System

Abstract

An object of a system according to an embodiment is to enable a user to quickly and appropriately identify an evacuation site and provide necessary information in the event of a disaster.SOLUTION: A system includes a reception part, an acquisition part, a position information acquisition part, a specification part, a summarization part, a provision part, and an interaction part. The receiving unit receives an emergency alert mail. The acquisition unit acquires evacuation site information. The position information acquisition unit acquires position information. The specification unit specifies an evacuation destination on the basis of the information acquired by the reception unit, the acquisition unit, and the position information acquisition unit. The summarizer summarizes the information on the disaster. The providing unit provides the user with the information summarized by the summarizing unit. The interaction unit provides information through interaction with a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] With conventional technology, it was difficult for users to quickly identify appropriate evacuation sites during disasters, and there was a problem that information was so confusing that users were unable to find the information they needed.

[0005] The system according to the embodiment aims to enable users to quickly and appropriately identify evacuation sites and provide necessary information in the event of a disaster. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, an acquiring unit, a location information acquiring unit, an identifying unit, a summarizing unit, a providing unit, and a dialogue unit. The receiving unit receives an emergency alert email. The acquiring unit acquires evacuation site information. The location information acquiring unit acquires location information. The identifying unit identifies an evacuation site based on the information acquired by the receiving unit, the acquiring unit, and the location information acquiring unit. The summarizing unit summarizes information related to the disaster. The providing unit provides the information summarized by the summarizing unit to the user. The dialogue unit provides the information through dialogue with the user. [Effects of the Invention]

[0007] The system according to the embodiment allows a user to quickly and appropriately identify evacuation sites in the event of a disaster and provides necessary information. [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) The AI-Disaster Guide, an embodiment of the present invention, is a system that uses generative AI to provide interactive information to people during disasters. The AI-Disaster Guide links emergency alert emails with local government evacuation site information and location information to quickly provide evacuation destinations. It also summarizes disaster-related information and news and provides it to users. It also supports multiple languages, making it accessible to users who do not understand Japanese or English. It provides support and peace of mind through its interactive approach. For example, the AI-Disaster Guide acquires the user's current location and identifies the nearest evacuation site. For example, even if a disaster occurs while visiting family or traveling, it allows users to find evacuation sites even if they are unfamiliar with the area. It also provides information in multiple languages ​​to help overseas trainees understand the warnings. Next, it summarizes disaster-related information and news and provides it to users. The generative AI analyzes vast amounts of disaster-related information, extracts and summarizes important information, allowing users to quickly find the information they need, even when disaster information is confusing. It also provides support and peace of mind through its interactive approach. Through dialogue with the user, the generating AI provides appropriate advice and information tailored to the situation. For example, it provides specific guidance on routes to evacuation sites and important points to note when evacuating. It can also send encouraging and reassuring messages to alleviate users' anxiety. This allows the AI-Disaster Guide to reduce anxiety during disasters and support prompt and appropriate evacuation. For example, it can help users find evacuation sites even if they are unfamiliar with the area, even if they are visiting their hometown or traveling and are affected by a disaster. It also provides information in multiple languages ​​so that overseas trainees can understand the warnings. Furthermore, even when disaster information is confusing, users can quickly find the information they need.

[0029] An AI-based disaster guide system according to an embodiment includes a receiving unit, an acquiring unit, a location information acquiring unit, an identifying unit, a summarizing unit, a providing unit, and a dialogue unit. The receiving unit receives emergency alert emails. For example, the receiving unit can receive emergency alert emails such as disaster information, evacuation instructions, and warnings. The acquiring unit acquires evacuation site information from local governments. For example, the acquiring unit can acquire information such as the location, capacity, and facility status of evacuation sites. The location information acquiring unit acquires the user's current location. For example, the location information acquiring unit can acquire the user's current location using GPS, Wi-Fi location information, mobile base station information, etc. The identifying unit identifies an evacuation destination based on the information acquired by the receiving unit, the acquiring unit, and the location information acquiring unit. For example, the identifying unit can identify the optimal evacuation destination based on criteria such as safety, distance, and capacity. The summarizing unit uses a generation AI to summarize information and news related to disasters. For example, the summarizing unit can analyze disaster information such as earthquakes, typhoons, and floods, and extract and summarize important information. The providing unit provides the user with the information summarized by the summarizing unit. For example, the providing unit can provide the information by a notification sound, a display format, or the like. The dialogue unit provides the information through dialogue with the user using the generation AI. For example, the dialogue unit can provide the user with information by voice dialogue, text dialogue, or the like. As a result, the AI-disaster guide according to the embodiment can link emergency alert emails, evacuation site information, and location information in the event of a disaster, and provide the user with prompt and appropriate evacuation site information.

[0030] When receiving an emergency alert email, the receiving unit can analyze past reception history and select the optimal reception method. The receiving unit, for example, analyzes the history of emergency alert emails received by the user in the past. For example, the receiving unit can analyze data such as the reception date and time, the received content, and the user's reaction, and select the most effective reception method. The receiving unit can also prioritize receiving emails of high importance based on the content of emergency alert emails received by the user in the past. For example, the receiving unit prioritizes notifying disaster information of high importance based on the past reception history. Furthermore, the receiving unit can analyze the user's reaction time to emergency alert emails received in the past and select the optimal reception timing. For example, the receiving unit adjusts the future reception timing based on the reception timing of emails to which the user responded quickly. In this way, by analyzing the past reception history, the optimal reception method for the user can be provided.

[0031] When receiving an emergency alert email, the receiving unit can customize the notification method based on the user's current activity status. The receiving unit, for example, uses sensor information of the smartphone to grasp the user's current activity status. For example, the receiving unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The receiving unit can also grasp the user's activity status using calendar information. For example, the receiving unit can determine whether the user is in a meeting based on the user's calendar. The receiving unit customizes the notification method based on the user's current activity status. For example, if the user is driving, the receiving unit can prioritize audio notification and refrain from visual notification. Also, if the user is in a meeting, the receiving unit can prioritize vibration notification and refrain from audio notification. Furthermore, if the user is relaxing, the receiving unit can prioritize visual notification and refrain from audio notification. This makes it possible to convey information in an appropriate manner by providing a notification method according to the user's activity status.

[0032] When receiving an emergency alert email, the receiving unit can select the optimal receiving means based on the user's device information. The receiving unit, for example, acquires the user's device information. For example, the receiving unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the receiving unit selects the optimal receiving means. For example, if the user is using a smartphone, the receiving unit can prioritize push notifications. Also, if the user is using a tablet, the receiving unit can prioritize pop-up notifications on the screen. Furthermore, if the user is using a smartwatch, the receiving unit can prioritize vibration notifications. This improves information reception efficiency by providing the optimal receiving means according to the user's device.

[0033] When acquiring evacuation site information, the acquisition unit can analyze past acquisition history and select the optimal acquisition method. The acquisition unit, for example, analyzes the history of evacuation site information previously acquired by the user. For example, the acquisition unit can analyze data such as the acquisition date and time, the acquired content, and the user's reaction, and select the most effective acquisition method. The acquisition unit can also prioritize acquisition of information of high importance based on the content of evacuation site information previously acquired by the user. For example, the acquisition unit prioritizes acquisition of evacuation site information of high importance based on the past acquisition history. Furthermore, the acquisition unit can analyze the reaction time of evacuation site information previously acquired by the user and select the optimal acquisition timing. For example, the acquisition unit adjusts the future acquisition timing based on the acquisition timing of information to which the user responded quickly. In this way, the optimal acquisition method for the user can be provided by analyzing the past acquisition history.

