Programs, methods, information processing devices, and systems

Abstract

To improve the accuracy of safety checks while reducing the resources required to confirm the safety of monitored individuals. [Solution] The program is a program to be executed in a system comprising a processor, a user terminal and a server, the program causing the processor to perform the following steps: notify the user terminal of a first request to the user at a predetermined timing to execute an AI dialogue function and start a voice dialogue with the AI; determine whether the user terminal has responded to the first request; and if the user terminal determines that there has been no response to the first request, send to the server a notification that there has been no response and a second request to contact by another first means of communication.

Description

Technical Field

[0001] This disclosure relates to programs, methods, information processing apparatuses, and systems.

Background Art

[0002] Conventionally, various monitoring services have been provided to confirm the safety of monitored persons such as the elderly. In these services, a mechanism is generally used to automatically call the target person at a specific time and confirm the physical condition and safety from the response and conversation content.

[0003] In Patent Document 1, the server makes a phone call to a specific target person to confirm safety, alleviates loneliness by having a conversation, and also conducts physical condition management based on the tone of voice. In addition, the server utilizes a conversion system that imitates human voices, converts the voice into text, creates an answer using a generative AI, converts it back into voice, and takes the form of a phone conversation. Further, the server uses voice recognition technology to convert the target person's voice into text. Additionally, the server analyzes the text using generative AI and generates an appropriate answer. Moreover, the server converts the generated answer from text to voice and conveys it to the target person via the phone. Also, the server推测 the physical condition from the tone of voice and conversation content and notifies family members or medical institutions as necessary.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, Patent Document 1 does not describe any countermeasures in the case where the target person does not answer the phone.

[0006] The purpose of this disclosure is to improve the accuracy of safety checks while reducing the resources required to check on the safety of monitored individuals. [Means for solving the problem]

[0007] To solve the above problems, a program according to one aspect of the present disclosure is a program to be executed in a system including a processor, a user terminal and a server, the program causing the processor to perform the following steps: notify the user terminal of a first request to the user at a predetermined timing to execute an AI dialogue function and start a voice dialogue with the AI; determine whether the user terminal has responded to the first request; and if the user terminal determines that there has been no response to the first request, send to the server a notification that there has been no response and a second request to contact by another first means of communication. [Effects of the Invention]

[0008] According to this disclosure, it is possible to improve the accuracy of safety checks while reducing the resources required to check on the safety of monitored individuals. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows a schematic configuration of an information processing system according to an embodiment of the present disclosure. [Figure 2] This figure shows the hardware configuration of a user terminal according to an embodiment of this disclosure. [Figure 3] This is a functional block diagram of a user terminal according to an embodiment of this disclosure. [Figure 4] This figure shows the hardware configuration of the server according to the embodiment of this disclosure. [Figure 5] This is a functional block diagram of a server according to an embodiment of this disclosure. [Figure 6] This figure shows an example of the configuration of a prompt according to an embodiment of this disclosure. [Figure 7]This figure shows an example of the data structure of a user information table according to the embodiment of this disclosure. [Figure 8] This figure shows an example of the data structure of an escalation rule table according to the embodiment of this disclosure. [Figure 9] This figure shows an example of the data structure of the dialogue log table according to the embodiment of this disclosure. [Figure 10] This figure shows an example of the data structure of a status management table according to an embodiment of this disclosure. [Figure 11] This is a flowchart showing the processing operation of an information processing system according to an embodiment of this disclosure. [Figure 12] This figure shows an example of a user terminal screen according to the embodiment of this disclosure. [Figure 13] This figure shows an example of the first screen of a monitor terminal according to an embodiment of this disclosure. [Figure 14] This figure shows an example of a second screen of a monitor terminal according to an embodiment of this disclosure. [Modes for carrying out the invention]

[0010] The embodiments of this disclosure will be described below with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted. The following embodiments are not intended to unduly limit the content of this disclosure as described in the claims. Not all components shown in the embodiments are necessarily essential components of this disclosure. Also, each drawing is a schematic diagram and is not necessarily a strict illustration.

[0011] Also, in the following description, "processor" refers to one or more processors. A processor may be expressed as, for example, processing circuitry. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may also be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core. Also, at least one processor may be a general-purpose processor or a special-purpose processor.

[0012] Also, at least one processor may be a processor in a broad sense such as a hardware circuit (e.g., FPGA (Field-Programmable Gate Array), ASIC (Application Specific Integrated Circuit)) that performs part or all of the processing.

[0013] Also, in the following description, expressions such as "xxx table" may be used to describe information from which an output is obtained for an input. This information may be data of any structure or a learning model such as a neural network that generates an output for an input. Therefore, "xxx table" can be referred to as "xxx information".

[0014] Also, in the following description, the configuration of each table is an example. One table may be divided into two or more tables, or all or part of two or more tables may be one table.

[0015] The program may be pre-installed in the information processing apparatus described below, or may be, for example, on a record medium (e.g., non-transitory) readable by the information processing apparatus, and this program may be installed in the information processing apparatus. Also, the program may be transmitted from a program distribution server to the information processing apparatus and installed. Further, in the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

[0016] Also, in the following description, identification information for various objects is used, but the identification information may be information indicating a predetermined object, and the specific data is not limited to the embodiments. The identification information may be an identification number or an identifier including letters or symbols.

[0017] <Overview> In the information processing system 1 according to this embodiment (hereinafter simply referred to as system 1), for confirming the safety of a monitoring target person (user) such as a single elderly person, the user terminal 10 (such as a smartphone) that the user uses daily and the server 20 (external device) operate in cooperation. The user terminal 10 notifies a first request for starting a voice dialogue with the AI by executing the AI dialogue function by the AI application for the user at a predetermined timing. When there is no response, the server 20 makes a call by another first communication means (for example, an IP phone, a phone on a mobile phone network, etc.) according to a preset escalation rule. Further, when there is no response, a call is made by a second communication means (for example, a phone on a fixed phone network, etc.) with a high probability of getting in touch. Thereby, it is possible to improve the accuracy of safety confirmation while reducing the resources for implementing the safety confirmation of the monitoring target person. Further, when there is a response, based on the log of the AI dialogue, the server 20 instructs the AI system 30 to automatically generate a concise and easy-to-understand summary report and presents it to a monitoring terminal 40 (such as a smartphone) of a pre-registered family member or the like. Thereby, the monitor can easily grasp and share the daily safety status of the user.

[0018] <Configuration of the entire system> Figure 1 is a block diagram showing an example of the overall configuration of System 1. System 1 is a system for providing a safety confirmation service using AI dialogue functionality.

[0019] System 1 shown in Figure 1 includes, for example, a user terminal 10, a server 20, a generation AI system 30, and a monitor terminal 40. The user terminal 10, server 20, generation AI system 30, and monitor terminal 40 communicate with each other via, for example, a network 80.

[0020] Figure 1 shows an example where System 1 includes one user terminal 10, but System 1 may include two or more user terminals 10. Also, while Server 20 is assumed to consist of one unit, it may also be configured as a collection of multiple devices. The method of distributing the multiple functions required to realize Server 20 to multiple devices can be appropriately determined according to the processing capacity of each device and / or the specifications required for Server 20. Also, while Figure 1 shows an example where System 1 includes one monitor terminal 40, System 1 may include two or more monitor terminals 40.

[0021] The user terminal 10 is, for example, an information processing device operated by a user who is to be monitored. The user terminal 10 can be implemented as, for example, a mobile device such as a smartphone or tablet. In this embodiment, the user terminal 10 is assumed to be a smartphone. The user terminal 10 may also be implemented as, for example, a stationary PC (Personal Computer), a laptop PC, etc. The user terminal 10 displays a screen (first request) that notifies the execution of the AI ​​dialogue function at a predetermined timing via a dedicated application, receives a response from the user (voice input, screen operation), and sends the result to the server 20.

