system

Abstract

The system according to the embodiment aims to grasp the situation at evacuation centers and on-site in real time and to give optimal instructions for rescue operations. [Solution] The system according to the embodiment includes a collection unit, an analysis unit, an extraction unit, an instruction generation unit, a grasp unit, and a transmission unit. The collection unit collects video or audio data of residents at evacuation shelters or at the scene. The analysis unit analyzes the data collected by the collection unit. The extraction unit extracts information from the data analyzed by the analysis unit. The instruction generation unit generates rescue operation instructions based on the information extracted by the extraction unit. The grasp unit grasps the location information or activity status of rescue workers based on the instructions generated by the instruction generation unit. The transmission unit transmits and shares the information grasped by the grasp unit to the scene in real time.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology had the problem of making it difficult to grasp the situation at evacuation centers and on-site in real time and give optimal instructions for rescue operations.

[0005] The system according to the embodiment aims to grasp the situation at evacuation centers and on-site in real time and to give optimal instructions for rescue operations. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, an extraction unit, an instruction generation unit, a grasp unit, and a transmission unit. The collection unit collects video data or audio data of residents at evacuation shelters or at the scene. The analysis unit analyzes the data collected by the collection unit. The extraction unit extracts information from the data analyzed by the analysis unit. The instruction generation unit generates rescue operation instructions based on the information extracted by the extraction unit. The grasp unit grasps the location information or activity status of rescue workers based on the instructions generated by the instruction generation unit. The transmission unit transmits and shares the information grasped by the grasp unit to the scene in real time. [Effects of the Invention]

[0007] The system according to the embodiment can grasp the situation at evacuation centers and on-site in real time and give optimal instructions for rescue operations. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) A relief operation support system according to an embodiment of the present invention utilizes multimodal generation AI to allow people engaged in relief operations to receive video and audio data of evacuation shelter residents and the scene in real time and analyze the vast amount of data. This relief operation support system collects video and audio data of evacuation shelter residents and the scene, and the multimodal generation AI analyzes this data to extract important information. The extracted information is integrated to generate optimal rescue operation instructions. Furthermore, the system grasps the evacuation status (evacuated or missing) at the location where relief workers are operating and transmits and shares this information with the scene in real time. This system optimizes personnel resources and saves lives. For example, the relief operation support system collects video and audio data of evacuation shelter residents and the scene. In this process, sensors such as cameras and microphones are used to record the situation at the evacuation shelter and the scene in real time. For example, the system captures images of the evacuation shelter with a camera and collects the voices of residents with a microphone. This allows detailed information about the scene to be obtained. The multimodal generation AI then analyzes the collected data. Generative AI understands video and audio data and extracts important information. For example, it can analyze the congestion level of evacuation centers and residents' facial expressions from video data, and understand residents' requests and emergencies from audio data. This allows for a detailed understanding of the situation on the ground. The extracted information is integrated to generate optimal rescue operation instructions. Based on the extracted information, Generative AI provides specific instructions to rescue workers. For example, it can instruct them to send additional supplies or deploy personnel to respond to emergencies depending on the congestion level of the evacuation center. This allows for efficient rescue operations. Furthermore, it grasps the evacuation situation in the area where rescue workers are working and transmits and shares this information with the field in real time. Generative AI analyzes the location and activity status of rescue workers to determine whether they have evacuated or are missing. For example, when rescue workers arrive at a shelter, they can check the list of evacuated residents and instruct them to search for missing people. This allows for swift and effective rescue operations. This system optimizes personnel resources and saves lives.Generative AI analyzes massive amounts of data, extracts and integrates important information, allowing rescue workers to grasp the situation on the ground in real time and receive optimal instructions. This allows rescue workers to carry out rescue operations more efficiently and save more lives. The rescue operation support system allows rescue workers to receive video and audio data from residents in evacuation centers and the scene in real time, analyzes this massive amount of data, extracts and integrates important information, provides optimal rescue operation instructions, optimizes personnel resources, and saves lives.

[0029] A rescue operation support system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, an instruction generation unit, a grasp unit, and a transmission unit. The collection unit collects video data or audio data of residents at a shelter or at a disaster site. The collection unit records the situation at the shelter or at a disaster site in real time using sensors such as a camera or a microphone. For example, the collection unit can capture images of the shelter using a camera and collect the voices of residents using a microphone. The collection unit can also record the situation at the shelter or at a disaster site in detail using sensors such as a fixed camera or a portable microphone. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit interprets the video data and audio data and extracts important information. For example, the analysis unit can analyze the congestion situation at the shelter and the facial expressions of residents from the video data and grasp the requests of residents or emergencies from the audio data. The extraction unit extracts information from the data analyzed by the analysis unit. For example, the extraction unit can analyze the situation at the shelter and the facial expressions of residents from the video data and grasp the requests of residents or emergencies from the audio data. The instruction generation unit provides specific instructions to rescue workers based on the extracted information. For example, the instruction generation unit can issue instructions to send additional supplies or allocate personnel to respond to emergencies depending on the congestion level of the evacuation shelter. The grasping unit grasps the location information and activity status of rescue workers based on the instructions generated by the instruction generation unit. For example, the grasping unit can analyze the location information and activity status of rescue workers to grasp whether they have evacuated or are missing. The transmission unit transmits and shares the information grasped by the grasping unit to the site in real time. For example, when rescue workers arrive at the evacuation shelter, the transmission unit can check a list of evacuated residents and instruct them to search for missing people. As a result, the rescue operation support system according to the embodiment collects and analyzes data on residents at evacuation shelters and on-site data, extracts and integrates important information, and provides optimal rescue operation instructions, thereby optimizing personnel resources and saving lives.

[0030] The collection unit can record the situation at the evacuation shelter or the site in real time using sensors such as a camera or a microphone. The collection unit can record the situation at the evacuation shelter or the site in real time using sensors such as a camera or a microphone. For example, the collection unit can capture images of the evacuation shelter with a camera and collect the voices of residents with a microphone. The collection unit can also record the situation at the evacuation shelter or the site in detail using sensors such as a fixed camera or a portable microphone. In this way, the situation at the evacuation shelter or the site can be recorded in detail by using sensors such as a camera or a microphone. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input video data captured by a camera and audio data collected by a microphone into a generation AI, which can then analyze the data.

[0031] The analysis unit can analyze the video data or audio data and extract information. The analysis unit, for example, understands the video data or audio data and extracts important information. For example, the analysis unit can analyze the congestion situation at an evacuation shelter and the facial expressions of residents from the video data, and can grasp the requests of residents and emergency situations from the audio data. In this way, by understanding the video data and audio data, important information can be accurately extracted. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the video data or audio data into a generation AI, and have the generation AI analyze the data.

[0032] The extraction unit can analyze the situation at the evacuation shelter or the facial expressions of residents from the video data, and grasp the residents' requests or emergency situations from the audio data. For example, the extraction unit can analyze the situation at the evacuation shelter or the facial expressions of residents from the video data, and grasp the residents' requests or emergency situations from the audio data. For example, the extraction unit can analyze the congestion situation at the evacuation shelter or the facial expressions of residents from the video data, and grasp the residents' requests or emergency situations from the audio data. In this way, by analyzing the video data and audio data, the situation at the evacuation shelter and the residents' requests can be grasped in detail. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the video data and audio data to a generation AI, which can analyze the data.

[0033] The instruction generation unit can provide specific instructions to rescue workers based on the extracted information. The instruction generation unit can provide specific instructions to rescue workers based on, for example, the extracted information. For example, the instruction generation unit can issue instructions to send additional supplies or to allocate personnel to respond to the emergency depending on the congestion situation at the evacuation shelter. In this way, by providing specific instructions based on the extracted information, rescue operations can be carried out efficiently. Some or all of the above-mentioned processing in the instruction generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the instruction generation unit can input the extracted information into a generation AI, which can generate instructions.

[0034] The ascertaining unit can analyze the location information or activity status of rescue workers to determine whether they have evacuated or are missing. The ascertaining unit can, for example, analyze the location information and activity status of rescue workers to determine whether they have evacuated or are missing. For example, the ascertaining unit can analyze the location information and activity status of rescue workers, check a list of evacuated residents, and instruct a search for missing people. In this way, by analyzing the location information and activity status of rescue workers, it is possible to accurately determine whether they have evacuated or are missing. Some or all of the above-mentioned processing in the ascertaining unit may be performed using, for example, AI, or may be performed without using AI. For example, the ascertaining unit can input the location information and activity status of rescue workers to a generation AI, which can then analyze the data.

[0035] The transmission unit can transmit and share the information grasped by the grasping unit to the site in real time. The transmission unit, for example, transmits and shares the information grasped by the grasping unit to the site in real time. For example, when rescue workers arrive at an evacuation shelter, the transmission unit can check the list of evacuated residents and instruct them to search for missing persons. In this way, by transmitting and sharing the grasped information in real time, rescue operations at the site can be carried out quickly and effectively. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the information grasped by the grasping unit into a generation AI, and the generation AI can transmit and share the information.