[0034] When acquiring evacuation location information, the acquisition unit can perform filtering based on the user's current living situation or area of ​​interest. The acquisition unit, for example, uses sensor information from a smartphone to grasp the user's current living situation. For example, the acquisition unit can detect whether the user is with family using an acceleration sensor or a gyro sensor. The acquisition unit can also grasp the user's living situation using calendar information. For example, the acquisition unit can prioritize acquiring evacuation location information for families based on the user's calendar. Furthermore, the acquisition unit can identify the user's area of ​​interest based on past search history or social media activity. For example, if the user has a pet, the acquisition unit prioritizes acquiring evacuation location information that allows pets. This makes it possible to provide appropriate information by providing evacuation location information that is tailored to the user's living situation and area of ​​interest.

[0035] When acquiring evacuation location information, the acquisition unit can select the optimal acquisition means depending on the user's input means. The acquisition unit, for example, detects the user's input means. For example, the acquisition unit can detect means such as voice input, text input, and image input. The acquisition unit selects the optimal acquisition means depending on the user's input means. For example, if the user uses voice input, the acquisition unit can acquire evacuation location information using voice recognition technology. Also, if the user uses text input, the acquisition unit can also acquire evacuation location information using text analysis technology. Furthermore, if the user uses image input, the acquisition unit can also acquire evacuation location information using image recognition technology. This improves information acquisition efficiency by providing the optimal acquisition means depending on the user's input means.

[0036] When acquiring location information, the location information acquisition unit can analyze past location information history and select the optimal acquisition method. The location information acquisition unit, for example, analyzes the history of location information acquired by the user in the past. For example, the location information acquisition unit can analyze data such as acquisition date and time, acquisition location, and movement pattern to select the most effective acquisition method. The location information acquisition unit can also prioritize acquisition of information of high importance based on the content of location information acquired by the user in the past. For example, the location information acquisition unit prioritizes acquisition of location information of high importance based on the past location information history. Furthermore, the location information acquisition unit can analyze the reaction time of location information acquired by the user in the past and select the optimal acquisition timing. For example, the location information acquisition unit adjusts the future acquisition timing based on the acquisition timing of information to which the user responded quickly. In this way, by analyzing the past location information history, the optimal acquisition method for the user can be provided.

[0037] When acquiring location information, the location information acquisition unit can customize the acquisition method based on the user's current activity status. The location information acquisition unit, for example, uses sensor information from the smartphone to grasp the user's current activity status. For example, the location information acquisition unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The location information acquisition unit can also grasp the user's activity status using calendar information. For example, the location information acquisition unit can determine whether the user is resting based on the user's calendar. The location information acquisition unit customizes the acquisition method based on the user's current activity status. For example, when the user is exercising, the location information acquisition unit acquires location information in real time and updates it frequently. When the user is resting, the location information acquisition unit can reduce the frequency of location information acquisition to reduce battery consumption. Furthermore, when the user is moving, the location information acquisition unit can regularly update the location information and provide an optimal route. This allows information to be acquired in an appropriate form by providing an acquisition method according to the user's activity status.

[0038] When acquiring location information, the location information acquisition unit can select the optimal acquisition means based on the user's device information. The location information acquisition unit acquires, for example, the user's device information. For example, the location information acquisition unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the location information acquisition unit selects the optimal acquisition means. For example, if the user is using a smartphone, the location information acquisition unit can acquire location information using GPS. Also, if the user is using a tablet, the location information acquisition unit can acquire location information using Wi-Fi location information. Furthermore, if the user is using a smartwatch, the location information acquisition unit can acquire location information using Bluetooth (registered trademark) location information. This improves information acquisition efficiency by providing the optimal acquisition means according to the user's device.

[0039] When identifying an evacuation destination, the identification unit can analyze past evacuation history to select the optimal identification method. The identification unit, for example, analyzes the history of locations to which the user has evacuated in the past. For example, the identification unit can analyze data such as evacuation dates and times, evacuation locations, and evacuation routes to select the most effective identification method. The identification unit can also prioritize identification of evacuation destinations with high importance based on the details of locations to which the user has evacuated in the past. For example, the identification unit prioritizes identification of evacuation destinations with high importance based on the past evacuation history. Furthermore, the identification unit can analyze the reaction time of locations to which the user has evacuated in the past to select the optimal identification timing. For example, the identification unit adjusts the future identification timing based on the timing of identification of an evacuation destination to which the user responded quickly. In this way, the analysis of past evacuation history can provide the optimal identification method for the user.

[0040] When identifying an evacuation destination, the identification unit can customize the identification method based on the user's current activity status. The identification unit, for example, uses sensor information from the smartphone to grasp the user's current activity status. For example, the identification unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The identification unit can also grasp the user's activity status using calendar information. For example, the identification unit can determine whether the user is resting based on the user's calendar. The identification unit customizes the identification method based on the user's current activity status. For example, if the user is exercising, the identification unit can identify an evacuation destination in real time and update it frequently. Also, if the user is resting, the identification unit can reduce the frequency of identifying the evacuation destination to reduce battery consumption. Furthermore, if the user is moving, the identification unit can regularly update the evacuation destination and provide an optimal route. This makes it possible to provide information in an appropriate form by providing an identification method according to the user's activity status.

[0041] When identifying an evacuation destination, the identification unit can select the optimal identification means based on the user's device information. The identification unit, for example, acquires the user's device information. For example, the identification unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the identification unit selects the optimal identification means. For example, if the user is using a smartphone, the identification unit can identify the evacuation destination using GPS. Also, if the user is using a tablet, the identification unit can identify the evacuation destination using Wi-Fi location information. Furthermore, if the user is using a smartwatch, the identification unit can identify the evacuation destination using Bluetooth location information. This improves the efficiency of information identification by providing the optimal identification means according to the user's device.

[0042] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the disaster information. The summarization unit, for example, evaluates the importance of the disaster information. For example, the summarization unit can evaluate the importance of the disaster information based on criteria such as the scale of damage and the scope of impact. When generating a summary, the summarization unit adjusts the level of detail of the summary based on the importance of the disaster information. For example, for disaster information with high importance, the summarization unit can generate a detailed summary. Also, for disaster information with low importance, the summarization unit can generate a concise summary. Furthermore, the summarization unit can adjust the length of the summary based on the importance of the disaster information. In this way, by providing the level of detail of the summary according to the importance of the disaster information, it is possible to convey information in an appropriate form.

[0043] When generating summaries, the summarization unit can apply different summarization algorithms depending on the category of disaster information. The summarization unit, for example, classifies the category of disaster information. For example, the summarization unit can classify disaster information based on categories such as earthquake, typhoon, and flood. When generating summaries, the summarization unit applies different summarization algorithms depending on the category of disaster information. For example, for earthquake information, the summarization unit can generate a summary regarding the earthquake's scale and epicenter. For typhoon information, the summarization unit can also generate a summary regarding the typhoon's path and wind speed. Furthermore, for flood information, the summarization unit can also generate a summary regarding the location of the flood and the damage situation. In this way, by providing a summarization algorithm depending on the category of disaster information, it is possible to convey information in an appropriate form.

