Information generation device, information generation method, and program

Abstract

An information generating device, an information generating method, and a program are provided that can effectively and efficiently transmit information that should be notified to a user to the user. [Solution] The information generation device includes a first information acquisition unit that acquires notification target information to be notified to the user from an information provider, a second information acquisition unit that acquires conversation information held in an information provision group in which the user participates, and a conversation generation unit that uses the conversation information and notification target information to generate provision information to be provided to the user and output it to the information provision group.

Description

[Technical Field]

[0001] The present invention relates to an information generating device, an information generating method, and a program. [Background technology]

[0002] Patent Document 1 describes a method for adapting the transmission channel and transmission timing for sending a message to an intended recipient to information related to the content of the message. The technology in Patent Document 1 selects the transmission timing by, for example, using location information from the recipient's mobile device to analyze whether the recipient is at home or the time of day when the recipient tends to read emails. Furthermore, the type of message is also taken into consideration when selecting the transmission channel and transmission timing to ensure effective transmission. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-186566 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 may not be able to efficiently transmit information when the recipient is in a state different from their usual state. [Means for solving the problem]

[0005] An information generating device according to one aspect of the present disclosure includes: a first information acquisition means for acquiring notification target information to be notified to a user from an information provider; a second information acquisition means for acquiring conversation information held in an information providing group in which the user participates; a conversation generation means for generating provision information to be provided to the user using the conversation information and the notification target information, and outputting the provision information to an information provision group; Equipped with.

[0006] An information generation method according to one aspect of the present disclosure includes: One or more computers Acquires notification information to be notified to the user from the information provider; Acquire conversation information held in an information providing group in which the user participates; The method includes generating provision information to be provided to the user using the conversation information and the notification target information and outputting the information to an information provision group.

[0007] In one aspect of the present disclosure, the program On the computer, a first information acquisition process for acquiring notification target information to be notified to a user from an information provider; a second information acquisition process for acquiring conversation information held in an information providing group in which the user participates; a conversation generation process for generating provision information to be provided to the user using the conversation information and the notification target information and outputting the information to an information provision group; Execute the following. [Effects of the Invention]

[0008] According to an example of the present disclosure, information that should be notified to a user can be effectively and efficiently communicated to the user. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a functional block diagram illustrating a configuration example of an information generating device according to the present disclosure. [Figure 2] 10 is a flowchart illustrating an example of a processing operation of the information generating device according to the present disclosure. [Figure 3] FIG. 1 is a diagram conceptually illustrating an example of a system configuration of an information processing system according to the present disclosure. [Figure 4]FIG. 1 is a diagram illustrating an example of a configuration of a computer that realizes an information generating device according to the present disclosure. [Figure 5] FIG. 10 is a diagram illustrating an example of a data structure of notification target information. [Figure 6] FIG. 10 is a diagram illustrating an example of a data structure of conversation information. [Figure 7] FIG. 10 is a diagram illustrating an example of a data structure of tone of voice information. [Figure 8] FIG. 10 is a diagram illustrating an example of a data structure of provided information. [Figure 9] FIG. 10 is a diagram illustrating an example of a data structure of situation information. [Figure 10] 10 is a flowchart illustrating an example of a processing operation of the information generating device according to the present disclosure. [Figure 11] 10 is a flowchart illustrating an example of a processing operation of the information generating device according to the present disclosure. [Figure 12] FIG. 1 is a functional block diagram illustrating a configuration example of an information generating device according to the present disclosure. [Figure 13] 10 is a flowchart illustrating an example of a processing operation of the information generating device according to the present disclosure. [Figure 14] FIG. 10 is a diagram illustrating an example of a data structure of user identification information. [Figure 15] FIG. 2 is a diagram illustrating an example of a data structure of resident information. [Figure 16] FIG. 10 is a diagram illustrating an example of a data structure of resident status information. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, in this disclosure, the drawings relate to one or more embodiments. In all drawings, similar components are given similar reference numerals and descriptions thereof are omitted as appropriate. In each of the following drawings, configurations of parts that are not related to the essence of this disclosure are omitted and are not shown.

[0011] In this disclosure, "acquisition" includes at least one of a device going to retrieve data or information stored in another device or storage medium (active acquisition) and a device inputting data or information output from another device (passive acquisition). Examples of active acquisition include making a request or inquiry to another device and receiving a reply, and accessing and reading information from another device or storage medium. Examples of passive acquisition include receiving information that is distributed (or transmitted, pushed, etc.). Furthermore, "acquisition" may also mean selecting and acquiring data or information from received data or information, or selecting and receiving distributed data or information.

[0012] <Example of functional configuration> An example of the configuration of an information generating device 100 according to the present disclosure will be described with reference to FIG. The information generating device 100 includes a first information acquiring unit 102, a second information acquiring unit 104, and a conversation generating unit . The first information acquisition unit 102 acquires notification target information to be notified to the user from an information provider. The second information acquisition unit 104 acquires conversation information that has taken place in an information providing group in which the user participates. The conversation generation unit 106 uses the conversation information and the notification target information to generate provision information to be provided to the user and outputs the information to the information provision group.

[0013] The information to be provided generated by the conversation generation unit 106 is obtained by converting information to be notified to the user into expressions and content suitable for the user, using conversation information within a message exchange group such as an SNS (Social Networking Service). Examples of expressions and content suitable for the user include expressions that are easy for the user to understand, expressions that the user likes, expressions that are likely to interest the user, content that motivates the user to take action based on the information, content that can resolve the user's problems, etc.

[0014] <Example of operation> An example of the operation of the information generating device 100 will be described below with reference to FIG. First, the first information acquisition unit 102 acquires notification target information to be notified to the user from an information provider (step S101). Then, the second information acquisition unit 104 acquires conversation information held in an information provision group in which the user participates (step S103). Then, the conversation generation unit 106 uses the conversation information and the notification target information to generate provision information to be provided to the user and outputs the information to the information provision group (step S105).

[0015] According to this information generating device 100, information to be notified to the user, obtained from the information provider, and information about conversations that took place in an information providing group in which the user participates are used to generate information to be provided and output the information to the information providing group, thereby making it possible to effectively and efficiently communicate information to be notified to the user.

[0016] A detailed example of the information generating device 100 will be described below.

[0017] (First embodiment) <System Overview> FIG. 3 is a diagram conceptually illustrating the system configuration of an information processing system 1 according to the present disclosure. The information processing system 1 includes an information generating device 100, an SNS (Social Networking Service) server 10, a communication device 30 of an information provider U1, and a communication device 40 of a user U2. The information generating device 100, the SNS server 10, the communication device 30 of the information provider U1, and the communication device 40 of the user U2 are connected to one another via a communication network 3. The communication network 3 is, for example, a network such as the Internet, but is not limited to this and may be a combination of multiple different networks.

[0018] The information provider U1 is an employee of a public institution (for example, the Japan Meteorological Agency, a local government, etc.), an employee of a private business, etc., or a person in charge of public relations work, etc. However, as will be described later, the information provider U1 is not limited to these, and various people can be the information provider U1. The information provider U1 provides notification target information (for example, evacuation information, welfare consultation, etc.) to be notified to the user U2.

[0019] User U2 is a resident of a specific area, and receives information provided by information provider U1 using communication device 40 via information generating device 100. User U2 also creates an information providing group G1 with at least two members who exchange messages and chat on the SNS. It is preferable that members of information providing group G1 exchange messages and chat on a daily basis. Although the figure shows one information provider U1 and one user U2, there may be more than one of them. The other members of the information providing group G1 also use communication devices 40.

[0020] The information generating device 100 includes a storage device 120. The storage device 120 may be a piece of hardware that is integrated with the information generating device 100, or may be a piece of hardware that is separate from the information generating device 100.

[0021] The information generating device 100 is a computer such as a personal computer, a server computer, etc. The information generating device 100 realizes the function of an AI (Artificial Intelligence) agent 20. The communication device 30 of the information provider U1 and the communication device 40 of the user U2 are computers such as a personal computer, a tablet terminal, a smartphone, etc.

[0022] The SNS server 10 has a function that allows users to exchange messages (or chats) with other users, for example. The information generating device 100 acquires messages or chats exchanged between users on the SNS server 10 as conversation information. The conversation information includes, for example, the contents of messages (e.g., text information of the conversation), and may further include information indicating the frequency of message exchanges, whether or not a reply has been made to a message, the time until a reply (time lag), etc.

[0023] In order to use the message exchange service and chat service provided by the SNS server 10, applications for using each service are pre-installed and activated on the communication device 40 of the user U2. In order to use the services provided by the SNS server 10, the user U2 pre-registers as a user, obtains a user account, and performs user authentication using the communication device 40 to log in to the system. Alternatively, the user U2 may use the services provided by the system by logging in to the system using the communication device 40 from the website of the SNS server 10 instead of using an application.

[0024] The information generating device 100 may constantly acquire conversation information between groups containing at least two members on the SNS server 10 with the consent of each member, but as will be described later, it is preferable to acquire the information only when certain conditions are met. Note that although information provision groups G1 and G2 are shown in the figure, the number of groups is not limited to two. Also, since there is no need to distinguish between the groups hereafter, the information provision group is referred to as G1, but other groups are also included. Furthermore, as will be described later, if the purpose is to check the safety of people who need to be monitored, the information provision group G1 may have at least two members: the account of the AI ​​agent 20 and the user U2.

[0025] The information generating device 100 further acquires notification target information that the information provider U1 should notify user U2 of from the communication device 30 of the information provider U1. Then, the information generating device 100 converts the acquired conversation information and notification target information into provision information for effectively conveying the notification target information to user U2 who is participating in the group G1, and outputs the information to the information providing group G1 in which user U2, who is exchanging messages on the SNS server 10, is participating.