[0022] Server 20, for example, is an information processing device implemented by a computer connected to the network, which executes various processes of the safety confirmation system 1. Server 20 performs escalation in response to requests from user terminals 10 and sends notifications to pre-registered monitoring terminals 40. When it receives a report creation request from user terminal 10, it generates an appropriate prompt, queries the generation AI system 30, and presents the result to the monitoring terminal 40.

[0023] The Generative AI System 30 provides the use of Generative AI. This disclosure describes, as an example, the case in which the Generative AI System 30 provides the use of Large Language Models (LLMs), which are a type of Generative AI. Large Language Models are natural language models designed to perform multiple tasks of natural language processing. Large Language Models are an example of a trained model, and are models trained using a large number of parameters (e.g., billions to hundreds of billions) and high-level computing resources. Large Language Models are computer programs or algorithms designed to perform tasks of natural language processing. For example, in natural language processing, processes such as morphological analysis, syntactic analysis, information extraction, and text generation are performed, enabling a computer to analyze human language (i.e., natural language) and perform predetermined processing. When a prompt (instruction) is input to a Large Language Model, it generates output based on the text, image, etc., of the prompt. The prompt can be defined in natural language.

[0024] Examples of large-scale language models include the GPT series (Generative Pre-TrAIned Transformer) developed by OPEN AI, StableLM developed by Stability AI, Llama2 developed by Meta, and Palm2® and LamDA2® developed by Google. Note that other language models are also acceptable, not limited to large-scale models. For example, BERT (Bidirectional Encoder Representations from Transformers) developed by Google may also be used. In this embodiment, the generative AI system 30 is used via an API (Application Programming Interface) provided by the server 20. Note that the generative AI system 30 is not limited to an external service; it may also be operated by the provider of the server 20 itself.

[0025] A prompt is primarily a query input to a generating AI. A query can include, for example, text, strings, images, videos, audio, etc. A prompt may also include gestures. The user instructs the generating AI to process information by inputting a prompt. The user may include information in the prompt that causes the generating AI to produce a desired output.

[0026] The prompt may be generated by the server 20 in a format that integrates the dialogue log (text data of the audio) and the instruction text. Alternatively, the prompt may be generated by the user terminal 10 in a format that integrates the dialogue log and the instruction text.

[0027] The prompt may include information to specify the output format. Examples of such information include function definition information in a function call, JSON schema, XML format specification, and other structured data format specification. This information allows the output from the generating AI to be obtained in a predetermined structured format. For example, function definition information may include the function name, parameter names, parameter types, and parameter descriptions. Based on this output format specification information, the generating AI generates output results in the specified format.

[0028] A prompt contains an instruction. A prompt may also contain reference data. Here, an instruction is data that indicates the information processing to be performed by the generating AI. Reference data is data that the generating AI uses as a reference (learns from) when performing the information processing. The instruction and reference data may be included in the prompt in any form. For example, the instruction and reference data may be included in the prompt as text data entered in response to user operation. Another example is that the instruction may be included in the prompt as text data entered in response to user operation, and the reference data may be included in the prompt as a separate file from the text data. Furthermore, the instruction and reference data for the same instruction content do not necessarily have to be input to the generating AI as a single prompt. For example, a prompt containing the instruction may be input to the generating AI first, and then a prompt containing the reference data may be input to the generating AI.

[0029] The monitoring terminal 40 is an information processing device operated by a monitor, such as a family member of the user being monitored. The monitoring terminal 40 is implemented by a mobile device such as a smartphone or tablet. In this embodiment, the monitoring terminal 40 is assumed to be a smartphone. The monitoring terminal 40 may also be implemented by a stationary PC, laptop PC, etc. The monitoring terminal 40 displays, for example, the results of safety confirmation, escalation status, and reports generated by AI, which are provided from the server 20 via a dedicated application or web browser. The monitoring terminal 40 also receives, for example, reports of contact history from monitors (information sharing among monitors).

[0030] <User terminal configuration> Figure 2 is a block diagram showing an example of the hardware configuration of the user terminal 10 shown in Figure 1. As shown in Figure 2, the user terminal 10 comprises a control unit 101, a storage unit 102, a communication unit 103, an input unit 104, and an output unit 105. The user terminal 10 may also include a camera 106, a position sensor 107, and an acceleration sensor 108. Each block included in the user terminal 10 is electrically connected, for example, by a bus.

[0031] The control unit 101 performs various processes by executing various programs stored in the memory unit 102. The control unit 101 is a processor, such as a CPU. A processor is hardware for executing instruction sets written in a program. A processor consists of an arithmetic unit, registers, peripheral circuits, etc. By operating according to the program, the control unit 101 performs the functions of an operation reception unit 131, a transmission / reception unit 132, a presentation control unit 133, and a safety confirmation control unit 134. The control unit 101 performs processes related to notifying a first request at a predetermined timing, determining whether or not there is a response, sending a second request if there is no response, determining whether or not predetermined requirements are met, sending a third request if the predetermined requirements are not met, and sending a fourth request for report creation.

[0032] The storage unit 102 includes a main memory and an auxiliary memory. The storage unit 102 stores various programs and various information. For example, the storage unit 102 stores an application program 120. The application program 120 includes, for example, a programming language that is executed on a web browser application (not shown) stored in the storage unit 102, or it is executed as a dedicated application. The storage unit 102 also stores an AI model for dialogue (e.g., a response generation model, a speech recognition model, etc.) to realize AI dialogue functionality, and the control unit 101 uses these to perform dialogue. The AI ​​model for dialogue is not limited to the storage unit 102 of the user terminal 10, but may also be stored in the storage unit 202 of the server 20.

[0033] The communication unit 103 performs processing such as modulation and demodulation for the user terminal 10 to communicate with an external device (for example, a server 20). The communication unit 103 performs transmission processing on the signal generated by the control unit 101 and transmits it to the external device. The communication unit 103 performs reception processing on the signal received from the external device and outputs it to the control unit 101.

[0034] The input unit 104 receives instructions or information input from the user. The input unit 104 may be implemented, for example, by a touch-sensitive device that inputs instructions, etc., by touching the operating surface. If the user terminal 10 is a PC, the input unit 104 may be implemented by a reader, keyboard, mouse, etc. The input unit 104 converts the instructions, etc., input by the user into electrical signals and outputs them to the control unit 101. The input unit 104 may also include, for example, a receiving port that accepts electrical signals input from an external input device. The input unit 104 may include, for example, a microphone that accepts voice input in order to implement a voice dialogue function with an AI.

[0035] The output unit 105 presents information to the user. The output unit 105 is implemented, for example, by a display. The display shows various information according to the control of the control unit 101. The display is implemented, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display. The output unit 105 may also include, for example, an output port that outputs electrical signals to an external output device. The output unit 105 includes, for example, a speaker that plays response voices from the AI. In other words, the presentation includes, for example, display on the display unit and output to a speaker or other output device.

[0036] Camera 106 is an imaging device that captures images using visible light. In other words, camera 106 is a device that receives visible light using a photodetector and outputs image data as a capture signal. In this embodiment, camera 106 may, for example, capture the user's situation (facial expressions, movements, etc.), and the image data may be used as auxiliary information during AI dialogue.

[0037] The position sensor 107 is a sensor that detects the position of the user terminal 10, and is generally a GNSS device, such as a GPS module. The position sensor 107 may also detect the current position of the user terminal 10 from the position of the wireless base station to which the user terminal 10 is connected via the communication unit 103.

[0038] The acceleration sensor 108 is a sensor that detects the acceleration applied to the user terminal 10. Preferably, the acceleration sensor 108 has the function of detecting the tilt around each axis (X axis, Y axis, Z axis) of a three-dimensional coordinate system with the position of the user terminal 10 as the origin. An acceleration sensor 108 having such a function can detect the orientation of the user terminal 10 by detecting the gravitational acceleration due to the force of gravity on the Earth.

