System

Abstract

An object of the system according to the embodiment is to allow citizens to efficiently acquire information on administrative procedures and local governments and solve questions and problems.SOLUTION: A system includes an information provision part, a guide part, a support part, an enlightenment part, and a feedback collection part. The information providing part answers the questions of the citizens and provides information. The guidance unit guides a necessary document or procedure based on the information provided by the information providing unit. The support unit solves the questions and problems of the citizens based on the information guided by the guide unit. The enlightening department provides information on measures and events of the local government and important information based on the information solved by the support department. The feedback collection unit collects feedback and requests from citizens based on the information provided by the enlightenment unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has made it difficult for citizens to efficiently obtain information about administrative procedures and local government, and to resolve their questions and problems.

[0005] The system according to the embodiment aims to enable citizens to efficiently obtain information on administrative procedures and local governments and resolve their questions and problems. [Means for solving the problem]

[0006] The system according to the embodiment comprises an information providing unit, a guidance unit, a support unit, an awareness raising unit, and a feedback collecting unit. The information providing unit answers citizens' questions and provides information. The guidance unit provides guidance on necessary documents or procedures based on the information provided by the information providing unit. The support unit solves citizens' questions and problems based on the information provided by the guidance unit. The awareness raising unit provides information on local government policies, events, and important announcements based on the information resolved by the support unit. The feedback collecting unit collects feedback and requests from citizens based on the information provided by the awareness raising unit. [Effects of the Invention]

[0007] The system according to the embodiment enables citizens to efficiently obtain information on administrative procedures and local governments and resolve their questions and problems. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The administrative procedure support system according to an embodiment of the present invention utilizes generative AI to assist citizens in carrying out administrative procedures. The system answers citizens' questions, provides necessary information, and guides them through the necessary documents and procedures. It also provides online support to help citizens resolve questions and problems related to administrative services and local governments. Citizens can receive support 24 hours a day, 365 days a year through generative AI. Generative AI is used to provide citizens with information on local government policies, events, important announcements, and other information to raise awareness. Generative AI also provides opportunities for citizens to become interested in and participate in their local communities. Generative AI is also used to collect feedback and requests from citizens and use them to improve local government policies and services. Generative AI aggregates opinions through dialogue with citizens, promoting transparency and citizen participation in government administration. For example, generative AI answers citizens' questions and provides them with the necessary information. Citizens input the procedures they wish to perform, and the generative AI provides the information necessary for those procedures. For example, it provides information on specific procedures, such as obtaining a resident registration card or filing a change of address notification. Next, the generative AI guides citizens through the necessary documents and procedures. The generative AI guides citizens through the necessary documents and procedural steps to proceed with the procedure. For example, providing a list of required documents and a procedure flow allows citizens to proceed smoothly. Furthermore, generative AI is used to provide online support to help citizens resolve questions and problems regarding administrative services and local government. Citizens can receive support through generative AI 24 hours a day, 365 days a year. For example, generative AI can solve questions and problems regarding local government services, improving convenience for citizens. Generative AI is also used to provide citizens with information on local government policies, events, important announcements, and other information to raise awareness. Generative AI provides opportunities for citizens to become interested in and participate in their local community. For example, providing information on local events and policies allows citizens to actively participate in their local community. Furthermore, generative AI is used to collect feedback and requests from citizens and use them to improve local government policies and services. Generative AI aggregates opinions through dialogue with citizens, promoting transparency in administration and citizen participation.For example, local governments can operate more effectively by collecting citizen opinions and requests and using them to improve policies and services. In this way, administrative procedure support systems can improve the efficiency of administrative procedures and strengthen citizen support by answering citizen questions, providing necessary information, guiding citizens through documents and procedures, resolving doubts and problems, providing information on policies and events, and collecting feedback.

[0029] An administrative procedure support system according to an embodiment includes an information providing unit, a guidance unit, a support unit, an education unit, and a feedback collection unit. The information providing unit answers citizens' questions and provides them with necessary information. For example, the information providing unit generates appropriate answers to citizens' questions using a generation AI. The information providing unit can also input the procedures citizens wish to perform and provide them with the information necessary for those procedures. For example, the information providing unit can provide information on procedures for obtaining a resident registration card or notifying a change of address. The information providing unit can also analyze citizens' past question history and select the optimal information provision method. For example, the information providing unit can prioritize providing related information based on frequently asked questions. The guidance unit provides guidance on necessary documents and procedures based on the information provided by the information providing unit. For example, the guidance unit uses a generation AI to guide citizens through the necessary documents and procedural steps to proceed with a procedure. The guidance unit can also adjust the level of detail in the guidance based on the importance of the procedure. For example, detailed guidance is provided for important procedures, and brief guidance is provided for simple procedures. The guidance unit can also estimate citizens' emotions and adjust the way the guidance is presented based on the estimated emotions. For example, if a citizen is nervous, it provides a simple, highly visible display method. The Support Department solves citizens' questions and problems based on the information provided by the Guidance Department. For example, the Support Department uses generative AI to provide appropriate solutions to citizens' questions and problems. The Support Department can also analyze citizens' past problem-solving history and select the optimal support method. For example, it provides the optimal support method based on previously successful solutions. Furthermore, the Support Department can estimate citizens' emotions and adjust the support method based on the estimated citizen emotions. For example, if a citizen is feeling stressed, it provides simple and quick support. The Awareness Department provides information on local government policies, events, important announcements, etc. based on the information resolved by the Support Department. For example, the Awareness Department uses generative AI to provide citizens with information on policies and events. The Awareness Department can also estimate citizens' emotions and adjust the display method of awareness based on the estimated citizen emotions. For example, if a citizen is relaxed, it provides a display method with more detailed information.Furthermore, the awareness department can optimize current awareness content by referring to past awareness data. For example, the current awareness content is optimized based on past successful awareness methods. The feedback collection department collects feedback and requests from citizens based on the information provided by the awareness department. For example, the feedback collection department collects opinions and requests from citizens using generative AI. The feedback collection department can also estimate citizens' emotions and adjust the feedback collection method based on the estimated citizens' emotions. For example, if citizens are feeling anxious, the feedback collection department can provide a simple and quick feedback collection method. Furthermore, the feedback collection department can analyze citizens' past feedback history and select the optimal collection method. For example, the feedback collection department can provide the optimal collection method based on the past feedback history. As a result, the administrative procedure support system according to the embodiment answers citizens' questions, provides necessary information, guides them through documents and procedures, solves their doubts and problems, provides information on policies and events, and collects feedback, thereby improving the efficiency of administrative procedures and strengthening citizen support.