[0036] During data collection, the collection unit can analyze the past behavioral history of evacuation shelter residents and select the optimal collection method. The collection unit, for example, analyzes the past behavioral history of evacuation shelter residents and selects the optimal collection method. For example, the collection unit analyzes what evacuation behavior the evacuation shelter residents have taken in the past and selects a data collection method for similar situations. The collection unit can also analyze what information the evacuation shelter residents have provided in the past and prioritize collecting similar information. Furthermore, the collection unit can analyze what media (audio, video, etc.) the evacuation shelter residents have used in the past and select the optimal media. In this way, the optimal collection method can be selected by analyzing the past behavioral history. Some or all of the above-described processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the residents' past behavioral history data into a generation AI, and the generation AI can select a data collection method.

[0037] The collection unit can filter the data based on the current health status and stress level of the evacuation shelter residents during collection. The collection unit can filter, for example, based on the current health status and stress level of the evacuation shelter residents. For example, if the evacuation shelter residents are in poor health, the collection unit can prioritize collecting health-related data. Furthermore, if the evacuation shelter residents are at a high stress level, the collection unit can also prioritize collecting stress-related data. Furthermore, if the evacuation shelter residents are in good health, the collection unit can also collect data about their general living conditions. This allows for more appropriate data to be collected by filtering based on the residents' health status and stress level. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data on the residents' health status and stress level into a generation AI, which can then filter the data.

[0038] During collection, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the residents of the evacuation shelter. The collection unit, for example, prioritizes collecting highly relevant data by taking into account the geographical location information of the residents of the evacuation shelter. For example, if the residents of the evacuation shelter are in a specific area, the collection unit prioritizes collecting data related to that area. In addition, if the residents of the evacuation shelter are moving, the collection unit can also prioritize collecting data related to their movement route. Furthermore, if the residents of the evacuation shelter are in a specific evacuation shelter, the collection unit can also prioritize collecting data related to that evacuation shelter. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the residents' geographical location information to a generation AI, and the generation AI can collect data.

[0039] During collection, the collection unit can analyze the social media activities of the evacuation shelter residents and collect related data. The collection unit, for example, analyzes the social media activities of the evacuation shelter residents and collects related data. For example, the collection unit collects information posted by the evacuation shelter residents on social media. The collection unit can also collect information on accounts that the evacuation shelter residents follow on social media. Furthermore, the collection unit can collect images and videos that the evacuation shelter residents have shared on social media. This allows for efficient collection of related data by analyzing social media activities. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the residents' social media activity data into a generation AI, which then collects the data.

[0040] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the data during analysis. For example, the analysis unit performs a detailed analysis on data of high importance. The analysis unit can also perform a simplified analysis on data of low importance. Furthermore, the analysis unit can also perform an analysis at an appropriate level of detail on data of medium importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the data to a generation AI, and the generation AI can adjust the level of detail of the analysis.

[0041] The analysis unit can apply different analysis algorithms depending on the category of data during analysis. For example, the analysis unit can apply different analysis algorithms depending on the category of data during analysis. For example, the analysis unit can apply an image analysis algorithm to video data. The analysis unit can also apply an audio analysis algorithm to audio data. Furthermore, the analysis unit can apply a natural language processing algorithm to text data. This improves the accuracy of analysis by applying an appropriate analysis algorithm depending on the category of data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the category of data to a generation AI, which can then apply an appropriate analysis algorithm.

[0042] The analysis unit can determine the analysis priority based on the time of data collection during analysis. The analysis unit, for example, determines the analysis priority based on the time of data collection during analysis. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also analyze older data as needed. Furthermore, the analysis unit can determine an appropriate analysis order based on the time of data collection. In this way, by determining the analysis priority based on the time of data collection, the most recent information can be analyzed preferentially. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time of data collection into the generation AI, and the generation AI can determine the analysis priority.

[0043] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the data during analysis. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can determine an appropriate analysis order based on the relevance of the data. This enables efficient analysis by adjusting the analysis order based on the relevance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of the data into a generation AI, and the generation AI can adjust the order of analysis.

[0044] The extraction unit can improve the accuracy of extraction by taking into account the interrelationships between data during extraction. For example, the extraction unit can improve the accuracy of extraction by taking into account the interrelationships between data during extraction. For example, the extraction unit extracts important information by taking into account the interrelationships between video data and audio data. The extraction unit can also extract important information by taking into account the interrelationships between text data and audio data. Furthermore, the extraction unit can extract important information by taking into account the interrelationships between video data and text data. In this way, the accuracy of extraction is improved by taking into account the interrelationships between data. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the interrelationships between data into a generation AI, and the generation AI can improve the accuracy of extraction.

[0045] The extraction unit can perform extraction while taking into account attribute information of the data submitter. For example, the extraction unit can perform extraction while taking into account attribute information of the data submitter. For example, if the data submitter is a resident of an evacuation shelter, the extraction unit can perform extraction while taking into account attribute information of the data submitter. Furthermore, if the data submitter is a relief worker, the extraction unit can perform extraction while taking into account attribute information of the data submitter. Furthermore, if the data submitter is a third party, the extraction unit can perform extraction while taking into account attribute information of the data submitter. In this way, more appropriate information can be extracted by taking into account the attribute information of the data submitter. Some or all of the above-described processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input attribute information of the data submitter into a generation AI, and the generation AI can perform extraction.

[0046] The extraction unit can perform extraction taking into account the geographical distribution of the data. For example, the extraction unit performs extraction taking into account the geographical distribution of the data. For example, the extraction unit preferentially extracts data related to a specific region. The extraction unit can also extract data that is geographically distributed over a wide area. Furthermore, the extraction unit can extract geographically limited data. In this way, by taking the geographical distribution of the data into account, highly relevant information can be extracted. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the geographical distribution of the data into a generation AI, and the generation AI can perform extraction.

[0047] The extraction unit can improve the accuracy of extraction by referring to literature related to the data during extraction. The extraction unit can improve the accuracy of extraction by referring to literature related to the data during extraction, for example. For example, the extraction unit extracts important information by referring to literature related to the data. The extraction unit can also improve the accuracy of extraction by referring to literature related to the data. Furthermore, the extraction unit can improve the reliability of extraction by referring to literature related to the data. As a result, by referring to related literature, the accuracy and reliability of extraction are improved. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input literature related to the data into a generation AI, which can improve the accuracy of extraction.

[0048] The instruction generation unit can adjust the level of detail of the instruction based on the importance of the extracted information when generating the instruction. For example, the instruction generation unit adjusts the level of detail of the instruction based on the importance of the extracted information when generating the instruction. For example, the instruction generation unit provides detailed instructions for information of high importance. The instruction generation unit can also provide simplified instructions for information of low importance. Furthermore, the instruction generation unit can also provide instructions with an appropriate level of detail for information of medium importance. This enables efficient instruction by adjusting the level of detail of the instruction based on the importance of the information. Some or all of the above-mentioned processing in the instruction generation unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction generation unit can input the importance of the information to the generation AI, and the generation AI can adjust the level of detail of the instruction.

[0049] The instruction generation unit can apply different instruction algorithms depending on the category of information when generating instructions. For example, the instruction generation unit applies different instruction algorithms depending on the category of information when generating instructions. For example, the instruction generation unit applies an algorithm that instructs a rapid response to information regarding an emergency. The instruction generation unit can also apply an algorithm that instructs efficient distribution to information regarding the distribution of supplies. Furthermore, the instruction generation unit can apply an algorithm that instructs appropriate management to information regarding the management of evacuation shelters. In this way, by applying an appropriate instruction algorithm depending on the category of information, the accuracy of instructions is improved. Some or all of the above-mentioned processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the category of information to the generation AI, and the generation AI can apply an appropriate instruction algorithm.

[0050] The instruction generation unit can determine the priority of instructions based on the time when information was collected when generating the instructions. The instruction generation unit, for example, determines the priority of instructions based on the time when information was collected when generating the instructions. For example, the instruction generation unit provides instructions preferentially based on the latest information. The instruction generation unit can also provide instructions for older information as needed. Furthermore, the instruction generation unit can determine an appropriate instruction order based on the time when information was collected. In this way, by determining the priority of instructions based on the time when information was collected, instructions based on the latest information can be provided. Some or all of the above-described processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the time when information was collected into the generation AI, and the generation AI can determine the priority of instructions.

[0051] The instruction generation unit can adjust the order of instructions based on the relevance of information when generating instructions. The instruction generation unit, for example, adjusts the order of instructions based on the relevance of information when generating instructions. For example, the instruction generation unit provides instructions preferentially based on highly relevant information. The instruction generation unit can also provide instructions for less relevant information at a later date. Furthermore, the instruction generation unit can determine an appropriate order of instructions based on the relevance of information. This enables efficient instruction by adjusting the order of instructions based on the relevance of information. Some or all of the above-described processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the relevance of information to a generation AI, and the generation AI can adjust the order of instructions.