[0026] <Hardware configuration example> The information generating device 100 according to the present disclosure is realized by the computer 1000 in Fig. 4. The SNS server 10, the communication device 30 of the information provider U1, and the communication device 40 of the user U2 in Fig. 3 are also realized by the computer 1000. The functions of the information generating device 100 may be shared between the computer 1000 of the SNS server 10 and the computer 1000 of the information generating device 100.

[0027] The computer 1000 includes a bus 1010 , a processor 1020 , a memory 1030 , a storage device 1040 , an input / output interface 1050 , and a network interface 1060 .

[0028] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0029] The processor 1020 is implemented by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

[0030] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0031] The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, a read-only memory (ROM), or the like. The storage device 1040 stores program modules that realize each function of the information generating device 100 (e.g., the first information acquiring unit 102, the second information acquiring unit 104, the conversation generating unit 106, and the identifying unit 110, the output unit 112, and the consent accepting unit described below). The processor 1020 loads each of these program modules into the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 may also function as the storage device 120 that stores various information of the information generating device 100 described below (e.g., notification target information 200, conversation information 210, tone of voice information 220, provision information 230, situation information 240, user identifying information 250, resident information 260, and resident situation information 270).

[0032] The program module may be recorded on a recording medium. The recording medium on which the program module is recorded may include a non-transitory, tangible medium usable by the computer 1000, and the program code readable by the computer 1000 (processor 1020) may be embedded in the medium.

[0033] The input / output interface 1050 is an interface for connecting the computer 1000 to various input / output devices. The input / output interface 1050 also functions as a communication interface for short-range wireless communication such as Bluetooth (registered trademark) and NFC (Near Field Communication). The input / output interface 1050 also functions as a wired communication interface such as USB (Universal Serial Bus) and HDMI (High Definition Multimedia Interface) (registered trademark).

[0034] The network interface 1060 is an interface for connecting the computer 1000 to a communication network 3. This communication network 3 is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The network interface 1060 may be connected to the communication network 3 wirelessly or by wire. Furthermore, the network interface 1060 also functions as a communication interface for performing mobile wireless communication via a mobile communication network or the like.

[0035] The computer 1000 then connects to necessary equipment (e.g., the information generating device 100, the communication device 30 of the information provider U1, the communication device 40 of the user U2, and the display, touch panel, operation buttons, touchpad, keyboard, mouse, speaker, microphone, camera, printer, etc. of the SNS server 10) via the input / output interface 1050 or the network interface 1060.

[0036] Each component of the information generating device 100 according to the present disclosure in each figure is realized by any combination of hardware and software of the computer 1000 in Figure 4. Those skilled in the art will understand that there are various variations in the realization method and device. The functional block diagram showing the information generating device 100 according to the present disclosure in each figure shows blocks of logical functional units, rather than a configuration in hardware units.

[0037] <Example of functional configuration> An example of the configuration of the information generating device 100 in the present disclosure will be described below with reference to FIG. The information generating device 100 includes a first information acquiring unit 102, a second information acquiring unit 104, and a conversation generating unit . The first information acquisition unit 102 acquires notification target information to be notified to the user U2 from the information provider U1. The first information acquisition unit 102 stores the acquired notification target information in the storage device 120.

[0038] The information to be notified is not particularly limited, but one example is information related to disaster prevention, including information indicating, for example, the type of disaster, the area where the disaster is (expected to occur), the time of (expected) occurrence, the level of the disaster (information indicating the seismic intensity, rainfall, wind speed, etc.), evacuation information (alert level, time when evacuation information is issued, etc.), etc.

[0039] 5, the notification target information 200 includes a serial number that is assigned to each piece of information and that can identify the information, information indicating the registration date and time of the notification target information 200, information indicating the type of the information, and information indicating the content (message, etc.) of the notification target information 200. The notification target information 200 may further include reference information that indicates the detailed content of the notification target information 200, as shown in FIG. The reference information includes information indicating the time related to the notification target information 200 and information indicating the content of the notification target information 200.

[0040] The information indicating the registration date and time of the notification target information 200 is the time when the information was registered or transmitted by the information provider U1 on the information provider U1's communication device 30, the time when the first information acquisition unit 102 acquired the information or recorded it in the storage device 120, etc., and is not particularly limited.

[0041] The information indicating the type of information is, for example, information indicating that the information is evacuation information issued because a flood is predicted to occur, and is shown as "flood evacuation information" in the example of FIG. 5, but in other examples, it may be identification information indicating the type of information. In that case, the specific type of information may be stored in the storage device 120 in association with the identification information. The first information acquisition unit 102 reads and acquires the type of information associated with the identification information indicating the type of the acquired notification target information 200 from the storage device 120.

[0042] The type of notification target information 200 is information indicating what the notification target information 200 is related to. When the notification target information 200 is information related to a disaster, the notification target information 200 may be classified into one of disaster types such as typhoons, heavy rain, strong winds, spring tides, high waves, river overflows, inundation, floods, landslides, tornadoes, lightning, volcanic eruptions, pyroclastic flows, earthquakes, tsunamis, heatstroke warning information, air pollution, land subsidence, and ballistic missile information, and evacuation information, confirmation of the safety of residents, traffic information (road closures, bridge collapses, building collapses), lifeline information (power outages, water outages, water supply), fire outbreak information, and evacuation shelter information. In addition, if the notification information 200 is a safety or status check for people who need to be monitored continuously, such as residents living alone, elderly people, physically disabled people, people recovering from an infectious disease at home (or in a lodging facility), shut-ins, abused children, young carers, victims of domestic violence, victims of stalking, or people in addiction recovery programs, the type indicates that it is safety confirmation information for the person being monitored.

[0043] The information indicating the time related to the notification target information 200 includes information indicating the time when the information was issued, the time when the notification should be conveyed to the user, the deadline by which the user should take action in response to the notification, etc. In the example of Fig. 5, the information indicating the time related to the notification target information 200 indicates that it is the time when the flood evacuation information was issued, along with the time.

[0044] The information indicating the content of the notification target information 200 is information indicating the specific notification content. In the example of Fig. 5, the notification target information 200 is flood evacuation information, and therefore includes information indicating the evacuation target area and information indicating the alert level for the evacuation target area. The information indicating the content of the notification target information 200 differs depending on the type of information.

[0045] Furthermore, for example, when the purpose is to check the safety of a person being watched over, the notification target information 200 may include a predetermined message to be notified at a predetermined timing. For example, when watching over an elderly person living alone, the notification target information 200 may include a predetermined message (such as "How are you feeling today?", "What's your temperature?", or "Do you have an appetite?") to be notified at a predetermined time every day. The notification target information 200 may also include a UI for responding to safety check questions (for example, a smiling icon indicating a good mood and a worried face icon indicating an unwell mood). The notification target information 200 may include only categories such as "Checking today's health," "Question about temperature," and "Question about appetite," and the conversation generation unit 106 (described later) may generate the above-mentioned messages corresponding to the categories indicated by the notification target information 200.

[0046] Furthermore, if the purpose is to confirm the safety of a victim of stalking, the information to be notified 200 may be information transmitted from a communication device 30 used by a police officer or the like who is the information provider U1.

[0047] The first information acquisition unit 102 acquires the notification target information 200 from the communication device 30 of the information provider U1 via the communication network 3.

[0048] In the communication device 30 of the information provider U1, an operator of the communication device 30 of the information provider U1 makes advance preparations to use the services provided by the information processing system 1. First, the operator registers to use the information processing system 1 and obtains a user account.

[0049] Next, on the communication device 30 of the information provider U1, an application for using the information processing system 1 is installed and launched, or a browser is used to access a website provided by the information processing system 1. Then, on the communication device 30 of the information provider U2, the information provider U2 logs in using a user account previously acquired from the login menu of the application or website.

[0050] As a result, the communication device 30 of the information provider U1 can use the services provided by the information processing system 1. Furthermore, the information provider U1 can display the above-mentioned input form by selecting the input menu for the notification target information 200 on the communication device 30 of the information provider U1.

[0051] The input form includes various UIs (User Interfaces) for accepting input or selection of information to be notified. The information processing system 1 displays an input form for accepting input of notification target information 200 from the information provider U1 on the display of the communication device 30 of the information provider U1. Then, the information processing system 1 accepts input through operation of the information provider U1 on the communication device 30 of the information provider U1, and causes the communication device 30 of the information provider U1 to transmit the notification target information 200 to the information generating device 100.

[0052] For example, when the input form accepts an operation of an operation icon for collecting (recording) a message, the voice of the information provider U1 speaking the message to be notified is collected and recorded by the microphone of the information provider U1's communication device 30. Alternatively, the information processing system 1 may accept the selection of an audio file of a pre-recorded message in the input form. Furthermore, the information processing system 1 may accept input of information related to the message (such as text, images, and URLs (Uniform Resource Locators) of related websites) in an input form.

[0053] The voice message may be converted into text information, which may then be displayed on an input form so that the information provider U1 can check the converted content and, if necessary, make corrections or edits.

[0054] The message may also be a video. In the case of a video, the message may be a message in which audio is converted into text information and superimposed on the video as subtitles.

[0055] The notification target information acquired by the first information acquisition unit 102 includes at least one of audio data, video data, and text data that represent a message that the information provider U1 should notify the target person.

[0056] Furthermore, the input form may accept input or selection of information indicating the type of message, and the communication device 30 of the information provider U1 may associate the information with the notification target information and transmit it to the information generating device 100. Furthermore, the input form may accept input or selection of reference information related to the content of the message, and the communication device 30 of the information provider U1 may associate the information with the notification target information and transmit it to the information generating device 100.

[0057] Furthermore, the input form may accept the selection of data files such as maps showing the disaster situation, schematic diagrams, illustrations, and images (videos, still images) captured by surveillance cameras, etc., and the communication device 30 of the information provider U1 may associate the data with the information to be notified and transmit it to the information generating device 100.