[0030] The information provision unit can analyze the citizen's past question history and select the information provision method. For example, the information provision unit allows the generation AI to prioritize providing related information based on the content of questions that the citizen has frequently asked in the past. The information provision unit can also select the most effective information provision method for the generation AI from the citizen's past question history. The information provision unit can also analyze the citizen's past question history and allow the generation AI to provide information at the optimal timing. In this way, the optimal information provision method can be selected by analyzing the citizen's past question history. Some or all of the above-mentioned processing in the information provision unit may be performed, for example, using AI or may be performed without using AI. For example, the information provision unit can input the citizen's past question history data into the generation AI and have the generation AI select the optimal information provision method.

[0031] The information providing unit can filter information based on the citizen's current areas of interest when providing the information. For example, the information providing unit allows the generation AI to prioritize information related to areas in which the citizen is currently interested. The information providing unit can also filter information that the generation AI does not need based on the citizen's areas of interest. The information providing unit can also analyze the citizen's current areas of interest and allow the generation AI to provide the most appropriate information. In this way, by filtering information based on the citizen's current areas of interest, highly relevant information can be provided. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input citizen's area of ​​interest data to the generation AI and cause the generation AI to filter information based on the areas of interest.

[0032] When providing information, the information providing unit can select a means of providing information depending on the citizen's input method. For example, if the citizen uses voice input, the information providing unit can have the generation AI provide the information by voice. Furthermore, if the citizen uses text input, the information providing unit can have the generation AI provide the information by text. Furthermore, if the citizen uses image input, the information providing unit can have the generation AI provide the information using an image. This improves the convenience of information provision by selecting the optimal means of providing information depending on the citizen's input method. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input the citizen's input data into the generation AI and have the generation AI select an information providing means depending on the input method.

[0033] When providing information, the information providing unit can prioritize providing highly relevant information based on the citizen's geographical location information. For example, the information providing unit allows the generation AI to prioritize providing information related to the citizen's current location. The information providing unit can also allow the generation AI to provide optimal information based on the citizen's geographical location information. The information providing unit can also provide information on events and measures related to the citizen's current location. This makes it possible to provide highly relevant information by taking the citizen's geographical location information into consideration. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input the citizen's geographical location data into the generation AI and cause the generation AI to provide information based on the geographical location.

[0034] When providing information, the information providing unit can analyze the citizen's social media activity and provide related information. For example, the information providing unit analyzes the citizen's social media posts, and the generation AI provides the related information. The information providing unit can also provide the related information by referring to the activity of the citizen's friends on social media. The information providing unit can also provide the related information by the generation AI based on the citizen's social media check-in information. In this way, related information can be provided by analyzing the citizen's social media activity. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input the citizen's social media data into the generation AI and cause the generation AI to provide information based on the social media activity.

[0035] When providing information, the information provision unit can customize the method of providing information by reflecting past feedback from citizens. For example, the information provision unit allows the generation AI to select the optimal method of providing information based on past feedback from citizens. The information provision unit can also allow the generation AI to adjust the timing of information provision by reflecting past feedback from citizens. The information provision unit can also analyze past feedback from citizens and allow the generation AI to provide optimal information. In this way, the method of providing information can be customized by reflecting past feedback from citizens. Some or all of the above-mentioned processing in the information provision unit may be performed using AI, for example, or may be performed without using AI. For example, the information provision unit can input past feedback data from citizens into the generation AI and cause the generation AI to customize the method of providing information based on the feedback.

[0036] The guidance unit can adjust the level of detail of the guidance based on the importance of the procedure when providing guidance. For example, in the case of an important procedure, the generation AI of the guidance unit can provide detailed guidance. In addition, in the case of a simple procedure, the generation AI of the guidance unit can also provide concise guidance. In addition, in the guidance unit, the generation AI can adjust the level of detail of the guidance according to the importance of the procedure. In this way, by adjusting the level of detail of the guidance based on the importance of the procedure, appropriate guidance can be provided. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input procedure importance data to the generation AI and cause the generation AI to adjust the level of detail of the guidance based on the importance.

[0037] When providing guidance, the guidance unit can apply different guidance algorithms depending on the procedure category. For example, in the case of a procedure to obtain a resident registration certificate, the generation AI can apply a dedicated guidance algorithm. In addition, in the case of a procedure to notify a move of residence, the generation AI can apply a different guidance algorithm. In addition, the guidance unit can select the optimal guidance algorithm depending on the procedure category. In this way, optimal guidance can be provided by applying different guidance algorithms depending on the procedure category. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input procedure category data into the generation AI and have the generation AI apply a guidance algorithm based on the category.