[0052] The ascertaining unit can analyze the past activity history of the relief workers and select the optimal ascertaining method when ascertaining. For example, the ascertaining unit can analyze the past activity history of the relief workers and select the optimal ascertaining method when ascertaining. For example, the ascertaining unit can analyze what activities the relief workers have performed in the past and select an ascertaining method for similar situations. The ascertaining unit can also analyze what information the relief workers have provided in the past and prioritize ascertaining similar information. Furthermore, the ascertaining unit can analyze what media (audio, video, etc.) the relief workers have used in the past and select the optimal media. In this way, the optimal ascertaining method can be selected by analyzing the past activity history. Some or all of the above-described processing in the ascertaining unit can be performed using, for example, AI, or can be performed without using AI. For example, the ascertaining unit can input the past activity history data of the relief workers into the generation AI, and the generation AI can select the ascertaining method.

[0053] The ascertaining unit can perform filtering based on the current health condition and stress level of the relief worker when ascertaining. For example, the ascertaining unit can perform filtering based on the current health condition and stress level of the relief worker when ascertaining. For example, if the relief worker is in poor health, the ascertaining unit can prioritize ascertaining health-related information. Furthermore, if the relief worker is at a high stress level, the ascertaining unit can also prioritize ascertaining stress-related information. Furthermore, if the relief worker is in good health, the ascertaining unit can also ascertain information about the general activity status. As a result, more appropriate information can be ascertained by filtering based on the relief worker's health condition and stress level. Some or all of the above-described processing in the ascertaining unit can be performed using, for example, AI, or without AI. For example, the ascertaining unit can input data on the relief worker's health condition and stress level into the generating AI, and the generating AI can filter the data.

[0054] The ascertaining unit can prioritize ascertaining highly relevant information by taking into account the geographical location information of the relief workers when ascertaining. For example, the ascertaining unit prioritizes ascertaining highly relevant information by taking into account the geographical location information of the relief workers when ascertaining. For example, if the relief workers are in a specific area, the ascertaining unit prioritizes ascertaining information related to that area. Furthermore, if the relief workers are traveling, the ascertaining unit can also prioritize ascertaining information related to their travel route. Furthermore, if the relief workers are in a specific evacuation shelter, the ascertaining unit can also prioritize ascertaining information related to the evacuation shelter. In this way, by taking the geographical location information into account, highly relevant information can be prioritized. Some or all of the above-described processing in the ascertaining unit may be performed using, for example, AI, or may be performed without using AI. For example, the ascertaining unit can input the geographical location information of the relief workers to the generation AI, and the generation AI can ascertain the information.

[0055] The ascertaining unit can analyze the social media activities of the relief workers and ascertain related information during ascertaining. For example, the ascertaining unit analyzes the social media activities of the relief workers and ascertains related information during ascertaining. For example, the ascertaining unit ascertains information posted by the relief workers on social media. The ascertaining unit can also ascertain information on accounts the relief workers follow on social media. Furthermore, the ascertaining unit can ascertain images and videos shared by the relief workers on social media. In this way, related information can be efficiently ascertained by analyzing social media activities. Some or all of the above-described processing in the ascertaining unit may be performed using, for example, AI, or may be performed without using AI. For example, the ascertaining unit can input social media activity data of the relief workers into a generation AI, and the generation AI can ascertain the information.

[0056] The transmission unit can analyze the past activity history of the relief worker and select the optimal transmission method when transmitting a message. For example, the transmission unit analyzes the past activity history of the relief worker and selects the optimal transmission method when transmitting a message. For example, the transmission unit analyzes what activities the relief worker has performed in the past and selects a transmission method for similar situations. The transmission unit can also analyze what information the relief worker has provided in the past and prioritize transmitting similar information. Furthermore, the transmission unit can analyze what media (audio, video, etc.) the relief worker has used in the past and select the optimal media. In this way, the optimal transmission method can be selected by analyzing the past activity history. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the past activity history data of the relief worker into a generation AI and have the generation AI select the transmission method.

[0057] The transmission unit can filter information based on the current health condition and stress level of the relief worker when transmitting the information. For example, the transmission unit can filter information based on the current health condition and stress level of the relief worker when transmitting the information. For example, if the relief worker is in poor health, the transmission unit can prioritize transmitting health-related information. Furthermore, if the relief worker is at a high stress level, the transmission unit can also prioritize transmitting stress-related information. Furthermore, if the relief worker is in good health, the transmission unit can transmit information about the general activity status. In this way, filtering based on the health condition and stress level of the relief worker allows more appropriate information to be transmitted. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input data on the health condition and stress level of the relief worker into the generation AI, and the generation AI can filter the data.

[0058] The transmission unit can prioritize relevant information when transmitting information by taking into consideration the geographical location information of the relief worker. For example, the transmission unit prioritizes relevant information when transmitting information by taking into consideration the geographical location information of the relief worker. For example, if the relief worker is in a specific area, the transmission unit can prioritize information related to that area. Also, if the relief worker is traveling, the transmission unit can prioritize information related to the travel route. Furthermore, if the relief worker is in a specific evacuation shelter, the transmission unit can prioritize information related to the evacuation shelter. In this way, by taking the geographical location information into consideration, highly relevant information can be prioritized. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the geographical location information of the relief worker into a generation AI, and the generation AI can transmit the information.

[0059] The transmission unit can analyze the social media activities of the relief workers and transmit relevant information at the time of transmission. For example, the transmission unit analyzes the social media activities of the relief workers and transmits relevant information at the time of transmission. For example, the transmission unit transmits information posted by the relief workers on social media. The transmission unit can also transmit information about accounts that the relief workers follow on social media. Furthermore, the transmission unit can also transmit images and videos that the relief workers have shared on social media. In this way, by analyzing social media activities, relevant information can be transmitted efficiently. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input social media activity data of the relief workers into a generation AI, and the generation AI can transmit information.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] During data collection, the collection unit can analyze the past behavioral history of evacuation shelter residents and select the optimal collection method. For example, the collection unit can analyze what evacuation behavior the evacuation shelter residents have taken in the past and select a data collection method for similar situations. The collection unit can also analyze what information the evacuation shelter residents have provided in the past and prioritize collecting similar information. Furthermore, the collection unit can analyze what media (audio, video, etc.) the evacuation shelter residents have used in the past and select the optimal media. In this way, the optimal collection method can be selected by analyzing the past behavioral history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the residents' past behavioral history data into a generation AI, and the generation AI can select a data collection method.

[0062] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis on data of high importance. The analysis unit can also perform a simplified analysis on data of low importance. Furthermore, the analysis unit can also perform an analysis with an appropriate level of detail on data of medium importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the data to the generation AI, and the generation AI can adjust the level of detail of the analysis.

[0063] When generating instructions, the instruction generation unit can adjust the level of detail of the instructions based on the importance of the extracted information. For example, the instruction generation unit provides detailed instructions for information of high importance. The instruction generation unit can also provide simplified instructions for information of low importance. Furthermore, the instruction generation unit can also provide instructions with an appropriate level of detail for information of medium importance. This enables efficient instructions to be given by adjusting the level of detail of the instructions based on the importance of the information. Some or all of the above-described processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the importance of the information to the generation AI, and the generation AI can adjust the level of detail of the instructions.

[0064] When performing the assessment, the assessment unit can analyze the past activity history of the relief workers and select the optimal assessment method. For example, the assessment unit can analyze what activities the relief workers have performed in the past and select an assessment method for similar situations. The assessment unit can also analyze what information the relief workers have provided in the past and prioritize assessing similar information. Furthermore, the assessment unit can analyze what media (audio, video, etc.) the relief workers have used in the past and select the optimal media. In this way, the optimal assessment method can be selected by analyzing the past activity history. Some or all of the above-described processing in the assessment unit may be performed using, for example, AI, or may be performed without using AI. For example, the assessment unit can input the past activity history data of the relief workers into the generation AI, and the generation AI can select the assessment method.

[0065] When making a transmission, the transmission unit can analyze the past activity history of the relief worker and select the optimal transmission method. For example, the transmission unit analyzes what activities the relief worker has performed in the past and selects a transmission method for similar situations. The transmission unit can also analyze what information the relief worker has provided in the past and transmit similar information preferentially. Furthermore, the transmission unit can analyze what media (audio, video, etc.) the relief worker has used in the past and select the optimal media. In this way, the optimal transmission method can be selected by analyzing the past activity history. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can analyze the past activity history of the relief worker and select the optimal transmission method for similar situations. Historical data can be input into the generation AI, which can then select the method of transmission.

[0066] The processing flow of the first embodiment will be briefly explained below.

