system

Abstract

The system according to this embodiment aims to streamline the operation of neighborhood associations and automate tasks such as responding to inquiries from residents, resolving community disputes, and proposing methods for managing events. [Solution] The system according to this embodiment comprises a reception unit, an inquiry handling unit, a trouble resolution unit, and an operation proposal unit. The reception unit receives inquiries from residents. The inquiry handling unit provides an automated response based on the inquiries received by the reception unit. The trouble resolution unit proposes solutions to local troubles. The operation proposal unit proposes methods for managing events.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that in the operation of the neighborhood association, it takes time and effort to respond to inquiries from residents, solve local troubles, and propose methods for operating events, and it is difficult to perform efficiently. [[ID=3​​​​​​​​The system according to this embodiment comprises a reception unit, an inquiry handling unit, a troubleshooting unit, and an operational proposal unit. The reception unit receives inquiries from residents. The inquiry handling unit provides automated responses based on inquiries received by the reception unit. The troubleshooting unit proposes solutions to local problems. The operational proposal unit proposes methods for managing events. [Effects of the Invention]

[0007] The system according to this embodiment can streamline the operation of neighborhood associations and automate tasks such as responding to inquiries from residents, resolving community disputes, and proposing methods for managing events. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0028] (Example of form 1) The neighborhood association management support system according to an embodiment of the present invention is a system that provides a wide range of support to both residents and neighborhood association management. For residents, the neighborhood association management support system provides functions that make daily life more convenient by linking with services such as electronic payment systems, delivery services, and transportation arrangements. For example, if a resident wants to go shopping, the neighborhood association management support system can arrange a taxi or use a delivery service through the app. It also provides a monitoring function for the elderly, ensuring their safety by using the location information of their smartphone. For neighborhood association management, it provides functions that reduce the workload of management, such as automating inquiries from residents, suggesting solutions to local troubles, and suggesting methods for running events. For example, in response to a resident's question, "How do I prepare for the Bon Odori festival?", the neighborhood association management support system's AI will guide them through the application process to the city hall and how to apply electronically. In addition, for noise problems, it automatically generates a notice circulating that does not identify individuals. Furthermore, the AI ​​also supports tasks such as creating meeting minutes, revising regulations, and suggesting and checking distributed materials. This will address issues such as the aging and entrenched nature of board members and a shortage of volunteers, thereby streamlining the operation of neighborhood associations. A portion of the neighborhood association's operating expenses will be collected as a user fee, securing operating funds in the form of the number of households multiplied by the user fee. This service targets approximately 300,000 neighborhood associations nationwide and will solve issues such as a shortage of volunteers to run neighborhood associations, the aging of board members, a decrease in new members, and excessive workload due to analog operations. By using generation AI, it will provide a wide range of support, including automatic generation of meeting minutes, handling of foreign residents, confirmation of rules and regulations, and addressing residents' concerns. In this way, the neighborhood association operation support system will make residents' lives more convenient and realize the efficiency of neighborhood association operations.

[0029] The community association management support system according to this embodiment comprises a reception unit, an inquiry handling unit, a troubleshooting unit, and an operation proposal unit. The reception unit receives inquiries from residents. Inquiries from residents include, but are not limited to, telephone, email, and online forms. The reception unit can, for example, receive inquiries by telephone. The reception unit can also receive inquiries by email. The reception unit can also receive inquiries through online forms. For example, when receiving telephone inquiries, the reception unit automatically records the content using speech recognition technology. Email inquiries can be received through a dedicated email address. Online forms are provided through a website or application. The inquiry handling unit uses generative AI to provide automated responses based on inquiries received by the reception unit. Automated responses are based on, for example, preset answers or answers generated by generative AI, but are not limited to these. For example, the inquiry handling unit uses preset answers to provide automated responses to frequently asked questions. The inquiry handling unit can also use generative AI to generate customized answers to individual inquiries. Furthermore, the inquiry response department can use a generation AI to provide the most appropriate answer to each inquiry. For example, the inquiry response department can input the prompt "Generate the best answer to this inquiry" to the generation AI, and the generation AI will generate the answer. The trouble resolution department proposes solutions to local troubles. Local troubles include, but are not limited to, noise problems, illegal dumping of garbage, and traffic congestion. For example, the trouble resolution department can automatically generate a notice to warn against noise problems in a way that does not identify individuals. The trouble resolution department can also propose the installation of surveillance cameras to address illegal dumping of garbage. The trouble resolution department can also propose traffic regulations to address traffic congestion. For example, when the trouble resolution department automatically generates a notice to warn against noise problems, it uses a generation AI to generate the content. For illegal dumping of garbage, it proposes locations for installing surveillance cameras. For traffic congestion, it proposes specific methods for traffic regulation.The operations proposal department uses generative AI to propose methods for managing events. These methods include, but are not limited to, event scheduling, participant management, and budget management. For example, the operations proposal department can propose an event schedule. It can also propose methods for managing participants. It can also propose methods for managing the budget. For example, the operations proposal department uses generative AI to optimize the event schedule. For participant management, it uses generative AI to propose an efficient management method. For budget management, it uses generative AI to propose an optimal budget allocation. As a result, the community association management support system according to this embodiment can efficiently handle inquiries from residents, resolve community disputes, and propose methods for managing events.

[0030] The reception department receives inquiries from residents. These inquiries include, but are not limited to, telephone, email, and online forms. For example, when receiving telephone inquiries, the reception department uses speech recognition technology to automatically record the content. Speech recognition technology converts the inquiry content into text data and stores it in a database, making subsequent processing easier. Email inquiries can be received through a dedicated email address, and received emails are automatically categorized and routed to the appropriate person in charge. Online forms are provided through websites and applications, allowing residents to easily enter and submit their inquiries. Online forms have fields for detailed inquiry information, ensuring that all necessary information is collected without omission. Furthermore, the reception department monitors the status of inquiries in real time and can respond quickly by allocating additional resources when inquiries are concentrated. For example, during peak times, an automated response system is used for initial responses, and if more detailed assistance is needed, it is handed over to the appropriate person in charge. The reception department can also analyze the content of inquiries to understand common questions and trouble trends, allowing them to take preventative measures in advance. This will enable the reception department to respond quickly and accurately to a variety of inquiries from residents, thereby improving the efficiency of community association operations.

[0031] The inquiry handling department uses generative AI to automatically respond to inquiries received by the reception department. These automated responses are based on, for example, preset answers or answers generated by the generative AI, but are not limited to these examples. The generative AI utilizes natural language processing technology to understand the inquiry and generate an appropriate response. For example, the inquiry handling department uses preset answers to automatically respond to frequently asked questions, enabling quick responses to common inquiries. The inquiry handling department can also use the generative AI to generate customized answers to individual inquiries. The generative AI refers to past inquiry data and related information to provide the optimal response. For example, the inquiry handling department can input a prompt to the generative AI such as, "Generate the best answer for this inquiry," and the generative AI will generate the response. The generative AI analyzes the inquiry, searches for relevant information, and generates an appropriate response. Furthermore, the inquiry handling department can continuously evaluate and improve the accuracy of the responses generated by the generative AI. For example, it can collect user feedback and use it as training data for the generative AI to improve the accuracy of the responses. Furthermore, the inquiry handling department can handle multiple languages ​​and respond quickly to inquiries in foreign languages. This allows the inquiry handling department to respond quickly and accurately to a wide range of inquiries from residents, thereby improving the efficiency of community association operations.

[0032] The Trouble Resolution Department proposes solutions to community problems. These problems include, but are not limited to, noise pollution, illegal dumping of waste, and traffic congestion. For example, regarding noise pollution, the Trouble Resolution Department automatically generates anonymous notices to raise awareness. Using AI, it appropriately generates the content of these notices and distributes them to residents to facilitate early problem resolution. The Trouble Resolution Department can also propose the installation of surveillance cameras to address illegal dumping. It provides specific suggestions regarding camera placement and installation methods to implement effective countermeasures. Furthermore, the Trouble Resolution Department can propose traffic regulations to address traffic congestion. For example, it proposes specific traffic regulation methods such as introducing one-way streets during certain times or establishing no-parking zones. The Trouble Resolution Department optimizes solutions to community problems using AI. For example, regarding noise pollution, the AI ​​analyzes past data to propose the most effective method of raising awareness. Regarding illegal dumping, it optimizes the placement of surveillance cameras to build an effective monitoring system. To address traffic congestion, specific methods of traffic regulation will be proposed to alleviate congestion. This will enable the Trouble Resolution Department to make concrete proposals for resolving local disputes and improve the living environment for residents.

[0033] The Operations Proposal Department uses generative AI to propose methods for managing events. These methods include, but are not limited to, event scheduling, participant management, and budget management. For example, the Operations Proposal Department can propose an event schedule. Based on past event data and participant feedback, the generative AI generates an optimal schedule. For instance, it optimizes the event's start and end times, and the placement of each program to improve participant satisfaction. The Operations Proposal Department can also propose methods for managing participants. The generative AI analyzes participant registration information and past participation history to propose efficient management methods. For example, it optimizes participant check-in methods and participant list management to improve operational efficiency. Furthermore, the Operations Proposal Department can propose methods for managing the budget. The generative AI analyzes past budget data and expenditure history to propose optimal budget allocation. For example, it proposes budget allocation for each program and methods for cost reduction to ensure efficient budget management. The Operations Proposal Department uses generative AI to optimize event management methods. For example, when optimizing an event schedule, the generative AI analyzes past data to propose the most effective schedule. Regarding participant management, the generating AI proposes efficient management methods to streamline operations. Regarding budget management, the generating AI proposes optimal budget allocation to ensure efficient budget utilization. This allows the operations proposal department to optimize event management methods and efficiently support the management of community association events.

[0034] The Liaison Department will collaborate with services for residents. These services include, but are not limited to, public services, medical services, and educational services. For example, the Liaison Department can collaborate with public services to enable residents to complete necessary procedures online. It can also collaborate with medical services to allow residents to make online appointments with medical institutions. Furthermore, it can collaborate with educational services to allow residents to access information about educational institutions online. For instance, the Liaison Department could collaborate with public services to allow residents to apply for resident registration online. It could collaborate with medical services to allow residents to make online appointments. It could collaborate with educational services to allow residents to access information about schools online. This collaboration with services for residents will improve convenience for residents.

[0035] The monitoring unit provides monitoring functions for the elderly. These monitoring functions include, but are not limited to, regular contact, location tracking, and health monitoring. For example, the monitoring unit can contact the elderly regularly to check on their well-being. It can also track the elderly's location using smartphone location information. Furthermore, the monitoring unit can monitor their health and notify if any abnormalities are detected. For example, the monitoring unit can call the elderly regularly to check on their well-being. It can track the elderly's location in real time using smartphone location information. To monitor their health, it can use wearable devices to measure heart rate and blood pressure and notify if any abnormalities are detected. This ensures the safety of the elderly.