[0038] When providing guidance, the guidance unit can improve the accuracy of the guidance by referring to the citizen's past guidance results. In the guidance unit, for example, the generation AI improves the accuracy of the guidance based on the citizen's past guidance results. The guidance unit can also analyze the citizen's past guidance results, and the generation AI can select the optimal guidance method. The guidance unit can also reflect the citizen's past guidance results and the generation AI can improve the accuracy of the guidance. In this way, the accuracy of the guidance is improved by referring to the citizen's past guidance results. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input the citizen's past guidance result data into the generation AI and have the generation AI improve the accuracy of the guidance.

[0039] When providing guidance, the guidance unit can determine the priority of guidance based on the submission date of the procedure. For example, in the case of a procedure with an approaching deadline, the guidance unit has the generation AI provide guidance preferentially. In addition, in the case of a procedure with a distant submission date, the guidance unit can have the generation AI provide guidance later. In addition, in the guidance unit, the generation AI can determine the priority of guidance based on the submission date of the procedure. In this way, by determining the priority of guidance based on the submission date of the procedure, appropriate guidance can be provided. Some or all of the above-mentioned processing in the guidance unit may be performed using, for example, AI, or may be performed without using AI. For example, the guidance unit can input procedure submission date data into the generation AI and have the generation AI determine the priority of guidance based on the submission date.

[0040] The guidance unit can adjust the order of guidance based on the relevance of the procedures when providing guidance. For example, in the case of highly relevant procedures, the guidance unit has the generation AI provide guidance first. In addition, in the case of less relevant procedures, the guidance unit can have the generation AI provide guidance later. In addition, the guidance unit can have the generation AI adjust the order of guidance based on the relevance of the procedures. In this way, by adjusting the order of guidance based on the relevance of the procedures, appropriate guidance can be provided. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input procedure relevance data into the generation AI and cause the generation AI to adjust the order of guidance based on the relevance.

[0041] When providing guidance, the guidance unit can adjust the use of technical terminology in the guidance depending on the citizen's level of expertise. For example, if the citizen has technical expertise, the guidance unit can have the generation AI provide guidance using technical terminology. Also, if the citizen does not have technical expertise, the guidance unit can have the generation AI provide guidance in simple language. Also, the guidance unit can have the generation AI adjust the use of technical terminology in the guidance depending on the citizen's level of expertise. This allows appropriate guidance to be provided by adjusting the use of technical terminology in the guidance depending on the citizen's level of expertise. Some or all of the above-mentioned processing in the guidance unit can be performed using AI, for example, or without AI. For example, the guidance unit can input citizen's expertise level data into the generation AI and cause the generation AI to adjust the use of technical terminology based on the expertise level.

[0042] When providing support, the support unit can analyze the citizen's past problem-solving history and select the optimal support method. For example, the support unit allows the generation AI to select the optimal support method based on the citizen's past problem-solving history. The support unit can also analyze the citizen's past problem-solving history and allow the generation AI to provide the most effective support method. The support unit can also allow the generation AI to select the optimal support method by referring to the citizen's past problem-solving history. In this way, the optimal support method can be selected by analyzing the citizen's past problem-solving history. Some or all of the above-mentioned processing in the support unit may be performed, for example, using AI or may be performed without using AI. For example, the support unit can input the citizen's past problem-solving history data into the generation AI and have the generation AI select a support method based on the problem-solving history.

[0043] During support, the support unit can customize the support means based on the citizen's current living situation. For example, the support unit allows the generation AI to select the optimal support means based on the citizen's current living situation. The support unit can also analyze the citizen's current living situation and allow the generation AI to provide the most effective support means. The support unit can also allow the generation AI to select the optimal support means based on the citizen's current living situation. In this way, optimal support can be provided by customizing the support means based on the citizen's current living situation. Some or all of the above-described processing in the support unit may be performed, for example, using AI or without AI. For example, the support unit can input the citizen's living situation data into the generation AI and have the generation AI customize the support means based on the living situation.

[0044] The support unit can improve the support method by reflecting citizen feedback during support. For example, the support unit allows the generation AI to improve the support method based on citizen feedback. The support unit can also analyze citizen feedback and allow the generation AI to select the optimal support method. The support unit can also customize the support method by reflecting citizen feedback. In this way, the support method can be improved by reflecting citizen feedback. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input citizen feedback data into the generation AI and cause the generation AI to improve the support method based on the feedback.

[0045] When providing support, the support unit can select the optimal support method by taking into account the citizen's geographical location information. In the support unit, for example, the generation AI selects the optimal support method based on the citizen's current location. The support unit can also analyze the citizen's geographical location information and have the generation AI provide the most effective support method. The support unit can also have the generation AI provide relevant support information based on the citizen's current location. This makes it possible to select the optimal support method by taking into account the citizen's geographical location information. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the citizen's geographical location data into the generation AI and have the generation AI select a support method based on the geographical location.

[0046] When providing support, the support unit can analyze the citizen's social media activity and suggest support methods. For example, the support unit analyzes the citizen's social media posts, and the generation AI suggests the optimal support method. The support unit can also refer to the activity of the citizen's friends on social media to have the generation AI provide relevant support information. The support unit can also have the generation AI suggest the optimal support method based on the citizen's social media check-in information. In this way, the optimal support method can be suggested by analyzing the citizen's social media activity. Some or all of the above-mentioned processing in the support unit may be performed, for example, using AI, or may be performed without using AI. For example, the support unit can input the citizen's social media data into the generation AI and have the generation AI suggest support methods based on the social media activity.