[0067] Step 1: The collection unit collects video data or audio data of residents at the evacuation center or at the site. The collection unit records the situation at the evacuation center or at the site in real time using sensors such as cameras and microphones. For example, the collection unit can capture images of the evacuation center with a camera and collect the voices of residents with a microphone. The collection unit can also record the situation at the evacuation center or at the site in detail using sensors such as fixed cameras and portable microphones. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit, for example, understands the video data and audio data and extracts important information. For example, the analysis unit can analyze the congestion situation at evacuation shelters and the facial expressions of residents from the video data, and can understand the requests of residents and emergency situations from the audio data. Step 3: The extraction unit extracts information from the data analyzed by the analysis unit. For example, the extraction unit can analyze the situation at the evacuation shelter and the expressions of the residents from the video data, and can understand the residents' requests and emergency situations from the audio data. Step 4: The instruction generator provides specific instructions to relief workers based on the extracted information. For example, the instruction generator can instruct the evacuation center to send additional supplies or allocate personnel to respond to the emergency, depending on the overcrowding situation. Step 5: The ascertaining unit ascertains the location information and activity status of the rescue workers based on the instructions generated by the instruction generating unit. The ascertaining unit can, for example, analyze the location information and activity status of the rescue workers and determine whether they have evacuated or are missing. Step 6: The information gathered by the information gathering unit is sent to the scene in real time and shared. For example, when rescue workers arrive at an evacuation center, the information gathering unit can check the list of evacuated residents and instruct them to search for missing people.

[0068] (Example 2) A relief operation support system according to an embodiment of the present invention utilizes multimodal generation AI to allow people engaged in relief operations to receive video and audio data of evacuation shelter residents and the scene in real time and analyze the vast amount of data. This relief operation support system collects video and audio data of evacuation shelter residents and the scene, and the multimodal generation AI analyzes this data to extract important information. The extracted information is integrated to generate optimal rescue operation instructions. Furthermore, the system grasps the evacuation status (evacuated or missing) at the location where relief workers are operating and transmits and shares this information with the scene in real time. This system optimizes personnel resources and saves lives. For example, the relief operation support system collects video and audio data of evacuation shelter residents and the scene. In this process, sensors such as cameras and microphones are used to record the situation at the evacuation shelter and the scene in real time. For example, the system captures images of the evacuation shelter with a camera and collects the voices of residents with a microphone. This allows detailed information about the scene to be obtained. The multimodal generation AI then analyzes the collected data. Generative AI understands video and audio data and extracts important information. For example, it can analyze the congestion level of evacuation centers and residents' facial expressions from video data, and understand residents' requests and emergencies from audio data. This allows for a detailed understanding of the situation on the ground. The extracted information is integrated to generate optimal rescue operation instructions. Based on the extracted information, Generative AI provides specific instructions to rescue workers. For example, it can instruct them to send additional supplies or deploy personnel to respond to emergencies depending on the congestion level of the evacuation center. This allows for efficient rescue operations. Furthermore, it grasps the evacuation situation in the area where rescue workers are working and transmits and shares this information with the field in real time. Generative AI analyzes the location and activity status of rescue workers to determine whether they have evacuated or are missing. For example, when rescue workers arrive at a shelter, they can check the list of evacuated residents and instruct them to search for missing people. This allows for swift and effective rescue operations. This system optimizes personnel resources and saves lives.Generative AI analyzes massive amounts of data, extracts and integrates important information, allowing rescue workers to grasp the situation on the ground in real time and receive optimal instructions. This allows rescue workers to carry out rescue operations more efficiently and save more lives. The rescue operation support system allows rescue workers to receive video and audio data from residents in evacuation centers and the scene in real time, analyzes this massive amount of data, extracts and integrates important information, provides optimal rescue operation instructions, optimizes personnel resources, and saves lives.

[0069] A rescue operation support system according to an embodiment includes a collection unit, an analysis unit, an extraction unit, an instruction generation unit, a grasp unit, and a transmission unit. The collection unit collects video data or audio data of residents at a shelter or at a disaster site. The collection unit records the situation at the shelter or at a disaster site in real time using sensors such as a camera or a microphone. For example, the collection unit can capture images of the shelter using a camera and collect the voices of residents using a microphone. The collection unit can also record the situation at the shelter or at a disaster site in detail using sensors such as a fixed camera or a portable microphone. The analysis unit analyzes the data collected by the collection unit. For example, the analysis unit interprets the video data and audio data and extracts important information. For example, the analysis unit can analyze the congestion situation at the shelter and the facial expressions of residents from the video data and grasp the requests of residents or emergencies from the audio data. The extraction unit extracts information from the data analyzed by the analysis unit. For example, the extraction unit can analyze the situation at the shelter and the facial expressions of residents from the video data and grasp the requests of residents or emergencies from the audio data. The instruction generation unit provides specific instructions to rescue workers based on the extracted information. For example, the instruction generation unit can issue instructions to send additional supplies or allocate personnel to respond to emergencies depending on the congestion level of the evacuation shelter. The grasping unit grasps the location information and activity status of rescue workers based on the instructions generated by the instruction generation unit. For example, the grasping unit can analyze the location information and activity status of rescue workers to grasp whether they have evacuated or are missing. The transmission unit transmits and shares the information grasped by the grasping unit to the site in real time. For example, when rescue workers arrive at the evacuation shelter, the transmission unit can check a list of evacuated residents and instruct them to search for missing people. As a result, the rescue operation support system according to the embodiment collects and analyzes data on residents at evacuation shelters and on-site data, extracts and integrates important information, and provides optimal rescue operation instructions, thereby optimizing personnel resources and saving lives.

[0070] The collection unit can record the situation at the evacuation shelter or the site in real time using sensors such as a camera or a microphone. The collection unit can record the situation at the evacuation shelter or the site in real time using sensors such as a camera or a microphone. For example, the collection unit can capture images of the evacuation shelter with a camera and collect the voices of residents with a microphone. The collection unit can also record the situation at the evacuation shelter or the site in detail using sensors such as a fixed camera or a portable microphone. In this way, the situation at the evacuation shelter or the site can be recorded in detail by using sensors such as a camera or a microphone. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or can be performed without using AI. For example, the collection unit can input video data captured by a camera and audio data collected by a microphone into a generation AI, which can then analyze the data.

[0071] The analysis unit can analyze the video data or audio data and extract information. The analysis unit, for example, understands the video data or audio data and extracts important information. For example, the analysis unit can analyze the congestion situation at an evacuation shelter and the facial expressions of residents from the video data, and can grasp the requests of residents and emergency situations from the audio data. In this way, by understanding the video data and audio data, important information can be accurately extracted. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the video data or audio data into a generation AI, and have the generation AI analyze the data.

[0072] The extraction unit can analyze the situation at the evacuation shelter or the facial expressions of residents from the video data, and grasp the residents' requests or emergency situations from the audio data. For example, the extraction unit can analyze the situation at the evacuation shelter or the facial expressions of residents from the video data, and grasp the residents' requests or emergency situations from the audio data. For example, the extraction unit can analyze the congestion situation at the evacuation shelter or the facial expressions of residents from the video data, and grasp the residents' requests or emergency situations from the audio data. In this way, by analyzing the video data and audio data, the situation at the evacuation shelter and the residents' requests can be grasped in detail. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the video data and audio data to a generation AI, which can analyze the data.

[0073] The instruction generation unit can provide specific instructions to rescue workers based on the extracted information. The instruction generation unit can provide specific instructions to rescue workers based on, for example, the extracted information. For example, the instruction generation unit can issue instructions to send additional supplies or to allocate personnel to respond to the emergency depending on the congestion situation at the evacuation shelter. In this way, by providing specific instructions based on the extracted information, rescue operations can be carried out efficiently. Some or all of the above-mentioned processing in the instruction generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the instruction generation unit can input the extracted information into a generation AI, which can generate instructions.

[0074] The ascertaining unit can analyze the location information or activity status of rescue workers to determine whether they have evacuated or are missing. The ascertaining unit can, for example, analyze the location information and activity status of rescue workers to determine whether they have evacuated or are missing. For example, the ascertaining unit can analyze the location information and activity status of rescue workers, check a list of evacuated residents, and instruct a search for missing people. In this way, by analyzing the location information and activity status of rescue workers, it is possible to accurately determine whether they have evacuated or are missing. Some or all of the above-mentioned processing in the ascertaining unit may be performed using, for example, AI, or may be performed without using AI. For example, the ascertaining unit can input the location information and activity status of rescue workers to a generation AI, which can then analyze the data.

[0075] The transmission unit can transmit and share the information grasped by the grasping unit to the site in real time. The transmission unit, for example, transmits and shares the information grasped by the grasping unit to the site in real time. For example, when rescue workers arrive at an evacuation shelter, the transmission unit can check the list of evacuated residents and instruct them to search for missing persons. In this way, by transmitting and sharing the grasped information in real time, rescue operations at the site can be carried out quickly and effectively. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the information grasped by the grasping unit into a generation AI, and the generation AI can transmit and share the information.

[0076] The collection unit can estimate the emotions of the evacuation shelter residents and adjust the type of data to be collected based on the estimated emotions. For example, the collection unit estimates the emotions of the evacuation shelter residents and adjusts the type of data to be collected based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the collection unit can prioritize collecting the residents' tone of voice and facial expressions. Furthermore, if the evacuation shelter residents are relaxed, the collection unit can also collect ambient sounds and background images. Furthermore, if the evacuation shelter residents are facing an emergency, the collection unit can prioritize collecting audio and video related to the emergency. This allows for more appropriate data to be collected by adjusting the type of data to be collected based on the residents' emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input residents' emotional data into the generation AI, and the generation AI can collect the data.