[0044] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit, for example, analyzes the user's past summarization results. For example, the summarization unit can analyze data such as the accuracy of the summary and user feedback to improve the accuracy of the summary. When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. For example, a summary can be generated by referring to a summarization style that the user has previously preferred. It can also avoid summarization styles that the user has previously dissatisfied with. Furthermore, the summarization unit can suggest an optimal summarization method based on the user's past summarization results. In this way, the accuracy of the summary can be improved by referring to the user's past summarization results.

[0045] When providing information, the providing unit can select the optimal providing method by analyzing the past providing history. The providing unit, for example, analyzes the history of information provided to the user in the past. For example, the providing unit can analyze data such as the date and time of information provision, the content of the information provided, and the user's reaction, and select the most effective providing method. The providing unit can also preferentially use an information providing method (audio, text, etc.) that the user has preferred in the past. For example, the providing unit provides information in a method that the user has preferred based on the past providing history. Furthermore, the providing unit can avoid an information providing method that the user has been dissatisfied with in the past. For example, the providing unit avoids a method that the user has been dissatisfied with based on the past providing history. In this way, by analyzing the past providing history, the optimal providing method for the user can be provided.

[0046] The providing unit can customize the method of providing information based on the user's current activity status when providing information. The providing unit grasps the user's current activity status, for example, using sensor information of the smartphone. For example, the providing unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The providing unit can also grasp the user's activity status using calendar information. For example, the providing unit can determine whether the user is taking a break based on the user's calendar. The providing unit customizes the method of providing information based on the user's current activity status. For example, if the user is exercising, the providing unit can provide information by voice. Also, if the user is taking a break, the providing unit can provide information by text. Furthermore, if the user is moving, the providing unit can provide concise information. In this way, by providing a method of providing information according to the user's activity status, it is possible to convey information in an appropriate form.

[0047] When providing information, the providing unit can select the optimal providing means based on the user's device information. The providing unit, for example, acquires the user's device information. For example, the providing unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the providing unit selects the optimal providing means. For example, if the user is using a smartphone, the providing unit can provide information by push notification. Also, if the user is using a tablet, the providing unit can provide information by a pop-up on the screen. Furthermore, if the user is using a smartwatch, the providing unit can provide information by vibration. This improves the efficiency of information provision by providing the optimal providing means according to the user's device.

[0048] During a dialogue, the dialogue unit can analyze past dialogue history to select the optimal dialogue method. The dialogue unit, for example, analyzes the history of dialogues the user has had in the past. For example, the dialogue unit can analyze data such as the date and time of the dialogue, the content of the dialogue, and the user's reaction to select the most effective dialogue method. The dialogue unit can also preferentially use a dialogue style that the user has preferred in the past. For example, the dialogue unit conducts a dialogue in a style that the user has preferred based on the past dialogue history. Furthermore, the dialogue unit can avoid a dialogue style that the user has been dissatisfied with in the past. For example, the dialogue unit avoids a style that the user has been dissatisfied with based on the past dialogue history. In this way, by analyzing the past dialogue history, it is possible to provide the optimal dialogue method for the user.

[0049] The dialogue unit can customize the dialogue method based on the user's current activity status during dialogue. The dialogue unit grasps the user's current activity status using, for example, sensor information of the smartphone. For example, the dialogue unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The dialogue unit can also grasp the user's activity status using calendar information. For example, the dialogue unit can determine whether the user is taking a break based on the user's calendar. The dialogue unit customizes the dialogue method based on the user's current activity status. For example, if the user is exercising, the dialogue unit can provide a concise and to-the-point dialogue. If the user is taking a break, the dialogue unit can provide a dialogue that includes detailed information. Furthermore, if the user is on the move, the dialogue unit can provide a dialogue that is easy to understand quickly. As a result, by providing a dialogue method according to the user's activity status, information can be conveyed in an appropriate manner.

[0050] During a dialogue, the dialogue unit can select the optimal dialogue means based on the user's device information. The dialogue unit, for example, acquires the user's device information. For example, the dialogue unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the dialogue unit selects the optimal dialogue means. For example, if the user is using a smartphone, the dialogue unit can prioritize voice dialogue. Also, if the user is using a tablet, the dialogue unit can prioritize text dialogue. Furthermore, if the user is using a smartwatch, the dialogue unit can prioritize concise dialogue. This improves the efficiency of information transmission by providing the optimal dialogue means according to the user's device.

[0051] The providing unit may have a translation function for supporting multiple languages. The providing unit performs multilingual translation using, for example, machine translation technology. For example, the providing unit may have a translation function for supporting multiple languages, such as Japanese, English, and French. The providing unit may also use human translation in combination to improve the accuracy of the translation. For example, the providing unit may have a human translator check and correct the translation results obtained by machine translation. Furthermore, the providing unit may have a feedback function for evaluating and improving the accuracy of the translation. For example, the providing unit improves the translation algorithm based on feedback from users. In this way, by providing a multilingual translation function, information can be provided to users who speak different languages.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The acquisition unit can analyze the user's past behavioral history and adjust the timing of acquiring evacuation location information based on the behavioral pattern. For example, the acquisition unit can analyze what time of day the user acquired evacuation location information in the past and provide the information at the optimal timing. Also, if the user tends to acquire evacuation location information on a specific day of the week, the acquisition unit can provide the information according to that day of the week. Furthermore, if the user tends to acquire evacuation location information when they are in a specific location, the acquisition unit can provide the information when they are in that location. This makes it possible to provide information based on the user's behavioral pattern.

[0054] The identification unit can analyze the user's social media activity and adjust the method for identifying an evacuation destination. For example, the identification unit can analyze location information and post content shared by the user on social media to help identify an evacuation destination. The identification unit can also identify a reliable evacuation destination based on information about accounts the user follows on social media. Furthermore, the identification unit can also identify the optimal evacuation destination based on the user's search history for information about evacuation destinations on social media. This makes it possible to identify an evacuation destination based on the user's social media activity.

[0055] The summarization unit can customize the summary content of disaster information based on the user's interests. For example, the summarization unit prioritizes summarization of information that is of high interest to the user based on keywords searched for in the past and browsing history. Also, if the user is interested in a specific disaster, information about that disaster can be summarized in detail. Furthermore, if the user is interested in a specific region, disaster information related to that region can be prioritized for summary. This makes it possible to provide information that meets the user's interests.

[0056] The providing unit can adjust the method of providing information based on the remaining battery level of the user's device. For example, when the remaining battery level of the user's device is low, the providing unit can provide concise and to-the-point information. When the remaining battery level is sufficient, the providing unit can provide detailed information. Furthermore, when the remaining battery level is very low, the providing unit can prioritize providing only important information. This makes it possible to provide information according to the remaining battery level of the user's device.

[0057] The acquisition unit can adjust the timing of acquiring evacuation site information based on the user's current weather conditions. For example, the acquisition unit acquires weather information for the user's current location and provides evacuation site information preferentially in the event of bad weather. Furthermore, detailed information can be provided in the event of good weather. Furthermore, evacuation site information can be provided early in the event of a potential sudden change in weather. This makes it possible to provide information according to the user's current weather conditions.