[0039] Figure 3 is a block diagram showing the functional units implemented by the control unit 101. The control unit 101 comprises an operation reception unit 131, a transmission / reception unit 132, a presentation control unit 133, and a safety confirmation control unit 134 as functional units. Specifically, the control unit 101 implements each functional unit by reading the application program 120 stored in the storage unit 102 and executing the instructions contained in the application program 120.

[0040] The operation reception unit 131 processes instructions or information input from the input unit 104. Specifically in this embodiment, it receives responses to notifications of activation of the AI ​​dialogue function (such as the start of voice input or the pressing of the "Respond" button on the screen) and outputs the results to the safety confirmation control unit 134.

[0041] The transmitting / receiving unit 132 performs processing to enable the user terminal 10 to send and receive data with an external device (server 20) according to a communication protocol. Specifically, the transmitting / receiving unit 132 sends various requests to the server 20 in response to instructions from the safety confirmation control unit 134. The transmitting / receiving unit 132 receives information sent from the server 20.

[0042] The safety confirmation control unit 134 executes various control processes related to safety confirmation. Specifically, the safety confirmation control unit 134 executes a dialogue function with the AI ​​at a predetermined timing and instructs the presentation control unit 133 to notify the first request to start voice dialogue with the AI. The predetermined timing is, for example, a predetermined time, after a predetermined action (e.g., eating, walking, etc.), or at a predetermined cycle. The safety confirmation control unit 134 also determines whether or not there has been a response to the first request based on the response input from the operation reception unit 131. If the safety confirmation control unit 134 determines that there has been no response, it sends a notification that there has been no response and a second request to contact the server 20 (external device) by a different means of communication. If there is a response, the safety confirmation control unit 134 uses the dialogue AI model in the memory unit 102 to perform dialogue with the user and generates a dialogue log. Furthermore, if the dialogue is established and a response is received, the safety confirmation control unit 134 determines whether or not the content of the response meets predetermined requirements (anomaly detection). If the safety confirmation control unit 134 determines that the response does not meet the predetermined requirements, it sends a third request to the server 20 to contact a pre-registered monitor. Furthermore, if the dialogue is successful and the predetermined requirements are met, the safety confirmation control unit 134 sends a fourth request to the server 20 to create a report based on the generated dialogue log.

[0043] The presentation control unit 133 controls the output unit 105 in order to present various information to the user, such as notifications for the start of AI dialogue and responses from the AI, in response to instructions from the safety confirmation control unit 134.

[0044] <Server Configuration> Figure 4 is a block diagram showing an example of the hardware configuration of the server 20 shown in Figure 1. As shown in Figure 4, the server 20 comprises a control unit 201, a storage unit 202, a communication unit 203, and an input / output IF 204. Each block included in the server 20 is electrically connected, for example, by a bus.

[0045] The control unit 201 executes various processes by running various programs (for example, application program 2025) stored in the memory unit 202. The control unit 201 is a processor such as a CPU or GPU. By operating according to the program, the control unit 201 performs functions as a receiving control unit 2031, a transmitting control unit 2032, a presentation control unit 2033, and a service processing unit 2034.

[0046] The storage unit 202 includes a main memory and an auxiliary memory. The storage unit 202 stores various programs, various information, and various tables. The storage unit 202 stores various databases. As various databases, the storage unit 202 stores, for example, a user information table 2021, an escalation rule table 2022, an interaction log table 2023, a status management table 2024, and an application program 2025 for executing the safety confirmation service according to this embodiment.

[0047] User Information Table 2021 is, for example, a database used to manage service users. User Information Table 2021 stores information such as the user's (monitored) "User ID," "Name," "Contact Information," and "Monitoring Manager." Further details will be provided later.

[0048] The escalation rule table 2022 is a database for managing rules such as the priority and waiting time of contact methods to be used when there is no response from user terminal 10. The escalation rule table 2022 stores items such as "Rule ID," "User ID," "Contact Priority," "Waiting Time," and "Emergency Contact." Further details will be described later.

[0049] The Dialogue Log Table 2023 is a database for storing information such as dialogue logs with user terminal 10, escalation history, and whether or not contact was made by a supervisor. The Dialogue Log Table 2023 stores items such as "Log ID," "User ID," "Dialogue Date and Time," "Dialogue Content," "Dialogue Duration," and "Response Present / Not Present." Further details will be described later.

[0050] The Status Management Table 2024 is a database that manages, for example, the current status of safety confirmations and the history of information sharing among monitors. The Status Management Table 2024 stores items such as "Status ID," "User ID," "Escalation Stage," and "Response Status." Further details will be provided later.

[0051] Application Program 2025 is, for example, application software for executing and managing this safety confirmation service. Application Program 2025 includes, for example, program code for implementing various processes necessary to provide this service (escalation control, notification to monitors, prompt generation, report creation control, etc.).

[0052] The communication unit 203 performs modulation and demodulation processing for the server 20 to communicate with external devices (e.g., user terminal 10, monitoring terminal 40, and generation AI system 30). The communication unit 203 performs transmission processing on the signals generated by the control unit 201 and transmits them to the external devices. The communication unit 203 performs reception processing on the signals received from the external devices and outputs them to the control unit 201.

[0053] The input / output interface 204 receives instructions or information input from the administrator of server 20, and functions as an interface for presenting information to the administrator. For example, the input / output interface 204 is connected to input / output devices such as a keyboard, mouse, and display.

[0054] Figure 5 is a block diagram showing the functional units implemented by the control unit 201. The control unit 201 comprises a receiving control unit 2031, a transmitting control unit 2032, a presentation control unit 2033, and a service processing unit 2034 as functional units. Specifically, the control unit 201 implements each functional unit by reading the application program 2025 stored in the storage unit 202 and executing the instructions contained in the application program 2025.

[0055] The receiving control unit 2031 processes data or information transmitted from an external device via the communication unit 203. Specifically, the receiving control unit 2031 receives, for example, a second request (a request for contact via another first means of communication), a third request (a notification that the response content does not meet predetermined requirements and a request for contact with the monitor), and a fourth request (a request for report creation) transmitted from the user terminal 10. The receiving control unit 2031 also receives, for example, information transmitted from the monitor terminal 40 regarding whether or not contact has been made by the monitor, and the results of report creation transmitted from the generation AI system 30.

[0056] The transmission control unit 2032 performs processing via the communication unit 203 to enable the server 20 to send and receive data with external devices in accordance with the communication protocol. Specifically, the transmission control unit 2032 transmits data such as a request to initiate contact with other means of communication for escalation (e.g., IP phone, other terminal), a notification to the monitoring terminal 40, and a prompt to the generating AI system 30, in response to instructions from the service processing unit 2034.

[0057] The service processing unit 2034 performs various processes in safety confirmation. For example, based on the second request received by the receiving control unit 2031, the service processing unit 2034 refers to the escalation rule table 2022 in the storage unit 202 and performs control to contact the user via other first contact means. The first contact means is, for example, a contact means using another communication method with the user terminal 10. The first contact means is, for example, a telephone call to the user terminal 10 via IP communication, or a telephone call to the user terminal 10 via a mobile phone network. For example, if the service processing unit 2034 determines that there is no response to the contact via the first contact means, it performs control to contact the user via other second contact means that is more likely to elicit a response from the user than the first contact means. The second contact means is a device different from the user terminal 10, for example, a telephone call to a landline owned by the user via a landline network. The second contact means may also be, for example, a voice notification device such as a smart speaker installed in the user's home, or other wearable devices capable of voice and vibration notifications. Here, "high probability" refers to a pre-configured communication method in which the user is more likely to notice the notification and respond than, for example, the first communication method.