[0077] During data collection, the collection unit can analyze the past behavioral history of evacuation shelter residents and select the optimal collection method. The collection unit, for example, analyzes the past behavioral history of evacuation shelter residents and selects the optimal collection method. For example, the collection unit analyzes what evacuation behavior the evacuation shelter residents have taken in the past and selects a data collection method for similar situations. The collection unit can also analyze what information the evacuation shelter residents have provided in the past and prioritize collecting similar information. Furthermore, the collection unit can analyze what media (audio, video, etc.) the evacuation shelter residents have used in the past and select the optimal media. In this way, the optimal collection method can be selected by analyzing the past behavioral history. Some or all of the above-described processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the residents' past behavioral history data into a generation AI, and the generation AI can select a data collection method.

[0078] The collection unit can filter the data based on the current health status and stress level of the evacuation shelter residents during collection. The collection unit can filter, for example, based on the current health status and stress level of the evacuation shelter residents. For example, if the evacuation shelter residents are in poor health, the collection unit can prioritize collecting health-related data. Furthermore, if the evacuation shelter residents are at a high stress level, the collection unit can also prioritize collecting stress-related data. Furthermore, if the evacuation shelter residents are in good health, the collection unit can also collect data about their general living conditions. This allows for more appropriate data to be collected by filtering based on the residents' health status and stress level. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input data on the residents' health status and stress level into a generation AI, which can then filter the data.

[0079] The collection unit can estimate the emotions of the evacuation shelter residents and determine the priority of data to be collected based on the estimated emotions. For example, the collection unit can estimate the emotions of the evacuation shelter residents and determine the priority of data to be collected based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the collection unit can prioritize collecting data related to anxiety. Also, if the evacuation shelter residents are relaxed, the collection unit can prioritize collecting data related to relaxation. Furthermore, if the evacuation shelter residents are facing an emergency, the collection unit can prioritize collecting data related to the emergency. In this way, by determining the priority of data to be collected based on the emotions of the residents, important data can be collected preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the residents' emotion data into a generation AI, and the generation AI can determine the priority of the data.

[0080] During collection, the collection unit can prioritize collecting highly relevant data by taking into account the geographical location information of the residents of the evacuation shelter. The collection unit, for example, prioritizes collecting highly relevant data by taking into account the geographical location information of the residents of the evacuation shelter. For example, if the residents of the evacuation shelter are in a specific area, the collection unit prioritizes collecting data related to that area. In addition, if the residents of the evacuation shelter are moving, the collection unit can also prioritize collecting data related to their movement route. Furthermore, if the residents of the evacuation shelter are in a specific evacuation shelter, the collection unit can also prioritize collecting data related to that evacuation shelter. In this way, highly relevant data can be collected preferentially by taking into account the geographical location information. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the residents' geographical location information to a generation AI, and the generation AI can collect data.

[0081] During collection, the collection unit can analyze the social media activities of the evacuation shelter residents and collect related data. The collection unit, for example, analyzes the social media activities of the evacuation shelter residents and collects related data. For example, the collection unit collects information posted by the evacuation shelter residents on social media. The collection unit can also collect information on accounts that the evacuation shelter residents follow on social media. Furthermore, the collection unit can collect images and videos that the evacuation shelter residents have shared on social media. This allows for efficient collection of related data by analyzing social media activities. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the residents' social media activity data into a generation AI, which then collects the data.

[0082] The analysis unit can estimate the emotions of the evacuation shelter residents and adjust the presentation method of the analysis based on the estimated emotions. For example, the analysis unit can estimate the emotions of the evacuation shelter residents and adjust the presentation method of the analysis based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the analysis unit can provide the analysis results in a simple and easy-to-understand format. Furthermore, if the evacuation shelter residents are relaxed, the analysis unit can also provide detailed analysis results. Furthermore, if the evacuation shelter residents are facing an emergency, the analysis unit can also provide information that is highly urgent. This allows for more appropriate analysis results to be provided by adjusting the presentation method of the analysis based on the emotions of the residents. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the residents' emotion data into a generation AI, and the generation AI can adjust the presentation method of the analysis.

[0083] The analysis unit can adjust the level of detail of the analysis based on the importance of the data during analysis. The analysis unit, for example, adjusts the level of detail of the analysis based on the importance of the data during analysis. For example, the analysis unit performs a detailed analysis on data of high importance. The analysis unit can also perform a simplified analysis on data of low importance. Furthermore, the analysis unit can also perform an analysis at an appropriate level of detail on data of medium importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the data to a generation AI, and the generation AI can adjust the level of detail of the analysis.

[0084] The analysis unit can apply different analysis algorithms depending on the category of data during analysis. For example, the analysis unit can apply different analysis algorithms depending on the category of data during analysis. For example, the analysis unit can apply an image analysis algorithm to video data. The analysis unit can also apply an audio analysis algorithm to audio data. Furthermore, the analysis unit can apply a natural language processing algorithm to text data. This improves the accuracy of analysis by applying an appropriate analysis algorithm depending on the category of data. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can input the category of data to a generation AI, which can then apply an appropriate analysis algorithm.

[0085] The analysis unit can estimate the emotions of the evacuation shelter residents and adjust the length of the analysis based on the estimated emotions. For example, the analysis unit estimates the emotions of the evacuation shelter residents and adjusts the length of the analysis based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the analysis unit can provide a short and concise analysis result. If the evacuation shelter residents are relaxed, the analysis unit can also provide a detailed analysis result. Furthermore, if the evacuation shelter residents are facing an emergency, the analysis unit can quickly provide an analysis result. This allows for adjusting the length of the analysis based on the residents' emotions to provide an analysis result of an appropriate length. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit can be performed using AI, for example, or without AI. For example, the analysis unit can input the residents' emotion data into the generation AI and have the generation AI adjust the length of the analysis.

[0086] The analysis unit can determine the analysis priority based on the time of data collection during analysis. The analysis unit, for example, determines the analysis priority based on the time of data collection during analysis. For example, the analysis unit prioritizes analysis of the most recent data. The analysis unit can also analyze older data as needed. Furthermore, the analysis unit can determine an appropriate analysis order based on the time of data collection. In this way, by determining the analysis priority based on the time of data collection, the most recent information can be analyzed preferentially. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time of data collection into the generation AI, and the generation AI can determine the analysis priority.

[0087] The analysis unit can adjust the order of analysis based on the relevance of the data during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the data during analysis. For example, the analysis unit prioritizes analysis of highly relevant data. The analysis unit can also postpone analysis of less relevant data. Furthermore, the analysis unit can determine an appropriate analysis order based on the relevance of the data. This enables efficient analysis by adjusting the analysis order based on the relevance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of the data into a generation AI, and the generation AI can adjust the order of analysis.

[0088] The extraction unit can estimate the emotions of the evacuation shelter residents and determine the priority of information to be extracted based on the estimated emotions. For example, the extraction unit can estimate the emotions of the evacuation shelter residents and determine the priority of information to be extracted based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the extraction unit can prioritize extracting information related to anxiety. Furthermore, if the evacuation shelter residents are relaxed, the extraction unit can prioritize extracting information related to relaxation. Furthermore, if the evacuation shelter residents are facing an emergency, the extraction unit can prioritize extracting information related to the emergency. Thus, by determining the priority of information to be extracted based on the emotions of the residents, important information can be preferentially extracted. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the extraction unit can be performed using, for example, AI, or without AI. For example, the extraction unit can input the residents' emotion data into a generation AI, which can then prioritize the information.

[0089] The extraction unit can improve the accuracy of extraction by taking into account the interrelationships between data during extraction. For example, the extraction unit can improve the accuracy of extraction by taking into account the interrelationships between data during extraction. For example, the extraction unit extracts important information by taking into account the interrelationships between video data and audio data. The extraction unit can also extract important information by taking into account the interrelationships between text data and audio data. Furthermore, the extraction unit can extract important information by taking into account the interrelationships between video data and text data. In this way, the accuracy of extraction is improved by taking into account the interrelationships between data. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the interrelationships between data into a generation AI, and the generation AI can improve the accuracy of extraction.

[0090] The extraction unit can perform extraction while taking into account attribute information of the data submitter. For example, the extraction unit can perform extraction while taking into account attribute information of the data submitter. For example, if the data submitter is a resident of an evacuation shelter, the extraction unit can perform extraction while taking into account attribute information of the data submitter. Furthermore, if the data submitter is a relief worker, the extraction unit can perform extraction while taking into account attribute information of the data submitter. Furthermore, if the data submitter is a third party, the extraction unit can perform extraction while taking into account attribute information of the data submitter. In this way, more appropriate information can be extracted by taking into account the attribute information of the data submitter. Some or all of the above-described processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input attribute information of the data submitter into a generation AI, and the generation AI can perform extraction.