[0058] The second information acquisition unit 104 acquires conversation information held in the information provision group G1 in which the user U2 participates from the SNS server 10 via the communication network 3. The conversation information is, for example, information indicating the contents of messages or chats exchanged between at least two members participating in the information provision group G1.

[0059] The information provision group G1 is a group including at least two members who share messages or chat content using the message exchange function or chat function provided by the SNS server 10. Furthermore, as described above, if the purpose is to check the safety of the person being watched over, the information provision group G1 may have at least two members: the account of the AI ​​agent 20 and the user U2 who is being watched over. Furthermore, the information provision group G1 may also include as members people who actually watch over the person being watched over, such as caregivers, nurses, social workers, mental health and welfare workers, helpers, various types of counselors, instructors, teachers, and staff at welfare offices or child consultation centers. In this case, conversations such as everyday conversations, consultations, counseling, and safety checks may take place between the person being watched over and the person watching over them within the information provision group G1.

[0060] The members who are participants in the information provision group G1 include, for example, a user U2 who is the recipient of the information to be notified, and the user U2's family, close relatives, colleagues, friends, etc. It is preferable that messages are exchanged between members of the information provision group G1 on a daily basis.

[0061] The second information acquisition unit 104 stores the acquired conversation information in the storage device 120. As shown in Fig. 6, the conversation information 210 includes, for each information provision group, identification information that can identify the information provision group, and the contents of messages or chats exchanged within the information provision group, associated with the sender (user) and the time of sending.

[0062] The second information acquisition unit 104 can acquire conversation information of the information provision group G1 on the SNS server 10 by having the user account of the AI ​​agent 20 participate in the information provision group G1.

[0063] Furthermore, the information generation device 100 is configured so that the first information acquisition unit 102, the second information acquisition unit 104, and the conversation generation unit 106 all function when a predetermined disaster condition is met.

[0064] The predetermined disaster conditions include, for example, an earthquake of seismic intensity 6 or higher, a large tsunami, a landslide, river overflow, flooding, flooding above floor level, or the issuance of an evacuation information alert level 3 or higher (evacuation for elderly people, etc.). The disaster conditions may be set by the information provider U1 who provides the notification information or the administrator of the information generating device 100 using a setting menu on the communication device 30 or the information generating device 100 for each disaster, region, or type of notification information. Alternatively, if the SNS server 10 controls the participation of the AI ​​agent 20, the administrator of the SNS server 10 may determine the disaster conditions. Alternatively, the user U2 may be able to set the disaster conditions as conditions for allowing the participation of the AI ​​agent 20 using a setting menu provided by the SNS server 10 to the communication device 40 of the user U2.

[0065] Specifically, when a predetermined disaster condition is met, the information generating device 100 identifies an information providing group G1 whose members include residents of the area that meets the condition. Then, the information generating device 100 causes the SNS server 10 to simultaneously request the identified information providing group G1 to add an account for the AI ​​agent 20. When any member of each information providing group accepts the request and performs an operation to additionally register the account of the AI ​​agent 20 in the group G1, all of the functions of the AI ​​agent 20 (the first information acquiring unit 102, the second information acquiring unit 104, and the conversation generating unit 106) can be made to function. The process of identifying the information providing group G1 whose members include residents of the area that meets the condition can be performed by the identifying unit 110, which will be described later.

[0066] Alternatively, when a predetermined disaster condition is met, the information generation device 100 causes the SNS server 10 to identify an information provision group G1 whose members include residents of the area that meets the condition. The information generation device 100 then automatically adds accounts for the AI ​​agents 20 to the information provision group G1 all at once. This allows all of the functions of the AI ​​agent 20 (the first information acquisition unit 102, the second information acquisition unit 104, and the conversation generation unit 106) to function.

[0067] It is assumed that before registering the account of the AI ​​agent 20 in the information provision group G1, the information processing system 1 has obtained consent from the members of the group G1 to additionally register the account of the AI ​​agent 20.

[0068] As described above, the account of the AI ​​agent 20 is not added to the information provision group G1 if the predetermined disaster condition is not met. Furthermore, the SNS server 10 may automatically delete the account of the AI ​​agent 20 from the information provision group G1 if the predetermined disaster condition is no longer met and if a predetermined cancellation condition is met. The predetermined cancellation conditions include when disaster evacuation information is lifted, when the alert level falls below 3, when evacuation shelters are closed, or when monitoring by the AI ​​agent 20 is no longer necessary. Furthermore, the user U2 or a member of the information provision group G1 may be able to manually delete the account of the AI ​​agent 20 at any time.

[0069] Alternatively, the AI ​​agents 20 may be provided for each municipality or region. In this case, the identification unit 110, which will be described later, identifies an information provision group G1 whose members include residents of a municipality or region that meets a predetermined disaster condition. The AI ​​agents 20 in charge of the municipality or region that meets the predetermined disaster condition are then added to and registered in the information provision group G1 whose members include residents of the identified municipality or region. Specifically, the information generating device 100 instructs the SNS server 10 to notify the information provision group G1 to which the AI ​​agent 20 should be added, for example.

[0070] Furthermore, the AI ​​agent 20 may be provided for each private SNS system (message exchange application). When a predetermined disaster condition is met, the SNS system may use user registration information to identify which information provision group G1 the AI ​​agent 20 should be added to, and may add the account of the AI ​​agent 20 to that information provision group G1.

[0071] Furthermore, the user U2 may be able to register or delete the AI ​​agent 20 at any time, regardless of the disaster conditions. For example, a user account for the AI ​​agent 20 may be set up for each region, and the account of the AI ​​agent 20 for the region where user U2 wants to receive notifications (e.g., his / her own residence, workplace, school district, family residences, workplaces, school districts, etc.) may be registered in the information provision group G1. Furthermore, a user account for the AI ​​agent 20 is provided for each monitored target, and the account of the AI ​​agent 20 corresponding to the monitored target for which user U2 wants to receive notifications (such as monitoring of user U2 himself or user U2's family, friends, colleagues, etc., living alone or undergoing home treatment for an infectious disease) may be registered in the information provision group G1.

[0072] The conversation generation unit 106 uses the conversation information and the notification target information to generate information to be provided to the user U2 and outputs the information to the information provision group G1. Note that the conversation generation unit 106 "outputting information" to the information provision group G1 can also be rephrased as "posting a message," for example.

[0073] The conversation generation unit 106 may generate the information to be provided using a machine learning model. The machine learning model includes a language model such as LLM (Large Language Models) or GPT (Generative Pretrained Transformer). Furthermore, the machine learning model is not limited to a language model and may include generative AI. In this case, data output from the model may include not only text but also various types of content such as images and audio. Furthermore, the machine learning model may be a chat-type machine learning model using these models.

[0074] The conversation generation unit 106 inputs the conversation information and notification target information into a machine learning model to generate information to be provided to user U2 as a natural conversation that is easy for user U2 to understand, and outputs the information to the information provision group G1 as a message on the account of the AI ​​agent 20.

[0075] The provided information includes evacuation instructions in the event of a disaster, messages urging the user to confirm the safety of the person being watched over, etc. As another example, the provided information may include a message including a question to confirm the safety of the person being watched over.

[0076] Specifically, examples of the information provided include evacuation instructions such as, "An evacuation order has been issued for the AA district. BB, who lives in the AA district, please evacuate immediately. CC, who lives near the AA district, please prepare to evacuate," messages encouraging group safety checks such as, "Everyone, please confirm each other's safety status," and messages containing questions to check safety such as, "DD, what are your plans for today?"

[0077] Furthermore, the provided information may include maps, schematic diagrams, illustrations, images (video, still images) taken by surveillance cameras, etc. showing the disaster situation provided by information provider U1, call messages (video, audio, etc.) from information provider U1, images representing messages (including so-called stamps, etc.), etc.

[0078] The conversation generation unit 106 uses the past conversation information 210 to generate tone of voice information that can identify a tone of voice according to the information provision group G1 in which the user U2 participates, and generates the information to be provided 230 using the generated tone of voice information.

[0079] The conversation generation unit 106 identifies the tone of speech of each member in past conversation information for each information provision group. As shown in FIG. 7, tone of speech information 220 stores information that can identify the tone of speech of each member for each information provision group. The tone of speech information 220 includes, for each member, user identification information (shown as user ID in the figure) that can identify the member, as well as information indicating frequently used endings, frequently used first-person pronouns, frequently used second-person pronouns, tone tendencies (polite tone, casual speaking style), the length of a sentence or a sentence in a post, etc. Furthermore, the tone of speech information 220 may include, for each member, frequently used backchannels, the frequency of positive or negative words, catchphrases, response speed (time lag), etc.

[0080] For example, the conversation generation unit 106 may use tone information 220 to generate a message in a polite tone when asking a question to member 1 of information provision group G1, and may generate a message in short sentences using simple terms when asking a question to member 2.

[0081] For example, assume that the notification target information 200 is a message saying, "An evacuation order has been issued. Everyone living in the AA district, please evacuate immediately," and that the member 1, who is the user U2, lives in the AA district. As shown in Fig. 8, the conversation generation unit 106 converts this notification target information 200 into at least one of messages such as "An evacuation order has been issued for the AA district. Mom, please head to the evacuation center, XYZ Elementary School, right now!" and "Hanako, please! Tell your mom to evacuate!" to generate provision information 230 and output it to the information provision group G1.

[0082] Furthermore, for example, if the conversation generation unit 106 determines based on the tone of voice information 220 that, among the members of the information provision group G1, member 2 talks more frequently or responds faster than member 1, the conversation generation unit 106 may output a message to member 2 with priority, since member 2 is more likely to check the message earlier.