[0058] The identification unit can adjust the method for identifying an evacuation destination based on the user's family composition. For example, if the user evacuates with his or her family, the identification unit prioritizes identifying an evacuation destination that can accommodate the entire family. Also, if the user has pets, the identification unit can identify an evacuation destination that allows pets. Furthermore, if the user evacuates with elderly people or children, the identification unit can also identify an evacuation destination that meets their needs. This makes it possible to identify an evacuation destination that suits the user's family composition.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The receiving unit receives an emergency alert email. For example, the receiving unit can receive emergency alert emails such as disaster information, evacuation instructions, and warnings. Step 2: The acquisition unit acquires information about evacuation sites from the local government. For example, the acquisition unit can acquire information about the location, capacity, and facility status of evacuation sites. Step 3: The location information acquisition unit acquires the user's current location. For example, the location information acquisition unit can acquire the user's current location using GPS, Wi-Fi location information, mobile base station information, etc. Step 4: The identification unit identifies an evacuation destination based on the information acquired by the receiving unit, the acquiring unit, and the location information acquiring unit. For example, the identification unit can identify an optimal evacuation destination based on criteria such as safety, distance, and capacity. Step 5: The summarization unit uses generative AI to summarize disaster-related information and news. For example, the summarization unit can analyze disaster information such as earthquakes, typhoons, and floods, and extract and summarize important information. Step 6: The providing unit provides the information summarized by the summarizing unit to the user. For example, the providing unit can provide the information by a notification sound, a display format, or the like. Step 7: The dialogue unit uses the generation AI to provide information through dialogue with the user. For example, the dialogue unit can provide information to the user through voice dialogue, text dialogue, or other methods.

[0061] (Example 2) The AI-Disaster Guide, an embodiment of the present invention, is a system that uses generative AI to provide interactive information to people during disasters. The AI-Disaster Guide links emergency alert emails with local government evacuation site information and location information to quickly provide evacuation destinations. It also summarizes disaster-related information and news and provides it to users. It also supports multiple languages, making it accessible to users who do not understand Japanese or English. It provides support and peace of mind through its interactive approach. For example, the AI-Disaster Guide acquires the user's current location and identifies the nearest evacuation site. For example, even if a disaster occurs while visiting family or traveling, it allows users to find evacuation sites even if they are unfamiliar with the area. It also provides information in multiple languages ​​to help overseas trainees understand the warnings. Next, it summarizes disaster-related information and news and provides it to users. The generative AI analyzes vast amounts of disaster-related information, extracts and summarizes important information, allowing users to quickly find the information they need, even when disaster information is confusing. It also provides support and peace of mind through its interactive approach. Through dialogue with the user, the generating AI provides appropriate advice and information tailored to the situation. For example, it provides specific guidance on routes to evacuation sites and important points to note when evacuating. It can also send encouraging and reassuring messages to alleviate users' anxiety. This allows the AI-Disaster Guide to reduce anxiety during disasters and support prompt and appropriate evacuation. For example, it can help users find evacuation sites even if they are unfamiliar with the area, even if they are visiting their hometown or traveling and are affected by a disaster. It also provides information in multiple languages ​​so that overseas trainees can understand the warnings. Furthermore, even when disaster information is confusing, users can quickly find the information they need.

[0062] An AI-based disaster guide system according to an embodiment includes a receiving unit, an acquiring unit, a location information acquiring unit, an identifying unit, a summarizing unit, a providing unit, and a dialogue unit. The receiving unit receives emergency alert emails. For example, the receiving unit can receive emergency alert emails such as disaster information, evacuation instructions, and warnings. The acquiring unit acquires evacuation site information from local governments. For example, the acquiring unit can acquire information such as the location, capacity, and facility status of evacuation sites. The location information acquiring unit acquires the user's current location. For example, the location information acquiring unit can acquire the user's current location using GPS, Wi-Fi location information, mobile base station information, etc. The identifying unit identifies an evacuation destination based on the information acquired by the receiving unit, the acquiring unit, and the location information acquiring unit. For example, the identifying unit can identify the optimal evacuation destination based on criteria such as safety, distance, and capacity. The summarizing unit uses a generation AI to summarize information and news related to disasters. For example, the summarizing unit can analyze disaster information such as earthquakes, typhoons, and floods, and extract and summarize important information. The providing unit provides the user with the information summarized by the summarizing unit. For example, the providing unit can provide the information by a notification sound, a display format, or the like. The dialogue unit provides the information through dialogue with the user using the generation AI. For example, the dialogue unit can provide the user with information by voice dialogue, text dialogue, or the like. As a result, the AI-disaster guide according to the embodiment can link emergency alert emails, evacuation site information, and location information in the event of a disaster, and provide the user with prompt and appropriate evacuation site information.

[0063] The receiving unit estimates the user's emotion and adjusts the timing of receiving the emergency alert email based on the estimated user's emotion. The receiving unit estimates the user's emotion using, for example, facial expression recognition technology. For example, the receiving unit can analyze the user's facial expression data and estimate emotions such as stress or relaxation. The receiving unit can also estimate the user's emotion using voice analysis technology. For example, the receiving unit can analyze the tone and speed of the user's voice to estimate the emotion. Furthermore, the receiving unit can analyze behavioral patterns to estimate the user's emotion. For example, the receiving unit can estimate the emotion based on the user's behavioral data. The receiving unit adjusts the timing of receiving the emergency alert email based on the estimated user's emotion. For example, if the user is feeling stressed, the receiving unit can slightly delay the receipt of the emergency alert email so that the user is notified when they are calm. Furthermore, if the user is relaxed, the receiving unit can immediately receive the emergency alert email so that the user can respond quickly. Furthermore, if the user is in a hurry, the receiving unit can prioritize the emergency alert email so that important information can be provided quickly. This allows the timing of receiving emergency alert emails to be adjusted according to the user's emotions, reducing stress for the user and providing information at the appropriate time.

[0064] When receiving an emergency alert email, the receiving unit can analyze past reception history and select the optimal reception method. The receiving unit, for example, analyzes the history of emergency alert emails received by the user in the past. For example, the receiving unit can analyze data such as the reception date and time, the received content, and the user's reaction, and select the most effective reception method. The receiving unit can also prioritize receiving emails of high importance based on the content of emergency alert emails received by the user in the past. For example, the receiving unit prioritizes notifying disaster information of high importance based on the past reception history. Furthermore, the receiving unit can analyze the user's reaction time to emergency alert emails received in the past and select the optimal reception timing. For example, the receiving unit adjusts the future reception timing based on the reception timing of emails to which the user responded quickly. In this way, by analyzing the past reception history, the optimal reception method for the user can be provided.

[0065] When receiving an emergency alert email, the receiving unit can customize the notification method based on the user's current activity status. The receiving unit, for example, uses sensor information of the smartphone to grasp the user's current activity status. For example, the receiving unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The receiving unit can also grasp the user's activity status using calendar information. For example, the receiving unit can determine whether the user is in a meeting based on the user's calendar. The receiving unit customizes the notification method based on the user's current activity status. For example, if the user is driving, the receiving unit can prioritize audio notification and refrain from visual notification. Also, if the user is in a meeting, the receiving unit can prioritize vibration notification and refrain from audio notification. Furthermore, if the user is relaxing, the receiving unit can prioritize visual notification and refrain from audio notification. This makes it possible to convey information in an appropriate manner by providing a notification method according to the user's activity status.

[0066] When receiving an emergency alert email, the receiving unit can select the optimal receiving means based on the user's device information. The receiving unit, for example, acquires the user's device information. For example, the receiving unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the receiving unit selects the optimal receiving means. For example, if the user is using a smartphone, the receiving unit can prioritize push notifications. Also, if the user is using a tablet, the receiving unit can prioritize pop-up notifications on the screen. Furthermore, if the user is using a smartwatch, the receiving unit can prioritize vibration notifications. This improves information reception efficiency by providing the optimal receiving means according to the user's device.