[0036] The inquiry response department uses a generative AI to automatically respond to inquiries from residents. For example, the inquiry response department uses the generative AI to generate the optimal answer to a resident's inquiry. For instance, the inquiry response department inputs the prompt "Generate the optimal answer to this inquiry" to the generative AI, and the generative AI generates the answer. The inquiry response department can also use the generative AI to provide customized answers tailored to the content of the inquiry. For example, the inquiry response department inputs the prompt "Generate an answer for this specific situation" to the generative AI, and the generative AI generates a customized answer. Furthermore, the inquiry response department can use the generative AI to adjust the level of detail in the answer based on the content of the inquiry. For example, the inquiry response department inputs the prompt "Generate a detailed answer to this inquiry" to the generative AI, and the generative AI generates a detailed answer. As a result, the accuracy of inquiry response is improved by using the generative AI.

[0037] The Operations Proposal Department uses generative AI to propose methods for managing events. For example, the Operations Proposal Department can use generative AI to optimize event schedules. For instance, the Operations Proposal Department inputs the prompt "Please propose the optimal schedule for this event" into the generative AI, and the AI ​​generates a schedule. The Operations Proposal Department can also use generative AI to propose methods for managing participants. For example, the Operations Proposal Department inputs the prompt "Please propose a method for managing participants for this event" into the generative AI, and the AI ​​generates a management method. Furthermore, the Operations Proposal Department can also use generative AI to propose methods for managing budgets. For example, the Operations Proposal Department inputs the prompt "Please propose a method for managing the budget for this event" into the generative AI, and the AI ​​generates a management method. In this way, using generative AI allows for efficient proposals regarding event management methods.

[0038] The Trouble Resolution Department proposes solutions to local problems. For example, regarding noise problems, the Trouble Resolution Department can automatically generate anonymous notices to raise awareness. For example, the Trouble Resolution Department uses a generation AI to generate notices to raise awareness about noise problems. The Trouble Resolution Department can also propose the installation of surveillance cameras to prevent illegal dumping of garbage. For example, the Trouble Resolution Department uses a generation AI to suggest locations for surveillance cameras to prevent illegal dumping of garbage. The Trouble Resolution Department can also propose traffic regulations to address traffic congestion. For example, the Trouble Resolution Department uses a generation AI to suggest specific methods for traffic regulations to address traffic congestion. This allows for the efficient proposal of solutions to local problems.

[0039] The reception desk can analyze a resident's past inquiry history and select the most suitable method of contact. For example, the reception desk can automatically display as suggestions the type of inquiry the resident has frequently made in the past. For example, the reception desk can use AI to analyze past inquiry history and identify frequently asked questions. The reception desk can also prioritize suggesting inquiry methods (phone, email, etc.) that the resident has used in the past. For example, the reception desk can use AI to analyze past inquiry methods and suggest the most suitable method. Furthermore, the reception desk can suggest the most suitable method for specific time periods based on the resident's past inquiry history. For example, the reception desk can use AI to analyze past inquiry history and suggest the most suitable method for specific time periods. In this way, the reception desk can select the most suitable method of contact by analyzing the resident's past inquiry history.

[0040] The reception desk can filter inquiries based on the resident's current situation and areas of interest. For example, when a resident enters their current situation, the reception desk can prioritize displaying relevant inquiries. For instance, the reception desk can use AI to analyze the resident's current situation and identify relevant inquiries. The reception desk can also filter relevant inquiries based on the resident's areas of interest. For example, the reception desk can use AI to analyze the resident's areas of interest and identify relevant inquiries. Furthermore, the reception desk can suggest appropriate inquiries based on the resident's current situation (e.g., emergency). For example, the reception desk can use AI to analyze the resident's current situation and suggest appropriate inquiries. This allows for the suggestion of more appropriate inquiries by filtering based on the resident's current situation and areas of interest.

[0041] The reception desk can prioritize inquiries based on the resident's geographical location when receiving inquiries. For example, if a resident is in a specific area, the reception desk will prioritize inquiries related to that area. For example, the reception desk can use AI to analyze the resident's geographical location and identify relevant inquiries. The reception desk can also suggest the most appropriate inquiry based on the resident's geographical location. For example, the reception desk can use AI to analyze the resident's geographical location and suggest the most appropriate inquiry. Furthermore, if a resident is on the move, the reception desk can prioritize inquiries based on their current location. For example, the reception desk can use AI to analyze the resident's current location and identify relevant inquiries. This allows for more appropriate responses by prioritizing inquiries based on the resident's geographical location.

[0042] The reception desk can analyze residents' social media activity when receiving inquiries and accept relevant inquiries. For example, the reception desk can analyze residents' social media posts and suggest relevant inquiries. For example, the reception desk can use AI to analyze residents' social media posts and identify relevant inquiries. The reception desk can also filter inquiries based on residents' areas of interest from their social media activity. For example, the reception desk can use AI to analyze residents' areas of interest and identify relevant inquiries. Furthermore, the reception desk can suggest the most appropriate way to make an inquiry based on residents' social media activity. For example, the reception desk can use AI to analyze residents' social media activity and suggest the most appropriate way to make an inquiry. In this way, by analyzing residents' social media activity, it is possible to suggest relevant inquiries.

[0043] The inquiry response unit can adjust the level of detail in its response based on the importance of the inquiry. For example, it can provide a detailed response to high-priority inquiries. For instance, it can use AI to analyze the importance of the inquiry and generate a detailed response. It can also provide a concise response to low-priority inquiries. For example, it can use AI to analyze the importance of the inquiry and generate a concise response. Furthermore, the inquiry response unit can adjust the level of detail in its response in stages according to the importance of the inquiry. For example, it can use AI to analyze the importance of the inquiry and adjust the level of detail in its response. This allows for more appropriate responses by adjusting the level of detail based on the importance of the inquiry.

[0044] The inquiry handling unit can apply different response algorithms depending on the category of the inquiry. For example, the inquiry handling unit can apply a specialized response algorithm to technical inquiries. For instance, the inquiry handling unit can use AI to analyze the content of technical inquiries and then apply a specialized response algorithm. The inquiry handling unit can also apply a simplified response algorithm to general inquiries. For example, the inquiry handling unit can use AI to analyze the content of general inquiries and then apply a simplified response algorithm. Furthermore, the inquiry handling unit can apply a rapid response algorithm to urgent inquiries. For example, the inquiry handling unit can use AI to analyze the content of urgent inquiries and then apply a rapid response algorithm. By applying different response algorithms depending on the category of the inquiry, more appropriate responses become possible.

[0045] The inquiry response department can determine the priority of responses based on when an inquiry is submitted. For example, the inquiry response department will respond immediately to urgent inquiries. For example, the inquiry response department can use AI to analyze when an inquiry is submitted, determine its urgency, and respond immediately. The inquiry response department can also respond to regular inquiries with normal priority. For example, the inquiry response department can use AI to analyze when an inquiry is submitted and respond with normal priority. Furthermore, the inquiry response department can adjust the priority of responses in stages according to when an inquiry is submitted. For example, the inquiry response department can use AI to analyze when an inquiry is submitted and adjust the priority of responses. This allows for more appropriate responses by determining the priority of responses based on when an inquiry is submitted.

[0046] The inquiry response department can adjust the order of responses based on the relevance of the inquiries. For example, the inquiry response department will prioritize responses to highly relevant inquiries. For instance, the inquiry response department can use AI to analyze the relevance of inquiries, identify highly relevant inquiries, and prioritize responses to them. The inquiry response department can also postpone responses to less relevant inquiries. For example, the inquiry response department can use AI to analyze the relevance of inquiries, identify less relevant inquiries, and postpone responses to them. Furthermore, the inquiry response department can adjust the order of responses in stages according to the relevance of the inquiries. For example, the inquiry response department can use AI to analyze the relevance of inquiries and adjust the order of responses. By adjusting the order of responses based on the relevance of the inquiries, more appropriate responses become possible.

[0047] The troubleshooting unit can adjust the level of detail in its solutions based on the type of problem. For example, for serious problems, the troubleshooting unit provides detailed solutions. For instance, it uses AI to analyze the type of problem and generate detailed solutions. The troubleshooting unit can also provide concise solutions for minor problems. For example, it uses AI to analyze the type of problem and generate concise solutions. Furthermore, the troubleshooting unit can adjust the level of detail in its solutions in stages depending on the type of problem. For example, it uses AI to analyze the type of problem and adjust the level of detail in its solutions. This allows the system to propose more appropriate solutions by adjusting the level of detail in its solutions based on the type of problem.

[0048] The troubleshooting unit can apply different troubleshooting algorithms depending on the frequency of the problem. For example, for frequently occurring problems, the troubleshooting unit can apply a rapid troubleshooting algorithm. For instance, the troubleshooting unit can use AI to analyze the frequency of the problem and then apply the rapid troubleshooting algorithm. The troubleshooting unit can also apply a detailed troubleshooting algorithm for rarely occurring problems. For example, the troubleshooting unit can use AI to analyze the frequency of the problem and then apply the detailed troubleshooting algorithm. Furthermore, the troubleshooting unit can adjust the troubleshooting algorithm in stages depending on the frequency of the problem. For example, the troubleshooting unit can use AI to analyze the frequency of the problem and then adjust the troubleshooting algorithm. This allows for more effective troubleshooting by applying the optimal troubleshooting algorithm according to the frequency of the problem.

[0049] The troubleshooting unit can customize solutions based on the location where the problem occurred. For example, for a problem occurring in a specific area, the troubleshooting unit can provide a solution appropriate for that area. For instance, the troubleshooting unit can use AI to analyze the location of the problem and generate a solution appropriate for that area. The troubleshooting unit can also propose the optimal solution based on the location of the problem. For example, the troubleshooting unit can use AI to analyze the location of the problem and propose the optimal solution. Furthermore, the troubleshooting unit can adjust the solution step by step depending on the location of the problem. For example, the troubleshooting unit can use AI to analyze the location of the problem and adjust the solution. By customizing the solution based on the location of the problem, a more appropriate solution becomes possible.