[0058] Furthermore, the service processing unit 2034, for example, based on the third request received by the receiving control unit 2031, refers to the user information table 2021 in the storage unit 202 and executes control to contact the pre-registered monitoring terminal 40. Also, if the service processing unit 2034 receives information from the monitoring terminal 40 regarding whether or not contact has been made, for example, it stores that information in the storage unit 202 and executes control to share it with other monitoring terminals 40. The information regarding whether or not contact has been made may include, for example, information that the user has not been contacted, information that an attempt was made to contact the user, information that contact was made with the user, or information that contact was not made with the user. Furthermore, the service processing unit 2034, for example, based on the fourth request received by the receiving control unit 2031, generates a prompt that includes the content (log) of the voice dialogue from the user terminal 10 and a predetermined instruction to create a report, sends this to the generation AI system 30, and executes the process of receiving the resulting report.

[0059] The prescribed instructions are text that provides instructions for the generating AI to generate a report. The prescribed instructions are included in the example prompt structure, as shown in Figure 6. The prescribed instructions may be in the form of a request to a person, for example, "You are an excellent care support consultant. Please analyze the following dialogue log and summarize the key points regarding the user's safety and any concerns regarding their health in three lines." The prescribed instructions may also include instructions such as, for privacy reasons, "Please do not include any private information such as personal names or addresses contained in the dialogue log in the report."

[0060] The service processing unit 2034 obtains a predetermined instruction statement from the storage unit 202 based on the information (such as the dialogue log ID) contained in the fourth request received by the receiving control unit 2031. Then, the service processing unit 2034 generates a prompt that includes the obtained predetermined instruction statement and the text data of the target dialogue log. The configuration of the prompt can be set arbitrarily.

[0061] Figure 6 shows an example of the structure of a prompt generated by the service processing unit 2034. As shown in Figure 6, prompt P is text data and includes text data for each part exemplified by instruction P1, reference data P2, data P3, output format P4, and log information P5. Note that the order in which instruction P1 to log information P5 are written is not particularly limited. Prompt P may also contain strings other than instruction P1 to log information P5.

[0062] (Instruction P1) Instruction P1 includes a predetermined instruction statement that instructs the large-scale language model on its role in generating the report. The instruction includes a statement that specifies the role of the large-scale language model in generating the text, such as, "You are an excellent care support consultant. Analyze the following dialogue log and summarize the key points regarding the user's well-being and concerns regarding their health in three lines." The service processing unit 2034 generates a prompt by combining this instruction with the following reference data, etc.

[0063] (Reference data P2) Reference data P2 includes the content (text data) of the voice dialogue between the user and the AI, which the service processing unit 2034 obtained from the dialogue log table 2023 in Figure 9. The service processing unit 2034 combines this dialogue content as reference data P2 with instruction P1.

[0064] (Data P3) Data P3 includes text specifying the image to be read by the Large-Scale Language Model (LLM). Data P3 can include, for example, image data converted to any format, or information that can identify the image (image identification information, image URL, etc.). The service processing unit 2034 receives, for example, image data (for example, an image of the person being monitored) sent from the user terminal 10 (for example, as a result of being captured by the camera 106) along with a report creation request, and combines this as Data P3 with the instruction P1 to the generating AI. This makes it possible to request the generating AI to provide a response that takes into account not only text information (reference data P2) but also image information (data P3).

[0065] (Output format P4) Output format P4 includes information about the report's output format (template) or examples of responses to the generation AI. Service processing unit 2034 takes instructions such as "Summary of Key Points," "Changes in Health," and "Points of Concern" to be output in a structured data format (e.g., JSON), or "Please list the key points in three bullet points," and combines these instructions into the output format.

[0066] (Log information P5) Log information P5 is an area where the service processing unit 2034 stores contextual information such as a summary of the user's past dialogue history or trends related to safety confirmation, such as response times, obtained from the dialogue log table 2023 in Figure 9. For example, if a user tends to have difficulty holding a conversation at a particular time of day, information indicating that tendency (e.g., "tendency to respond slowly in the morning") is included in prompt P as log information P5. This allows the generating AI to create a more personalized report that takes into account not only the information from instruction P1 and reference data P2, but also the past context contained in log information P5, in response to differences from the user's normal behavior or potential changes.

[0067] The service processing unit 2034 sends the generated prompt to the large-scale language model, causing the large-scale language model to generate generated data (responses) such as reports. Specifically, the service processing unit 2034 sends the generated prompt to the generation AI system 30 via the transmission control unit 2032. Then, via the reception control unit 2031, it receives the report data generated by the large-scale language model from the generation AI system 30. The service processing unit 2034 presents the generated report to the monitor terminal 40.

[0068] The presentation control unit 2033 controls the transmission control unit 2032 to present the execution results of the service processing unit 2034 (for example, reports created by the generation AI system 30, escalation status, whether or not contact was made by the monitor, etc.) to the monitor terminal 40. The presentation control unit 2033 also controls a display device (not shown) connected to the input / output IF 204, for example, to present various information to the administrator of the server 20, etc.

[0069] <Data structure> In this embodiment, the main data structures managed by the storage unit 202 of the server 20 will be described with reference to Figures 7-10. Note that the data structures described are examples and do not exclude data not listed.

[0070] Figure 7 shows an example of the data structure of User Information Table 2021. As shown in Figure 7, User Information Table 2021 is a table that has columns such as Name, Age, Gender, Date of Birth, Contact Information, and Supervisor, with User ID as the key. Various information about the same user is stored in a single record. The columns that User Information Table 2021 has are not limited to these.

[0071] The "User ID" field stores an identifier to uniquely identify users of this safety confirmation service. The "Name" field stores the user's name. The "Age" field stores the user's age. The "Gender" field stores the user's gender. The "Date of Birth" field stores the user's date of birth. The "Name," "Age," "Gender," and "Date of Birth" fields are the user's basic information and are used, for example, as contextual information when analyzing conversation content and creating reports. The "Contact Information" field stores information about contact information for the user terminal 10 used for escalation (e.g., mobile phone number, IP phone number, landline phone number, etc.). The "Monitoring Person" field stores information such as the name, contact information, and relationship to the user of a family member or other person who monitors the user. User Information Table 2021 is generated or updated based on the information entered, for example, when a user registers to use this safety confirmation service.

[0072] Figure 8 shows an example of the data structure of the escalation rule table 2022. As shown in Figure 8, the escalation rule table 2022 is a table that has columns such as User ID, Contact Priority, Waiting Time, and Emergency Contact, with Rule ID as the key.

[0073] The "Rule ID" field stores an identifier to uniquely identify the escalation rule. The "User ID" field stores an identifier to uniquely identify the user of this safety confirmation service. The "User ID" field corresponds to the "User ID" field stored in User Information Table 2021. The "Contact Priority" field stores information indicating the order of contact methods to try if there is no response (e.g., 1 (e.g., IP phone) → 2 (e.g., mobile phone) → 3 (e.g., landline)). This order is set based on the likelihood of successful contact. The "Waiting Time" field stores a predetermined time (e.g., hours, minutes) to wait for a response from each contact method. The "Emergency Contact" field stores the contact information of the monitor who will be the final escalation destination, or the contact information of an external service (e.g., security company, local government, etc.).

[0074] Figure 9 shows an example of the data structure of the dialogue log table 2023. As shown in Figure 9, the dialogue log table 2023 is a table that has columns such as user ID, dialogue date and time, dialogue content, dialogue duration, and response status, with log ID as the key. Each record stores information about one AI dialogue by the AI ​​application. The dialogue log table 2023 is a database for storing the dialogue history with the user terminal 10. Note that the dialogue log table 2023 may also store information about AI dialogues other than those with the AI ​​application (e.g., IP phones, mobile phones, landlines, etc.).

[0075] The "Log ID" field stores an identifier to uniquely identify each dialogue history. The "User ID" field is an identifier to identify the user who conducted the dialogue. The "User ID" field corresponds to the "User ID" field stored in User Information Table 2021. The "Dialogue Date and Time" and "Dialogue Duration" fields store the date and time and duration (length) of the dialogue. The "Dialogue Content" field stores the text data (log) of the voice dialogue between the user and the AI. The "Response Status" field stores information such as whether a response was given during the dialogue, whether the dialogue was completed successfully, or whether the response was interrupted midway.