[0067] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring evacuation site information based on the estimated user's emotions. The acquisition unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the acquisition unit can analyze the user's facial expression data and estimate emotions such as stress or relaxation. The acquisition unit can also estimate the user's emotions using voice analysis technology. For example, the acquisition unit can analyze the tone and speed of the user's voice to estimate the emotion. Furthermore, the acquisition unit can analyze behavioral patterns to estimate the user's emotions. For example, the acquisition unit can estimate the emotion based on the user's behavioral data. The acquisition unit adjusts the timing of acquiring evacuation site information based on the estimated user's emotions. For example, if the user is feeling stressed, the acquisition of evacuation site information can be slightly delayed and provided when the user is calm. Furthermore, if the user is relaxed, the evacuation site information can be acquired immediately and provided quickly. Furthermore, if the user is in a hurry, the evacuation site information can be acquired preferentially and important information can be provided quickly. In this way, by adjusting the timing of acquiring evacuation site information according to the user's emotions, the user's stress can be reduced and information can be provided at an appropriate time.

[0068] When acquiring evacuation site information, the acquisition unit can analyze past acquisition history and select the optimal acquisition method. The acquisition unit, for example, analyzes the history of evacuation site information previously acquired by the user. For example, the acquisition unit can analyze data such as the acquisition date and time, the acquired content, and the user's reaction, and select the most effective acquisition method. The acquisition unit can also prioritize acquisition of information of high importance based on the content of evacuation site information previously acquired by the user. For example, the acquisition unit prioritizes acquisition of evacuation site information of high importance based on the past acquisition history. Furthermore, the acquisition unit can analyze the reaction time of evacuation site information previously acquired by the user and select the optimal acquisition timing. For example, the acquisition unit adjusts the future acquisition timing based on the acquisition timing of information to which the user responded quickly. In this way, the optimal acquisition method for the user can be provided by analyzing the past acquisition history.

[0069] When acquiring evacuation location information, the acquisition unit can perform filtering based on the user's current living situation or area of ​​interest. The acquisition unit, for example, uses sensor information from a smartphone to grasp the user's current living situation. For example, the acquisition unit can detect whether the user is with family using an acceleration sensor or a gyro sensor. The acquisition unit can also grasp the user's living situation using calendar information. For example, the acquisition unit can prioritize acquiring evacuation location information for families based on the user's calendar. Furthermore, the acquisition unit can identify the user's area of ​​interest based on past search history or social media activity. For example, if the user has a pet, the acquisition unit prioritizes acquiring evacuation location information that allows pets. This makes it possible to provide appropriate information by providing evacuation location information that is tailored to the user's living situation and area of ​​interest.

[0070] When acquiring evacuation location information, the acquisition unit can select the optimal acquisition means depending on the user's input means. The acquisition unit, for example, detects the user's input means. For example, the acquisition unit can detect means such as voice input, text input, and image input. The acquisition unit selects the optimal acquisition means depending on the user's input means. For example, if the user uses voice input, the acquisition unit can acquire evacuation location information using voice recognition technology. Also, if the user uses text input, the acquisition unit can also acquire evacuation location information using text analysis technology. Furthermore, if the user uses image input, the acquisition unit can also acquire evacuation location information using image recognition technology. This improves information acquisition efficiency by providing the optimal acquisition means depending on the user's input means.

[0071] The location information acquisition unit can estimate the user's emotions and adjust the timing of acquiring location information based on the estimated user's emotions. The location information acquisition unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the location information acquisition unit can analyze the user's facial expression data and estimate emotions such as stress or relaxation. The location information acquisition unit can also estimate the user's emotions using voice analysis technology. For example, the location information acquisition unit can analyze the tone and speed of the user's voice to estimate emotions. Furthermore, the location information acquisition unit can analyze behavioral patterns to estimate the user's emotions. For example, the location information acquisition unit can estimate emotions based on the user's behavioral data. Based on the estimated user's emotions, the location information acquisition unit adjusts the timing of acquiring location information. For example, if the user is feeling stressed, the acquisition of location information can be slightly delayed and provided when the user is calm. Furthermore, if the user is relaxed, the location information can be acquired immediately and provided quickly. Furthermore, if the user is in a hurry, the location information can be acquired preferentially and important information can be provided quickly. This allows the timing of acquiring location information to be adjusted according to the user's emotions, reducing stress on the user and providing information at an appropriate time.

[0072] When acquiring location information, the location information acquisition unit can analyze past location information history and select the optimal acquisition method. The location information acquisition unit, for example, analyzes the history of location information acquired by the user in the past. For example, the location information acquisition unit can analyze data such as acquisition date and time, acquisition location, and movement pattern to select the most effective acquisition method. The location information acquisition unit can also prioritize acquisition of information of high importance based on the content of location information acquired by the user in the past. For example, the location information acquisition unit prioritizes acquisition of location information of high importance based on the past location information history. Furthermore, the location information acquisition unit can analyze the reaction time of location information acquired by the user in the past and select the optimal acquisition timing. For example, the location information acquisition unit adjusts the future acquisition timing based on the acquisition timing of information to which the user responded quickly. In this way, by analyzing the past location information history, the optimal acquisition method for the user can be provided.

[0073] When acquiring location information, the location information acquisition unit can customize the acquisition method based on the user's current activity status. The location information acquisition unit, for example, uses sensor information from the smartphone to grasp the user's current activity status. For example, the location information acquisition unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The location information acquisition unit can also grasp the user's activity status using calendar information. For example, the location information acquisition unit can determine whether the user is resting based on the user's calendar. The location information acquisition unit customizes the acquisition method based on the user's current activity status. For example, when the user is exercising, the location information acquisition unit acquires location information in real time and updates it frequently. When the user is resting, the location information acquisition unit can reduce the frequency of location information acquisition to reduce battery consumption. Furthermore, when the user is moving, the location information acquisition unit can regularly update the location information and provide an optimal route. This allows information to be acquired in an appropriate form by providing an acquisition method according to the user's activity status.

[0074] When acquiring location information, the location information acquisition unit can select the optimal acquisition means based on the user's device information. The location information acquisition unit acquires, for example, the user's device information. For example, the location information acquisition unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the location information acquisition unit selects the optimal acquisition means. For example, if the user is using a smartphone, the location information acquisition unit can acquire location information using GPS. Also, if the user is using a tablet, the location information acquisition unit can acquire location information using Wi-Fi location information. Furthermore, if the user is using a smartwatch, the location information acquisition unit can acquire location information using Bluetooth location information. This improves information acquisition efficiency by providing the optimal acquisition means according to the user's device.

[0075] The identification unit can estimate the user's emotions and adjust a method for identifying an evacuation destination based on the estimated user's emotions. The identification unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the identification unit can analyze the user's facial expression data and estimate emotions such as stress or relaxation. The identification unit can also estimate the user's emotions using voice analysis technology. For example, the identification unit can analyze the tone and speed of the user's voice to estimate the emotion. Furthermore, the identification unit can analyze behavioral patterns to estimate the user's emotions. For example, the identification unit can estimate the emotion based on the user's behavioral data. The identification unit adjusts the method for identifying an evacuation destination based on the estimated user's emotions. For example, if the user is feeling stressed, the identification unit can slightly delay the identification of an evacuation destination and provide the information when the user is calm. Furthermore, if the user is relaxed, the identification unit can immediately identify an evacuation destination and provide the information quickly. Furthermore, if the user is in a hurry, the identification unit can prioritize the identification of an evacuation destination and provide important information quickly. In this way, by adjusting the method for identifying an evacuation destination according to the user's emotions, the user's stress can be reduced and information can be provided at an appropriate time.