[0083] Furthermore, when the conversation generation unit 106 determines based on the tone of voice information 220 that the tone of voice of the user U2 is casual, it may generate a message for the user U2 that includes many emoticons or is spoken in an amiable tone of voice, and output the message to the information provision group G1.

[0084] Furthermore, the tone of voice information 220 may include information indicating whether the conversation is lively or not. For an information provision group G1 in which a user U2, whose tone of voice information 220 includes information indicating that the conversation is lively, is participating, the conversation generation unit 106 repeatedly generates messages to encourage the user U2 to actively participate in the conversation and outputs the messages to the information provision group G1.

[0085] In this way, by continuing the conversation, it is possible to acquire more conversation information 210, and therefore it is possible to increase the amount of conversation information 210 used for estimating the situation of user U2, etc. This is expected to improve the accuracy of estimating the situation of user U2, etc.

[0086] Furthermore, the conversation generation unit 106 may generate a message in a tone of voice similar to that used in everyday conversation by user U2 or the information provider group G1, or may generate a message in a tone of voice different from that used in everyday conversation by user U2 or the information provider group G1. In the former case, it is expected that the message will be more easily understood by user U2 or the information provider group G1, and that the message will be more easily familiar and accepted by user U2 or the information provider group G1. In the latter case, it is expected that the message will convey a sense of the extraordinary (for example, a sense of urgency or imminence) to user U2 or the information provider group G1, attracting their attention to the message. The conversation generation unit 106 may determine which tone of voice to adopt by posting a message and observing the reaction of the information provider group G1. In addition, the conversation generation unit 106 may change the tone of voice for each message to more effectively communicate the message.

[0087] When the conversation generation unit 106 uses a machine learning model, the conversation generation unit 106 generates and inputs to the machine learning model, for example, a prompt including an item such as "Make it a polite message for member 1 that includes detailed information" together with the message text and reference information of the notification target information 200. Alternatively, the conversation generation unit 106 generates and inputs to the machine learning model, for example, a prompt including an item such as "Make it a short, easy-to-understand message for member 2" together with the message text and reference information of the notification target information 200.

[0088] Note that the prompt may be a standard prompt that allows a user to specify a tone of voice. The conversation generation unit 106 may generate and use a prompt that specifies a tone of voice that corresponds to the tone of voice of the user U2 or the information providing group G1.

[0089] Alternatively, by having the machine learning model learn the tone of voice information 220 in advance, the conversation generation unit 106 may simply generate a prompt including items such as "Make a message for member 1," "Make a message for member 2," or "Make a message for each member of information provision group G1," and input this into the machine learning model to output a message for each member.

[0090] Alternatively, the conversation generation unit 106 may have a machine learning model learn the conversation information 210 in advance, generate tone of voice information 220, and then learn the generated tone of voice information 220 for each user.

[0091] The conversation generation unit 106 causes the message output from the machine learning model to be output to the information providing group G1 as a message for the account of the AI ​​agent 20.

[0092] When the purpose is to check the safety of the person being watched over, the conversation generation unit 106 generates the information to be provided 230 using the notification target information 200 and the conversation information 210. For example, when the type of the notification target information 200 indicates "checking today's health" and the person to be notified is member 1, the conversation generation unit 106 generates a message to member 1 saying, "Mom, how are you feeling today?" Alternatively, the conversation generation unit 106 may generate messages to other members of the information provision group G1 such as "Have you heard from Mom?", "Is Mom well?", "Try calling Mom", "Everyone, please check each other's safety status", etc.

[0093] The conversation generation unit 106 generates the information to be provided 230 using attribute information of at least one of the user U2 and the information provision group G1. The attribute information of the user U2 or each member of the information provision group G1 includes, for example, information indicating gender, age, occupation, family structure (number of people, living together, living separately (nearby, far away), etc.) The attribute information of the information provision group G1 includes information indicating the relationships between members (family (parent and child, siblings, couple), friends, colleagues, neighbors, etc.).

[0094] The attribute information may be estimated from past conversation information, or may be obtained from information recorded in the profile information of the information provider group G1 or user U2. The information generating device 100 may cause a machine learning model to learn the conversation information 210 and generate attribute information of user U2 or the information provider group G1. For example, the conversation generation unit 106 may cause the machine learning model to learn the conversation information 210, and then generate and input a prompt including items such as "Estimate the age of user U2" and "Estimate the gender of user U2" to estimate the attributes of user U2, and generate a message appropriate for the estimated attributes.

[0095] For example, the conversation generation unit 106 may generate a message in a tone of voice that is appropriate for the gender and age indicated in the attribute information of user U2 or each member of the information provision group G1. For example, if the attribute information indicates that the information provision group G1 is a family and user U2 is an elderly parent living alone, the conversation generation unit 106 may generate a message for the family of user U2 in the information provision group G1 to confirm the safety of user U2.

[0096] When the conversation generation unit 106 uses a machine learning model, the conversation generation unit 106 may use attribute information of user U2 or information provider group G1 to generate and input prompts including items such as "Make it a message for teenage girls" or "Make it a message for elderly people" into the machine learning model, thereby outputting a message that takes into account the attributes of user U2 or information provider group G1.

[0097] Furthermore, for example, if the attribute information of user U2 indicates that user U2 is in his / her teens, the conversation generation unit 106 may generate provided information 230 that uses many pictograms and images (such as stamps). Alternatively, for example, if the attribute information of user U2 indicates that user U2 is in his / her 70s, the conversation generation unit 106 may generate provided information 230 that includes text information as well as an audio file in which the text information is output as audio. If user U2 is elderly, his / her hearing or eyesight may be declining, and therefore, outputting provided information 230 as both text information and audio information may facilitate understanding of the content.

[0098] The conversation generation unit 106 can use the attribute information of the user U2 or the information provider group G1 to generate a message that matches the attributes of the user U2 or the information provider group G1, which is expected to make it easier for the user U2 or the information provider group G1 to understand and accept the message.

[0099] <Example of operation> An example of the operation of the second information generating device 100 according to the present disclosure will be described below with reference to FIG. 2. The flow in this figure starts when a predetermined disaster condition is satisfied. Furthermore, the processing of steps S101 to S105 may be repeated until the predetermined disaster condition is no longer satisfied and a predetermined cancellation condition is satisfied. When the predetermined disaster condition is no longer satisfied and a predetermined cancellation condition is satisfied, the flow in this figure may be terminated.

[0100] First, the first information acquisition unit 102 acquires notification target information to be notified to the user U2 from the information provider U1 (step S101). Specifically, the first information acquisition unit 102 receives the notification target information from the communication device 30 of the information provider U1 and stores it in the storage device 120 as notification target information 200. Furthermore, the information provider U1 can input the notification target information using the communication device 30 of the information provider U1 and transmit it to the information generating device 100. The first information acquisition unit 102 may periodically inquire of the communication device 30 of the information provider U1 about the presence or absence of notification target information to acquire the information, or may receive the notification target information transmitted from the communication device 30 of the information provider U1 at any timing as needed.

[0101] Then, the second information acquisition unit 104 acquires conversation information held in the information provision group G1 in which the user U2 participates (step S103). For example, assume that the user U2 is using a chat service provided by the SNS server 10 using the communication device 30 of the information provider U1. By registering the account of the AI ​​agent 20 in the information provision group G1 in which the user U2 participates, the second information acquisition unit 104 can acquire conversation information of the information provision group G1. The second information acquisition unit 104 stores the acquired conversation information in the storage device 120.

[0102] Then, the conversation generation unit 106 uses the conversation information 210 and the notification target information 200 to generate provision information 230 to be provided to the user U2, and outputs the information to the information provision group G1 (step S105). For example, examples of the provided information 230 include a message indicating an evacuation order, such as "An evacuation order has been issued for the AA district. Mr. BB, who lives in the AA district, please evacuate immediately. Mr. CC, who lives near the AA district, please prepare to evacuate," a message encouraging confirmation of safety within the information providing group G1, such as "Everyone, please confirm your safety status," and a message including a question to confirm safety, such as "Mr. DD, what are your plans for today?"

[0103] As described above, according to this embodiment, the information generating device 100 includes a first information acquisition unit 102, a second information acquisition unit 104, and a conversation generation unit 106. The first information acquisition unit 102 acquires notification target information to be notified to the user from an information provider. The second information acquisition unit 104 acquires conversation information held in an information providing group in which the user participates. The conversation generation unit 106 uses the conversation information and the notification target information to generate provision information to be provided to the user and outputs the provision information to the information providing group.

[0104] This configuration allows effective communication of notification target information in the daily communication of the information provision group G1 that the user U2 participates in. Furthermore, by outputting the provision information 230 to the information provision group G1 as well as the user U2, it is expected that the members of the information provision group G1 will be encouraged to reach out to the user U2.

[0105] Furthermore, the conversation generation unit 106 uses the past conversation information 210 to generate tone of voice information capable of identifying a tone of voice corresponding to the information provision group G1 in which the user U2 participates, and generates the provided information 230 using the generated tone of voice information. With this configuration, by using a tone of voice similar to the tone of voice used in everyday conversations between the user U2 and the information provision group G1, it is possible to make the message more easily conveyed to the user U2 and the information provision group G1. Furthermore, by using a tone of voice different from the tone of voice used in everyday conversations between the user U2 and the information provision group G1, it is possible to convey a sense of the extraordinary (for example, a sense of urgency or imminence) to the user U2 and the information provision group G1, and attract their attention to the message.

[0106] Furthermore, the conversation generation unit 106 uses attribute information of at least one of the user U2 and the information provider group G1 to generate the information to be provided 230. This configuration makes it possible to generate messages that match the attributes of the user U2 or the information provider group G1, and therefore to provide the information to be provided 230 that includes messages that are easy for the user U2 and the information provider group G1 to understand and accept.