[0076] Figure 10 shows an example of the data structure of the status management table 2024. As shown in Figure 10, the status management table 2024 is a table that has columns such as user ID, escalation stage, last response date and time, and response status, with status ID as the key. This table is used to manage the current safety confirmation status and the history of information sharing among monitors.

[0077] The "Status ID" field stores an identifier to uniquely identify the current safety confirmation cycle. The "User ID" field stores an identifier to uniquely identify the person whose safety confirmation status is being addressed. The "User ID" field corresponds to the "User ID" field stored in User Information Table 2021. The "Escalation Stage" field stores the stage of the communication method currently being tried (e.g., 1→2, 1→2→3, etc.). The "Escalation Stage" field may include, for example, the user's response status in each communication method. The "Response Status" field stores information that should be shared among monitors, such as the contact status by monitors and whether or not the safety confirmation has been completed (e.g., "Contacted by XX", "Not yet responded"). This information helps to avoid duplicate contact by multiple monitors and prevents situations where no one makes contact.

[0078] <Operation> Figure 11 is a flowchart showing an example of the operation of System 1 according to this embodiment. The operation flow shown in Figure 11 includes, for example, safety confirmation processing through AI dialogue and communication means escalation, anomaly detection processing from user responses, and report creation processing based on the content of voice dialogue.

[0079] (Safety confirmation process) First, in step S11, the user terminal 10 executes the AI ​​dialogue function at a predetermined timing and presents the user with a notification of a first request to initiate a voice dialogue with the AI. Specifically, the safety confirmation control unit 134 of the user terminal 10 starts the AI ​​application at a predetermined timing (for example, every day at 8:00 a.m.). The safety confirmation control unit 134 then instructs the presentation control unit 133 to present the first request to the user via screen display and voice output on the user terminal 10. For example, the safety confirmation control unit 134 presents "Good morning. Let's have a conversation!" as the first request. At this time, the safety confirmation control unit 134 may, for example, send information regarding the user's response (for example, dialogue date and time, dialogue content, dialogue duration, whether or not there was a response, etc.) to the server 20 via the transmission / reception unit 132, and the server 20 may store this information in the dialogue log table 2023.

[0080] Next, in step S12, the user terminal 10 determines whether or not there has been a response to the first request. Specifically, the safety confirmation control unit 134 of the user terminal 10 determines whether or not there has been a response based on the response input from the operation reception unit 131 within a predetermined waiting time. For example, the safety confirmation control unit 134 determines whether or not the user has made a voice input or pressed the "Respond" button on the screen.

[0081] Next, if it is determined in step S13 that there is no response (in the case of No in step S13), in step S14, the user terminal 10 sends a notification that there is no response and a second request to contact the server 20 using a different means of communication. Specifically, the safety confirmation control unit 134 of the user terminal 10, for example, if it determines that there is no response for a predetermined time, sends a notification that there is no response to the server 20 via the transmitting / receiving unit 132. The safety confirmation control unit 134 of the user terminal 10 also sends a second request to the server 20 via the transmitting / receiving unit 132, for example, in parallel, to contact the user using a different means of communication. For example, as a notification that there is no response, the safety confirmation control unit 134 sends the user's "User ID" and status information indicating "No response" to the server 20. Also, for example, as a second request, the safety confirmation control unit 134 sends an escalation instruction to the server 20 stating "Execute contact using the next highest priority means of communication."

[0082] Next, in step S21, the server 20 performs communication (escalation processing) using a different means of communication. Specifically, the service processing unit 2034 of the server 20 refers to the escalation rule table 2022 based on the second request received by the receiving control unit 2031 from the user terminal 10. The service processing unit 2034 then, for example, performs communication with the user using another first means of communication via the transmission control unit 2032. The first means of communication is, for example, a communication method using the user terminal 10, such as a telephone call to the user terminal 10 via IP communication or a telephone call to the user terminal 10 via a mobile phone network. For example, the service processing unit 2034 refers to the escalation rule table 2022 and automatically makes a telephone call to the user terminal 10 via IP communication or a telephone call to the user terminal 10 via a mobile phone network that is registered with the user terminal 10. The telephone conversation is performed, for example, by an AI stored in the server 20.

[0083] Next, in step S31, the monitoring terminal 40 shares its status. Specifically, the monitoring terminal 40 receives notification from the server 20 that it has attempted to contact the monitored person using a different means of communication. This allows the monitor who possesses the monitoring terminal 40 to understand the current communication status with the monitored person. If there are multiple monitors, the server 20 may send notifications to each monitoring terminal 40. At this time, the server 20 may store information regarding the user's response (e.g., date and time of the conversation, content of the conversation, duration of the conversation, whether or not a response was given, etc.) in the conversation log table 2023. The server 20 may also store the current status in the status management table 2024.

[0084] Meanwhile, in parallel with step S31, in step S22, the server 20 determines whether or not there was a response to the communication by the first communication means. Specifically, the service processing unit 2034 of the server 20 makes a determination based, for example, on whether or not there was a response within a predetermined waiting time. For example, the service processing unit 2034 determines whether or not the user performed a response operation, such as picking up the receiver, within the waiting time of 3 minutes.

[0085] Next, if it is determined that there is no response in step S23 (the result of step S23 is No), the process returns to step S21. That is, the server 20 performs communication using a different means of communication (escalation processing). Specifically, the service processing unit 2034 refers to the escalation rule table 2022, for example, and performs communication with the user using another second means of communication via the transmission control unit 2032. The second means of communication is a means of communication in which the user is more likely to respond than the first means of communication. The second means of communication is a device different from the user terminal 10, for example, a telephone call via the fixed telephone network to a landline telephone owned by the user. The second means of communication may also be, for example, a voice notification device such as a smart speaker installed in the user's home, or other wearable devices capable of voice and vibration notifications. For example, the service processing unit 2034 refers to the escalation rule table 2022 and automatically makes a telephone call via the fixed telephone network to a landline telephone owned by the user. The conversation via this telephone is performed, for example, by an AI stored in the server 20.

[0086] If the means of contact in the first step S21 was a telephone call via IP communication registered on the user terminal 10, the means of contact in the second step S21 may be a telephone call via the mobile phone network to the user terminal 10, which is the first means of contact. If there is no response to any of the first means of contact (means of contact to the user terminal 10) in step S21, it is desirable to make contact using a second means of contact (a device different from the user terminal 10).

[0087] If no response is determined in step S23, the processing in steps S21-S22 will continue until a contact via a different means becomes the contact of the supervisor to whom the case will be ultimately escalated, or the contact of an external service (e.g., security company, local government, etc.).

[0088] On the other hand, if it is determined in step S23 that there is a response (if the answer to step S23 is Yes), the process proceeds to step S32. In step S32, the monitoring terminal 40 shares the status. Specifically, the monitoring terminal 40 receives notification from the server 20 that the monitored person has responded. This allows the monitor who owns the monitoring terminal 40 to know that the monitored person is safe at the moment. If there are multiple monitors, the server 20 may send a notification to each monitoring terminal 40. The server 20 may also store information about the user's response (e.g., date and time of the conversation, content of the conversation, duration of the conversation, whether or not a response was received, etc.) in the conversation log table 2023. The server 20 may also store the current status in the status management table 2024. This completes the safety confirmation process.