[0076] When identifying an evacuation destination, the identification unit can analyze past evacuation history to select the optimal identification method. The identification unit, for example, analyzes the history of locations to which the user has evacuated in the past. For example, the identification unit can analyze data such as evacuation dates and times, evacuation locations, and evacuation routes to select the most effective identification method. The identification unit can also prioritize identification of evacuation destinations with high importance based on the details of locations to which the user has evacuated in the past. For example, the identification unit prioritizes identification of evacuation destinations with high importance based on the past evacuation history. Furthermore, the identification unit can analyze the reaction time of locations to which the user has evacuated in the past to select the optimal identification timing. For example, the identification unit adjusts the future identification timing based on the timing of identification of an evacuation destination to which the user responded quickly. In this way, the analysis of past evacuation history can provide the optimal identification method for the user.

[0077] When identifying an evacuation destination, the identification unit can customize the identification method based on the user's current activity status. The identification unit, for example, uses sensor information from the smartphone to grasp the user's current activity status. For example, the identification unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The identification unit can also grasp the user's activity status using calendar information. For example, the identification unit can determine whether the user is resting based on the user's calendar. The identification unit customizes the identification method based on the user's current activity status. For example, if the user is exercising, the identification unit can identify an evacuation destination in real time and update it frequently. Also, if the user is resting, the identification unit can reduce the frequency of identifying the evacuation destination to reduce battery consumption. Furthermore, if the user is moving, the identification unit can regularly update the evacuation destination and provide an optimal route. This makes it possible to provide information in an appropriate form by providing an identification method according to the user's activity status.

[0078] When identifying an evacuation destination, the identification unit can select the optimal identification means based on the user's device information. The identification unit, for example, acquires the user's device information. For example, the identification unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the identification unit selects the optimal identification means. For example, if the user is using a smartphone, the identification unit can identify the evacuation destination using GPS. Also, if the user is using a tablet, the identification unit can identify the evacuation destination using Wi-Fi location information. Furthermore, if the user is using a smartwatch, the identification unit can identify the evacuation destination using Bluetooth location information. This improves the efficiency of information identification by providing the optimal identification means according to the user's device.

[0079] The summarization unit can estimate the user's emotion and adjust the presentation style of the summary based on the estimated user's emotion. The summarization unit can estimate the user's emotion using, for example, facial expression recognition technology. For example, the summarization unit can analyze the user's facial expression data and estimate emotions such as stress or relaxation. The summarization unit can also estimate the user's emotion using voice analysis technology. For example, the summarization unit can analyze the tone and speed of the user's voice to estimate the emotion. Furthermore, the summarization unit can analyze behavioral patterns to estimate the user's emotion. For example, the summarization unit can estimate the emotion based on the user's behavioral data. The summarization unit adjusts the presentation style of the summary based on the estimated user's emotion. For example, if the user is stressed, the summarization unit can generate a concise and to-the-point summary. Also, if the user is relaxed, the summarization unit can generate a summary that includes detailed information. Furthermore, if the user is in a hurry, the summarization unit can generate a summary that can be quickly understood. This allows information to be conveyed in an appropriate manner by providing a summary presentation style that corresponds to the user's emotion.

[0080] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the disaster information. The summarization unit, for example, evaluates the importance of the disaster information. For example, the summarization unit can evaluate the importance of the disaster information based on criteria such as the scale of damage and the scope of impact. When generating a summary, the summarization unit adjusts the level of detail of the summary based on the importance of the disaster information. For example, for disaster information with high importance, the summarization unit can generate a detailed summary. Also, for disaster information with low importance, the summarization unit can generate a concise summary. Furthermore, the summarization unit can adjust the length of the summary based on the importance of the disaster information. In this way, by providing the level of detail of the summary according to the importance of the disaster information, it is possible to convey information in an appropriate form.

[0081] When generating summaries, the summarization unit can apply different summarization algorithms depending on the category of disaster information. The summarization unit, for example, classifies the category of disaster information. For example, the summarization unit can classify disaster information based on categories such as earthquake, typhoon, and flood. When generating summaries, the summarization unit applies different summarization algorithms depending on the category of disaster information. For example, for earthquake information, the summarization unit can generate a summary regarding the earthquake's scale and epicenter. For typhoon information, the summarization unit can also generate a summary regarding the typhoon's path and wind speed. Furthermore, for flood information, the summarization unit can also generate a summary regarding the location of the flood and the damage situation. In this way, by providing a summarization algorithm depending on the category of disaster information, it is possible to convey information in an appropriate form.

[0082] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit, for example, analyzes the user's past summarization results. For example, the summarization unit can analyze data such as the accuracy of the summary and user feedback to improve the accuracy of the summary. When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. For example, a summary can be generated by referring to a summarization style that the user has previously preferred. It can also avoid summarization styles that the user has previously dissatisfied with. Furthermore, the summarization unit can suggest an optimal summarization method based on the user's past summarization results. In this way, the accuracy of the summary can be improved by referring to the user's past summarization results.

[0083] The providing unit can estimate the user's emotions and adjust the method of providing information based on the estimated user's emotions. The providing unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the providing unit can analyze the user's facial expression data and estimate emotions such as stress or relaxation. The providing unit can also estimate the user's emotions using voice analysis technology. For example, the providing unit can analyze the tone and speed of the user's voice to estimate the emotion. Furthermore, the providing unit can analyze behavioral patterns to estimate the user's emotions. For example, the providing unit can estimate the emotion based on the user's behavioral data. The providing unit adjusts the method of providing information based on the estimated user's emotions. For example, if the user is feeling stressed, the providing unit can provide concise and to-the-point information. On the other hand, if the user is relaxed, the providing unit can provide information including detailed information. Furthermore, if the user is in a hurry, the providing unit can provide information that can be quickly understood. As a result, by providing an information providing method according to the user's emotions, information can be conveyed in an appropriate manner.

[0084] When providing information, the providing unit can select the optimal providing method by analyzing the past providing history. The providing unit, for example, analyzes the history of information provided to the user in the past. For example, the providing unit can analyze data such as the date and time of information provision, the content of the information provided, and the user's reaction, and select the most effective providing method. The providing unit can also preferentially use an information providing method (audio, text, etc.) that the user has preferred in the past. For example, the providing unit provides information in a method that the user has preferred based on the past providing history. Furthermore, the providing unit can avoid an information providing method that the user has been dissatisfied with in the past. For example, the providing unit avoids a method that the user has been dissatisfied with based on the past providing history. In this way, by analyzing the past providing history, the optimal providing method for the user can be provided.

[0085] The providing unit can customize the method of providing information based on the user's current activity status when providing information. The providing unit grasps the user's current activity status, for example, using sensor information of the smartphone. For example, the providing unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The providing unit can also grasp the user's activity status using calendar information. For example, the providing unit can determine whether the user is taking a break based on the user's calendar. The providing unit customizes the method of providing information based on the user's current activity status. For example, if the user is exercising, the providing unit can provide information by voice. Also, if the user is taking a break, the providing unit can provide information by text. Furthermore, if the user is moving, the providing unit can provide concise information. In this way, by providing a method of providing information according to the user's activity status, it is possible to convey information in an appropriate form.