[0047] The support unit can customize the support method by reflecting the citizen's past feedback when providing support. For example, the support unit allows the generation AI to select the optimal support method based on the citizen's past feedback. The support unit can also analyze the citizen's past feedback and allow the generation AI to provide the most effective support method. The support unit can also allow the generation AI to customize the support method by reflecting the citizen's past feedback. In this way, the support method can be customized by reflecting the citizen's past feedback. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the citizen's past feedback data into the generation AI and have the generation AI customize the support method based on the feedback.

[0048] During enlightenment, the enlightenment unit can optimize the current enlightenment content by referring to past enlightenment data. For example, the enlightenment unit allows the generation AI to provide optimal enlightenment content based on past enlightenment data. The enlightenment unit can also analyze past enlightenment data and allow the generation AI to select the most effective enlightenment method. The enlightenment unit can also allow the generation AI to optimize the current enlightenment content by referring to past enlightenment data. In this way, the current enlightenment content can be optimized by referring to past enlightenment data. Some or all of the above-mentioned processing in the enlightenment unit may be performed, for example, using AI or may be performed without using AI. For example, the enlightenment unit can input past enlightenment data into the generation AI and cause the generation AI to optimize the enlightenment content.

[0049] The awareness department can apply different awareness methods to each category of measures and events during awareness generation. For example, in the case of awareness generation related to measures, the generation AI can apply a dedicated awareness method. In addition, in the case of awareness generation related to events, the awareness department can also have the generation AI apply a different awareness method. In addition, the awareness department can have the generation AI select the optimal awareness method depending on the category of the measures and events. In this way, optimal awareness can be provided by applying different awareness methods to each category of measures and events. Some or all of the above-mentioned processing in the awareness department may be performed using, for example, AI, or may be performed without using AI. For example, the awareness department can input category data of measures and events into the generation AI and have the generation AI apply an awareness method based on the category.

[0050] The awareness department can customize the awareness content by taking into account the citizen's attribute information when raising awareness. For example, the awareness department allows the generation AI to provide the most appropriate awareness content based on the citizen's age and gender. The awareness department can also allow the generation AI to provide the most appropriate awareness content based on the citizen's occupation and interests. The awareness department can also analyze the citizen's attribute information and customize the most appropriate awareness content based on the citizen's attribute information. In this way, the most appropriate awareness content can be customized by taking into account the citizen's attribute information. Some or all of the above-mentioned processing in the awareness department may be performed using AI, for example, or may be performed without using AI. For example, the awareness department can input citizen's attribute information data into the generation AI and have the generation AI customize the awareness content based on the attribute information.

[0051] The awareness department can determine the priority of awareness based on the timing of measures and events during awareness raising. For example, in the case of an upcoming event, the awareness department can have the generation AI prioritize awareness raising. In addition, in the case of an event that is far away, the awareness department can have the generation AI postpone awareness raising. In addition, the awareness department can have the generation AI determine the priority of awareness raising based on the timing of measures and events. In this way, appropriate awareness raising can be provided by determining the priority of awareness raising based on the timing of measures and events. Some or all of the above-mentioned processing in the awareness department can be performed using, for example, AI, or can be performed without using AI. For example, the awareness department can input data on the timing of measures and events into the generation AI and have the generation AI determine the priority of awareness raising based on the timing.

[0052] The enlightenment unit can optimize the enlightenment content by referring to relevant market data during enlightenment. For example, the enlightenment unit allows the generation AI to provide optimal enlightenment content based on relevant market data. The enlightenment unit can also analyze the relevant market data and allow the generation AI to select the most effective enlightenment method. The enlightenment unit can also allow the generation AI to optimize the current enlightenment content by referring to the relevant market data. In this way, the enlightenment content can be optimized by referring to the relevant market data. Some or all of the above-mentioned processing in the enlightenment unit may be performed, for example, using AI or may be performed without using AI. For example, the enlightenment unit can input relevant market data into the generation AI and cause the generation AI to optimize the enlightenment content.

[0053] The awareness department can adjust the awareness content during awareness raising, taking into account the technical maturity of the measures and events. For example, in the case of a technically mature measure, the awareness department can have the generation AI provide detailed awareness content. In addition, in the case of a technically immature measure, the awareness department can have the generation AI provide concise awareness content. In addition, the awareness department can have the generation AI adjust the awareness content based on the technical maturity of the measure or event. This makes it possible to provide appropriate awareness content by taking into account the technical maturity of the measure or event. Some or all of the above-mentioned processing in the awareness department can be performed, for example, using AI, or can be performed without using AI. For example, the awareness department can input technical maturity data of the measure or event into the generation AI, and have the generation AI adjust the awareness content based on the technical maturity.

[0054] When collecting feedback, the feedback collection unit can analyze the citizen's past feedback history and select the optimal collection method. In the feedback collection unit, for example, the generation AI selects the optimal collection method based on the citizen's past feedback history. The feedback collection unit can also analyze the citizen's past feedback history and provide the generation AI with the most effective collection method. The feedback collection unit can also select the optimal collection method by referring to the citizen's past feedback history. In this way, the optimal collection method can be selected by analyzing the citizen's past feedback history. Some or all of the above-mentioned processing in the feedback collection unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback collection unit can input the citizen's past feedback history data into the generation AI and cause the generation AI to select a collection method based on the feedback history.