[0089] (Anomaly detection processing) If it is determined in step S13 that there is a response (if the answer to step S13 is Yes), then in step S15, the user terminal 10 determines whether the response to the first request meets predetermined requirements. Specifically, the safety confirmation control unit 134 of the user terminal 10 determines whether the predetermined requirements are met based, for example, on the generated dialogue log (for example, the content of the voice dialogue stored in the dialogue log table 2023). Here, meeting the predetermined requirements means that there are no concerns regarding the user (for example, the user is in good health). Whether the predetermined requirements are met is determined, for example, based on the content of the voice dialogue being at a predetermined level or predetermined words included in the voice dialogue. The predetermined level includes, for example, the response time or the amount of response. For example, if the response time is less than or equal to a predetermined time, or if the amount of response (number of characters in the dialogue) is less than or equal to a predetermined amount, it is determined that the predetermined requirements are not met. Also, predetermined words include, for example, negative words indicating poor health. For example, if the voice dialogue includes words such as "I feel unwell," "I collapsed," or "My chest hurts," it is determined that the predetermined requirements are not met.

[0090] Next, if it is determined in step S15 that the predetermined requirements are not met (in the case of No in step S15), in step S16, the user terminal 10 sends a third request to the server 20 to contact the monitor. Specifically, the safety confirmation control unit 134 of the user terminal 10 extracts information that serves as the basis for anomaly detection (e.g., dialogue logs) if it determines that the predetermined requirements are not met. The safety confirmation control unit 134 then sends the extracted information (anomaly detection information) and the third request to contact the monitor to the server 20 via the transmission / reception unit 132. For example, the safety confirmation control unit 134 sends the dialogue log "My chest has been a little sore since last night" to the server as anomaly detection information along with the third request.

[0091] Next, in step S24, the server 20 contacts the monitor. Specifically, when the server 20's service processing unit 2034 receives a third request sent from the user terminal 10 by the receiving control unit 2031, for example, it sends a notification of an anomaly detection to a pre-registered monitor via the transmission control unit 2032. The service processing unit 2034 then refers to the user information table 2021, for example, and sends a notification to the registered monitor's contact information. For example, the service processing unit 2034 sends a notification to the monitor terminal 40 stating, "Mr. / Ms. XX has made a statement indicating signs of poor health." The contact with the monitor terminal 40 may be made by, for example, an AI application or a communication tool linked via API.

[0092] Next, in step S33, the monitoring terminal 40 receives communication from the server 20 and shares its status. Specifically, the monitoring terminal 40 receives notification of an anomaly detection from the server 20. The monitoring terminal 40 may, for example, present the anomaly detection of the monitored person to the monitor and accept a request from the monitor to contact the monitored person. The monitoring terminal 40 may, for example, connect interactively with the user terminal 10 by linking with a predetermined communication tool via API in response to a contact request (e.g., pressing the "Contact Monitored Person" button). In this case, if there are multiple monitors, the status (contact history) of communication between any monitor and the monitored person is shared with each monitoring terminal 40. This prevents duplicate and uncontacted communications to the monitored person by multiple monitors. With this, the anomaly detection process is completed.

[0093] Furthermore, the acceptance of contact requests from the monitor to the monitored person by the monitor terminal 40 may be performed in status sharing steps other than step S33. For example, the monitor terminal 40 may present the detected anomaly of the monitored person to the monitor and accept contact requests from the monitor to the monitored person in the status sharing steps in steps S31 and S32. Alternatively, the monitor terminal 40 may present the detected anomaly of the monitored person to the monitor and accept contact requests from the monitor to the monitored person in the report presentation step in step S34, which will be described later.

[0094] (Report creation process) If it is determined in step S15 that the predetermined requirements are met (if the answer to step S15 is Yes), then in step S17, the user terminal 10 sends a fourth request to the server 20 to create a report based on the generated dialogue log. Specifically, for example, if it is determined that the response meets the predetermined requirements (no abnormalities), the user terminal 10 extracts the generated dialogue log. Then, the safety confirmation control unit 134 sends the extracted dialogue log along with the fourth request (report creation request) to the server 20, for example, via the transmitting / receiving unit 132. For example, the safety confirmation control unit 134 sends the dialogue log "What did you eat for breakfast?" "I ate natto" along with the fourth request to the server.

[0095] Next, in step S25, the server 20 performs report creation. Specifically, the service processing unit 2034 of the server 20 generates a prompt including a dialogue log and instructions for report creation when the receiving control unit 2031 receives the fourth request. The service processing unit 2034 then sends the generated prompt to the generating AI system 30, for example, to create a report based on the content of the voice dialogue. For example, the service processing unit 2034 sends a prompt to the generating AI system 30 including a dialogue log and instructions such as, "Analyze the following dialogue log and summarize the main points concisely in three lines." The service processing unit 2034 receives the report output from the generating AI system 30 via the receiving control unit 2031, for example. The report includes, for example, "Mr. / Ms. XX ate natto for breakfast today, and no particular abnormalities were found in the content of the conversation." The service processing unit 2034 then sends the received report to the monitor terminal 40 via the transmission control unit 2032, for example.

[0096] Next, in step S34, the monitoring terminal 40 presents the report to the monitor. Specifically, the monitoring terminal 40 receives the report transmitted via the transmission control unit 2032 of the server 20 with its receiving control unit. The monitoring terminal 40 then presents the report to the monitor, for example, by displaying it on the screen or reading it aloud using synthesized speech. This completes the report creation process.

[0097] <Screen example> In System 1 of this embodiment, examples of screens displayed on the user terminal 10 and the monitor terminal 40 will be described.

[0098] Figure 12 shows an example of a user terminal screen according to an embodiment of this disclosure. Figure 12 shows a notification of a first request to start safety confirmation presented to the user terminal 10 in step S11.

[0099] As shown in Figure 12, the example screen includes, for example, the first region 1411.

[0100] The first area 1411 is an area where, for example, a message prompting the user to start a conversation to check on their well-being is displayed. Here, a concise message to start a conversation is displayed, for example, "Good morning. Let's talk!" The first area 1411 may also include, for example, a "Respond" button. The user can start a conversation with the AI ​​by, for example, pressing the "Respond" button.

[0101] Figure 13 shows an example of the first screen of a monitoring terminal according to an embodiment of this disclosure. Figure 13 shows the status display of whether or not a response was presented to the monitoring terminal 40 in step S31.

[0102] As shown in Figure 13, the first example screen includes, for example, the first region 1421.

[0103] The first area 1421 is, for example, an area where the status of whether or not a user has responded is displayed in a list. Here, the results of the safety check and the current confirmation status are displayed, for example, "No response on [Month] [Day] at [Time]" or "Checking via IP phone on [Month] [Day] at [Time]". The first area 1421 may also include, for example, an input field or button for updating the response status, which can be entered by a monitor. For example, if a monitor contacts a user using a method other than an AI app, they may enter the response status using the input field and button. The first area 1421 may also include, for example, a button to accept a contact request (for example, a "Contact Monitored Person" button). By pressing, for example, the button to accept a contact request, the monitor can interact with the user terminal 10 via API integration with a predetermined contact tool. This allows multiple monitors to share the safety check status and the response status of other monitors in real time.

[0104] Figure 14 shows an example of a second screen of a monitor terminal according to an embodiment of this disclosure. Figure 14 shows the report display presented to the monitor terminal 40 in step S34.

[0105] As shown in Figure 14, the second example screen includes, for example, a first region 1431 and a second region 1432.

[0106] Area 1431 is an area that displays, for example, the date and time of the response, the duration of the conversation, and the content of the conversation, summarizing the response results. Here, for example, a summary of the conversation content is displayed, such as, "We talked about XX. The health status is XX....." Area 1431 may also include, for example, a "Details" button to check the details of the report. Area 2432 is an area that displays, for example, a graph showing the trend of conversation time on the day of the conversation. Here, for example, the conversation time over the past few days is displayed as a graph. Area 2432 may also include, for example, details of the conversation time data. This allows monitors to visually grasp the content of the user's conversations as well as their daily conversation trends (changes in conversation time), which can help in the early detection of anomalies.