[0086] When providing information, the providing unit can select the optimal providing means based on the user's device information. The providing unit, for example, acquires the user's device information. For example, the providing unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the providing unit selects the optimal providing means. For example, if the user is using a smartphone, the providing unit can provide information by push notification. Also, if the user is using a tablet, the providing unit can provide information by a pop-up on the screen. Furthermore, if the user is using a smartwatch, the providing unit can provide information by vibration. This improves the efficiency of information provision by providing the optimal providing means according to the user's device.

[0087] The dialogue unit can estimate the user's emotions and adjust the dialogue expression method based on the estimated user's emotions. The dialogue unit can estimate the user's emotions using, for example, facial expression recognition technology. For example, the dialogue unit can analyze the user's facial expression data and estimate emotions such as stress or relaxation. The dialogue unit can also estimate the user's emotions using voice analysis technology. For example, the dialogue unit can analyze the tone and speed of the user's voice to estimate the emotion. Furthermore, the dialogue unit can analyze behavioral patterns to estimate the user's emotions. For example, the dialogue unit can estimate the emotion based on the user's behavioral data. The dialogue unit adjusts the dialogue expression method based on the estimated user's emotions. For example, if the user is stressed, the dialogue unit can use a calm tone to communicate. On the other hand, if the user is relaxed, the dialogue unit can use a bright tone to communicate. Furthermore, if the user is in a hurry, the dialogue unit can use a quick and concise dialogue. This makes it possible to convey information in an appropriate manner by providing a dialogue expression method that corresponds to the user's emotions.

[0088] During a dialogue, the dialogue unit can analyze past dialogue history to select the optimal dialogue method. The dialogue unit, for example, analyzes the history of dialogues the user has had in the past. For example, the dialogue unit can analyze data such as the date and time of the dialogue, the content of the dialogue, and the user's reaction to select the most effective dialogue method. The dialogue unit can also preferentially use a dialogue style that the user has preferred in the past. For example, the dialogue unit conducts a dialogue in a style that the user has preferred based on the past dialogue history. Furthermore, the dialogue unit can avoid a dialogue style that the user has been dissatisfied with in the past. For example, the dialogue unit avoids a style that the user has been dissatisfied with based on the past dialogue history. In this way, by analyzing the past dialogue history, it is possible to provide the optimal dialogue method for the user.

[0089] The dialogue unit can customize the dialogue method based on the user's current activity status during dialogue. The dialogue unit grasps the user's current activity status using, for example, sensor information of the smartphone. For example, the dialogue unit can detect whether the user is exercising using an acceleration sensor or a gyro sensor. The dialogue unit can also grasp the user's activity status using calendar information. For example, the dialogue unit can determine whether the user is taking a break based on the user's calendar. The dialogue unit customizes the dialogue method based on the user's current activity status. For example, if the user is exercising, the dialogue unit can provide a concise and to-the-point dialogue. If the user is taking a break, the dialogue unit can provide a dialogue that includes detailed information. Furthermore, if the user is on the move, the dialogue unit can provide a dialogue that is easy to understand quickly. As a result, by providing a dialogue method according to the user's activity status, information can be conveyed in an appropriate manner.

[0090] During a dialogue, the dialogue unit can select the optimal dialogue means based on the user's device information. The dialogue unit, for example, acquires the user's device information. For example, the dialogue unit can acquire information such as the device type, OS version, and communication environment. Based on the user's device information, the dialogue unit selects the optimal dialogue means. For example, if the user is using a smartphone, the dialogue unit can prioritize voice dialogue. Also, if the user is using a tablet, the dialogue unit can prioritize text dialogue. Furthermore, if the user is using a smartwatch, the dialogue unit can prioritize concise dialogue. This improves the efficiency of information transmission by providing the optimal dialogue means according to the user's device.

[0091] The providing unit may have a translation function for supporting multiple languages. The providing unit performs multilingual translation using, for example, machine translation technology. For example, the providing unit may have a translation function for supporting multiple languages, such as Japanese, English, and French. The providing unit may also use human translation in combination to improve the accuracy of the translation. For example, the providing unit may have a human translator check and correct the translation results obtained by machine translation. Furthermore, the providing unit may have a feedback function for evaluating and improving the accuracy of the translation. For example, the providing unit improves the translation algorithm based on feedback from users. In this way, by providing a multilingual translation function, information can be provided to users who speak different languages.

[0092] The dialogue unit can send messages that give the user a sense of security. The dialogue unit, for example, uses a generation AI to generate messages that give the user a sense of security. For example, the dialogue unit can estimate the user's emotions and send encouraging words or messages that give the user a sense of security based on the estimated emotions. The dialogue unit can also provide specific advice or information according to the user's situation. For example, the dialogue unit can provide directions to evacuation sites and important points to note when evacuating. Furthermore, the dialogue unit can send encouraging words or messages that give the user a sense of security to reduce the user's anxiety. In this way, by sending messages that give the user a sense of security, anxiety during a disaster can be reduced. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned receiving unit, acquiring unit, location information acquiring unit, identifying unit, summarizing unit, providing unit, and dialogue unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the receiving unit receives an emergency alert email using the communication I / F 44 of the smart device 14. The acquiring unit acquires evacuation site information from a local government using the identifying processing unit 290 of the data processing device 12. The location information acquiring unit acquires the user's current location using the GPS function of the smart device 14. The identifying unit identifies the evacuation destination using the identifying processing unit 290 of the data processing device 12. The summarizing unit summarizes the disaster information using the identifying processing unit 290 of the data processing device 12. The providing unit provides information using the output device 40 of the smart device 14. The dialogue unit dialogues with the user using the control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned receiving unit, acquiring unit, location information acquiring unit, identifying unit, summarizing unit, providing unit, and dialogue unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the receiving unit receives an emergency alert email using the communication I / F 44 of the smart glasses 214. The acquiring unit acquires local government evacuation site information using the identification processing unit 290 of the data processing device 12. The location information acquiring unit acquires the user's current location using the GPS function of the smart glasses 214. The identifying unit identifies the evacuation destination using the identification processing unit 290 of the data processing device 12. The summarizing unit summarizes the disaster information using the identification processing unit 290 of the data processing device 12. The providing unit provides information using the speaker 240 of the smart glasses 214. The dialogue unit dialogues with the user using the control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned receiving unit, acquiring unit, location information acquiring unit, identifying unit, summarizing unit, providing unit, and dialogue unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the receiving unit receives an emergency alert email using the communication I / F 44 of the headset type terminal 314. The acquiring unit acquires evacuation site information of a local government using the identifying processing unit 290 of the data processing device 12. The location information acquiring unit acquires the user's current location using the GPS function of the headset type terminal 314. The identifying unit identifies the evacuation destination using the identifying processing unit 290 of the data processing device 12. The summarizing unit summarizes the disaster information using the identifying processing unit 290 of the data processing device 12. The providing unit provides information using the display 343 of the headset type terminal 314. The dialogue unit dialogues with the user using the control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned receiving unit, acquiring unit, location information acquiring unit, identifying unit, summarizing unit, providing unit, and dialogue unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the receiving unit receives an emergency alert email using the communication I / F 44 of the robot 414. The acquiring unit acquires evacuation site information from a local government using the identifying processing unit 290 of the data processing device 12. The location information acquiring unit acquires the user's current location using the GPS function of the robot 414. The identifying unit identifies the evacuation destination using the identifying processing unit 290 of the data processing device 12. The summarizing unit summarizes the disaster information using the identifying processing unit 290 of the data processing device 12. The providing unit provides information using the speaker 240 of the robot 414. The dialogue unit dialogues with the user using the control unit 46A of the robot 414.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The providing unit can monitor the user's health condition and adjust the method of providing information based on the health condition. For example, the providing unit can monitor the user's heart rate and blood pressure, and if an abnormality is detected, prioritize receiving an emergency alert email. In addition, if the user's health condition is good, detailed information can be provided. Furthermore, if the user is tired, concise information can be provided that focuses on the main points. In this way, by providing a method of providing information according to the user's health condition, information can be conveyed in an appropriate manner.