[0050] The troubleshooting unit can improve the accuracy of its solutions by referring to relevant literature on the problem. For example, the troubleshooting unit can propose the optimal solution based on relevant literature on the problem. For example, the troubleshooting unit can use AI to analyze relevant literature and generate the optimal solution. The troubleshooting unit can also improve the accuracy of its solutions by referring to relevant literature on the problem. For example, the troubleshooting unit can use AI to analyze relevant literature and improve the accuracy of its solutions. The troubleshooting unit can also analyze relevant literature on the problem and propose the most effective solution. For example, the troubleshooting unit can use AI to analyze relevant literature and generate the most effective solution. In this way, the accuracy of the solutions is improved by referring to relevant literature on the problem.

[0051] The operational proposal department can adjust the level of detail in the operational methods based on the type of event. For example, the operational proposal department provides detailed operational methods for important events. For instance, the operational proposal department uses AI to analyze the type of event and generate detailed operational methods. The operational proposal department can also provide concise operational methods for smaller events. For instance, the operational proposal department uses AI to analyze the type of event and generate concise operational methods. Furthermore, the operational proposal department can adjust the level of detail in the operational methods in stages depending on the type of event. For instance, the operational proposal department uses AI to analyze the type of event and adjust the level of detail in the operational methods. This allows for the proposal of more appropriate operational methods by adjusting the level of detail in the operational methods based on the type of event.

[0052] The Operations Proposal Department can optimize event management methods by referring to past successful event management examples. For example, the Operations Proposal Department proposes the optimal management method based on the management methods of past successful events. For example, the Operations Proposal Department uses AI to analyze past successful cases and generate the optimal management method. The Operations Proposal Department can also improve event management methods by referring to past successful cases. For example, the Operations Proposal Department uses AI to analyze past successful cases and improve management methods. The Operations Proposal Department can also analyze past successful cases and propose the most effective management method. For example, the Operations Proposal Department uses AI to analyze past successful cases and generate the most effective management method. This improves the accuracy of management methods by referring to past successful event management examples.

[0053] The Operations Proposal Department can customize operational methods based on the event venue. For example, for events held in a specific location, the Operations Proposal Department can provide operational methods suitable for that location. For instance, the Operations Proposal Department can use AI to analyze the event venue and generate operational methods appropriate for that location. The Operations Proposal Department can also propose the optimal operational method based on the event venue. For example, the Operations Proposal Department can use AI to analyze the event venue and propose the optimal operational method. Furthermore, the Operations Proposal Department can adjust the operational method in stages according to the event venue. For example, the Operations Proposal Department can use AI to analyze the event venue and adjust the operational method. This allows for more appropriate operation by customizing the operational method based on the event venue.

[0054] The operational proposal department can improve the accuracy of operational methods by referring to relevant literature on events. For example, the operational proposal department can propose the optimal operational method based on relevant literature on events. For example, the operational proposal department can use AI to analyze relevant literature and generate the optimal operational method. The operational proposal department can also improve the accuracy of operational methods by referring to relevant literature on events. For example, the operational proposal department can use AI to analyze relevant literature and improve the accuracy of operational methods. The operational proposal department can also analyze relevant literature on events and propose the most effective operational method. For example, the operational proposal department can use AI to analyze relevant literature and generate the most effective operational method. In this way, the accuracy of operational methods is improved by referring to relevant literature on events.

[0055] The integration unit can optimize the integration method based on the frequency of use of the services being integrated. For example, the integration unit can provide a rapid integration method for frequently used services. For instance, it can use AI to analyze the frequency of service use and generate a rapid integration method. The integration unit can also provide a standard integration method for services that are rarely used. For example, it can use AI to analyze the frequency of service use and generate a standard integration method. Furthermore, the integration unit can adjust the integration method in stages according to the frequency of service use. For example, it can use AI to analyze the frequency of service use and adjust the integration method. This allows for more efficient integration by optimizing the integration method based on the frequency of use of the services being integrated.

[0056] The integration unit can customize integration methods by considering the geographical distribution of the services being integrated. For example, for services used in a specific region, the integration unit can provide integration methods suitable for that region. For instance, the integration unit can use AI to analyze the geographical distribution of services and generate integration methods suitable for that region. The integration unit can also propose the optimal integration method based on the geographical distribution of services. For example, the integration unit can use AI to analyze the geographical distribution of services and propose the optimal integration method. Furthermore, the integration unit can adjust the integration method in stages according to the geographical distribution of services. For example, the integration unit can use AI to analyze the geographical distribution of services and adjust the integration method. This allows for more appropriate responses by customizing the integration method by considering the geographical distribution of the services being integrated.

[0057] The monitoring unit can optimize monitoring methods by referring to the elderly person's past behavioral history. For example, the monitoring unit can propose the optimal monitoring method based on actions the elderly person has frequently performed in the past. For example, the monitoring unit can use AI to analyze the elderly person's past behavioral history and generate the optimal monitoring method. The monitoring unit can also propose the optimal monitoring method for specific time periods based on the elderly person's past behavioral history. For example, the monitoring unit can use AI to analyze the elderly person's past behavioral history and generate the optimal monitoring method for specific time periods. The monitoring unit can also analyze the elderly person's past behavioral history and propose the most effective monitoring method. For example, the monitoring unit can use AI to analyze the elderly person's past behavioral history and generate the most effective monitoring method. This allows for the proposal of more appropriate monitoring methods by referring to the elderly person's past behavioral history.

[0058] The monitoring unit can customize monitoring methods by considering the geographical location information of elderly individuals. For example, if an elderly person is in a specific area, the monitoring unit can provide a monitoring method suitable for that area. For instance, the monitoring unit can use AI to analyze the elderly person's geographical location information and generate a monitoring method appropriate for that area. The monitoring unit can also propose the optimal monitoring method based on the elderly person's geographical location information. For example, the monitoring unit can use AI to analyze the elderly person's geographical location information and propose the optimal monitoring method. Furthermore, if an elderly person is on the move, the monitoring unit can customize the monitoring method based on their current location. For example, the monitoring unit can use AI to analyze the elderly person's current location and customize the monitoring method. This allows for more appropriate responses by customizing monitoring methods while considering the elderly person's geographical location information.

[0059] The monitoring unit can customize monitoring methods by considering the geographical location information of elderly individuals. For example, if an elderly person is in a specific area, the monitoring unit can provide a monitoring method suitable for that area. For instance, the monitoring unit can use AI to analyze the elderly person's geographical location information and generate a monitoring method appropriate for that area. The monitoring unit can also propose the optimal monitoring method based on the elderly person's geographical location information. For example, the monitoring unit can use AI to analyze the elderly person's geographical location information and propose the optimal monitoring method. Furthermore, if an elderly person is on the move, the monitoring unit can customize the monitoring method based on their current location. For example, the monitoring unit can use AI to analyze the elderly person's current location and customize the monitoring method. This allows for more appropriate responses by customizing monitoring methods while considering the elderly person's geographical location information.

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

[0061] The community association management support system can analyze residents' past participation history and suggest optimal events and activities. For example, it can suggest similar events based on residents' past event participation history. Specifically, it uses AI to analyze residents' past participation history, identify frequently attended events, and suggest them as future events. It can also prioritize suggesting highly-rated events based on residents' evaluations of past events. For example, it uses AI to analyze residents' past event evaluations, identify highly-rated events, and suggest them as future events. Furthermore, it can suggest events suitable for specific seasons or time slots based on residents' past participation history. For example, it uses AI to analyze residents' past participation history and suggest events best suited to specific seasons or time slots. In this way, by analyzing residents' past participation history, the system can suggest optimal events and activities.

[0062] The community association management support system can propose community-specific events and activities based on residents' geographical location information. For example, if a resident lives in a specific area, it can propose events related to that area. Specifically, it uses AI to analyze residents' geographical location information, identify relevant events, and propose them. It can also propose the most suitable events based on a resident's current location if they are on the move. For example, it uses AI to analyze a resident's current location and proposes nearby events. Furthermore, it can propose events tailored to the characteristics of a region based on residents' geographical location information. For example, it uses AI to analyze the characteristics of a region and propose events suitable for that region. In this way, by proposing community-specific events and activities based on residents' geographical location information, it can increase residents' motivation to participate.

[0063] The community association management support system can analyze residents' social media activity and suggest events and activities based on their areas of interest. For example, it can analyze residents' social media posts and suggest events related to themes they are interested in. Specifically, it uses AI to analyze residents' social media posts, identify themes of interest, and suggest events related to those themes. It can also suggest events related to specific groups or communities based on residents' social media activity. For example, it uses AI to analyze residents' social media activity, identify events related to specific groups or communities, and suggest them. Furthermore, it can suggest new events that residents might be interested in based on their social media activity. For example, it uses AI to analyze residents' social media activity, identify new events that might be interesting, and suggest them. In this way, by analyzing residents' social media activity, it is possible to suggest events and activities based on their areas of interest.

[0064] The community association management support system can analyze residents' past inquiry history and suggest the most suitable way to handle inquiries. For example, it can automatically display as suggestions the types of inquiries residents have frequently made in the past. Specifically, it uses AI to analyze past inquiry history, identify frequently asked questions, and automatically display them the next time an inquiry is made. It can also prioritize suggesting inquiry methods (phone, email, etc.) that residents have used in the past. For example, it uses AI to analyze past inquiry methods and suggest the most suitable method. Furthermore, it can suggest the most suitable method for specific time periods based on residents' past inquiry history. For example, it uses AI to analyze past inquiry history and suggest the most suitable method for specific time periods. In this way, by analyzing residents' past inquiry history, the system can suggest the most suitable way to handle inquiries.

[0065] The community association management support system can provide region-specific support for inquiries based on residents' geographical location information. For example, if a resident lives in a specific area, inquiries related to that area will be prioritized. Specifically, AI is used to analyze the resident's geographical location information, identify inquiries related to that area, and prioritize their response. Furthermore, if a resident is on the move, the system can provide the most appropriate response based on their current location. For example, AI is used to analyze the resident's current location and address problems occurring nearby. In addition, the system can provide inquiry support tailored to the characteristics of the region based on the resident's geographical location information. For example, AI is used to analyze the characteristics of the region and provide a response appropriate to that region. This allows for more appropriate responses by providing region-specific support based on residents' geographical location information.