[0055] The feedback collection unit can customize the collection means based on the citizen's current living situation when collecting feedback. In the feedback collection unit, for example, the generation AI selects the optimal collection means based on the citizen's current living situation. The feedback collection unit can also analyze the citizen's current living situation and have the generation AI provide the most effective collection means. The feedback collection unit can also have the generation AI select the optimal collection means based on the citizen's current living situation. In this way, optimal feedback can be collected by customizing the collection means based on the citizen's current living situation. Some or all of the above-mentioned processing in the feedback collection unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback collection unit can input citizen's living situation data into the generation AI and have the generation AI customize the collection means based on the living situation.

[0056] The feedback collection unit can improve the collection method by reflecting citizen feedback when collecting feedback. In the feedback collection unit, for example, the generation AI improves the collection method based on citizen feedback. The feedback collection unit can also analyze citizen feedback and the generation AI can select the optimal collection method. The feedback collection unit can also customize the collection method by reflecting citizen feedback. In this way, the collection method can be improved by reflecting citizen feedback. Some or all of the above-mentioned processing in the feedback collection unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback collection unit can input citizen feedback data into the generation AI and cause the generation AI to improve the collection method based on the feedback.

[0057] When collecting feedback, the feedback collection unit can select the optimal collection method by taking into account the citizen's geographical location information. In the feedback collection unit, for example, the generation AI selects the optimal collection method based on the citizen's current location. The feedback collection unit can also analyze the citizen's geographical location information and have the generation AI provide the most effective collection method. The feedback collection unit can also provide the generation AI with a relevant feedback collection method based on the citizen's current location. This allows the optimal collection method to be selected by taking into account the citizen's geographical location information. Some or all of the above-mentioned processing in the feedback collection unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback collection unit can input the citizen's geographical location data into the generation AI and have the generation AI select a collection method based on the geographical location.

[0058] When collecting feedback, the feedback collection unit can analyze the citizen's social media activity and suggest a collection method. For example, the feedback collection unit analyzes the content of the citizen's social media posts, and the generation AI suggests the optimal collection method. The feedback collection unit can also refer to the activity of the citizen's friends on social media to provide a relevant feedback collection method. The feedback collection unit can also have the generation AI suggest the optimal collection method based on the citizen's social media check-in information. In this way, the optimal collection method can be suggested by analyzing the citizen's social media activity. Some or all of the above-mentioned processing in the feedback collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback collection unit can input the citizen's social media data into the generation AI and have the generation AI suggest collection methods based on the social media activity.

[0059] When collecting feedback, the feedback collection unit can customize the collection method by reflecting citizens' past feedback. In the feedback collection unit, for example, the generation AI selects the optimal collection method based on citizens' past feedback. The feedback collection unit can also analyze citizens' past feedback and have the generation AI provide the most effective collection method. In addition, the feedback collection unit can also have the generation AI customize the collection method by reflecting citizens' past feedback. In this way, the collection method can be customized by reflecting citizens' past feedback. Some or all of the above-mentioned processing in the feedback collection unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback collection unit can input citizens' past feedback data into the generation AI and have the generation AI customize the collection method based on the feedback.

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

[0061] The information provision unit can adjust the content of the information provided taking into account the citizen's health condition. For example, if a citizen asks a question about health, the generation AI will prioritize providing health-related information. The information provision unit can also have the generation AI provide appropriate health advice based on the citizen's health condition. Furthermore, the information provision unit can analyze the citizen's health data and have the generation AI provide optimal health information. This allows the provision of more appropriate information by adjusting the content of the information provided based on the citizen's health condition.

[0062] The guidance unit can analyze the citizen's past behavior history and select the optimal guidance method. For example, based on what procedures the citizen has performed in the past, the generation AI will prioritize providing guidance on related procedures. The guidance unit can also analyze the citizen's past behavior history and the generation AI can select the most effective guidance method. Furthermore, the guidance unit can refer to the citizen's past behavior history and the generation AI can provide guidance at the optimal timing. In this way, the optimal guidance method can be selected by analyzing the citizen's past behavior history.

[0063] The support department can customize the content of support based on the citizen's living environment. For example, if the citizen lives in an urban area, the generation AI can provide support information specialized for urban areas. Also, if the citizen lives in a rural area, the generation AI can provide support information specialized for rural areas. Furthermore, the support department can analyze the citizen's living environment, and the generation AI can select the optimal support method. This allows the support content to be customized based on the citizen's living environment, making it possible to provide more appropriate support.

[0064] The Public Awareness Department can customize the public awareness content based on the hobbies and interests of citizens. For example, if a citizen is interested in sports, the generation AI can prioritize providing sports-related public awareness content. Also, if a citizen is interested in cultural activities, the generation AI can provide public awareness content related to cultural activities. Furthermore, the Public Awareness Department can analyze citizens' hobbies and interests, and the generation AI can provide the most appropriate public awareness content. This allows for more effective public awareness by customizing the public awareness content based on citizens' hobbies and interests.

[0065] The feedback collection unit can analyze citizens' past feedback history and select the optimal collection method. For example, the generation AI selects the optimal collection method based on citizens' past feedback history. The feedback collection unit can also analyze citizens' past feedback history and the generation AI can provide the most effective collection method. Furthermore, the feedback collection unit can also refer to citizens' past feedback history and the generation AI can select the optimal collection method. In this way, the optimal collection method can be selected by analyzing citizens' past feedback history.