[0107] Furthermore, the information generating device 100 is configured so that the first information acquiring unit 102, the second information acquiring unit 104, and the conversation generating unit 106 all function when a predetermined disaster condition is met. This configuration makes it possible to protect the privacy of conversations in the information providing group G1 that is usually used. Furthermore, it is possible to make the AI ​​agent 20 function when a predetermined disaster occurs.

[0108] (Second embodiment) The second information generation device 100 according to the present disclosure is the same as the above-described information generation device 100 except that it further includes a configuration for estimating a user's situation from conversation information. Note that the second information generation device 100 has the same configuration as the information generation device 100 in FIG. 1, and will be described using FIG. 1. Furthermore, each element of the second information generation device 100 may be combined with each element of one or more embodiments to the extent that no contradiction occurs.

[0109] <Example of functional configuration> The conversation generation unit 106 processes the conversation information 210 to generate situation information indicating the estimated result of the situation of the user U2, and generates the information to be provided 230 using this situation information and the notification target information 200.

[0110] The conversation generation unit 106 may, for example, input the conversation information 210 into a machine learning model to estimate the situation of user U2 and output the estimation result. Furthermore, in order to estimate the situation of user U2 in more detail, the conversation generation unit 106 may generate provision information 230 including a question for understanding the situation of user U2 and output the provision information 230 to the information provision group G1.

[0111] In this case, the conversation generation unit 106 may generate and input a prompt including the item "Estimate the situation of user U2" to the machine learning model to estimate the situation of user U2 and output the estimation result.

[0112] As shown in FIG. 9, the status information 240 includes, for each information provision group, identification information (group ID in the figure) that can identify the group, identification information (user ID in the figure) that can identify user U2 who is a participant in the information provision group G1, information indicating the last time that user U2 posted in the information provision group G1, information indicating the time that the safety confirmation message was posted from the information generating device 100, information indicating whether or not there was a response to the safety confirmation message, and information indicating the estimation result.

[0113] For example, if the notification target information 200 is evacuation information and the provided information 230 has called on user U2 to evacuate, the information indicating the estimated result showing the status of user U2 is information indicating "safety unknown," "safe," "evacuated," "moving to evacuation shelter," "staying at home," "uninterested," "out," "home flooded," "in trouble," "injured," "evacuated to a nearby building (e.g., a four-story apartment building)," etc. In the case of unknown safety, in the example of Fig. 9, since there has been no response since the last posting time, the information also includes information indicating that safety has been unknown since the last posting time.

[0114] When the notification target information 200 is a check on the safety of the person being monitored, the information showing the estimated result indicating the status of user U2 is, but is not limited to, for example, "normal," "no problem," "healthy," "low energy," "injured," "high fever," "no response," "request ambulance," "sleep-deprived," "anxious," "stable condition," "sudden change in condition (worsening)," "at home," "out," "whereabouts unknown," "sleeping," "has too much time on their hands," "in trouble," "depressed," "excited," "missing," etc.

[0115] Using the estimation result of user U2, for example, when the safety of user U2 is unknown or there is no response from user U2, the conversation generation unit 106 generates a message urging other members of the information provision group G1 to check on the safety of user U2 as provision information 230 and outputs the message to the information provision group G1. For example, the conversation generation unit 106 generates a message such as "Someone, call your mother" or "Ask a neighbor how your mother is" to check on the safety of user U2.

[0116] Furthermore, for example, if user U2 does not evacuate but remains at home, the conversation generation unit 106 generates a message urging evacuation as provided information 230 and outputs it to the information provision group G1. For example, the conversation generation unit 106 generates a message suggesting evacuation to user U2, such as, "It is dangerous to travel in the evening, so please head to a shelter while it is still light." Furthermore, the conversation generation unit 106 may generate provided information 230 including information informing user U2 of an impending danger and urging evacuation (for example, video footage from a surveillance camera of a nearby river with a rising water level), and output it to the information provision group G1. Furthermore, the conversation generation unit 106 may generate provided information 230 including information indicating that people are gathering at a shelter (for example, information indicating the number of people who have arrived at the shelter, or an image capturing the situation of people gathering at the shelter), and output it to the information provision group G1.

[0117] Furthermore, when the conversation generation unit 106 estimates that the user U2 is "safe" or "has evacuated to a nearby building," the conversation generation unit 106 generates a message to keep the user U2 alert as provided information 230 and outputs the message to the information provision group G1. For example, the conversation generation unit 106 generates a message to the user U2 suggesting next steps, such as "The area around the building may be flooded. You may be isolated, so we recommend evacuating to a shelter on higher ground." Alternatively, the conversation generation unit 106 generates a message to other members of the information provision group G1, such as "Call your mother and recommend that she move to an elementary school that is an evacuation shelter."

[0118] Furthermore, when it is estimated that user U2 is in a difficult situation, the conversation generation unit 106 generates provision information 230 including questions for eliciting specific details of the problem from user U2, and outputs the provision information 230 to the information provision group G1. For example, the conversation generation unit 106 generates messages such as "Where are you now?", "What do you need now?", "Are you hurt?", "Are you alone?", and "Are there people around?" as questions for user U2. To make it easier to answer, it is more preferable that the questions be replies with "yes," "no," "circle," "cross," or the like. Specifically, the questions include "Are you at home now?", "Are you in the AA district now?", "Are you at an evacuation shelter now?", "Are you at XYZ Elementary School now?", and "Are you on the move now?"

[0119] In this way, by generating a message including a question that guides the user U2 to provide an answer to the information that the user U2 wants to know, and outputting the message to the information providing group G1, the user U2 can efficiently obtain an answer to the question.

[0120] The conversation generation unit 106 may also generate the provided information 230 by including a UI that allows the user U2 to select from multiple options the supplies or responses that the user U2 needs. Alternatively, the conversation generation unit 106 may generate and output a message to the information provision group G1, such as "Let's discuss what we need now," in order to extract the needs of the user U2. Alternatively, the conversation generation unit 106 may generate the provided information 230 by including a UI that allows the user U2 to input a response by voice, along with a question for the user U2. After operating the UI, the user U2 may record the voice of the user U2 by speaking into the microphone of the communication device 40 of the user U2, generate an audio file, and post the audio file to the information provision group G1. Alternatively, the conversation generation unit 106 may convert the voice to text, accept the text as a response, and post it to the information provision group G1.

[0121] Furthermore, the conversation generation unit 106 may generate provision information 230 including a message suggesting a way to solve the "problem" of user U2 and output the information to the information provision group G1. For example, the conversation generation unit 106 may generate provision information 230 including a message including information about a place or contact point where user U2 can get advice about his / her "problem," or, if it is estimated from the conversation information 210 that user U2 is reluctant to seek advice, a message that it is okay to seek advice from others or a message encouraging user U2 to seek advice.

[0122] Furthermore, when the conversation generation unit 106 estimates that the status of user U2 is "out," "whereabouts unknown," "missing," etc., it generates provision information 230 including a message urging the user to contact a local government, family, the police, etc., and outputs the information to the information provision group G1. Specifically, the conversation generation unit 106 generates a message such as "Hanae-san does not seem to be at home. Please contact the police."

[0123] Furthermore, if the conversation generation unit 106 estimates that user U2 is "injured" or "worsening in condition," it generates provision information 230 including a message inquiring about the injury or condition, a message or video informing first aid methods for the injury, and information about hospitals where the user can be treated (hospital name, website link (URL (Uniform Resource Locator)), address, contact information, medical department, opening hours, whether or not there is an emergency outpatient clinic, etc.), and outputs this information to the information provision group G1.

[0124] Alternatively, the conversation generation unit 106 may generate and output to the information provision group G1 information 230 including a message urging the information provision group G1 to take action, such as, "Please call an ambulance to your parents' house and have Hanae-san transported to the hospital."

[0125] Furthermore, when it is estimated that the user U2 is "indifferent" to the provided information 230, the conversation generation unit 106 generates a message as the provided information 230 in an expression that will cause the user U2 to have a moderate interest, and outputs the message to the information provision group G1. In this case, since the generated provided information 230 is to be output to the originally indifferent user U2, it is preferable to use an expression that the user U2 will not find bothersome or preachy, and that is easy for the user U2 to listen to and accept.

[0126] Furthermore, in the case of evacuation information, the conversation generation unit 106 may include images and information shown in the following (1) to (4) in the provided information 230 so that the user U2 perceives the information as something that concerns him or her and becomes interested in it. (1) Surveillance camera images of the surrounding rivers showing rising water levels (2) An image of people gathering at the evacuation shelter where user U2 is taking refuge. (3) Information showing the change in the capacity of evacuation shelters (information showing the increase over time) (4) Information showing availability (information showing when availability is running low)

[0127] Furthermore, when the conversation generation unit 106 estimates that the user U2 is "indifferent" to the provided information 230 or the AI ​​agent 20, it may identify topics in which the user U2 is interested (for example, topics to which the user reacts frequently or quickly) from the past conversation information 210, generate provided information 230 including the identified topic, and output the information to the information provision group G1. Note that the estimation result indicating the status of the user U2 may include the degree of interest of the user U2 in the provided information 230 or the AI ​​agent 20.

[0128] When using a machine learning model, the conversation generation unit 106 may have the machine learning model learn the conversation information 210, generate a prompt including an item such as "Talk about a topic that interests user U2," input the prompt into the machine learning model, and output a message.

[0129] Furthermore, when checking the safety of a person being watched over and it is estimated that user U2 has "a lot of free time," the conversation generation unit 106 may generate information to be provided 230 including information about events, movies, etc. that user U2 might be interested in. For example, the conversation generation unit 106 generates information to be provided 230 including a message introducing a comedy event that user U2 is interested in, such as "It looks like there are tickets available for a manzai performance at a theater in Shinjuku this afternoon," and information about the event (such as the event's website URL, the venue, how to obtain tickets, and prices).

