emotion data and identifies the emotion pattern of the bystander. For example, the emotion data analysis unit may analyze what emotion the bystander shows in a specific situation based on past emotion data. The emotion data analysis unit may also integrate emotion data of multiple bystanders and grasp the overall emotion tendency. This allows the scene grasping system to realize advanced information collection and analysis based on the emotion of the bystander. Furthermore, the emotion data analysis unit may provide emotion data to other elements and optimize the processing of the collection unit and the analysis unit. For example, the emotion data analysis unit may provide emotion data to the collection unit and adjust the collection timing. This allows the scene grasping system to flexibly respond based on the emotion data.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The collection unit collects video and audio from the smart glasses. For example, the collection unit uses the smart glasses' camera to collect on-site video in real time and the smart glasses' microphone to collect on-site audio in real time. The collection unit can also collect video and audio simultaneously by combining a camera and microphone. Step 2: The analysis unit analyzes the video and audio collected by the collection unit. For example, the analysis unit uses a generative AI to analyze the video and extract important information. It can also use a generative AI to analyze audio and extract important information. Furthermore, the analysis unit combines and analyzes the video and audio to grasp the situation at the scene. Step 3: The generator generates a summary announcement based on the information analyzed by the analyzer. For example, the generator can generate a text-format announcement using a generation AI, and can also generate a voice-format announcement.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0112] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, consent unit, and provision 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 collects video and audio at the scene using the camera 42 and microphone 38B of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the video and audio using a generation AI to extract important information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates announcements in text and audio formats based on the analyzed information. The consent unit is realized, for example, by the control unit 46A of the smart device 14, and manages the consent of bystanders. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides the generated announcement to the emergency response team. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 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.

[0117] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] 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.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] 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 performed in a secure state.

[0122] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] 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.

[0124] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0126] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, consent unit, and provision unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects video and audio at the scene using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the video and audio using a generation AI to extract important information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates announcements in text and audio formats based on the analyzed information. The consent unit is realized, for example, by the control unit 46A of the smart glasses 214, and manages the consent of bystanders. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides the generated announcement to the emergency response team. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] 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.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] 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 performed in a secure state.

[0138] 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.

[0139] 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.

[0140] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

[0142] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, consent unit, and provision unit 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 collects video and audio at the scene using the camera 42 and microphone 238 of the headset type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the video and audio using a generation AI to extract important information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates announcements in text and audio formats based on the analyzed information. The consent unit is realized, for example, by the control unit 46A of the headset type terminal 314, and manages the consent of bystanders. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides the generated announcement to the emergency response team. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] 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.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0153] 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 performed in a secure state.

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0155] 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.

[0156] 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.

[0157] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0159] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0163] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, consent unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects video and audio at the scene using the camera 42 and microphone 238 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the video and audio using a generation AI to extract important information. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and generates announcements in text and audio formats based on the analyzed information. The consent unit is realized, for example, by the control unit 46A of the robot 414, and manages the consent of bystanders. The provision unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides the generated announcement to the emergency response team. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0171] 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.

[0172] 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 Universal Serial Bus (USB) 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.

[0173] In addition, 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 upon request from the data processing device 12.