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

[0067] Step 1: The information provision department answers citizens' questions and provides them with the necessary information. For example, it uses generative AI to generate appropriate answers to citizens' questions and provides information on procedures for obtaining a resident registration card and notifying a change of address. It also analyzes citizens' past question history and selects the most appropriate method of providing information. Step 2: The guidance section provides guidance on the necessary documents and procedures based on the information provided by the information provision section. For example, it uses generation AI to guide citizens through the necessary documents and procedural steps to proceed with a procedure, adjusting the level of detail in the guidance based on the importance of the procedure. It also estimates the citizen's emotions and adjusts the way the guidance is presented based on the estimated emotions. Step 3: The support department solves the citizen's questions and problems based on the information provided by the information department. For example, it uses generative AI to provide appropriate solutions and analyzes the citizen's past problem-solving history to select the most appropriate support method. It also estimates the citizen's emotions and adjusts the support method based on the estimated emotions. Step 4: The Public Awareness Department provides information on local government policies, events, important notices, etc. based on the information resolved by the Support Department. For example, they use generative AI to provide information on policies and events, estimate citizen sentiment, and adjust the display method. They also refer to past public awareness data to optimize current public awareness content. Step 5: The Feedback Collection Department collects feedback and requests from citizens based on the information provided by the Public Awareness Department. For example, it uses generative AI to collect opinions and requests from citizens, estimates their sentiments, and adjusts the collection method. It also analyzes citizens' past feedback history to select the optimal collection method.

[0068] (Example 2) The administrative procedure support system according to an embodiment of the present invention utilizes generative AI to assist citizens in carrying out administrative procedures. The system answers citizens' questions, provides necessary information, and guides them through the necessary documents and procedures. It also provides online support to help citizens resolve questions and problems related to administrative services and local governments. Citizens can receive support 24 hours a day, 365 days a year through generative AI. Generative AI is used to provide citizens with information on local government policies, events, important announcements, and other information to raise awareness. Generative AI also provides opportunities for citizens to become interested in and participate in their local communities. Generative AI is also used to collect feedback and requests from citizens and use them to improve local government policies and services. Generative AI aggregates opinions through dialogue with citizens, promoting transparency and citizen participation in government administration. For example, generative AI answers citizens' questions and provides them with the necessary information. Citizens input the procedures they wish to perform, and the generative AI provides the information necessary for those procedures. For example, it provides information on specific procedures, such as obtaining a resident registration card or filing a change of address notification. Next, the generative AI guides citizens through the necessary documents and procedures. The generative AI guides citizens through the necessary documents and procedural steps to proceed with the procedure. For example, providing a list of required documents and a procedure flow allows citizens to proceed smoothly. Furthermore, generative AI is used to provide online support to help citizens resolve questions and problems regarding administrative services and local government. Citizens can receive support through generative AI 24 hours a day, 365 days a year. For example, generative AI can solve questions and problems regarding local government services, improving convenience for citizens. Generative AI is also used to provide citizens with information on local government policies, events, important announcements, and other information to raise awareness. Generative AI provides opportunities for citizens to become interested in and participate in their local community. For example, providing information on local events and policies allows citizens to actively participate in their local community. Furthermore, generative AI is used to collect feedback and requests from citizens and use them to improve local government policies and services. Generative AI aggregates opinions through dialogue with citizens, promoting transparency in administration and citizen participation.For example, local governments can operate more effectively by collecting citizen opinions and requests and using them to improve policies and services. In this way, administrative procedure support systems can improve the efficiency of administrative procedures and strengthen citizen support by answering citizen questions, providing necessary information, guiding citizens through documents and procedures, resolving doubts and problems, providing information on policies and events, and collecting feedback.

[0069] An administrative procedure support system according to an embodiment includes an information providing unit, a guidance unit, a support unit, an education unit, and a feedback collection unit. The information providing unit answers citizens' questions and provides them with necessary information. For example, the information providing unit generates appropriate answers to citizens' questions using a generation AI. The information providing unit can also input the procedures citizens wish to perform and provide them with the information necessary for those procedures. For example, the information providing unit can provide information on procedures for obtaining a resident registration card or notifying a change of address. The information providing unit can also analyze citizens' past question history and select the optimal information provision method. For example, the information providing unit can prioritize providing related information based on frequently asked questions. The guidance unit provides guidance on necessary documents and procedures based on the information provided by the information providing unit. For example, the guidance unit uses a generation AI to guide citizens through the necessary documents and procedural steps to proceed with a procedure. The guidance unit can also adjust the level of detail in the guidance based on the importance of the procedure. For example, detailed guidance is provided for important procedures, and brief guidance is provided for simple procedures. The guidance unit can also estimate citizens' emotions and adjust the way the guidance is presented based on the estimated emotions. For example, if a citizen is nervous, it provides a simple, highly visible display method. The Support Department solves citizens' questions and problems based on the information provided by the Guidance Department. For example, the Support Department uses generative AI to provide appropriate solutions to citizens' questions and problems. The Support Department can also analyze citizens' past problem-solving history and select the optimal support method. For example, it provides the optimal support method based on previously successful solutions. Furthermore, the Support Department can estimate citizens' emotions and adjust the support method based on the estimated citizen emotions. For example, if a citizen is feeling stressed, it provides simple and quick support. The Awareness Department provides information on local government policies, events, important announcements, etc. based on the information resolved by the Support Department. For example, the Awareness Department uses generative AI to provide citizens with information on policies and events. The Awareness Department can also estimate citizens' emotions and adjust the display method of awareness based on the estimated citizen emotions. For example, if a citizen is relaxed, it provides a display method with more detailed information.Furthermore, the awareness department can optimize current awareness content by referring to past awareness data. For example, the current awareness content is optimized based on past successful awareness methods. The feedback collection department collects feedback and requests from citizens based on the information provided by the awareness department. For example, the feedback collection department collects opinions and requests from citizens using generative AI. The feedback collection department can also estimate citizens' emotions and adjust the feedback collection method based on the estimated citizens' emotions. For example, if citizens are feeling anxious, the feedback collection department can provide a simple and quick feedback collection method. Furthermore, the feedback collection department can analyze citizens' past feedback history and select the optimal collection method. For example, the feedback collection department can provide the optimal collection method based on the past feedback history. As a result, the administrative procedure support system according to the embodiment answers citizens' questions, provides necessary information, guides them through documents and procedures, solves their doubts and problems, provides information on policies and events, and collects feedback, thereby improving the efficiency of administrative procedures and strengthening citizen support.