[0091] The extraction unit can estimate the emotions of the evacuation shelter residents and adjust the display method of the extracted information based on the estimated emotions. For example, the extraction unit can estimate the emotions of the evacuation shelter residents and adjust the display method of the extracted information based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the extraction unit can provide a simple, highly visible display method. Furthermore, if the evacuation shelter residents are relaxed, the extraction unit can also provide a display method including detailed information. Furthermore, if the evacuation shelter residents are facing an emergency, the extraction unit can quickly display information. This enables highly visible display by adjusting the display method of information based on the emotions of the residents. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the extraction unit can be performed using, for example, AI, or without AI. For example, the extraction unit can input the residents' emotion data into a generation AI, which can then adjust the display method of information.

[0092] The extraction unit can perform extraction taking into account the geographical distribution of the data. For example, the extraction unit performs extraction taking into account the geographical distribution of the data. For example, the extraction unit preferentially extracts data related to a specific region. The extraction unit can also extract data that is geographically distributed over a wide area. Furthermore, the extraction unit can extract geographically limited data. In this way, by taking the geographical distribution of the data into account, highly relevant information can be extracted. Some or all of the above-described processing in the extraction unit may be performed using, for example, AI, or may be performed without using AI. For example, the extraction unit can input the geographical distribution of the data into a generation AI, and the generation AI can perform extraction.

[0093] The extraction unit can improve the accuracy of extraction by referring to literature related to the data during extraction. The extraction unit can improve the accuracy of extraction by referring to literature related to the data during extraction, for example. For example, the extraction unit extracts important information by referring to literature related to the data. The extraction unit can also improve the accuracy of extraction by referring to literature related to the data. Furthermore, the extraction unit can improve the reliability of extraction by referring to literature related to the data. As a result, by referring to related literature, the accuracy and reliability of extraction are improved. Some or all of the above-mentioned processing in the extraction unit can be performed using, for example, AI, or can be performed without using AI. For example, the extraction unit can input literature related to the data into a generation AI, which can improve the accuracy of extraction.

[0094] The instruction generation unit can estimate the emotions of the evacuation shelter residents and adjust the way instructions are expressed based on the estimated emotions. The instruction generation unit, for example, estimates the emotions of the evacuation shelter residents and adjusts the way instructions are expressed based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the instruction generation unit can provide simple and easy-to-understand instructions. Furthermore, if the evacuation shelter residents are relaxed, the instruction generation unit can also provide detailed instructions. Furthermore, if the evacuation shelter residents are facing an emergency, the instruction generation unit can also provide quick instructions. Thus, by adjusting the way instructions are expressed based on the emotions of the evacuation shelter residents, easy-to-understand instructions can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the instruction generation unit can be performed using, for example, AI, or without AI. For example, the instruction generation unit can input the residents' emotion data into the generation AI, and the generation AI can adjust the way instructions are expressed.

[0095] The instruction generation unit can adjust the level of detail of the instruction based on the importance of the extracted information when generating the instruction. For example, the instruction generation unit adjusts the level of detail of the instruction based on the importance of the extracted information when generating the instruction. For example, the instruction generation unit provides detailed instructions for information of high importance. The instruction generation unit can also provide simplified instructions for information of low importance. Furthermore, the instruction generation unit can also provide instructions with an appropriate level of detail for information of medium importance. This enables efficient instruction by adjusting the level of detail of the instruction based on the importance of the information. Some or all of the above-mentioned processing in the instruction generation unit may be performed using AI, for example, or may be performed without using AI. For example, the instruction generation unit can input the importance of the information to the generation AI, and the generation AI can adjust the level of detail of the instruction.

[0096] The instruction generation unit can apply different instruction algorithms depending on the category of information when generating instructions. For example, the instruction generation unit applies different instruction algorithms depending on the category of information when generating instructions. For example, the instruction generation unit applies an algorithm that instructs a rapid response to information regarding an emergency. The instruction generation unit can also apply an algorithm that instructs efficient distribution to information regarding the distribution of supplies. Furthermore, the instruction generation unit can apply an algorithm that instructs appropriate management to information regarding the management of evacuation shelters. In this way, by applying an appropriate instruction algorithm depending on the category of information, the accuracy of instructions is improved. Some or all of the above-mentioned processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the category of information to the generation AI, and the generation AI can apply an appropriate instruction algorithm.

[0097] The instruction generation unit can estimate the emotions of the evacuation shelter residents and adjust the length of the instructions based on the estimated emotions. The instruction generation unit, for example, estimates the emotions of the evacuation shelter residents and adjusts the length of the instructions based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the instruction generation unit can provide short and to-the-point instructions. Furthermore, if the evacuation shelter residents are relaxed, the instruction generation unit can also provide detailed instructions. Furthermore, if the evacuation shelter residents are facing an emergency, the instruction generation unit can also provide quick instructions. By adjusting the length of the instructions based on the emotions of the evacuation shelter residents, it is possible to provide instructions of an appropriate length. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the instruction generation unit may be performed using, for example, AI, or without AI. For example, the instruction generation unit can input the residents' emotion data into the generation AI and have the generation AI adjust the length of the instructions.

[0098] The instruction generation unit can determine the priority of instructions based on the time when information was collected when generating the instructions. The instruction generation unit, for example, determines the priority of instructions based on the time when information was collected when generating the instructions. For example, the instruction generation unit provides instructions preferentially based on the latest information. The instruction generation unit can also provide instructions for older information as needed. Furthermore, the instruction generation unit can determine an appropriate instruction order based on the time when information was collected. In this way, by determining the priority of instructions based on the time when information was collected, instructions based on the latest information can be provided. Some or all of the above-described processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the time when information was collected into the generation AI, and the generation AI can determine the priority of instructions.

[0099] The instruction generation unit can adjust the order of instructions based on the relevance of information when generating instructions. The instruction generation unit, for example, adjusts the order of instructions based on the relevance of information when generating instructions. For example, the instruction generation unit provides instructions preferentially based on highly relevant information. The instruction generation unit can also provide instructions for less relevant information at a later date. Furthermore, the instruction generation unit can determine an appropriate order of instructions based on the relevance of information. This enables efficient instruction by adjusting the order of instructions based on the relevance of information. Some or all of the above-described processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the relevance of information to a generation AI, and the generation AI can adjust the order of instructions.

[0100] The grasping unit can estimate the emotions of the evacuation shelter residents and determine the priority of information to be grasped based on the estimated emotions. For example, the grasping unit can estimate the emotions of the evacuation shelter residents and determine the priority of information to be grasped based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the grasping unit can prioritize information related to anxiety. Furthermore, if the evacuation shelter residents are relaxed, the grasping unit can prioritize information related to relaxation. Furthermore, if the evacuation shelter residents are facing an emergency, the grasping unit can prioritize information related to the emergency. In this way, by determining the priority of information to be grasped based on the emotions of the residents, important information can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the grasping unit can be performed using, for example, AI, or without AI. For example, the grasping unit can input the residents' emotion data into the generation AI, and the generation AI can determine the priority of information.

[0101] The ascertaining unit can analyze the past activity history of the relief workers and select the optimal ascertaining method when ascertaining. For example, the ascertaining unit can analyze the past activity history of the relief workers and select the optimal ascertaining method when ascertaining. For example, the ascertaining unit can analyze what activities the relief workers have performed in the past and select an ascertaining method for similar situations. The ascertaining unit can also analyze what information the relief workers have provided in the past and prioritize ascertaining similar information. Furthermore, the ascertaining unit can analyze what media (audio, video, etc.) the relief workers have used in the past and select the optimal media. In this way, the optimal ascertaining method can be selected by analyzing the past activity history. Some or all of the above-described processing in the ascertaining unit can be performed using, for example, AI, or can be performed without using AI. For example, the ascertaining unit can input the past activity history data of the relief workers into the generation AI, and the generation AI can select the ascertaining method.

[0102] The ascertaining unit can perform filtering based on the current health condition and stress level of the relief worker when ascertaining. For example, the ascertaining unit can perform filtering based on the current health condition and stress level of the relief worker when ascertaining. For example, if the relief worker is in poor health, the ascertaining unit can prioritize ascertaining health-related information. Furthermore, if the relief worker is at a high stress level, the ascertaining unit can also prioritize ascertaining stress-related information. Furthermore, if the relief worker is in good health, the ascertaining unit can also ascertain information about the general activity status. As a result, more appropriate information can be ascertained by filtering based on the relief worker's health condition and stress level. Some or all of the above-described processing in the ascertaining unit can be performed using, for example, AI, or without AI. For example, the ascertaining unit can input data on the relief worker's health condition and stress level into the generating AI, and the generating AI can filter the data.