[0066] The community association management support system can analyze residents' social media activity and respond to inquiries based on their areas of interest. For example, it can analyze residents' social media posts and prioritize inquiries related to topics of interest. Specifically, it uses AI to analyze residents' social media posts, identify topics of interest, and prioritize inquiries related to those topics. It can also prioritize inquiries related to specific groups or communities based on residents' social media activity. For example, it uses AI to analyze residents' social media activity, identify inquiries related to specific groups or communities, and prioritize them. Furthermore, it can suggest new inquiry topics that residents might be interested in based on their social media activity. For example, it uses AI to analyze residents' social media activity, identify new inquiry topics that residents might be interested in, and suggest them. In this way, analyzing residents' social media activity enables inquiry responses based on their areas of interest.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The reception desk receives inquiries from residents. These inquiries can be made via telephone, email, or online forms. For example, when receiving telephone inquiries, the reception desk uses speech recognition technology to automatically record the content. Email inquiries can be received through a dedicated email address, and online forms are provided through a website or application. Step 2: The inquiry handling department uses a generation AI to automatically respond to inquiries received by the reception department. The automated responses are based on preset answers or answers generated by the generation AI. For example, the inquiry handling department uses preset answers to automatically respond to frequently asked questions. It can also use the generation AI to generate customized answers for individual inquiries. Step 3: The Trouble Resolution Department proposes solutions to local problems. These problems include noise pollution, illegal dumping of waste, and traffic congestion. For example, the Trouble Resolution Department can automatically generate notices to raise awareness about noise pollution, propose the installation of surveillance cameras to address illegal dumping of waste, and propose specific methods for traffic control to address traffic congestion. Step 4: The Operations Proposal Department uses generative AI to propose methods for managing the event. These methods include scheduling, managing participants, and managing the budget. For example, the Operations Proposal Department uses generative AI to optimize the event schedule and propose methods for managing participants and the budget.

[0069] (Example of form 2) The neighborhood association management support system according to an embodiment of the present invention is a system that provides a wide range of support to both residents and neighborhood association management. For residents, the neighborhood association management support system provides functions that make daily life more convenient by linking with services such as electronic payment systems, delivery services, and transportation arrangements. For example, if a resident wants to go shopping, the neighborhood association management support system can arrange a taxi or use a delivery service through the app. It also provides a monitoring function for the elderly, ensuring their safety by using the location information of their smartphone. For neighborhood association management, it provides functions that reduce the workload of management, such as automating inquiries from residents, suggesting solutions to local troubles, and suggesting methods for running events. For example, in response to a resident's question, "How do I prepare for the Bon Odori festival?", the neighborhood association management support system's AI will guide them through the application process to the city hall and how to apply electronically. In addition, for noise problems, it automatically generates a notice circulating that does not identify individuals. Furthermore, the AI ​​also supports tasks such as creating meeting minutes, revising regulations, and suggesting and checking distributed materials. This will address issues such as the aging and entrenched nature of board members and a shortage of volunteers, thereby streamlining the operation of neighborhood associations. A portion of the neighborhood association's operating expenses will be collected as a user fee, securing operating funds in the form of the number of households multiplied by the user fee. This service targets approximately 300,000 neighborhood associations nationwide and will solve issues such as a shortage of volunteers to run neighborhood associations, the aging of board members, a decrease in new members, and excessive workload due to analog operations. By using generation AI, it will provide a wide range of support, including automatic generation of meeting minutes, handling of foreign residents, confirmation of rules and regulations, and addressing residents' concerns. In this way, the neighborhood association operation support system will make residents' lives more convenient and realize the efficiency of neighborhood association operations.

[0070] The community association management support system according to this embodiment comprises a reception unit, an inquiry handling unit, a troubleshooting unit, and an operation proposal unit. The reception unit receives inquiries from residents. Inquiries from residents include, but are not limited to, telephone, email, and online forms. The reception unit can, for example, receive inquiries by telephone. The reception unit can also receive inquiries by email. The reception unit can also receive inquiries through online forms. For example, when receiving telephone inquiries, the reception unit automatically records the content using speech recognition technology. Email inquiries can be received through a dedicated email address. Online forms are provided through a website or application. The inquiry handling unit uses generative AI to provide automated responses based on inquiries received by the reception unit. Automated responses are based on, for example, preset answers or answers generated by generative AI, but are not limited to these. For example, the inquiry handling unit uses preset answers to provide automated responses to frequently asked questions. The inquiry handling unit can also use generative AI to generate customized answers to individual inquiries. Furthermore, the inquiry response department can use a generation AI to provide the most appropriate answer to each inquiry. For example, the inquiry response department can input the prompt "Generate the best answer to this inquiry" to the generation AI, and the generation AI will generate the answer. The trouble resolution department proposes solutions to local troubles. Local troubles include, but are not limited to, noise problems, illegal dumping of garbage, and traffic congestion. For example, the trouble resolution department can automatically generate a notice to warn against noise problems in a way that does not identify individuals. The trouble resolution department can also propose the installation of surveillance cameras to address illegal dumping of garbage. The trouble resolution department can also propose traffic regulations to address traffic congestion. For example, when the trouble resolution department automatically generates a notice to warn against noise problems, it uses a generation AI to generate the content. For illegal dumping of garbage, it proposes locations for installing surveillance cameras. For traffic congestion, it proposes specific methods for traffic regulation.The operations proposal department uses generative AI to propose methods for managing events. These methods include, but are not limited to, event scheduling, participant management, and budget management. For example, the operations proposal department can propose an event schedule. It can also propose methods for managing participants. It can also propose methods for managing the budget. For example, the operations proposal department uses generative AI to optimize the event schedule. For participant management, it uses generative AI to propose an efficient management method. For budget management, it uses generative AI to propose an optimal budget allocation. As a result, the community association management support system according to this embodiment can efficiently handle inquiries from residents, resolve community disputes, and propose methods for managing events.

[0071] The reception department receives inquiries from residents. These inquiries include, but are not limited to, telephone, email, and online forms. For example, when receiving telephone inquiries, the reception department uses speech recognition technology to automatically record the content. Speech recognition technology converts the inquiry content into text data and stores it in a database, making subsequent processing easier. Email inquiries can be received through a dedicated email address, and received emails are automatically categorized and routed to the appropriate person in charge. Online forms are provided through websites and applications, allowing residents to easily enter and submit their inquiries. Online forms have fields for detailed inquiry information, ensuring that all necessary information is collected without omission. Furthermore, the reception department monitors the status of inquiries in real time and can respond quickly by allocating additional resources when inquiries are concentrated. For example, during peak times, an automated response system is used for initial responses, and if more detailed assistance is needed, it is handed over to the appropriate person in charge. The reception department can also analyze the content of inquiries to understand common questions and trouble trends, allowing them to take preventative measures in advance. This will enable the reception department to respond quickly and accurately to a variety of inquiries from residents, thereby improving the efficiency of community association operations.

[0072] The inquiry handling department uses generative AI to automatically respond to inquiries received by the reception department. These automated responses are based on, for example, preset answers or answers generated by the generative AI, but are not limited to these examples. The generative AI utilizes natural language processing technology to understand the inquiry and generate an appropriate response. For example, the inquiry handling department uses preset answers to automatically respond to frequently asked questions, enabling quick responses to common inquiries. The inquiry handling department can also use the generative AI to generate customized answers to individual inquiries. The generative AI refers to past inquiry data and related information to provide the optimal response. For example, the inquiry handling department can input a prompt to the generative AI such as, "Generate the best answer for this inquiry," and the generative AI will generate the response. The generative AI analyzes the inquiry, searches for relevant information, and generates an appropriate response. Furthermore, the inquiry handling department can continuously evaluate and improve the accuracy of the responses generated by the generative AI. For example, it can collect user feedback and use it as training data for the generative AI to improve the accuracy of the responses. Furthermore, the inquiry handling department can handle multiple languages ​​and respond quickly to inquiries in foreign languages. This allows the inquiry handling department to respond quickly and accurately to a wide range of inquiries from residents, thereby improving the efficiency of community association operations.

[0073] The Trouble Resolution Department proposes solutions to community problems. These problems include, but are not limited to, noise pollution, illegal dumping of waste, and traffic congestion. For example, regarding noise pollution, the Trouble Resolution Department automatically generates anonymous notices to raise awareness. Using AI, it appropriately generates the content of these notices and distributes them to residents to facilitate early problem resolution. The Trouble Resolution Department can also propose the installation of surveillance cameras to address illegal dumping. It provides specific suggestions regarding camera placement and installation methods to implement effective countermeasures. Furthermore, the Trouble Resolution Department can propose traffic regulations to address traffic congestion. For example, it proposes specific traffic regulation methods such as introducing one-way streets during certain times or establishing no-parking zones. The Trouble Resolution Department optimizes solutions to community problems using AI. For example, regarding noise pollution, the AI ​​analyzes past data to propose the most effective method of raising awareness. Regarding illegal dumping, it optimizes the placement of surveillance cameras to build an effective monitoring system. To address traffic congestion, specific methods of traffic regulation will be proposed to alleviate congestion. This will enable the Trouble Resolution Department to make concrete proposals for resolving local disputes and improve the living environment for residents.

[0074] The Operations Proposal Department uses generative AI to propose methods for managing events. These methods include, but are not limited to, event scheduling, participant management, and budget management. For example, the Operations Proposal Department can propose an event schedule. Based on past event data and participant feedback, the generative AI generates an optimal schedule. For instance, it optimizes the event's start and end times, and the placement of each program to improve participant satisfaction. The Operations Proposal Department can also propose methods for managing participants. The generative AI analyzes participant registration information and past participation history to propose efficient management methods. For example, it optimizes participant check-in methods and participant list management to improve operational efficiency. Furthermore, the Operations Proposal Department can propose methods for managing the budget. The generative AI analyzes past budget data and expenditure history to propose optimal budget allocation. For example, it proposes budget allocation for each program and methods for cost reduction to ensure efficient budget management. The Operations Proposal Department uses generative AI to optimize event management methods. For example, when optimizing an event schedule, the generative AI analyzes past data to propose the most effective schedule. Regarding participant management, the generating AI proposes efficient management methods to streamline operations. Regarding budget management, the generating AI proposes optimal budget allocation to ensure efficient budget utilization. This allows the operations proposal department to optimize event management methods and efficiently support the management of community association events.

[0075] The Liaison Department will collaborate with services for residents. These services include, but are not limited to, public services, medical services, and educational services. For example, the Liaison Department can collaborate with public services to enable residents to complete necessary procedures online. It can also collaborate with medical services to allow residents to make online appointments with medical institutions. Furthermore, it can collaborate with educational services to allow residents to access information about educational institutions online. For instance, the Liaison Department could collaborate with public services to allow residents to apply for resident registration online. It could collaborate with medical services to allow residents to make online appointments. It could collaborate with educational services to allow residents to access information about schools online. This collaboration with services for residents will improve convenience for residents.

[0076] The monitoring unit provides monitoring functions for the elderly. These monitoring functions include, but are not limited to, regular contact, location tracking, and health monitoring. For example, the monitoring unit can contact the elderly regularly to check on their well-being. It can also track the elderly's location using smartphone location information. Furthermore, the monitoring unit can monitor their health and notify if any abnormalities are detected. For example, the monitoring unit can call the elderly regularly to check on their well-being. It can track the elderly's location in real time using smartphone location information. To monitor their health, it can use wearable devices to measure heart rate and blood pressure and notify if any abnormalities are detected. This ensures the safety of the elderly.