[0070] The information provision unit can estimate the citizen's emotions and adjust the timing of information provision based on the estimated citizen's emotions. For example, if the citizen is feeling stressed, the information provision unit can have the generation AI provide information immediately and respond quickly. Furthermore, if the citizen is relaxed, the information provision unit can have the generation AI provide detailed information and explain things slowly. Furthermore, if the citizen is in a hurry, the information provision unit can have the generation AI provide concise information and respond quickly. This allows the timing of information provision to be adjusted according to the citizen's emotions, thereby providing information at a more appropriate time. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the information provision unit can be performed using, for example, AI, or without AI. For example, the information provision unit can input citizen's emotion data into the generation AI and cause the generation AI to adjust the timing of information provision based on the emotion.

[0071] The information provision unit can analyze the citizen's past question history and select the information provision method. For example, the information provision unit allows the generation AI to prioritize providing related information based on the content of questions that the citizen has frequently asked in the past. The information provision unit can also select the most effective information provision method for the generation AI from the citizen's past question history. The information provision unit can also analyze the citizen's past question history and allow the generation AI to provide information at the optimal timing. In this way, the optimal information provision method can be selected by analyzing the citizen's past question history. Some or all of the above-mentioned processing in the information provision unit may be performed, for example, using AI or may be performed without using AI. For example, the information provision unit can input the citizen's past question history data into the generation AI and have the generation AI select the optimal information provision method.

[0072] The information providing unit can filter information based on the citizen's current areas of interest when providing the information. For example, the information providing unit allows the generation AI to prioritize information related to areas in which the citizen is currently interested. The information providing unit can also filter information that the generation AI does not need based on the citizen's areas of interest. The information providing unit can also analyze the citizen's current areas of interest and allow the generation AI to provide the most appropriate information. In this way, by filtering information based on the citizen's current areas of interest, highly relevant information can be provided. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input citizen's area of ​​interest data to the generation AI and cause the generation AI to filter information based on the areas of interest.

[0073] When providing information, the information providing unit can select a means of providing information depending on the citizen's input method. For example, if the citizen uses voice input, the information providing unit can have the generation AI provide the information by voice. Furthermore, if the citizen uses text input, the information providing unit can have the generation AI provide the information by text. Furthermore, if the citizen uses image input, the information providing unit can have the generation AI provide the information using an image. This improves the convenience of information provision by selecting the optimal means of providing information depending on the citizen's input method. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input the citizen's input data into the generation AI and have the generation AI select an information providing means depending on the input method.

[0074] The information providing unit can estimate the citizen's emotions and determine the priority of information to be provided based on the estimated citizen's emotions. For example, if the citizen is feeling anxious, the information providing unit can cause the generation AI to prioritize important information. Furthermore, if the citizen is relaxed, the information providing unit can cause the generation AI to provide detailed information. Furthermore, if the citizen is in a hurry, the information providing unit can cause the generation AI to prioritize concise information. Thus, by determining the priority of information based on the citizen's emotions, important information can be provided preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the information providing unit can be performed using, for example, AI, or without AI. For example, the information providing unit can input citizen's emotion data into the generation AI and cause the generation AI to determine the priority of information based on emotions.

[0075] When providing information, the information providing unit can prioritize providing highly relevant information based on the citizen's geographical location information. For example, the information providing unit allows the generation AI to prioritize providing information related to the citizen's current location. The information providing unit can also allow the generation AI to provide optimal information based on the citizen's geographical location information. The information providing unit can also provide information on events and measures related to the citizen's current location. This makes it possible to provide highly relevant information by taking the citizen's geographical location information into consideration. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input the citizen's geographical location data into the generation AI and cause the generation AI to provide information based on the geographical location.

[0076] When providing information, the information providing unit can analyze the citizen's social media activity and provide related information. For example, the information providing unit analyzes the citizen's social media posts, and the generation AI provides the related information. The information providing unit can also provide the related information by referring to the activity of the citizen's friends on social media. The information providing unit can also provide the related information by the generation AI based on the citizen's social media check-in information. In this way, related information can be provided by analyzing the citizen's social media activity. Some or all of the above-mentioned processing in the information providing unit may be performed using AI, for example, or may be performed without using AI. For example, the information providing unit can input the citizen's social media data into the generation AI and cause the generation AI to provide information based on the social media activity.