[0174] 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.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0177] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) A collection unit that collects video and audio from the smart glasses; an analysis unit that analyzes the video and audio collected by the collection unit; A generating unit that generates a general announcement based on the information analyzed by the analyzing unit. A system characterized by: (Appendix 2) Have a consent department to manage the consent process 2. The system of claim 1, (Appendix 3) A provision unit for providing the generated announcement is provided. 2. The system of claim 1, (Appendix 4) The analysis unit is Analyze video and audio in real time and extract information based on specific criteria 2. The system of claim 1, (Appendix 5) The generation unit is Processing to generate announcements in text or audio format based on the analysis results 2. The system of claim 1, (Appendix 6) The providing unit is Providing generated announcements to emergency response teams 4. The system of claim 3. (Appendix 7) The collecting unit includes: Estimate the emotions of bystanders and adjust the timing of video and audio collection based on the estimated emotions. 2. The system of claim 1, (Appendix 8) The collecting unit includes: Analyze bystanders' past behavioral history and select the appropriate collection method 2. The system of claim 1, (Appendix 9) The collecting unit includes: When collecting video and audio, the collection range is dynamically adjusted based on the situation on-site 2. The system of claim 1, (Appendix 10) The collecting unit includes: Estimate the emotions of bystanders and prioritize the video and audio to be collected based on the estimated emotions 2. The system of claim 1, (Appendix 11) The collecting unit includes: When collecting video and audio, the most relevant information is collected based on the geographic location of bystanders. 2. The system of claim 1, (Appendix 12) The collecting unit includes: During video and audio collection, gather relevant information based on bystander social media activity 2. The system of claim 1, (Appendix 13) The analysis unit is Estimate bystander emotions and adjust analysis accuracy based on the estimated emotions 2. The system of claim 1, (Appendix 14) The analysis unit is Adjust the level of analysis detail based on the importance of video and audio during analysis 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, apply different analysis algorithms depending on the site category 2. The system of claim 1, (Appendix 16) The analysis unit is Infer bystander emotions and adjust how analysis results are displayed based on the inferred emotions 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, the analysis priority is determined based on the time of video and audio collection. 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, the order of analysis is adjusted based on the correlation between video and audio. 2. The system of claim 1, (Appendix 19) The generation unit is Estimate bystander emotions and adjust announcements based on those emotions 2. The system of claim 1, (Appendix 20) The generation unit is When generating announcements, adjust the level of detail in the announcement based on the importance of the analysis results 2. The system of claim 1, (Appendix 21) The generation unit is When generating announcements, apply different generation algorithms depending on the venue category. 2. The system of claim 1, (Appendix 22) The generation unit is Estimate bystander emotions and adjust the length of announcements based on the estimated emotions 2. The system of claim 1, (Appendix 23) The generation unit is When generating announcements, prioritize them based on when analysis results are submitted 2. The system of claim 1, (Appendix 24) The generation unit is When generating announcements, adjust the order of announcements based on the relevance of the analysis results 2. The system of claim 1, (Appendix 25) The consent unit is Inferring bystanders' emotions and adjusting the consent process based on those emotions 3. The system of claim 2, (Appendix 26) The consent unit is During the consent process, refer to bystanders' past consent history to select the appropriate consent method 3. The system of claim 2, (Appendix 27) The consent unit is Inferring bystander emotions and prioritizing the consent process based on the inferred emotions 3. The system of claim 2, (Appendix 28) The consent unit is During the consent process, consider bystander device information to select the appropriate consent method 3. The system of claim 2, (Appendix 29) The providing unit is Infer bystander emotions and adjust how announcements are delivered based on the inferred emotions 4. The system of claim 3. (Appendix 30) The providing unit is When providing an announcement, select the appropriate method of delivery by referring to the emergency response team's past response history. 4. The system of claim 3. (Appendix 31) The providing unit is Estimate bystander emotions and prioritize announcements based on the estimated emotions 4. The system of claim 3. (Appendix 32) The providing unit is When providing an announcement, select the appropriate method of delivery taking into account the device information of the emergency response team. 4. The system of claim 3. [Explanation of symbols]

[0183] 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 video and audio from the smart glasses; an analysis unit that analyzes the video and audio collected by the collection unit; A generating unit that generates a general announcement based on the information analyzed by the analyzing unit. A system characterized by:

2. Have a consent department to manage the consent process 2. The system of claim 1 .

3. A provision unit that provides the announcement generated by the generation unit.

2. The system of claim 1 .

4. The analysis unit is Analyze video and audio in real time and extract information based on specific criteria 2. The system of claim 1 .

5. The generation unit is Processing to generate announcements in text or audio format based on the analysis results 2. The system of claim 1 .

6. The providing unit is providing the announcement generated by the generating unit to an emergency response team; 4. The system of claim 3.

7. The collecting unit includes: Estimate the emotions of bystanders and adjust the timing of video and audio collection based on the estimated emotions.

2. The system of claim 1 .

8. The collecting unit includes: Analyze bystanders' past behavioral history and select the appropriate collection method 2. The system of claim 1 .

9. The collecting unit includes: When collecting video and audio, the collection range is dynamically adjusted based on on-site conditions 2. The system of claim 1 .

10. The collecting unit includes: Estimate the emotions of bystanders and prioritize the video and audio to be collected based on the estimated emotions.

2. The system of claim 1 .

Images