[0103] The grasping unit can estimate the emotions of the evacuation shelter residents and adjust the display method of the grasped information based on the estimated emotions. For example, the grasping unit can estimate the emotions of the evacuation shelter residents and adjust the display method of the grasped information based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the grasping unit can provide a simple, highly visible display method. Furthermore, if the evacuation shelter residents are relaxed, the grasping unit can also provide a display method including detailed information. Furthermore, if the evacuation shelter residents are facing an emergency, the grasping unit can quickly display information. This enables highly visible display by adjusting the display method of information based on the emotions of the residents. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the grasping unit can be performed using, for example, AI, or without AI. For example, the grasping unit can input the residents' emotion data into the generation AI, and the generation AI can adjust the display method of information.

[0104] The ascertaining unit can prioritize ascertaining highly relevant information by taking into account the geographical location information of the relief workers when ascertaining. For example, the ascertaining unit prioritizes ascertaining highly relevant information by taking into account the geographical location information of the relief workers when ascertaining. For example, if the relief workers are in a specific area, the ascertaining unit prioritizes ascertaining information related to that area. Furthermore, if the relief workers are traveling, the ascertaining unit can also prioritize ascertaining information related to their travel route. Furthermore, if the relief workers are in a specific evacuation shelter, the ascertaining unit can also prioritize ascertaining information related to the evacuation shelter. In this way, by taking the geographical location information into account, highly relevant information can be prioritized. Some or all of the above-described processing in the ascertaining unit may be performed using, for example, AI, or may be performed without using AI. For example, the ascertaining unit can input the geographical location information of the relief workers to the generation AI, and the generation AI can ascertain the information.

[0105] The ascertaining unit can analyze the social media activities of the relief workers and ascertain related information during ascertaining. For example, the ascertaining unit analyzes the social media activities of the relief workers and ascertains related information during ascertaining. For example, the ascertaining unit ascertains information posted by the relief workers on social media. The ascertaining unit can also ascertain information on accounts the relief workers follow on social media. Furthermore, the ascertaining unit can ascertain images and videos shared by the relief workers on social media. In this way, related information can be efficiently ascertained by analyzing social media activities. Some or all of the above-described processing in the ascertaining unit may be performed using, for example, AI, or may be performed without using AI. For example, the ascertaining unit can input social media activity data of the relief workers into a generation AI, and the generation AI can ascertain the information.

[0106] The transmission unit can estimate the emotions of the residents of the evacuation shelter and determine the priority of information to be transmitted based on the estimated emotions. For example, the transmission unit can estimate the emotions of the residents of the evacuation shelter and determine the priority of information to be transmitted based on the estimated emotions. For example, if the residents of the evacuation shelter are feeling anxious, the transmission unit can prioritize information related to anxiety. Furthermore, if the residents of the evacuation shelter are relaxed, the transmission unit can prioritize information related to relaxation. Furthermore, if the residents of the evacuation shelter are facing an emergency, the transmission unit can prioritize information related to the emergency. In this way, by determining the priority of information to be transmitted based on the emotions of the residents, important information can be transmitted preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the transmission unit can be performed using, for example, AI, or without AI. For example, the transmission unit can input residents' emotion data into a generation AI, which can then determine the priority of information.

[0107] The transmission unit can analyze the past activity history of the relief worker and select the optimal transmission method when transmitting a message. For example, the transmission unit analyzes the past activity history of the relief worker and selects the optimal transmission method when transmitting a message. For example, the transmission unit analyzes what activities the relief worker has performed in the past and selects a transmission method for similar situations. The transmission unit can also analyze what information the relief worker has provided in the past and prioritize transmitting similar information. Furthermore, the transmission unit can analyze what media (audio, video, etc.) the relief worker has used in the past and select the optimal media. In this way, the optimal transmission method can be selected by analyzing the past activity history. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input the past activity history data of the relief worker into a generation AI and have the generation AI select the transmission method.

[0108] The transmission unit can filter information based on the current health condition and stress level of the relief worker when transmitting the information. For example, the transmission unit can filter information based on the current health condition and stress level of the relief worker when transmitting the information. For example, if the relief worker is in poor health, the transmission unit can prioritize transmitting health-related information. Furthermore, if the relief worker is at a high stress level, the transmission unit can also prioritize transmitting stress-related information. Furthermore, if the relief worker is in good health, the transmission unit can transmit information about the general activity status. In this way, filtering based on the health condition and stress level of the relief worker allows more appropriate information to be transmitted. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input data on the health condition and stress level of the relief worker into the generation AI, and the generation AI can filter the data.

[0109] The transmission unit can estimate the emotions of the evacuation shelter residents and adjust the display method of the information to be transmitted based on the estimated emotions. For example, the transmission unit can estimate the emotions of the evacuation shelter residents and adjust the display method of the information to be transmitted based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the transmission unit can provide a simple, highly visible display method. Furthermore, if the evacuation shelter residents are relaxed, the transmission unit can also provide a display method including detailed information. Furthermore, if the evacuation shelter residents are facing an emergency, the transmission unit can quickly display information. This enables highly visible display by adjusting the display method of information based on the emotions of the residents. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the transmission unit can be performed using, for example, AI, or without AI. For example, the transmission unit can input residents' emotion data into a generation AI, and the generation AI can adjust the display method of information.

[0110] The transmission unit can prioritize relevant information when transmitting information by taking into consideration the geographical location information of the relief worker. For example, the transmission unit prioritizes relevant information when transmitting information by taking into consideration the geographical location information of the relief worker. For example, if the relief worker is in a specific area, the transmission unit can prioritize information related to that area. Also, if the relief worker is traveling, the transmission unit can prioritize information related to the travel route. Furthermore, if the relief worker is in a specific evacuation shelter, the transmission unit can prioritize information related to the evacuation shelter. In this way, by taking the geographical location information into consideration, highly relevant information can be prioritized. Some or all of the above-described processing in the transmission unit may be performed using AI, for example, or may be performed without using AI. For example, the transmission unit can input the geographical location information of the relief worker into a generation AI, and the generation AI can transmit the information.

[0111] The transmission unit can analyze the social media activities of the relief workers and transmit relevant information at the time of transmission. For example, the transmission unit analyzes the social media activities of the relief workers and transmits relevant information at the time of transmission. For example, the transmission unit transmits information posted by the relief workers on social media. The transmission unit can also transmit information about accounts that the relief workers follow on social media. Furthermore, the transmission unit can also transmit images and videos that the relief workers have shared on social media. In this way, by analyzing social media activities, relevant information can be transmitted efficiently. Some or all of the above-described processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can input social media activity data of the relief workers into a generation AI, and the generation AI can transmit information. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, instruction generation unit, understanding unit, and transmission 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 records the situation at the evacuation shelter or the site in real time using the camera 42 and microphone 38B of the smart device 14. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, extracts important information. The instruction generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, provides specific instructions to relief workers. The understanding unit, realized, for example, by the specific processing unit 290 of the data processing device 12, understands the location information and activity status of relief workers. The transmission unit, realized, for example, by the control unit 46A of the smart device 14, transmits and shares the understood information to the site in real time. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, instruction generation unit, understanding unit, and transmission unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit records the situation at the evacuation shelter or the site in real time using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, extracts important information. The instruction generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, provides specific instructions to relief workers. The understanding unit, realized, for example, by the specific processing unit 290 of the data processing device 12, understands the location information and activity status of relief workers. The transmission unit, realized, for example, by the control unit 46A of the smart glasses 214, transmits and shares the understood information to the site in real time. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, instruction generation unit, understanding unit, and transmission unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the collection unit records the situation at the evacuation shelter or the site in real time using the camera 42 and microphone 238 of the headset terminal 314. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, extracts important information. The instruction generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, provides specific instructions to relief workers. The understanding unit, realized, for example, by the specific processing unit 290 of the data processing device 12, understands the location information and activity status of relief workers. The transmission unit, realized, for example, by the control unit 46A of the headset terminal 314, transmits and shares the understood information to the site in real time. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, extraction unit, instruction generation unit, understanding unit, and transmission unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit records the situation at the evacuation shelter or the site in real time using the camera 42 and microphone 238 of the robot 414. The analysis unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes the collected data. The extraction unit, realized, for example, by the specific processing unit 290 of the data processing device 12, extracts important information. The instruction generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, provides specific instructions to rescue workers. The understanding unit, realized, for example, by the specific processing unit 290 of the data processing device 12, understands the location information and activity status of rescue workers. The transmission unit, realized, for example, by the control unit 46A of the robot 414, transmits and shares the understood information to the site in real time.

[0112] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0113] The collection unit can estimate the emotions of the evacuation shelter residents and adjust the type of data to be collected based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the collection unit can prioritize collecting the residents' tone of voice and facial expressions. Furthermore, if the evacuation shelter residents are relaxed, the collection unit can also collect surrounding environmental sounds and background images. Furthermore, if the evacuation shelter residents are facing an emergency, the collection unit can prioritize collecting audio and video related to the emergency. This allows for more appropriate data to be collected by adjusting the type of data to be collected based on the residents' emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, AI, or without AI. For example, the collection unit can input the residents' emotion data into a generation AI, which then collects the data.