[0130] <Example of operation> An example of the operation of the second information generating device 100 according to the present disclosure will be described below with reference to Fig. 10. The flow in Fig. 10 includes steps S101 and S103, which are the same as the flow in Fig. 2, and also includes steps S201 and S203 after step S103.

[0131] Like the flow in Fig. 2, the flow in this figure also starts when a predetermined disaster condition is satisfied. Furthermore, the processing of steps S101 to S203 may be repeated until the predetermined disaster condition is no longer satisfied and the predetermined cancellation condition is satisfied. When the predetermined disaster condition is no longer satisfied and the predetermined cancellation condition is satisfied, the flow in this figure may be terminated.

[0132] 2, the first information acquisition unit 102 acquires notification target information to be notified to the user from an information provider (step S101). Then, the second information acquisition unit 104 acquires conversation information held in an information provision group in which the user participates (step S103).

[0133] The conversation generation unit 106 then processes the conversation information 210 to generate situation information 240 indicating the estimation result of the situation of the user U2 (step S201). The generated situation information 240 is stored in the storage device 120.

[0134] Then, the conversation generation unit 106 generates the information to be provided 230 using the situation information 240 and the notification target information 200 generated in step S201 (step S203). Using the estimation result of user U2, for example, when the safety of user U2 is unknown or there is no response from user U2, the conversation generation unit 106 generates a message 230 to be provided to other members of the information provision group G1 to check on the safety of user U2, and outputs the message to the information provision group G1. For example, the conversation generation unit 106 generates a message such as "Someone, call your mother" or "Ask a neighbor how your mother is doing" to check on the safety of user U2.

[0135] As described above, according to this embodiment, the conversation generation unit 106 processes the conversation information 210 to generate situation information indicating the result of estimating the situation of user U2, and then generates the information to be provided 230 using this situation information and the notification target information 200. This configuration not only achieves the same effects as the above embodiment, but also enables estimation of user U2's situation from everyday conversations, making it possible to extract information about user U2's safety and any problems, and to generate and provide appropriate information to be provided 230. The information to be provided 230 can also suggest solutions to user U2's problems. Since the message is provided not only to user U2 but also to the information provision group G1, it is expected that members of the information provision group G1 will be encouraged to provide support for user U2's problems.

[0136] In addition, since the user can check on the user U2's troubles and safety during daily communication, it is possible to promote monitoring and mutual assistance.

[0137] (Third embodiment) The third information generation device 100 according to the present disclosure is the same as the second information generation device 100 described above, except that the notification target information is limited to including disaster-related information. Note that the third information generation device 100 has the same configuration as the information generation device 100 in FIG. 1, and will be described using FIG. 1. Furthermore, each element of the third information generation device 100 may be combined with each element of one or more embodiments to the extent that no contradiction occurs.

[0138] The notification target information 200 includes information related to the disaster. The conversation generation unit 106 generates situation information 240 that estimates at least one of the evacuation intention and evacuation situation of the user U2 as the situation of the user U2, and generates information to be provided 230 using this situation information 240 and the notification target information 200.

[0139] Specifically, the conversation generation unit 106 first refers to the conversation information 210. For example, in the conversation information 210, assume that in response to a question from member 2 of information provision group G1 to user U2, "Mom, are you going to a shelter?", user U2 replies, "I'm on the second floor of my house, so it's okay." From this conversation information 210, the conversation generation unit 106 infers that user U2 has no intention of evacuating, and includes information indicating that user U2 has no intention of evacuating as the situation information 240 of user U2.

[0140] The conversation generation unit 106 uses the situation information 240 of the user U2 to generate information to be provided 230 including a message such as, "Mom, there is a risk of flooding, so please evacuate to an elementary school shelter while it is still light out," for the user U2. Alternatively, the conversation generation unit 106 uses the situation information 240 of the user U2 to generate information to be provided 230 including a message such as, "Please ask your neighbors to take your mother to the shelter with you," for the information provision group G1.

[0141] In other words, if it is estimated that user U2 has no intention of evacuating or has not evacuated, the conversation generation unit 106 generates a message to user U2 containing information to encourage evacuation (for example, information informing user U2 of the imminent risk of flooding, information that evacuation will become difficult at night, etc.), and a message to the information provision group G1 containing information indicating measures to encourage user U2 to take evacuation action (for example, information indicating persuading user U2 himself, asking neighbors, etc.).

[0142] The conversation generation unit 106 may also generate provision information 230 including a message asking the user U2 about the evacuation intention and evacuation situation of the user U2, and output the provision information 230 to the information provision group G1.

[0143] Specifically, the conversation generation unit 106 may generate provided information 230 including a question for finding out whether or not user U2 intends to evacuate or the evacuation situation, and output the provided information 230 to the information provision group G1. The conversation generation unit 106 may use the answer to the question to estimate user U2's intention to evacuate or the evacuation situation. Specifically, the conversation generation unit 106 may generate messages such as "Are you going to evacuate?", "Please tell me if there is a reason why you cannot evacuate," or "Have you started preparing for evacuation?" as messages for user U2. Alternatively, the conversation generation unit 106 may generate messages such as "Call your mother and ask about the situation" or "Contact your neighbors and ask about your mother's situation" as messages for the information provision group G1.

[0144] The information generating device 100 may further include a consent receiving unit (not shown) that receives consent from the user U2 to output the situation information 240 indicating the estimation result of the situation of the user U2 to the information provision group G1. The conversation generation unit 106 outputs the situation information 240 with the consent of the user U2 to the information provision group G1. On the other hand, if the consent of the user U2 is not obtained, the conversation generation unit 106 does not output the situation information 240 of the user U2 to the information provision group G1.

[0145] The consent receiving unit may receive in advance whether or not it is OK to output future situation information 240 to the information provision group G1. When receiving in advance, consent may be received for each content of the situation information 240. For example, if the content of the situation information 240 indicates that the safety of the user U2 is unknown, consent from the user U2 cannot be obtained after the fact, and therefore consent must be obtained in advance. On the other hand, if the situation information 240 includes information indicating the current location of the user U2, it is preferable from the viewpoint of privacy protection to output the situation information 240 to the information provision group G1 after obtaining consent from the user U2.

[0146] The consent receiving unit may also present the situation information 240 to user U2 for each piece of situation information 240 and then receive a response from user U2 as to whether or not it is OK to output the situation information 240 to the information provision group G1. In this case, the consent receiving unit outputs the situation information 240 directly from the account of the AI ​​agent 20 to the account of user U2, and outputs information indicating a message inquiring user U2 as to whether or not it is OK to output the situation information 240 to the information provision group G1 (for example, "May I output this (indicating situation information 240), your situation, to the group?").

[0147] If a response indicating consent is received from user U2 in response to the inquiry, the consent receiving unit receives the information that consent has been received from user U2.

[0148] <Example of operation> An example of the operation of the third information generating device 100 according to the present disclosure will be described below with reference to Fig. 11. The operation shown in the flow of Fig. 11 is an example of the case where consent from user U2 is obtained for each of the above-described situation information 240. The flow of Fig. 11 includes steps S211 and S213 that are executed after step S201 of the flow of Fig. 10.

[0149] After step S201, the consent accepting unit presents the situation information 240 to the user U2 each time the situation information 240 is estimated in step S201 (step S211). Specifically, the consent accepting unit causes the situation information 240 to be displayed on the display of the communication device 40 of the user U2.

[0150] The consent receiving unit then receives an operation from the user U2 indicating whether or not it is OK to output the situation information 240 to the information providing group G1. If a consent response is obtained through the user operation (YES in step S213), the process proceeds to step S203 in Fig. 10, where the conversation generating unit 106 generates the information to be provided 230 using the situation information 240 and the notification target information 200 generated in step S201.

[0151] On the other hand, if an acceptance response is not obtained through the user operation (NO in step S213), the information generating device 100 ends this process. Alternatively, if an acceptance response is not obtained through the user operation (NO in step S213), the information generating device 100 may execute the process of step S105 in Fig. 2 instead of step S203 in Fig. 10. That is, the conversation generation unit 106 uses the conversation information and the notification target information to generate provision information to be provided to the user and outputs the information to the information provision group G1 (step S105).

[0152] As described above, according to this embodiment, the notification target information 200 includes information related to a disaster. The conversation generation unit 106 generates situation information 240 that estimates at least one of the evacuation intention and evacuation situation of the user U2 as the situation of the user U2, and generates the information to be provided 230 using the situation information 240 and the notification target information 200. As described above, the information generating device 100 of this embodiment not only produces the same effects as the above-described embodiments, but also can estimate the evacuation intention and evacuation situation of the user U2 from everyday conversations, and can provide the provided information 230 that encourages appropriate evacuation behavior according to the situation of the user U2. Furthermore, since the message is provided not only to the user U2 but also to the information providing group G1, it is expected that the members of the information providing group G1 will encourage the user U2 to take evacuation behavior.

[0153] The information generating device 100 further includes a consent receiving unit that receives consent from the user U2 to output the situation information 240 indicating the estimation result of the situation of the user U2 to the information provision group G1. This configuration makes it possible to protect the privacy of user U2.

[0154] (Fourth embodiment) The fourth information generating device 100 according to the present disclosure is the same as the second and third information generating devices 100 described above, except that it has a configuration in which it compares resident information with user U2 to identify user U2 for the resident, and collects, accumulates, and manages situation information about the resident. Note that each element of the fourth information generating device 100 may be combined with each element of one or more embodiments to the extent that no contradiction occurs.

[0155] As shown in FIG. 12, the fourth information generation device 100 includes the same first information acquisition unit 102, second information acquisition unit 104, and conversation generation unit 106 as in FIG. 1, and further includes an identification unit 110 and an output unit 112.