[0107] <Variation> The above embodiment shows an example of detecting anomalies based on the content of voice dialogue with the AI, but this embodiment is not limited to this. In this embodiment, for example, in addition to the content of voice dialogue, the user's anomalies may be detected based on data acquired from various sensors such as the accelerometer 108 and position sensor 107 mounted on the user terminal 10, or image data acquired from the camera 106. This makes it possible to detect physical and behavioral anomalies that cannot be captured by voice dialogue, such as falls or not being away from home for extended periods.

[0108] In the above embodiment, an example was shown where the monitored person was an elderly person living alone and the monitor was a family member, with the purpose of dialogue with the elderly person living alone. However, this embodiment is not limited to this. In this embodiment, for example, for the purpose of labor management, the monitored person may be an employee and the monitor may be a supervisor or human resources department. Alternatively, for the purpose of monitoring the health status of patients receiving home medical care, the monitored person may be a home-care patient and the monitor may be a doctor or nurse. This allows the dialogue function, anomaly detection, escalation processing, and report generation mechanism shown in this embodiment to be used with various combinations of monitored persons and monitors.

[0109] In the above embodiment, an example was shown where the timing for starting a dialogue with the AI ​​is set to a predetermined time (8:00 AM every day), but this embodiment is not limited to this. In this embodiment, the request to start a dialogue may be dynamically determined based on data acquired from the acceleration sensor 108 or position sensor 107 mounted on the user terminal 10. For example, a dialogue to check on the user's well-being may be started when an unusual behavioral pattern is detected, such as no activity for a long period of time. This allows for quick checking on the user's well-being when signs of abnormality are detected, providing a more effective monitoring system.

[0110] In the above embodiment, an example was shown in which the user terminal 10 performs some or all of the AI ​​interaction processing or anomaly detection processing, and the server 20 performs some or all of the escalation or report creation. However, this embodiment is not limited to this. In this embodiment, the user terminal 10 may perform some or all of the server 20's processing operations, or the server 20 may perform some or all of the user terminal 10's processing operations. This allows, for example, if the user terminal 10 has high processing power, the communication load with the server 20 to be reduced, and conversely, if the server 20 has high processing power, the load on the user terminal 10 to be reduced.

[0111] In the above embodiment, an example was described in which, in step S15, the user terminal 10 determines whether or not it satisfies predetermined requirements based on the AI ​​application's dialogue log, but the present invention is not limited thereto. For example, other communication means performed in step S21 of Figure 11, specifically, the service processing unit 2034 of the server 20, may acquire a dialogue log (voice data, text data) with the user via communication means such as a telephone via IP communication, a telephone via a mobile phone network, or a telephone via a fixed telephone network, and perform anomaly detection processing based on a predetermined level or predetermined word based on the dialogue log. In this case, if the server 20 determines, as a result of the anomaly detection processing, that the predetermined requirements are not met, it may send a third request to the monitor terminal 40 to contact it. This makes it possible to continuously monitor changes in the user's physical condition and situation after the first and second communication means have been executed.

[0112] In the above embodiment, an example was described in which, in step S17, the user terminal 10 sends a fourth request for report creation based on the AI ​​application's dialogue log. However, the present invention is not limited thereto. For example, other communication means performed in step S21 of Figure 11, specifically, the service processing unit 2034 of the server 20, may acquire a dialogue log (voice data, text data) with the user via communication means such as telephone via IP communication, telephone via a mobile phone network, or telephone via a fixed telephone network, and perform report creation based on the dialogue log. In this case, the server 20 generates a prompt including the dialogue log and instructions for report creation, and inputs it to the generating AI system 30 to create the report. The service processing unit 2034 receives the report output from the generating AI system 30 and transmits it to the monitor terminal 40 via the transmission control unit 2032. This makes it possible to share not only the dialogue function by the AI ​​application but also the results of safety confirmations by other communication means as reports with the monitor.

[0113] <Summary> As described above, according to this embodiment, the user terminal 10 executes an AI dialogue function at a predetermined timing and notifies the user of a first request to initiate voice dialogue with the AI. The user terminal 10 determines whether or not there has been a response to the first request. If the user terminal 10 determines that there has been no response to the first request, it sends a notification to the server stating that there has been no response and a second request to contact the user using another first means of communication. This reduces the resources required to perform safety checks on monitored individuals while improving the accuracy of safety checks.

[0114] Furthermore, according to this embodiment, the server 20 contacts the user via the first communication means in response to the second request. The server 20 determines whether or not there has been a response to the contact via the first communication means. This makes it possible to automatically attempt to contact the user using the next stage of communication means, such as an IP phone or mobile phone, even if there is no response from the AI ​​application, thereby preventing interruptions in safety confirmation.

[0115] Furthermore, according to this embodiment, if the server 20 determines that there is no response to the contact made by the first contact means, it contacts the user via another second contact means that is more likely to elicit a response from the user than the first contact means. This allows for a gradual escalation to a landline telephone or other means with a higher probability of response, thereby maximizing the likelihood that the user will notice the notification or respond, and significantly improving the success rate of safety confirmation.

[0116] Furthermore, according to this embodiment, the second communication means is a communication means that uses a device different from the user terminal 10. This makes it possible to attempt to contact the user in a terminal-independent manner, such as when the user does not have a smartphone or when the power is off, thereby improving the comprehensiveness of safety confirmation.

[0117] Furthermore, according to this embodiment, the first means of communication is a telephone call to the user terminal 10 via IP communication, or a telephone call to the user terminal 10 via the mobile phone network, and the second means of communication is a telephone call to the user's landline phone via the landline telephone network. This clarifies the means of communication based on the specific communication protocol and the device used, and makes it possible to set the escalation stages in the order of an application on the terminal, the mobile phone network, and the landline telephone network.

[0118] Furthermore, according to this embodiment, the user terminal 10 determines whether the response to the first request meets predetermined requirements. If the response to the first request does not meet the predetermined requirements, the user terminal 10 sends a third request to the server to contact a pre-registered monitor. This makes it possible to judge not only whether or not there is a response, but also the quality of the dialogue content (for example, signs of abnormality), detect potential health problems or other risks, and promptly notify the monitor.

[0119] Furthermore, according to this embodiment, whether or not a predetermined requirement is met is determined based on a predetermined level of the content of the voice dialogue. This makes it possible to detect signs of cognitive decline and sudden changes in physical condition from nonverbal information such as the continuity or volume of the user's conversation or delays in responses.

[0120] Furthermore, according to this embodiment, whether or not predetermined requirements are met is determined based on predetermined words included in the content of the voice dialogue. This makes it possible to detect direct words indicating urgency or danger, such as "I feel unwell" or "I collapsed," uttered by the user, and immediately connect to a supervisor (third request).

[0121] Furthermore, according to this embodiment, when a monitor contacts a user, the server 20 shares that information with other monitors. This makes it possible to avoid duplication of response status among multiple monitors, or to strengthen coordination to prevent omissions in safety confirmation due to no one contacting the user.

[0122] Furthermore, according to this embodiment, the user terminal 10 sends a fourth request to the server 20 to create a report based on the content of the voice dialogue. The server 20 inputs the content of the voice dialogue and a prompt containing instructions for creating a report into the generating AI and creates a report based on the content of the voice dialogue. This eliminates the need for the monitor to manually review and summarize a vast amount of dialogue logs, enabling them to efficiently understand the user's situation.

[0123] Although several embodiments of this disclosure have been described above, these embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. For example, configurations and processes in one embodiment may be combined with configurations and processes in another embodiment, or a modification of one embodiment may be applied to another embodiment. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents.

[0124] (Note) The details described in each of the above embodiments are noted below.

[0125] (Note 1) A program for execution in a system comprising a processor and a memory unit, and including a user terminal and a server, wherein the program is executed by the processor, The user terminal performs a dialogue function with the AI ​​at a predetermined timing and notifies the user of a first request to initiate a voice dialogue with the AI, The user terminal determines whether or not a response has been received to the first request. If the user terminal determines that there has been no response to the first request, it sends a notification to the server stating that there has been no response and a second request to contact the server using another first means of communication. A program that executes the command.