[0077] The inquiry response department uses a generative AI to automatically respond to inquiries from residents. For example, the inquiry response department uses the generative AI to generate the optimal answer to a resident's inquiry. For instance, the inquiry response department inputs the prompt "Generate the optimal answer to this inquiry" to the generative AI, and the generative AI generates the answer. The inquiry response department can also use the generative AI to provide customized answers tailored to the content of the inquiry. For example, the inquiry response department inputs the prompt "Generate an answer for this specific situation" to the generative AI, and the generative AI generates a customized answer. Furthermore, the inquiry response department can use the generative AI to adjust the level of detail in the answer based on the content of the inquiry. For example, the inquiry response department inputs the prompt "Generate a detailed answer to this inquiry" to the generative AI, and the generative AI generates a detailed answer. As a result, the accuracy of inquiry response is improved by using the generative AI.

[0078] The Operations Proposal Department uses generative AI to propose methods for managing events. For example, the Operations Proposal Department can use generative AI to optimize event schedules. For instance, the Operations Proposal Department inputs the prompt "Please propose the optimal schedule for this event" into the generative AI, and the AI ​​generates a schedule. The Operations Proposal Department can also use generative AI to propose methods for managing participants. For example, the Operations Proposal Department inputs the prompt "Please propose a method for managing participants for this event" into the generative AI, and the AI ​​generates a management method. Furthermore, the Operations Proposal Department can also use generative AI to propose methods for managing budgets. For example, the Operations Proposal Department inputs the prompt "Please propose a method for managing the budget for this event" into the generative AI, and the AI ​​generates a management method. In this way, using generative AI allows for efficient proposals regarding event management methods.

[0079] The Trouble Resolution Department proposes solutions to local problems. For example, regarding noise problems, the Trouble Resolution Department can automatically generate anonymous notices to raise awareness. For example, the Trouble Resolution Department uses a generation AI to generate notices to raise awareness about noise problems. The Trouble Resolution Department can also propose the installation of surveillance cameras to prevent illegal dumping of garbage. For example, the Trouble Resolution Department uses a generation AI to suggest locations for surveillance cameras to prevent illegal dumping of garbage. The Trouble Resolution Department can also propose traffic regulations to address traffic congestion. For example, the Trouble Resolution Department uses a generation AI to suggest specific methods for traffic regulations to address traffic congestion. This allows for the efficient proposal of solutions to local problems.

[0080] The reception desk can estimate residents' emotions and prioritize inquiries based on those emotions. For example, if a resident is angry, the reception desk will prioritize the inquiry as an urgent matter. For instance, the reception desk might use voice analysis technology to analyze the tone of the resident's voice and detect anger. The reception desk can also raise the priority of inquiries from residents who are feeling anxious in order to respond quickly. For example, the reception desk might use text analysis technology to analyze the content of the resident's message and detect anxiety. The reception desk can also handle inquiries from residents who are relaxed with the usual priority. For example, the reception desk might use facial recognition technology to analyze the resident's facial expression and detect relaxation. This allows for more appropriate responses by prioritizing inquiries based on residents' emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] The reception desk can analyze a resident's past inquiry history and select the most suitable method of contact. For example, the reception desk can automatically display as suggestions the type of inquiry the resident has frequently made in the past. For example, the reception desk can use AI to analyze past inquiry history and identify frequently asked questions. The reception desk can also prioritize suggesting inquiry methods (phone, email, etc.) that the resident has used in the past. For example, the reception desk can use AI to analyze past inquiry methods and suggest the most suitable method. Furthermore, the reception desk can suggest the most suitable method for specific time periods based on the resident's past inquiry history. For example, the reception desk can use AI to analyze past inquiry history and suggest the most suitable method for specific time periods. In this way, the reception desk can select the most suitable method of contact by analyzing the resident's past inquiry history.

[0082] The reception desk can filter inquiries based on the resident's current situation and areas of interest. For example, when a resident enters their current situation, the reception desk can prioritize displaying relevant inquiries. For instance, the reception desk can use AI to analyze the resident's current situation and identify relevant inquiries. The reception desk can also filter relevant inquiries based on the resident's areas of interest. For example, the reception desk can use AI to analyze the resident's areas of interest and identify relevant inquiries. Furthermore, the reception desk can suggest appropriate inquiries based on the resident's current situation (e.g., emergency). For example, the reception desk can use AI to analyze the resident's current situation and suggest appropriate inquiries. This allows for the suggestion of more appropriate inquiries by filtering based on the resident's current situation and areas of interest.

[0083] The reception desk can estimate the emotions of residents and adjust the timing of reception based on the estimated emotions. For example, if a resident is feeling stressed, the reception desk can process their request quickly. For example, the reception desk can use voice analysis technology to analyze the tone of the resident's voice and detect the emotion of stress. The reception desk can also process requests at the normal timing if the resident is relaxed. For example, the reception desk can use text analysis technology to analyze the content of the resident's message and detect the emotion of relaxation. The reception desk can also process requests immediately if the resident is in a hurry. For example, the reception desk can use facial recognition technology to analyze the resident's facial expression and detect the emotion of urgency. By adjusting the timing of reception based on the resident's emotions, it is possible to respond at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The reception desk can prioritize inquiries based on the resident's geographical location when receiving inquiries. For example, if a resident is in a specific area, the reception desk will prioritize inquiries related to that area. For example, the reception desk can use AI to analyze the resident's geographical location and identify relevant inquiries. The reception desk can also suggest the most appropriate inquiry based on the resident's geographical location. For example, the reception desk can use AI to analyze the resident's geographical location and suggest the most appropriate inquiry. Furthermore, if a resident is on the move, the reception desk can prioritize inquiries based on their current location. For example, the reception desk can use AI to analyze the resident's current location and identify relevant inquiries. This allows for more appropriate responses by prioritizing inquiries based on the resident's geographical location.

[0085] The reception desk can analyze residents' social media activity when receiving inquiries and accept relevant inquiries. For example, the reception desk can analyze residents' social media posts and suggest relevant inquiries. For example, the reception desk can use AI to analyze residents' social media posts and identify relevant inquiries. The reception desk can also filter inquiries based on residents' areas of interest from their social media activity. For example, the reception desk can use AI to analyze residents' areas of interest and identify relevant inquiries. Furthermore, the reception desk can suggest the most appropriate way to make an inquiry based on residents' social media activity. For example, the reception desk can use AI to analyze residents' social media activity and suggest the most appropriate way to make an inquiry. In this way, by analyzing residents' social media activity, it is possible to suggest relevant inquiries.

[0086] The inquiry response unit can estimate the emotions of residents and adjust the expression of its response based on those emotions. For example, if a resident is angry, the inquiry response unit will use a calm and polite expression. For instance, it might use voice analysis technology to analyze the tone of the resident's voice, detect anger, and generate a calm and polite expression. Similarly, if a resident is feeling anxious, the inquiry response unit can use a reassuring expression. For example, it might use text analysis technology to analyze the content of the resident's message, detect anxiety, and generate a reassuring expression. Furthermore, if a resident is relaxed, the inquiry response unit can use a friendly expression. For example, it might use facial recognition technology to analyze the resident's facial expression, detect relaxation, and generate a friendly expression. By adjusting the expression of the response based on the resident's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0087] The inquiry response unit can adjust the level of detail in its response based on the importance of the inquiry. For example, it can provide a detailed response to high-priority inquiries. For instance, it can use AI to analyze the importance of the inquiry and generate a detailed response. It can also provide a concise response to low-priority inquiries. For example, it can use AI to analyze the importance of the inquiry and generate a concise response. Furthermore, the inquiry response unit can adjust the level of detail in its response in stages according to the importance of the inquiry. For example, it can use AI to analyze the importance of the inquiry and adjust the level of detail in its response. This allows for more appropriate responses by adjusting the level of detail based on the importance of the inquiry.

[0088] The inquiry handling unit can apply different response algorithms depending on the category of the inquiry. For example, the inquiry handling unit can apply a specialized response algorithm to technical inquiries. For instance, the inquiry handling unit can use AI to analyze the content of technical inquiries and then apply a specialized response algorithm. The inquiry handling unit can also apply a simplified response algorithm to general inquiries. For example, the inquiry handling unit can use AI to analyze the content of general inquiries and then apply a simplified response algorithm. Furthermore, the inquiry handling unit can apply a rapid response algorithm to urgent inquiries. For example, the inquiry handling unit can use AI to analyze the content of urgent inquiries and then apply a rapid response algorithm. By applying different response algorithms depending on the category of the inquiry, more appropriate responses become possible.

[0089] The inquiry response unit can estimate the resident's emotions and adjust the length of the response based on the estimated emotions. For example, if the resident is in a hurry, the inquiry response unit will provide a short, to-the-point response. For example, the inquiry response unit can use voice analysis technology to analyze the resident's tone of voice, detect the emotion of urgency, and generate a short, to-the-point response. The inquiry response unit can also provide a longer response with detailed explanations if the resident is relaxed. For example, the inquiry response unit can use text analysis technology to analyze the content of the resident's message, detect the emotion of relaxation, and generate a response with detailed explanations. The inquiry response unit can also provide a response with visually stimulating effects if the resident is excited. For example, the inquiry response unit can use facial recognition technology to analyze the resident's facial expressions, detect the emotion of excitement, and generate a response with visually stimulating effects. By adjusting the length of the response based on the resident's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0090] The inquiry response department can determine the priority of responses based on when an inquiry is submitted. For example, the inquiry response department will respond immediately to urgent inquiries. For example, the inquiry response department can use AI to analyze when an inquiry is submitted, determine its urgency, and respond immediately. The inquiry response department can also respond to regular inquiries with normal priority. For example, the inquiry response department can use AI to analyze when an inquiry is submitted and respond with normal priority. Furthermore, the inquiry response department can adjust the priority of responses in stages according to when an inquiry is submitted. For example, the inquiry response department can use AI to analyze when an inquiry is submitted and adjust the priority of responses. This allows for more appropriate responses by determining the priority of responses based on when an inquiry is submitted.

[0091] The inquiry response department can adjust the order of responses based on the relevance of the inquiries. For example, the inquiry response department will prioritize responses to highly relevant inquiries. For instance, the inquiry response department can use AI to analyze the relevance of inquiries, identify highly relevant inquiries, and prioritize responses to them. The inquiry response department can also postpone responses to less relevant inquiries. For example, the inquiry response department can use AI to analyze the relevance of inquiries, identify less relevant inquiries, and postpone responses to them. Furthermore, the inquiry response department can adjust the order of responses in stages according to the relevance of the inquiries. For example, the inquiry response department can use AI to analyze the relevance of inquiries and adjust the order of responses. By adjusting the order of responses based on the relevance of the inquiries, more appropriate responses become possible.