[0156] The identification unit 110 compares the user identification information 250 of a user U2 participating in the information provision group G1 with the resident information 260 related to residents of a predetermined area. Then, based on the comparison result, the identification unit 110 identifies the user U2 corresponding to the resident in the resident information 260, and stores situation information indicating an estimated result of the situation of the identified user U2 as resident situation information 270 of the corresponding resident in the storage device 120. In other words, the identification unit 110 compares the user identification information 250 with the resident information 260 to match the user with the resident, and stores information indicating the user's situation in the resident situation information 270 as information indicating the resident's situation.

[0157] In this embodiment, too, it is desirable to obtain consent from user U2 to use the consent acceptance unit described above to compare user U2's user identification information 250 with resident information 260 and identify which resident user U2 is.

[0158] 14, the user identification information 250 includes, for each information provision group, identification information capable of identifying the group (group ID in the figure), identification information capable of identifying a user who is a participant of the information provision group G1 (user ID in the figure), and information indicating the name and place of residence of the user. The information indicating the place of residence of the user may be an address or information capable of identifying a predetermined area.

[0159] The resident information 260 may be a resident basic register or a disaster victim register managed by a local government. As shown in Fig. 15, the resident information 260 includes information on residents registered for each area. The resident information 260 includes, as resident information, information that can identify the user (for example, My Number), name, address, etc.

[0160] 16, the resident situation information 270 includes, for each region, situation information of the residents of the region. The resident situation information 270 includes, as the resident situation information, information that can identify the user (for example, My Number), name, address, etc., as well as information that indicates the estimated situation of user U2 matched with the resident as the resident's estimated situation. For example, when a disaster such as an earthquake occurs, information on the victims in the area can be grasped and accumulated in the resident status information 270 without the need for local government officials to visit the site.

[0161] The output unit 112 outputs resident situation information indicating the estimated situation of residents in a predetermined area stored in the storage device 120. The output unit 112 outputs the information to at least one of the display, printer, and storage device of the communication device 30 of the information provider U1.

[0162] This not only makes it possible to quickly collect and store information on the status of victims when a disaster occurs, but also enables information provider U1 to obtain the status of victims as output information, enabling appropriate measures to be taken according to the disaster situation.

[0163] Furthermore, when a disaster victim register is used as the resident information 260, the identification unit 110 may further identify whether or not there is a difference between the situation information indicating the estimated result of the situation of the identified user U2 as a result of the comparison and the information indicating the disaster situation of the corresponding resident recorded in the disaster victim register. The output unit 112 may output information indicating that there is a difference between the situation of user U2 and the corresponding resident. Note that the output unit 112 may output the estimated situation information of user U2 and the information indicating the disaster situation of the corresponding resident in a manner that allows them to be compared (for example, by displaying them side by side, highlighting the differences, etc.).

[0164] Furthermore, by combining this with the configuration of the above embodiment, it is possible to estimate the "problems" of disaster victims, and extract the supplies and support that disaster victims need, which is expected to enable local governments to collect information efficiently and lead to appropriate responses by local governments.

[0165] The identifying unit 110 further identifies residents who do not have resident situation information 270 . The conversation generation unit 106 generates provision information 230 inquiring about the safety of the identified resident and outputs the information to an information provision group G1 in which the user corresponding to the resident participates.

[0166] However, residents without resident status information 270 may include residents whose safety is unknown. This configuration can identify the status of residents in a given area of ​​a local government, which reduces the burden on residents and allows local governments to understand the status of residents without visiting the area, and also enables efficient confirmation of residents' safety and evacuation status. This enables local governments to quickly take measures such as increasing the number of evacuation shelters and identify people who need support and provide support.

[0167] The output unit 112 performs statistical processing on the resident status information 270 to generate and output output information.

[0168] For example, the output unit 112 may generate output information that schematically represents the resident status information 270 in a heat map format by plotting colored marks according to the resident's status (evacuated, not evacuated, etc.) at positions on a map corresponding to the resident's location information based on the resident status information 270. The resident's location information is, for example, the current location acquired from the communication device 40 of the user U2 or the resident's address identified by the resident information 260.

[0169] Alternatively, the output unit 112 may generate output information as a list showing the status of residents by region based on the resident status information 270. For example, the output unit 112 may tally the number of residents who have evacuated, residents who are currently evacuating, and residents who have not evacuated by region, and generate output information as a list.

[0170] In this way, the situation of user U2, that is, the situation of residents in a specified area, can be visualized. This makes it easier for local government officials in the specified area to understand the situation and plan appropriate countermeasures. Furthermore, the conversation generation unit 106 may include the output information in the provision information 230 and provide it to the information provision group G1 in which user U2, a resident, participates. This allows user U2 and members of the information provision group G1 to be informed of the evacuation situation of other residents in the area in an easy-to-understand manner.

[0171] <Example of operation> An example of the operation of the fourth information generating device 100 according to the present disclosure will be described below with reference to Fig. 13. The flow of this figure includes processing by the identification unit 110 to identify the status of the resident. This process may be started, for example, after a disaster occurs or evacuation information is issued, when a certain amount of user situation information 240 has been accumulated. Alternatively, for example, a UI such as an operation menu for checking resident situations or an operation button for starting processing may be displayed on the display of the communication device 30 of the information provider U1, and the resident situation identification process of Fig. 13 may be started when an operation of the UI is accepted.

[0172] First, the identification unit 110 compares the user identification information 250 of a user U2 participating in the information provision group G1 with the resident information 260 related to residents of a predetermined area, and identifies the user U2 corresponding to the resident in the resident information 260 based on the comparison result (step S301). Then, the identification unit 110 stores situation information indicating the estimated result of the situation of the identified user U2 in the storage device 120 as the resident situation information 270 of the corresponding resident (step S303).

[0173] Then, the output unit 112 outputs the resident situation information indicating the estimated situation of the residents in the predetermined area stored in the storage device 120 (step S305). Specifically, the output unit 112 displays the resident situation information 270 on the display of the communication device 30 of the information provider U1.

[0174] As described above, according to this embodiment, the information generating device 100 includes an identification unit 110 and an output unit 112. The identification unit 110 compares the user identification information 250 of a user U2 who participates in the information provision group G1 with the resident information 260 related to residents of a predetermined area. Then, based on the comparison result, the identification unit 110 identifies the user U2 corresponding to the resident in the resident information 260, and stores situation information indicating an estimation result of the situation of the identified user U2 in the storage device 120 as resident situation information 270 of the corresponding resident. The output unit 112 outputs the resident situation information indicating the estimated situation of the residents of the predetermined area stored in the storage device 120. This configuration achieves the same effects as the above embodiment, and furthermore, it makes it possible to treat the status of user U2 as the status of residents in a specified area, so that, for example, in the event of a disaster, resident status information 270 can be used as a database for storing the status of disaster victims.

[0175] When a disaster occurs, not only can it be possible to quickly collect and store information on the status of disaster victims, but also the information provider U1 can obtain the status of disaster victims as output information, which enables appropriate measures to be taken according to the disaster situation. Furthermore, by combining this with the above embodiment, it is possible to estimate the "problems" of disaster victims, which can be expected to lead to the extraction of supplies and support needed by disaster victims and lead to appropriate responses by local governments.

[0176] The identification unit 110 further identifies residents who do not have resident status information 270. Then, the conversation generation unit 106 generates provision information 230 inquiring about the safety of the identified residents, and outputs the provision information 230 to an information provision group G1 in which users corresponding to the residents participate. This configuration allows local governments in a given area to grasp the situation of residents without having to visit the area, without placing any burden on the residents, and enables them to efficiently check on the safety of residents.

[0177] The output unit 112 also generates and outputs output information by statistically processing the resident situation information 270. For example, the resident situation can be displayed in a heat map format on a map of a specific area, making it possible to communicate the situation to local government officials and residents in an easy-to-understand manner. This makes it easier for local government officials in a specific area to grasp the situation and plan appropriate countermeasures.

[0178] Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and various other configurations can also be adopted. (Another embodiment 1) For example, the conversation generation unit 106 may generate a conversation (such as a question) for identifying a topic in which the user U2 is interested (a topic in which the user U2 is not interested) or a topic in which the user U2 has a good response (a topic in which the user U2 has a poor response), and output the conversation to the information provision group G1. The conversation generation unit 106 may acquire the user U2's answers and reactions to the conversation as conversation information 210, and identify a topic in which the user U2 is interested (a topic in which the user U2 is not interested) or a topic in which the user U2 has a good response (a topic in which the user U2 has a poor response). The conversation generation unit 106 may then use the identified topic in which the user U2 is interested (a topic in which the user U2 is not interested) or a topic in which the user U2 has a good response (a topic in which the user U2 has a poor response) to reflect the identified topic in which the user U2 has an interest (a topic in which the user U2 has a poor response) in the information to be provided 230 to be generated subsequently. For example, the conversation generation unit 106 avoids topics in which the user U2 has no interest or a topic in which the user U2 has a poor response, and uses topics in which the user U2 has an interest or a topic in which the user U2 has a good response, to generate the information to be provided 230.

[0179] According to this configuration, by having a conversation with user U2, it is possible to identify topics that user U2 is interested in (topics that user U2 is not interested in) and topics that user U2 responds well to (topics that user U2 responds poorly to), and these can be reflected in the subsequently generated information to be provided 230. Therefore, it is possible to make user U2 more interested in the information to be provided 230 generated by the conversation generation unit 106, and it becomes possible to more effectively convey information to be notified to user U2.

[0180] (Another embodiment 2) In the above embodiment, the identifying unit 110 identifies residents for whom the resident status information 270 is not available, and generates the information to be provided 230 inquiring about the safety of the residents. In another embodiment 2, the conversation generation unit 106 may identify members in the information provision group G1 with whom there has been no conversation for a predetermined period of time, generate provision information 230 including a hearing message addressed to the identified members, and output the provision information 230 to the information provision group G1.