[0095] The acquisition unit can analyze the user's past behavioral history and adjust the timing of acquiring evacuation location information based on the behavioral pattern. For example, the acquisition unit can analyze what time of day the user acquired evacuation location information in the past and provide the information at the optimal timing. Also, if the user tends to acquire evacuation location information on a specific day of the week, the acquisition unit can provide the information according to that day of the week. Furthermore, if the user tends to acquire evacuation location information when they are in a specific location, the acquisition unit can provide the information when they are in that location. This makes it possible to provide information based on the user's behavioral pattern.

[0096] The identification unit can analyze the user's social media activity and adjust the method for identifying an evacuation destination. For example, the identification unit can analyze location information and post content shared by the user on social media to help identify an evacuation destination. The identification unit can also identify a reliable evacuation destination based on information about accounts the user follows on social media. Furthermore, the identification unit can also identify the optimal evacuation destination based on the user's search history for information about evacuation destinations on social media. This makes it possible to identify an evacuation destination based on the user's social media activity.

[0097] The summarization unit can customize the summary content of disaster information based on the user's interests. For example, the summarization unit prioritizes summarization of information that is of high interest to the user based on keywords searched for in the past and browsing history. Also, if the user is interested in a specific disaster, information about that disaster can be summarized in detail. Furthermore, if the user is interested in a specific region, disaster information related to that region can be prioritized for summary. This makes it possible to provide information that meets the user's interests.

[0098] The providing unit can adjust the method of providing information based on the remaining battery level of the user's device. For example, when the remaining battery level of the user's device is low, the providing unit can provide concise and to-the-point information. When the remaining battery level is sufficient, the providing unit can provide detailed information. Furthermore, when the remaining battery level is very low, the providing unit can prioritize providing only important information. This makes it possible to provide information according to the remaining battery level of the user's device.

[0099] The dialogue unit can estimate the user's emotions and adjust the content of the dialogue based on the estimated user emotions. For example, if the user is feeling anxious, the dialogue unit can send encouraging words or reassuring messages. If the user is relaxed, the dialogue unit can provide detailed information or advice. Furthermore, if the user is in a hurry, the dialogue unit can provide concise dialogue that can be quickly understood. In this way, by providing dialogue content that corresponds to the user's emotions, information can be conveyed in an appropriate manner.

[0100] The acquisition unit can adjust the timing of acquiring evacuation site information based on the user's current weather conditions. For example, the acquisition unit acquires weather information for the user's current location and provides evacuation site information preferentially in the event of bad weather. Furthermore, detailed information can be provided in the event of good weather. Furthermore, evacuation site information can be provided early in the event of a potential sudden change in weather. This makes it possible to provide information according to the user's current weather conditions.

[0101] The identification unit can adjust the method for identifying an evacuation destination based on the user's family composition. For example, if the user evacuates with his or her family, the identification unit prioritizes identifying an evacuation destination that can accommodate the entire family. Also, if the user has pets, the identification unit can identify an evacuation destination that allows pets. Furthermore, if the user evacuates with elderly people or children, the identification unit can also identify an evacuation destination that meets their needs. This makes it possible to identify an evacuation destination that suits the user's family composition.

[0102] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the summarization unit can generate a concise summary that gets to the point. If the user is relaxed, the summarization unit can generate a summary that includes detailed information. Furthermore, if the user is in a hurry, the summarization unit can generate a summary that can be quickly understood. In this way, by providing a summary presentation method that corresponds to the user's emotions, it is possible to convey information in an appropriate form.

[0103] The providing unit can estimate the user's emotions and adjust the method of providing information based on the estimated user's emotions. For example, if the user is feeling stressed, the providing unit can provide concise and to-the-point information. If the user is relaxed, the providing unit can provide detailed information. Furthermore, if the user is in a hurry, the providing unit can provide information that can be quickly understood. In this way, by providing a method of providing information according to the user's emotions, it is possible to convey information in an appropriate form.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The receiving unit receives an emergency alert email. For example, the receiving unit can receive emergency alert emails such as disaster information, evacuation instructions, and warnings. Step 2: The acquisition unit acquires information about evacuation sites from the local government. For example, the acquisition unit can acquire information about the location, capacity, and facility status of evacuation sites. Step 3: The location information acquisition unit acquires the user's current location. For example, the location information acquisition unit can acquire the user's current location using GPS, Wi-Fi location information, mobile base station information, etc. Step 4: The identification unit identifies an evacuation destination based on the information acquired by the receiving unit, the acquiring unit, and the location information acquiring unit. For example, the identification unit can identify an optimal evacuation destination based on criteria such as safety, distance, and capacity. Step 5: The summarization unit uses generative AI to summarize disaster-related information and news. For example, the summarization unit can analyze disaster information such as earthquakes, typhoons, and floods, and extract and summarize important information. Step 6: The providing unit provides the information summarized by the summarizing unit to the user. For example, the providing unit can provide the information by a notification sound, a display format, or the like. Step 7: The dialogue unit uses the generation AI to provide information through dialogue with the user. For example, the dialogue unit can provide information to the user through voice dialogue, text dialogue, or other methods.

[0106] 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.

[0107] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0108] 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.

[0109] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0110] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0111] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] 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.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0127] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0140] 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.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0157] 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.

[0158] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] [Explanation of symbols]

[0178] 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 receiving unit for receiving emergency alert emails; an acquisition unit for acquiring evacuation site information; a location information acquisition unit that acquires location information; an identification unit that identifies an evacuation destination based on the information acquired by the receiving unit, the acquiring unit, and the location information acquiring unit; a summary section that summarizes information about the disaster; a providing unit that provides the information summarized by the summarizing unit to a user; a dialogue unit that provides information through dialogue with a user; Equipped with A system characterized by:

2. The receiving unit Estimates the user's emotions and adjusts the timing of receiving emergency alert emails based on the estimated user emotions.

2. The system of claim 1.

3. The receiving unit When receiving an emergency alert email, analyze past reception history and select the appropriate reception method.

2. The system of claim 1.

4. The receiving unit Customize notification methods based on the user's current activity status when receiving emergency alert emails 2. The system of claim 1.

5. The receiving unit When receiving an emergency alert email, the optimal method of receiving it is selected based on the user's device information.

2. The system of claim 1.

6. The acquisition unit Estimates the user's emotions and adjusts the timing of obtaining evacuation site information based on the estimated user emotions.

2. The system of claim 1.

7. The acquisition unit When obtaining evacuation shelter information, analyze past acquisition history and select the optimal acquisition method.

2. The system of claim 1.

8. The acquisition unit When retrieving evacuation location information, filtering is performed based on the user's current living situation or area of ​​interest.

2. The system of claim 1.

Images