[0092] The trouble-solving unit can estimate the emotions of residents and adjust its proposed solutions based on those emotions. For example, if a resident is angry, the trouble-solving unit can propose a calm and polite solution. For instance, it might use voice analysis technology to analyze the tone of the resident's voice, detect anger, and generate a calm and polite solution. Furthermore, if a resident is feeling anxious, the trouble-solving unit can propose a reassuring solution. For example, it might use text analysis technology to analyze the content of the resident's message, detect anxiety, and generate a reassuring solution. Finally, if a resident is relaxed, the trouble-solving unit can propose a friendly solution. For example, it might use facial recognition technology to analyze the resident's facial expression, detect relaxation, and generate a friendly solution. This allows for the proposal of more appropriate solutions by adjusting them based on the resident's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0093] The troubleshooting unit can adjust the level of detail in its solutions based on the type of problem. For example, for serious problems, the troubleshooting unit provides detailed solutions. For instance, it uses AI to analyze the type of problem and generate detailed solutions. The troubleshooting unit can also provide concise solutions for minor problems. For example, it uses AI to analyze the type of problem and generate concise solutions. Furthermore, the troubleshooting unit can adjust the level of detail in its solutions in stages depending on the type of problem. For example, it uses AI to analyze the type of problem and adjust the level of detail in its solutions. This allows the system to propose more appropriate solutions by adjusting the level of detail in its solutions based on the type of problem.

[0094] The troubleshooting unit can apply different troubleshooting algorithms depending on the frequency of the problem. For example, for frequently occurring problems, the troubleshooting unit can apply a rapid troubleshooting algorithm. For instance, the troubleshooting unit can use AI to analyze the frequency of the problem and then apply the rapid troubleshooting algorithm. The troubleshooting unit can also apply a detailed troubleshooting algorithm for rarely occurring problems. For example, the troubleshooting unit can use AI to analyze the frequency of the problem and then apply the detailed troubleshooting algorithm. Furthermore, the troubleshooting unit can adjust the troubleshooting algorithm in stages depending on the frequency of the problem. For example, the troubleshooting unit can use AI to analyze the frequency of the problem and then adjust the troubleshooting algorithm. This allows for more effective troubleshooting by applying the optimal troubleshooting algorithm according to the frequency of the problem.

[0095] The trouble-solving unit can estimate residents' emotions and determine the priority of solutions based on those emotions. For example, if a resident is angry, the trouble-solving unit will prioritize addressing the resident's situation as a high-priority solution. For instance, it might use voice analysis technology to analyze the resident's tone of voice, detect anger, and generate a high-priority solution. The trouble-solving unit can also raise the priority of addressing a resident's anxiety for a quicker response. For example, it might use text analysis technology to analyze the resident's message content, detect anxiety, and generate a solution for a quicker response. The trouble-solving unit can also address a resident's situation with the normal priority if the resident is relaxed. For example, it might use facial recognition technology to analyze the resident's facial expression, detect relaxation, and generate a solution with the normal priority. This allows for more appropriate responses by prioritizing solutions based on residents' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0096] The troubleshooting unit can customize solutions based on the location where the problem occurred. For example, for a problem occurring in a specific area, the troubleshooting unit can provide a solution appropriate for that area. For instance, the troubleshooting unit can use AI to analyze the location of the problem and generate a solution appropriate for that area. The troubleshooting unit can also propose the optimal solution based on the location of the problem. For example, the troubleshooting unit can use AI to analyze the location of the problem and propose the optimal solution. Furthermore, the troubleshooting unit can adjust the solution step by step depending on the location of the problem. For example, the troubleshooting unit can use AI to analyze the location of the problem and adjust the solution. By customizing the solution based on the location of the problem, a more appropriate solution becomes possible.

[0097] The troubleshooting unit can improve the accuracy of its solutions by referring to relevant literature on the problem. For example, the troubleshooting unit can propose the optimal solution based on relevant literature on the problem. For example, the troubleshooting unit can use AI to analyze relevant literature and generate the optimal solution. The troubleshooting unit can also improve the accuracy of its solutions by referring to relevant literature on the problem. For example, the troubleshooting unit can use AI to analyze relevant literature and improve the accuracy of its solutions. The troubleshooting unit can also analyze relevant literature on the problem and propose the most effective solution. For example, the troubleshooting unit can use AI to analyze relevant literature and generate the most effective solution. In this way, the accuracy of the solutions is improved by referring to relevant literature on the problem.

[0098] The operational proposal department can estimate residents' emotions and adjust proposed operational methods based on those estimated emotions. For example, if residents are relaxed, the operational proposal department will propose an operational method that proceeds at a relaxed pace. For instance, it might use voice analysis technology to analyze the tone of a resident's voice, detect a relaxed emotion, and generate an operational method that proceeds at a relaxed pace. The operational proposal department can also propose an efficient operational method if residents are in a hurry. For example, it might use text analysis technology to analyze the content of a resident's message, detect an urgency, and generate an efficient operational method. Furthermore, if residents are excited, the operational proposal department can propose an operational method that incorporates visually stimulating effects. For example, it might use facial recognition technology to analyze a resident's facial expression, detect an excited emotion, and generate an operational method that incorporates visually stimulating effects. By adjusting proposed operational methods based on residents' emotions, the department can propose more appropriate operational methods. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0099] The operational proposal department can adjust the level of detail in the operational methods based on the type of event. For example, the operational proposal department provides detailed operational methods for important events. For instance, the operational proposal department uses AI to analyze the type of event and generate detailed operational methods. The operational proposal department can also provide concise operational methods for smaller events. For instance, the operational proposal department uses AI to analyze the type of event and generate concise operational methods. Furthermore, the operational proposal department can adjust the level of detail in the operational methods in stages depending on the type of event. For instance, the operational proposal department uses AI to analyze the type of event and adjust the level of detail in the operational methods. This allows for the proposal of more appropriate operational methods by adjusting the level of detail in the operational methods based on the type of event.

[0100] The Operations Proposal Department can optimize event management methods by referring to past successful event management examples. For example, the Operations Proposal Department proposes the optimal management method based on the management methods of past successful events. For example, the Operations Proposal Department uses AI to analyze past successful cases and generate the optimal management method. The Operations Proposal Department can also improve event management methods by referring to past successful cases. For example, the Operations Proposal Department uses AI to analyze past successful cases and improve management methods. The Operations Proposal Department can also analyze past successful cases and propose the most effective management method. For example, the Operations Proposal Department uses AI to analyze past successful cases and generate the most effective management method. This improves the accuracy of management methods by referring to past successful event management examples.

[0101] The operational proposal department can estimate residents' emotions and determine the priority of operational methods based on those estimated emotions. For example, if a resident is relaxed, the operational proposal department will propose operational methods in the usual priority order. For instance, it might use voice analysis technology to analyze the tone of a resident's voice, detect a relaxed emotion, and generate operational methods in the usual priority order. The operational proposal department can also quickly propose operational methods if a resident is in a hurry. For example, it might use text analysis technology to analyze the content of a resident's message, detect an urgent emotion, and quickly generate operational methods. Furthermore, if a resident is excited, the operational proposal department can propose visually stimulating operational methods. For example, it might use facial recognition technology to analyze a resident's facial expression, detect an excited emotion, and generate visually stimulating operational methods. This allows for more appropriate operations by determining the priority of operational methods based on residents' emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0102] The Operations Proposal Department can customize operational methods based on the event venue. For example, for events held in a specific location, the Operations Proposal Department can provide operational methods suitable for that location. For instance, the Operations Proposal Department can use AI to analyze the event venue and generate operational methods appropriate for that location. The Operations Proposal Department can also propose the optimal operational method based on the event venue. For example, the Operations Proposal Department can use AI to analyze the event venue and propose the optimal operational method. Furthermore, the Operations Proposal Department can adjust the operational method in stages according to the event venue. For example, the Operations Proposal Department can use AI to analyze the event venue and adjust the operational method. This allows for more appropriate operation by customizing the operational method based on the event venue.

[0103] The operational proposal department can improve the accuracy of operational methods by referring to relevant literature on events. For example, the operational proposal department can propose the optimal operational method based on relevant literature on events. For example, the operational proposal department can use AI to analyze relevant literature and generate the optimal operational method. The operational proposal department can also improve the accuracy of operational methods by referring to relevant literature on events. For example, the operational proposal department can use AI to analyze relevant literature and improve the accuracy of operational methods. The operational proposal department can also analyze relevant literature on events and propose the most effective operational method. For example, the operational proposal department can use AI to analyze relevant literature and generate the most effective operational method. In this way, the accuracy of operational methods is improved by referring to relevant literature on events.

[0104] The coordination unit can estimate residents' emotions and determine the priority of services to coordinate based on those estimated emotions. For example, if a resident is feeling stressed, the coordination unit will prioritize services to respond quickly. For instance, it might use voice analysis technology to analyze the tone of a resident's voice, detect feelings of stress, and select services for a quick response. The coordination unit can also respond with normal priority if a resident is relaxed. For example, it might use text analysis technology to analyze the content of a resident's message, detect feelings of relaxation, and select services for a normal priority. Furthermore, if a resident is in a hurry, the coordination unit can prioritize services for an immediate response. For example, it might use facial recognition technology to analyze a resident's facial expression, detect feelings of urgency, and select services for an immediate response. This allows for more appropriate responses by prioritizing services based on residents' emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The integration unit can optimize the integration method based on the frequency of use of the services being integrated. For example, the integration unit can provide a rapid integration method for frequently used services. For instance, it can use AI to analyze the frequency of service use and generate a rapid integration method. The integration unit can also provide a standard integration method for services that are rarely used. For example, it can use AI to analyze the frequency of service use and generate a standard integration method. Furthermore, the integration unit can adjust the integration method in stages according to the frequency of service use. For example, it can use AI to analyze the frequency of service use and adjust the integration method. This allows for more efficient integration by optimizing the integration method based on the frequency of use of the services being integrated.