[0181] According to this configuration, it is possible to encourage members who have not had a conversation for a predetermined period of time to post, so that conversation information 210 of the member in question can be acquired and the conversation information 210 can be used to estimate the recent situation of the member in question.

[0182] (Other embodiment 3) The conversation generation unit 106 may use the conversation information 210 to identify a key person from among the members of the information provision group G1. A key person is, for example, a leader among the members, and is a person whose words are expected to influence the other members. In other words, by having the key person call out to the other members, it is expected that the other members will take evacuation action.

[0183] The conversation generation unit 106 generates provision information 230 including a message requesting the identified key person to call out to other members and call for evacuation actions, and outputs the information to the information provision group G1.

[0184] According to this configuration, the key person can be made to call out to the other members, which is expected to encourage the other members to take evacuation action.

[0185] (Other embodiment 4) In the above embodiment, a configuration has been described in which the supplies and support needed by user U2 are identified from conversations within information provision group G1. In another embodiment 4, the identification unit 110 may associate user U2 with residents and store information about the needs of the identified user U2 in the resident situation information 270. The output unit 112 may aggregate the information stored in the resident situation information 270 by region and output information about the supplies and support needed in the region as output information.

[0186] According to this configuration, the needs of residents in a specified area can be compiled and output, allowing local governments and other organizations to efficiently grasp the needs of residents, leading to rapid response.

[0187] Other examples of the present disclosure may include a program that causes at least one computer to execute the above-disclosed method, or a computer-readable recording medium on which such a program is recorded. This recording medium includes a non-transitory tangible medium. The computer program comprises computer program code which, when executed by a computer, causes the computer to perform the information generation method on an information generation device.

[0188] Any combination of the above components, and conversion of the present disclosure into a method, device, system, recording medium, computer program, etc., are also valid aspects of the present disclosure.

[0189] Furthermore, the various components of the present disclosure do not necessarily have to be independent entities, but may be formed as a single member by multiple components, one component may be formed from multiple components, one component may be a part of another component, or part of one component may overlap with part of another component, etc.

[0190] Furthermore, although the methods and computer programs disclosed herein describe a number of steps in a sequential order, the order in which the steps are performed does not limit the order in which the steps are performed. Therefore, when implementing the methods and computer programs disclosed herein, the order of the steps can be changed as long as it does not cause any problems in terms of the content.

[0191] Furthermore, the steps of the method and computer program disclosed herein are not limited to being executed at different times, and may be executed while one step is being executed, or may be executed partially or entirely overlapping with another step, etc.

[0192] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate. In addition, when information on users and members of the information providing group, and information on residents is acquired and used in this disclosure, this will be done lawfully.

[0193] In addition, although the flowcharts used in the above description show multiple steps (processes) in a sequential order, the order of the steps executed in each embodiment is not limited to the order shown. In each embodiment, the order of the steps shown in the drawings can be changed as long as it does not cause any problems in terms of the content.

[0194] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes. 1. A first information acquisition means for acquiring notification target information to be notified to a user from an information provider; a second information acquisition means for acquiring conversation information held in an information providing group in which the user participates; a conversation generation means for generating provision information to be provided to the user using the conversation information and the notification target information, and outputting the provision information to an information provision group; An information generating device comprising: 2. In the information generating device described in 1., The conversation generation means processes the conversation information to generate situation information indicating an estimated result of the user's situation, and generates the information to be provided using this situation information and the notification target information. 3. In the information generating device according to 1. or 2., The conversation generation means uses past conversation information to generate tone information capable of identifying a tone of voice corresponding to the information provision group, and generates the information to be provided using the generated tone information. 4. In the information generating device according to any one of 1. to 3., The conversation generation means generates the information to be provided using attribute information of at least one of the user and the information providing group. 5. An information generation device described in any one of 1. to 4., wherein the first information acquisition means, the second information acquisition means, and the conversation generation means all function when a predetermined disaster condition is met. 6. In the information generating device according to any one of 2. and 3. to 5. which refer to 2., the notification target information includes information related to a disaster, The conversation generation means generates the situation information by estimating at least one of the user's intention to evacuate and the evacuation situation as the user's situation, and generates the information to be provided using this situation information and the notification target information. 7. In the information generating device according to any one of 2. and 3. to 6. which refer to 2., a consent receiving means for receiving consent from the user to output the situation information indicating the estimation result of the situation of the user to the information providing group; The conversation generating means outputs the situation information with the user's consent to the information providing group. 8. In the information generating device according to any one of 2. and 3. to 7. which refer to 2., an identification means for comparing user identification information of users participating in the information providing group with resident information on residents of a predetermined area, identifying the user corresponding to the resident in the resident information based on the comparison result, and storing the situation information indicating the estimated result of the situation of the identified user in a storage means as situation information of the corresponding resident; The information generating device further comprises an output means for outputting resident situation information indicating the estimated situation of the residents of the predetermined area stored in the storage means. 9. In the information generating device described in 8., The identification means further identifies residents for whom the resident status information is missing, The conversation generation means generates the provided information inquiring about the safety of the identified resident and outputs the provided information to the information providing group in which the user corresponding to the resident participates. 10. In the information generating device according to 8. or 9., The output means generates and outputs output information by statistically processing the resident status information.

[0195] 11. One or more computers Acquires notification information to be notified to the user from the information provider; Acquire conversation information held in an information providing group in which the user participates; generating provision information to be provided to the user using the conversation information and the notification target information, and outputting the provision information to an information provision group; Information generation method. 12. On the computer, a first information acquisition process for acquiring notification target information to be notified to a user from an information provider; a second information acquisition process for acquiring conversation information held in an information providing group in which the user participates; a conversation generation process for generating provision information to be provided to the user using the conversation information and the notification target information and outputting the information to an information provision group; A program to execute. 13. On the computer, a first information acquisition process for acquiring notification target information to be notified to a user from an information provider; a second information acquisition process for acquiring conversation information held in an information providing group in which the user participates; a conversation generation process for generating provision information to be provided to the user using the conversation information and the notification target information and outputting the information to an information provision group; A computer-readable recording medium that stores a program for executing the above.

[0196] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 10 that are dependent on Supplementary Note 1 (information generating device) may also be dependent on Supplementary Note 11 (information generating method), Supplementary Note 12 (program), and Supplementary Note 13 (recording medium) in the same dependent relationship as Supplementary Note 2 to 10. Furthermore, not limited to Supplementary Note 1, Supplementary Note 11, Supplementary Note 12, and Supplementary Note 13, some or all of the configurations described as Supplements may be similarly made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments. [Explanation of symbols]

[0197] 1. Information Processing Systems 3. Communication Network 10 SNS Server 20 AI Agents 30 Communication equipment 40 Communication equipment 100 Information generation device 102 1st Information Acquisition Department 104 2nd Information Acquisition Department 106 Conversation Generation Unit 110 Specific section 112 Output section 120 Storage device 200 Notification Information 210 Conversation Information 220 Tone Information 230 Provided information 240 Status Information 250 User-Specific Information 260 Resident Information 270 Resident Status Information 1000 computers 1010 Bus 1020 processor 1030 memory 1040 Storage Device 1050 Input / Output Interface 1060 Network Interface

Claims

1. a first information acquisition means for acquiring notification target information to be notified to a user from an information provider; a second information acquisition means for acquiring conversation information held in an information providing group in which the user participates; a conversation generation means for generating provision information to be provided to the user using the conversation information and the notification target information, and outputting the provision information to an information provision group; An information generating device comprising:

2. 2. The information generating device according to claim 1, The conversation generation means processes the conversation information to generate situation information indicating an estimated result of the user's situation, and generates the information to be provided using this situation information and the notification target information.

3. 3. The information generating device according to claim 1, The conversation generation means uses past conversation information to generate tone of voice information capable of identifying a tone of voice corresponding to the information provision group, and generates the information to be provided using the generated tone of voice information.

4. 3. The information generating device according to claim 1, The conversation generation means generates the information to be provided using attribute information of at least one of the user and the information providing group.

5. 3. The information generating device according to claim 1, wherein the first information acquiring means, the second information acquiring means, and the conversation generating means all function when a predetermined disaster condition is satisfied.

6. 3. The information generating device according to claim 2, the notification target information includes information related to a disaster, The conversation generation means generates the situation information by estimating at least one of the user's intention to evacuate and the evacuation situation as the user's situation, and generates the information to be provided using this situation information and the notification target information.

7. 3. The information generating device according to claim 2, an identification means for comparing user identification information of users participating in the information providing group with resident information on residents of a predetermined area, identifying the user corresponding to the resident in the resident information based on the comparison result, and storing the situation information indicating the estimated result of the situation of the identified user in a storage means as situation information of the corresponding resident; The information generating device further comprises an output means for outputting resident situation information indicating the estimated situation of the residents of the predetermined area stored in the storage means.

8. 8. The information generating device according to claim 7, The identification means further identifies residents for whom the resident status information is missing, The conversation generation means generates the provided information inquiring about the safety of the identified resident and outputs the provided information to the information providing group in which the user corresponding to the resident participates.

9. One or more computers Acquires notification information to be notified to the user from the information provider; Acquire conversation information held in an information providing group in which the user participates; generating provision information to be provided to the user using the conversation information and the notification target information, and outputting the provision information to an information provision group; Information generation method.

10. On the computer, a first information acquisition process for acquiring notification target information to be notified to a user from an information provider; a second information acquisition process for acquiring conversation information held in an information providing group in which the user participates; a conversation generation process for generating provision information to be provided to the user using the conversation information and the notification target information and outputting the information to an information provision group; A program to execute.

Images