[0126] (Note 2) The server, in response to the second request, contacts the user via the first communication means; The server determines whether or not it has received a response to the communication by the first communication means, The program described in (Appendix 1) that causes the aforementioned processor to execute.

[0127] (Note 3) If the server determines that there has been no response to the communication via the first communication means, it may take the step of contacting the user via a second communication means that is more likely to elicit a response from the user than the first communication means. The program described in (Appendix 2) to be executed by the aforementioned processor.

[0128] (Note 4) The second communication means is a communication means that uses a device different from the user terminal. The program described in (Appendix 3).

[0129] (Note 5) The first means of communication is a telephone call to the user terminal via IP communication, or a telephone call to the user terminal via a mobile phone network. The second means of communication is a telephone call to the user's landline phone via the landline network. The program described in (Appendix 3).

[0130] (Note 6) The user terminal determines whether the response to the first request satisfies predetermined requirements, If the user terminal does not satisfy the predetermined requirements in response to the first request, it sends a third request to the server stating that it will contact a pre-registered monitor. A program described in any of (Appendix 1) to (Appendix 5) that causes the processor to execute the above.

[0131] (Note 7) Whether or not the aforementioned predetermined requirements are met is determined based on the content of the voice dialogue according to a predetermined standard. The program described in (Appendix 6).

[0132] (Note 8) Whether or not the aforementioned predetermined requirements are met is determined based on predetermined words included in the content of the voice dialogue. The program described in (Appendix 6).

[0133] (Note 9) The server, when the monitor contacts the user, takes the step of sharing information that contact was made with other monitors. The program described in (Appendix 6) to be executed by the aforementioned processor.

[0134] (Note 10) The user terminal sends a fourth request to the server to create a report based on the content of the voice dialogue. The server inputs the content of the voice dialogue and prompts containing instructions for creating a report to the generating AI, and creates a report based on the content of the voice dialogue. The program described in (Appendix 1) that causes the aforementioned processor to execute.

[0135] (Note 11) A method performed on a system comprising a processor, wherein the processor performs all steps performed in any of the inventions described in (Appendix 1) to (Appendix 10).

[0136] (Note 12) A system comprising means for performing all steps performed in any of the inventions described in (Appendix 1) to (Appendix 10).

[0137] (Note 13) A program for which a processor is provided and to be executed on a user terminal, wherein the program is provided on the processor, The steps include: executing an AI dialogue function to the user at a predetermined timing and notifying the user of a first request to initiate a voice dialogue with the AI; A step of determining whether or not a response has been made to the first request, If it is determined that there is no response to the first request, the system sends a notification to the external device stating that there is no response and a second request to contact the system using another first means of communication. A program that executes the command.

[0138] (Note 14) A step of determining whether the response to the first request satisfies predetermined requirements, If the response to the first request does not meet the predetermined requirements, the third request is sent to the external device to contact a pre-registered monitor. The program described in (Appendix 13) that causes the processor to execute.

[0139] (Note 15) Whether or not the aforementioned predetermined requirements are met is determined based on the content of the voice dialogue according to a predetermined standard. The program described in (Appendix 14).

[0140] (Note 16) Whether or not the aforementioned predetermined requirements are met is determined based on predetermined words included in the content of the voice dialogue. The program described in (Appendix 14).

[0141] (Note 17) The step of sending a fourth request to the external device to create a report based on the content of the voice dialogue is as follows: The program described in any of (Appendix 13) to (Appendix 16) to be executed by the aforementioned processor.

[0142] (Note 18) A method to be executed on a server comprising a processor, wherein the processor performs all steps performed in any of the inventions described in (Appendix 13) to (Appendix 17).

[0143] (Note 19) An information processing apparatus comprising a processor, wherein the processor performs all steps performed in any of the inventions described in (Appendix 13) to (Appendix 17). [Explanation of Symbols]

[0144] 1... System 10…User terminal 101... Control Unit 102...Storage section 103... Communications Department 104...Input section 105...Output section 20... Server 201... Control Unit 202...Storage section 203... Communications Department 204… Input / Output Interface 30…Generating AI system 40... Monitor terminal 80…Network

Claims

1. A program to be executed on a system comprising a processor, a user terminal and a server, wherein the program is to be executed on the processor, The user terminal performs a dialogue function with the AI ​​at a predetermined timing and notifies the user of a first request to initiate a voice dialogue with the AI, The user terminal determines whether or not a response has been received to the first request. If the user terminal determines that there has been no response to the first request, it sends a notification to the server stating that there has been no response and a second request to contact the server using another first means of communication. Make it run, The first means of communication is a telephone call via IP communication to the user terminal, or a telephone call via the mobile phone network to the user terminal. program.

2. The server, in response to the second request, contacts the user via the first communication means; The server determines whether or not it has received a response to the communication by the first communication means, The program according to claim 1, which causes the processor to execute the following.

3. If the server determines that there has been no response to the communication via the first communication means, it may take the step of contacting the user via a second communication means that is more likely to elicit a response from the user than the first communication means. The program according to claim 2, which is to be executed by the processor.

4. The second communication means is a communication means that uses a device different from the user terminal. The program according to claim 3.

5. The second communication means is a telephone call to the user's landline via the landline network. The program according to claim 3.

6. The user terminal determines whether the response to the first request satisfies predetermined requirements, If the user terminal does not satisfy the predetermined requirements in response to the first request, it sends a third request to the server indicating that it will contact a pre-registered monitor. The program according to claim 1, which causes the processor to execute the following.

7. Whether or not the aforementioned predetermined requirements are met is determined based on the content of the voice dialogue according to a predetermined standard. The program according to claim 6.

8. Whether or not the aforementioned predetermined requirements are met is determined based on predetermined words included in the content of the voice dialogue. The program according to claim 6.

9. The server, when the monitor contacts the user, takes the step of sharing information that contact was made with other monitors. The program according to claim 6, which is to be executed by the aforementioned processor.

10. The user terminal sends a fourth request to the server to create a report based on the content of the voice dialogue. The server inputs the content of the voice dialogue and prompts containing instructions for creating a report to the generating AI, and creates a report based on the content of the voice dialogue. The program according to claim 1, which causes the processor to execute the following.

11. A method performed on a system comprising a processor, wherein the processor performs all steps performed in any of the inventions according to claims 1 to 10.

12. A system comprising means for performing all steps performed in the invention according to any one of claims 1 to 10.

13. A program for which a processor is provided and to be executed on a user terminal, wherein the program is provided on the processor, The steps include: executing an AI dialogue function to the user at a predetermined timing and notifying the user of a first request to initiate a voice dialogue with the AI; A step of determining whether or not a response has been made to the first request, If it is determined that there is no response to the first request, the system sends a notification to the external device stating that there is no response and a second request to contact the system using another first means of communication. Make it run, The first means of communication is a telephone call via IP communication to the user terminal, or a telephone call via the mobile phone network to the user terminal. program.

14. A step of determining whether the response to the first request satisfies predetermined requirements, If the response to the first request does not meet the predetermined requirements, the third request is sent to the external device to contact a pre-registered monitor. The program according to claim 13, which causes the processor to execute the following.

15. Whether or not the aforementioned predetermined requirements are met is determined based on the content of the voice dialogue according to a predetermined standard. The program according to claim 14.

16. Whether or not the aforementioned predetermined requirements are met is determined based on predetermined words included in the content of the voice dialogue. The program according to claim 14.

17. The step of sending a fourth request to the external device to create a report based on the content of the voice dialogue is as follows: The program according to claim 13, which is to be executed by the processor.

18. A method to be performed on an information processing device comprising a processor, wherein the processor performs all steps performed in the invention according to any one of claims 13 to 17.

19. An information processing apparatus comprising a processor, wherein the processor performs all steps performed in the invention according to any one of claims 13 to 17.

Images