[0106] The collaboration unit can estimate residents' emotions and select services to collaborate with based on those estimated emotions. For example, if a resident is feeling stressed, the collaboration unit can select services to respond quickly. For example, it can use voice analysis technology to analyze the tone of the resident's voice, detect the emotion of stress, and select services to respond quickly. The collaboration unit can also select normal services if the resident is relaxed. For example, it can use text analysis technology to analyze the content of the resident's message, detect the emotion of relaxation, and select normal services. The collaboration unit can also select services to respond immediately if the resident is in a hurry. For example, it can use facial recognition technology to analyze the resident's facial expression, detect the emotion of urgency, and select services to respond immediately. This allows for more appropriate responses by selecting services to collaborate with based on the resident's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The integration unit can customize integration methods by considering the geographical distribution of the services being integrated. For example, for services used in a specific region, the integration unit can provide integration methods suitable for that region. For instance, the integration unit can use AI to analyze the geographical distribution of services and generate integration methods suitable for that region. The integration unit can also propose the optimal integration method based on the geographical distribution of services. For example, the integration unit can use AI to analyze the geographical distribution of services and propose the optimal integration method. Furthermore, the integration unit can adjust the integration method in stages according to the geographical distribution of services. For example, the integration unit can use AI to analyze the geographical distribution of services and adjust the integration method. This allows for more appropriate responses by customizing the integration method by considering the geographical distribution of the services being integrated.

[0108] The monitoring unit can estimate the emotions of elderly individuals and adjust the monitoring method based on the estimated emotions. For example, if an elderly person is feeling anxious, the monitoring unit can provide a reassuring monitoring method. For instance, it can use voice analysis technology to analyze the tone of the elderly person's voice, detect feelings of anxiety, and generate a reassuring monitoring method. The monitoring unit can also provide a normal monitoring method if the elderly person is relaxed. For example, it can use text analysis technology to analyze the content of the elderly person's messages, detect feelings of relaxation, and generate a normal monitoring method. Furthermore, if an elderly person is agitated, the monitoring unit can provide a calming monitoring method. For example, it can use facial recognition technology to analyze the elderly person's facial expressions, detect feelings of agitation, and generate a calming monitoring method. This allows for more appropriate monitoring by adjusting the monitoring method based on the elderly person's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0109] The monitoring unit can optimize monitoring methods by referring to the elderly person's past behavioral history. For example, the monitoring unit can propose the optimal monitoring method based on actions the elderly person has frequently performed in the past. For example, the monitoring unit can use AI to analyze the elderly person's past behavioral history and generate the optimal monitoring method. The monitoring unit can also propose the optimal monitoring method for specific time periods based on the elderly person's past behavioral history. For example, the monitoring unit can use AI to analyze the elderly person's past behavioral history and generate the optimal monitoring method for specific time periods. The monitoring unit can also analyze the elderly person's past behavioral history and propose the most effective monitoring method. For example, the monitoring unit can use AI to analyze the elderly person's past behavioral history and generate the most effective monitoring method. This allows for the proposal of more appropriate monitoring methods by referring to the elderly person's past behavioral history.

[0110] The monitoring unit can estimate the emotions of elderly individuals and determine monitoring priorities based on those estimated emotions. For example, if an elderly person is feeling anxious, the unit will prioritize their response to ensure a quicker reaction. For instance, it might use voice analysis technology to analyze the tone of the elderly person's voice, detect feelings of anxiety, and generate a monitoring method for a quicker response. The unit can also respond with normal priority if the elderly person is relaxed. For example, it might use text analysis technology to analyze the content of the elderly person's messages, detect feelings of relaxation, and generate a monitoring method for normal priority. Furthermore, if an elderly person is in a hurry, the unit can prioritize their response to ensure an immediate reaction. For example, it might use facial recognition technology to analyze the elderly person's facial expressions, detect feelings of urgency, and generate a monitoring method for an immediate reaction. This allows for more appropriate responses by determining monitoring priorities based on the elderly person's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0111] The monitoring unit can customize monitoring methods by considering the geographical location information of elderly individuals. For example, if an elderly person is in a specific area, the monitoring unit can provide a monitoring method suitable for that area. For instance, the monitoring unit can use AI to analyze the elderly person's geographical location information and generate a monitoring method appropriate for that area. The monitoring unit can also propose the optimal monitoring method based on the elderly person's geographical location information. For example, the monitoring unit can use AI to analyze the elderly person's geographical location information and propose the optimal monitoring method. Furthermore, if an elderly person is on the move, the monitoring unit can customize the monitoring method based on their current location. For example, the monitoring unit can use AI to analyze the elderly person's current location and customize the monitoring method. This allows for more appropriate responses by customizing monitoring methods while considering the elderly person's geographical location information.

[0112] The monitoring unit can estimate the emotions of elderly individuals and determine monitoring priorities based on those estimated emotions. For example, if an elderly person is feeling anxious, the unit will prioritize their response to ensure a quicker reaction. For instance, it might use voice analysis technology to analyze the tone of the elderly person's voice, detect feelings of anxiety, and generate a monitoring method for a quicker response. The unit can also respond with normal priority if the elderly person is relaxed. For example, it might use text analysis technology to analyze the content of the elderly person's messages, detect feelings of relaxation, and generate a monitoring method for normal priority. Furthermore, if an elderly person is in a hurry, the unit can prioritize their response to ensure an immediate reaction. For example, it might use facial recognition technology to analyze the elderly person's facial expressions, detect feelings of urgency, and generate a monitoring method for an immediate reaction. This allows for more appropriate responses by determining monitoring priorities based on the elderly person's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI.

[0113] The monitoring unit can customize monitoring methods by considering the geographical location information of elderly individuals. For example, if an elderly person is in a specific area, the monitoring unit can provide a monitoring method suitable for that area. For instance, the monitoring unit can use AI to analyze the elderly person's geographical location information and generate a monitoring method appropriate for that area. The monitoring unit can also propose the optimal monitoring method based on the elderly person's geographical location information. For example, the monitoring unit can use AI to analyze the elderly person's geographical location information and propose the optimal monitoring method. Furthermore, if an elderly person is on the move, the monitoring unit can customize the monitoring method based on their current location. For example, the monitoring unit can use AI to analyze the elderly person's current location and customize the monitoring method. This allows for more appropriate responses by customizing monitoring methods while considering the elderly person's geographical location information.

[0114] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0115] The community association management support system can estimate residents' emotions and propose community association events and activities based on those estimates. For example, if a resident is feeling stressed, it can suggest relaxing events. Specifically, it uses voice analysis technology to analyze the tone of the resident's voice, detect feelings of stress, and suggest yoga or meditation events. If a resident is excited, it can also suggest energetic activities. For example, it uses facial recognition technology to analyze the resident's facial expressions, detect feelings of excitement, and suggest sports events or dance parties. If a resident is relaxed, it can also suggest normal events. For example, it uses text analysis technology to analyze the content of the resident's messages, detect feelings of relaxation, and suggest book clubs or movie screenings. By suggesting the most suitable events and activities based on residents' emotions, the system can improve resident satisfaction.

[0116] The community association management support system can analyze residents' past participation history and suggest optimal events and activities. For example, it can suggest similar events based on residents' past event participation history. Specifically, it uses AI to analyze residents' past participation history, identify frequently attended events, and suggest them as future events. It can also prioritize suggesting highly-rated events based on residents' evaluations of past events. For example, it uses AI to analyze residents' past event evaluations, identify highly-rated events, and suggest them as future events. Furthermore, it can suggest events suitable for specific seasons or time slots based on residents' past participation history. For example, it uses AI to analyze residents' past participation history and suggest events best suited to specific seasons or time slots. In this way, by analyzing residents' past participation history, the system can suggest optimal events and activities.

[0117] The community association management support system can propose community-specific events and activities based on residents' geographical location information. For example, if a resident lives in a specific area, it can propose events related to that area. Specifically, it uses AI to analyze residents' geographical location information, identify relevant events, and propose them. It can also propose the most suitable events based on a resident's current location if they are on the move. For example, it uses AI to analyze a resident's current location and proposes nearby events. Furthermore, it can propose events tailored to the characteristics of a region based on residents' geographical location information. For example, it uses AI to analyze the characteristics of a region and propose events suitable for that region. In this way, by proposing community-specific events and activities based on residents' geographical location information, it can increase residents' motivation to participate.

[0118] The community association management support system can analyze residents' social media activity and suggest events and activities based on their areas of interest. For example, it can analyze residents' social media posts and suggest events related to themes they are interested in. Specifically, it uses AI to analyze residents' social media posts, identify themes of interest, and suggest events related to those themes. It can also suggest events related to specific groups or communities based on residents' social media activity. For example, it uses AI to analyze residents' social media activity, identify events related to specific groups or communities, and suggest them. Furthermore, it can suggest new events that residents might be interested in based on their social media activity. For example, it uses AI to analyze residents' social media activity, identify new events that might be interesting, and suggest them. In this way, by analyzing residents' social media activity, it is possible to suggest events and activities based on their areas of interest.

[0119] The neighborhood association management support system can estimate residents' emotions and adjust the way neighborhood association meetings are conducted based on those estimated emotions. For example, if residents are feeling tense, it can suggest a more relaxing approach. Specifically, it uses voice analysis technology to analyze the tone of residents' voices, detect feelings of tension, and suggest a more relaxed approach. It can also suggest an energetic approach if residents are feeling excited. For example, it uses facial recognition technology to analyze residents' facial expressions, detect feelings of excitement, and suggest an energetic approach. Furthermore, if residents are relaxed, it can suggest a normal approach. For example, it uses text analysis technology to analyze the content of residents' messages, detect feelings of relaxation, and suggest a normal approach. By adjusting the meeting process based on residents' emotions, more effective meeting management becomes possible.

[0120] The community association management support system can analyze residents' past inquiry history and suggest the most suitable way to handle inquiries. For example, it can automatically display as suggestions the types of inquiries residents have frequently made in the past. Specifically, it uses AI to analyze past inquiry history, identify frequently asked questions, and automatically display them the next time an inquiry is made. It can also prioritize suggesting inquiry methods (phone, email, etc.) that residents have used in the past. For example, it uses AI to analyze past inquiry methods and suggest the most suitable method. Furthermore, it can suggest the most suitable method for specific time periods based on residents' past inquiry history. For example, it uses AI to analyze past inquiry history and suggest the most suitable method for specific time periods. In this way, by analyzing residents' past inquiry history, the system can suggest the most suitable way to handle inquiries.

[0121] The community association management support system can estimate residents' emotions and prioritize inquiries based on those emotions. For example, if a resident is angry, the inquiry will be given priority as an urgent matter. Specifically, it uses voice analysis technology to analyze the tone of the resident's voice, detect anger, and prioritize the inquiry. It can also raise the priority of inquiries from residents who are feeling anxious in order to respond quickly. For example, it uses text analysis technology to analyze the content of the resident's message, detect anxiety, and raise the priority. It can also respond to inquiries from residents who are relaxed with the usual priority. For example, it uses facial recognition technology to analyze the resident's facial expression to detect relaxation and respond with the usual priority. By prioritizing inquiries based on residents' emotions, more appropriate responses become possible.