[0114] The analysis unit can estimate the emotions of the evacuation shelter residents and adjust the presentation method of the analysis based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the analysis unit can provide the analysis results in a simple and easy-to-understand format. Furthermore, if the evacuation shelter residents are relaxed, the analysis unit can provide detailed analysis results. Furthermore, if the evacuation shelter residents are facing an emergency, the analysis unit can provide information with emphasis on urgent information. This allows for more appropriate analysis results to be provided by adjusting the presentation method of the analysis based on the residents' emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the residents' emotion data into a generation AI, which can then adjust the presentation method of the analysis.

[0115] The instruction generation unit can estimate the emotions of the evacuation shelter residents and adjust the way instructions are expressed based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the instruction generation unit can provide simple and easy-to-understand instructions. Furthermore, if the evacuation shelter residents are relaxed, the instruction generation unit can also provide detailed instructions. Furthermore, if the evacuation shelter residents are facing an emergency, the instruction generation unit can quickly provide instructions. By adjusting the way instructions are expressed based on the emotions of the evacuation shelter residents, easy-to-understand instructions can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the instruction generation unit can be performed using, for example, AI, or without AI. For example, the instruction generation unit can input the residents' emotion data into the generation AI, and the generation AI can adjust the way instructions are expressed.

[0116] The comprehension unit can estimate the emotions of the evacuation shelter residents and determine the priority of information to be comprehended based on the estimated emotions. For example, if the evacuation shelter residents are feeling anxious, the comprehension unit can prioritize information related to anxiety. Furthermore, if the evacuation shelter residents are feeling relaxed, the comprehension unit can prioritize information related to relaxation. Furthermore, if the evacuation shelter residents are facing an emergency, the comprehension unit can prioritize information related to the emergency. Thus, by determining the priority of information to be comprehended based on the emotions of the residents, important information can be prioritized. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the comprehension unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the comprehension unit can input the residents' emotion data into the generation AI, which can then determine the priority of information.

[0117] The transmission unit can estimate the emotions of the residents of the evacuation shelter and determine the priority of information to be transmitted based on the estimated emotions. For example, if the residents of the evacuation shelter are feeling anxious, the transmission unit can prioritize information related to anxiety. Furthermore, if the residents of the evacuation shelter are feeling relaxed, the transmission unit can prioritize information related to relaxation. Furthermore, if the residents of the evacuation shelter are facing an emergency, the transmission unit can prioritize information related to the emergency. Thus, by determining the priority of information to be transmitted based on the emotions of the residents, important information can be transmitted preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the transmission unit can be performed using, for example, AI, or without AI. For example, the transmission unit can input residents' emotion data into a generation AI, which can then determine the priority of information.

[0118] During data collection, the collection unit can analyze the past behavioral history of evacuation shelter residents and select the optimal collection method. For example, the collection unit can analyze what evacuation behavior the evacuation shelter residents have taken in the past and select a data collection method for similar situations. The collection unit can also analyze what information the evacuation shelter residents have provided in the past and prioritize collecting similar information. Furthermore, the collection unit can analyze what media (audio, video, etc.) the evacuation shelter residents have used in the past and select the optimal media. In this way, the optimal collection method can be selected by analyzing the past behavioral history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the residents' past behavioral history data into a generation AI, and the generation AI can select a data collection method.

[0119] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the data. For example, the analysis unit performs a detailed analysis on data of high importance. The analysis unit can also perform a simplified analysis on data of low importance. Furthermore, the analysis unit can also perform an analysis with an appropriate level of detail on data of medium importance. This enables efficient analysis by adjusting the level of detail of the analysis based on the importance of the data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of the data to the generation AI, and the generation AI can adjust the level of detail of the analysis.

[0120] When generating instructions, the instruction generation unit can adjust the level of detail of the instructions based on the importance of the extracted information. For example, the instruction generation unit provides detailed instructions for information of high importance. The instruction generation unit can also provide simplified instructions for information of low importance. Furthermore, the instruction generation unit can also provide instructions with an appropriate level of detail for information of medium importance. This enables efficient instructions to be given by adjusting the level of detail of the instructions based on the importance of the information. Some or all of the above-described processing in the instruction generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the instruction generation unit can input the importance of the information to the generation AI, and the generation AI can adjust the level of detail of the instructions.

[0121] When performing the assessment, the assessment unit can analyze the past activity history of the relief workers and select the optimal assessment method. For example, the assessment unit can analyze what activities the relief workers have performed in the past and select an assessment method for similar situations. The assessment unit can also analyze what information the relief workers have provided in the past and prioritize assessing similar information. Furthermore, the assessment unit can analyze what media (audio, video, etc.) the relief workers have used in the past and select the optimal media. In this way, the optimal assessment method can be selected by analyzing the past activity history. Some or all of the above-described processing in the assessment unit may be performed using, for example, AI, or may be performed without using AI. For example, the assessment unit can input the past activity history data of the relief workers into the generation AI, and the generation AI can select the assessment method.

[0122] When making a transmission, the transmission unit can analyze the past activity history of the relief worker and select the optimal transmission method. For example, the transmission unit analyzes what activities the relief worker has performed in the past and selects a transmission method for similar situations. The transmission unit can also analyze what information the relief worker has provided in the past and transmit similar information preferentially. Furthermore, the transmission unit can analyze what media (audio, video, etc.) the relief worker has used in the past and select the optimal media. In this way, the optimal transmission method can be selected by analyzing the past activity history. Some or all of the above-mentioned processing in the transmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the transmission unit can analyze the past activity history of the relief worker and select the optimal transmission method for similar situations. Historical data can be input into the generation AI, which can then select the method of transmission.

[0123] The processing flow of the second embodiment will be briefly explained below.

[0124] Step 1: The collection unit collects video data or audio data of residents at the evacuation center or at the site. The collection unit records the situation at the evacuation center or at the site in real time using sensors such as cameras and microphones. For example, the collection unit can capture images of the evacuation center with a camera and collect the voices of residents with a microphone. The collection unit can also record the situation at the evacuation center or at the site in detail using sensors such as fixed cameras and portable microphones. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit, for example, understands the video data and audio data and extracts important information. For example, the analysis unit can analyze the congestion situation at evacuation shelters and the facial expressions of residents from the video data, and can understand the requests of residents and emergency situations from the audio data. Step 3: The extraction unit extracts information from the data analyzed by the analysis unit. For example, the extraction unit can analyze the situation at the evacuation shelter and the expressions of the residents from the video data, and can understand the residents' requests and emergency situations from the audio data. Step 4: The instruction generator provides specific instructions to relief workers based on the extracted information. For example, the instruction generator can instruct the evacuation center to send additional supplies or allocate personnel to respond to the emergency, depending on the overcrowding situation. Step 5: The ascertaining unit ascertains the location information and activity status of the rescue workers based on the instructions generated by the instruction generating unit. The ascertaining unit can, for example, analyze the location information and activity status of the rescue workers and determine whether they have evacuated or are missing. Step 6: The information gathered by the information gathering unit is sent to the scene in real time and shared. For example, when rescue workers arrive at an evacuation center, the information gathering unit can check the list of evacuated residents and instruct them to search for missing people.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0127] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0130] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] 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.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0137] 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.

[0138] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0139] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0144] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0145] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0146] 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.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0148] 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.

[0149] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0152] 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.

[0153] 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.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0155] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0160] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0161] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0164] 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.

[0165] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0167] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0168] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0169] 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.

[0170] 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.

[0171] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0172] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0173] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0175] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0177] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0178] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0180] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0181] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0182] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0185] 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.

[0186] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0187] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0188] 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.

[0189] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0190] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0191] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0193] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0194] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0195] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0196] [Explanation of symbols]

[0197] 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 data or audio data of residents of the evacuation shelter or the site; an analysis unit that analyzes the data collected by the collection unit; an extraction unit that extracts information from the data analyzed by the analysis unit; an instruction generation unit that generates rescue operation instructions based on the information extracted by the extraction unit; a determination unit that determines location information or activity status of rescue workers based on the instructions generated by the instruction generation unit; a transmitting unit that transmits and shares the information grasped by the grasping unit to the site in real time. A system characterized by:

2. The collecting unit Record the situation at the evacuation center or site in real time using sensors such as cameras or microphones 2. The system of claim 1.

3. The analysis unit Analyze video or audio data and extract information 2. The system of claim 1.

4. The extraction unit Analyzing the situation at the evacuation center or the expressions of residents from video data, and grasping residents' requests or emergency situations from audio data 2. The system of claim 1.

5. The instruction generation unit Provide specific instructions to relief workers based on the extracted information 2. The system of claim 1.

6. The grasping unit is Analyzing the location or activity status of rescue workers to understand whether they have evacuated or are missing 2. The system of claim 1.

7. The transmitting unit The information grasped by the grasping unit is transmitted and shared to the site in real time.

2. The system of claim 1.

8. The collecting unit Estimate the emotions of evacuees and adjust the type of data collected based on those emotions.

2. The system of claim 1.

Images