[0122] The community association management support system can provide region-specific support for inquiries based on residents' geographical location information. For example, if a resident lives in a specific area, inquiries related to that area will be prioritized. Specifically, AI is used to analyze the resident's geographical location information, identify inquiries related to that area, and prioritize their response. Furthermore, if a resident is on the move, the system can provide the most appropriate response based on their current location. For example, AI is used to analyze the resident's current location and address problems occurring nearby. In addition, the system can provide inquiry support tailored to the characteristics of the region based on the resident's geographical location information. For example, AI is used to analyze the characteristics of the region and provide a response appropriate to that region. This allows for more appropriate responses by providing region-specific support based on residents' geographical location information.

[0123] The community association management support system can estimate residents' emotions and adjust the response method to inquiries based on those emotions. For example, if a resident is angry, it will use a calm and polite response method. Specifically, it uses voice analysis technology to analyze the tone of the resident's voice, detect anger, and generate a calm and polite response method. It can also use a reassuring response method if a resident is feeling anxious. For example, it uses text analysis technology to analyze the content of the resident's message, detect anxiety, and generate a reassuring response method. Furthermore, if a resident is relaxed, it can use a friendly response method. For example, it uses facial recognition technology to analyze the resident's facial expression, detect relaxation, and generate a friendly response method. In this way, by adjusting the response method to inquiries based on residents' emotions, more appropriate responses become possible.

[0124] The community association management support system can analyze residents' social media activity and respond to inquiries based on their areas of interest. For example, it can analyze residents' social media posts and prioritize inquiries related to topics of interest. Specifically, it uses AI to analyze residents' social media posts, identify topics of interest, and prioritize inquiries related to those topics. It can also prioritize inquiries related to specific groups or communities based on residents' social media activity. For example, it uses AI to analyze residents' social media activity, identify inquiries related to specific groups or communities, and prioritize them. Furthermore, it can suggest new inquiry topics that residents might be interested in based on their social media activity. For example, it uses AI to analyze residents' social media activity, identify new inquiry topics that residents might be interested in, and suggest them. In this way, analyzing residents' social media activity enables inquiry responses based on their areas of interest.

[0125] The following briefly describes the processing flow for example form 2.

[0126] Step 1: The reception desk receives inquiries from residents. These inquiries can be made via telephone, email, or online forms. For example, when receiving telephone inquiries, the reception desk uses speech recognition technology to automatically record the content. Email inquiries can be received through a dedicated email address, and online forms are provided through a website or application. Step 2: The inquiry handling department uses a generation AI to automatically respond to inquiries received by the reception department. The automated responses are based on preset answers or answers generated by the generation AI. For example, the inquiry handling department uses preset answers to automatically respond to frequently asked questions. It can also use the generation AI to generate customized answers for individual inquiries. Step 3: The Trouble Resolution Department proposes solutions to local problems. These problems include noise pollution, illegal dumping of waste, and traffic congestion. For example, the Trouble Resolution Department can automatically generate notices to raise awareness about noise pollution, propose the installation of surveillance cameras to address illegal dumping of waste, and propose specific methods for traffic control to address traffic congestion. Step 4: The Operations Proposal Department uses generative AI to propose methods for managing the event. These methods include scheduling, managing participants, and managing the budget. For example, the Operations Proposal Department uses generative AI to optimize the event schedule and propose methods for managing participants and the budget.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0128] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0129] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements described above, including the reception unit, inquiry handling unit, troubleshooting unit, operation proposal unit, collaboration unit, and monitoring unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and receives inquiries from residents. The inquiry handling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides automated responses using generation AI. The troubleshooting unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes solutions to local problems. The operation proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes methods for operating events. The collaboration unit is implemented by, for example, the control unit 46A of the smart device 14 and collaborates with services for residents. The monitoring unit is implemented by, for example, the control unit 46A of the smart device 14 and provides a monitoring function for the elderly. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0131] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0132] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

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

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements described above, including the reception unit, inquiry handling unit, troubleshooting unit, operation proposal unit, coordination unit, and monitoring unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and receives inquiries from residents. The inquiry handling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides automatic responses using generating AI. The troubleshooting unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes solutions to local problems. The operation proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes methods for operating events. The coordination unit is implemented by, for example, the control unit 46A of the smart glasses 214 and coordinates with services for residents. The monitoring unit is implemented by, for example, the control unit 46A of the smart glasses 214 and provides a monitoring function for the elderly. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0147] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0148] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

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

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0155] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0156] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0157] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0159] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0161] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0162] Each of the multiple elements described above, including the reception unit, inquiry handling unit, troubleshooting unit, operation proposal unit, coordination unit, and monitoring unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives inquiries from residents. The inquiry handling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides automatic responses using generation AI. The troubleshooting unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes solutions to local problems. The operation proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes methods for operating events. The coordination unit is implemented by, for example, the control unit 46A of the headset terminal 314 and coordinates with services for residents. The monitoring unit is implemented by, for example, the control unit 46A of the headset terminal 314 and provides a monitoring function for the elderly. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0163] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0164] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0165] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0166] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0167] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0169] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0170] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0171] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0172] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0173] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0174] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0175] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0176] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0177] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0178] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0179] Each of the multiple elements described above, including the reception unit, inquiry handling unit, troubleshooting unit, operation proposal unit, coordination unit, and monitoring unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives inquiries from residents. The inquiry handling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and provides automatic responses using generated AI. The troubleshooting unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes solutions to local problems. The operation proposal unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and proposes methods for operating events. The coordination unit is implemented by, for example, the control unit 46A of the robot 414 and coordinates with services for residents. The monitoring unit is implemented by, for example, the control unit 46A of the robot 414 and provides a monitoring function for the elderly. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0180] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0181] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0182] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0183] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0184] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0185] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0187] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes multiple computers, including computer 22.

[0188] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0189] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0190] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0191] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0192] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0193] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0194] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0195] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0196] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0197] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0198] (Note 1) A reception desk that handles inquiries from residents, An inquiry handling unit that provides an automated response based on the inquiry received by the aforementioned reception unit, The Trouble Resolution Department proposes solutions to local problems, It includes an operations proposal department that proposes methods for running events. A system characterized by the following features. (Note 2) It has a liaison department that coordinates with services for residents. The system described in Appendix 1, characterized by the features described herein. (Note 3) It is equipped with a monitoring unit that provides a function to keep the elderly in check. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned inquiry handling department, Use generation AI to automatically respond to inquiries from residents. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned operational proposal department, We propose event management methods using generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned troubleshooting unit, Proposing solutions to local disputes The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned linkage unit is, It integrates with services such as electronic payment systems, delivery services, and transportation arrangements. The system described in Appendix 2, characterized by the features described herein. (Note 8) The aforementioned monitoring unit is Using smartphone location information to ensure the safety of the elderly The system described in Appendix 3, characterized by the features described herein. (Note 9) The aforementioned reception unit is We estimate the sentiments of residents and determine the priority of inquiries based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is We analyze residents' past inquiry history and select the most suitable method of handling inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving inquiries, filtering is performed based on the resident's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is We estimate the residents' feelings and adjust the timing of reception based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When receiving inquiries, the system prioritizes inquiries that are highly relevant based on the resident's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is When receiving inquiries, the system analyzes residents' social media activity and receives inquiries that are relevant to that activity. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned inquiry handling department, The system estimates the residents' emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned inquiry handling department, The level of detail in the response will be adjusted based on the importance of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned inquiry handling department, Apply different response algorithms depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned inquiry handling department, The system estimates the residents' emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned inquiry handling department, We prioritize responses based on when the inquiry was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned inquiry handling department, The order of responses will be adjusted based on the relevance of the inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned troubleshooting unit, We estimate the residents' feelings and adjust the proposed solutions based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned troubleshooting unit, Adjust the level of detail in the solution based on the type of problem. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned troubleshooting unit, Apply different troubleshooting algorithms depending on the frequency of the problem. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned troubleshooting unit, The system estimates the residents' feelings and prioritizes solutions based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned troubleshooting unit, Customize the solution based on where the problem occurred. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned troubleshooting unit, Referencing relevant literature on the problem improves the accuracy of the solution. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned operational proposal department, We estimate the sentiments of the residents and adjust the proposed management methods based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned operational proposal department, Adjust the level of detail in the operational procedures based on the type of event. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned operational proposal department, Optimize the operational methods by referring to past success stories of events. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned operational proposal department, The system estimates the sentiments of the residents and prioritizes operational methods based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned operational proposal department, Customize the operational methods based on the event location. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned operational proposal department, Improve the accuracy of the operational methods by referring to relevant literature on the event. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned linkage unit is, The system estimates residents' sentiments and prioritizes services based on those estimated sentiments. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned linkage unit is, Optimize the integration method based on the frequency of use of the integrated services. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned linkage unit is, The system estimates the sentiments of residents and selects services to collaborate with based on those estimated sentiments. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned linkage unit is, Customize the integration method considering the geographical distribution of the services being integrated. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned monitoring unit is The system estimates the emotions of elderly individuals and adjusts monitoring methods based on these estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned monitoring unit is Optimizing monitoring methods by referring to the past behavioral history of elderly individuals. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned monitoring unit is The system estimates the emotions of elderly individuals and determines the priority of monitoring based on these estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned monitoring unit is Customize monitoring methods by taking into account the geographical location of elderly individuals. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0199] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that handles inquiries from residents, An inquiry handling unit that provides an automated response based on the inquiry received by the aforementioned reception unit, The Trouble Resolution Department proposes solutions to local problems, It includes an operations proposal department that proposes methods for running events. A system characterized by the following features.

2. It has a liaison department that coordinates with services for residents. The system according to feature 1.

3. It is equipped with a monitoring unit that provides a function to keep the elderly in check. The system according to feature 1.

4. The aforementioned inquiry handling department, Using AI to generate responses, we will automatically respond to inquiries from residents. The system according to feature 1.

5. The aforementioned operational proposal department, We propose event management methods using generative AI. The system according to feature 1.

6. The aforementioned troubleshooting unit, Proposing solutions to local disputes The system according to feature 1.

7. The aforementioned linkage unit is, It integrates with services such as electronic payment systems, delivery services, and transportation arrangements. The system according to feature 2.

8. The aforementioned monitoring unit is Using smartphone location information to ensure the safety of the elderly The system according to claim 3.

Images