[0077] When providing information, the information provision unit can customize the method of providing information by reflecting past feedback from citizens. For example, the information provision unit allows the generation AI to select the optimal method of providing information based on past feedback from citizens. The information provision unit can also allow the generation AI to adjust the timing of information provision by reflecting past feedback from citizens. The information provision unit can also analyze past feedback from citizens and allow the generation AI to provide optimal information. In this way, the method of providing information can be customized by reflecting past feedback from citizens. Some or all of the above-mentioned processing in the information provision unit may be performed using AI, for example, or may be performed without using AI. For example, the information provision unit can input past feedback data from citizens into the generation AI and cause the generation AI to customize the method of providing information based on the feedback.

[0078] The guidance unit can estimate the citizen's emotions and adjust the way the guidance is presented based on the estimated citizen's emotions. For example, if the citizen is nervous, the generation AI can provide a simple, highly visible presentation. Furthermore, if the citizen is relaxed, the generation AI can provide a presentation that includes detailed information. Furthermore, if the citizen is in a hurry, the generation AI can provide a concise, to-the-point presentation. This allows for more appropriate guidance by adjusting the way the guidance is presented based on the citizen's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the guidance unit can be performed using, for example, AI, or without AI. For example, the guidance unit can input citizen's emotion data into the generation AI and have the generation AI adjust the way the guidance is presented based on the emotion.

[0079] The guidance unit can adjust the level of detail of the guidance based on the importance of the procedure when providing guidance. For example, in the case of an important procedure, the generation AI of the guidance unit can provide detailed guidance. In addition, in the case of a simple procedure, the generation AI of the guidance unit can also provide concise guidance. In addition, in the guidance unit, the generation AI can adjust the level of detail of the guidance according to the importance of the procedure. In this way, by adjusting the level of detail of the guidance based on the importance of the procedure, appropriate guidance can be provided. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input procedure importance data to the generation AI and cause the generation AI to adjust the level of detail of the guidance based on the importance.

[0080] When providing guidance, the guidance unit can apply different guidance algorithms depending on the procedure category. For example, in the case of a procedure to obtain a resident registration certificate, the generation AI can apply a dedicated guidance algorithm. In addition, in the case of a procedure to notify a move of residence, the generation AI can apply a different guidance algorithm. In addition, the guidance unit can select the optimal guidance algorithm depending on the procedure category. In this way, optimal guidance can be provided by applying different guidance algorithms depending on the procedure category. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input procedure category data into the generation AI and have the generation AI apply a guidance algorithm based on the category.

[0081] When providing guidance, the guidance unit can improve the accuracy of the guidance by referring to the citizen's past guidance results. In the guidance unit, for example, the generation AI improves the accuracy of the guidance based on the citizen's past guidance results. The guidance unit can also analyze the citizen's past guidance results, and the generation AI can select the optimal guidance method. The guidance unit can also reflect the citizen's past guidance results and the generation AI can improve the accuracy of the guidance. In this way, the accuracy of the guidance is improved by referring to the citizen's past guidance results. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input the citizen's past guidance result data into the generation AI and have the generation AI improve the accuracy of the guidance.

[0082] The guidance unit can estimate the citizen's emotions and adjust the length of the guidance based on the estimated citizen's emotions. For example, if the citizen is in a hurry, the generation AI of the guidance unit can provide short, to-the-point guidance. Furthermore, if the citizen is relaxed, the generation AI can provide longer guidance with detailed explanations. Furthermore, if the citizen is excited, the generation AI can provide guidance with visually stimulating effects. By adjusting the length of the guidance based on the citizen's emotions, appropriate guidance can be provided. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the guidance unit can be performed using, for example, AI, or without AI. For example, the guidance unit can input citizen's emotion data into the generation AI and cause the generation AI to adjust the length of the guidance based on the emotion.

[0083] When providing guidance, the guidance unit can determine the priority of guidance based on the submission date of the procedure. For example, in the case of a procedure with an approaching deadline, the guidance unit has the generation AI provide guidance preferentially. In addition, in the case of a procedure with a distant submission date, the guidance unit can have the generation AI provide guidance later. In addition, in the guidance unit, the generation AI can determine the priority of guidance based on the submission date of the procedure. In this way, by determining the priority of guidance based on the submission date of the procedure, appropriate guidance can be provided. Some or all of the above-mentioned processing in the guidance unit may be performed using, for example, AI, or may be performed without using AI. For example, the guidance unit can input procedure submission date data into the generation AI and have the generation AI determine the priority of guidance based on the submission date.

[0084] The guidance unit can adjust the order of guidance based on the relevance of the procedures when providing guidance. For example, in the case of highly relevant procedures, the guidance unit has the generation AI provide guidance first. In addition, in the case of less relevant procedures, the guidance unit can have the generation AI provide guidance later. In addition, the guidance unit can have the generation AI adjust the order of guidance based on the relevance of the procedures. In this way, by adjusting the order of guidance based on the relevance of the procedures, appropriate guidance can be provided. Some or all of the above-mentioned processing in the guidance unit may be performed using AI, for example, or may be performed without using AI. For example, the guidance unit can input procedure relevance data into the generation AI and cause the generation AI to adjust the order of guidance based on the relevance.

[0085] When providing guidance, the guidance unit can adjust the use of technical terminology in the guidance depending on the citizen's level of expertise. For example, if the citizen has technical expertise, the guidance unit can have the generation AI provide guidance using technical terminology. Also, if the citizen does not have technical expertise, the guidance unit can have the generation AI provide guidance in simple language. Also, the guidance unit can have the generation AI adjust the use of technical terminology in the guidance depending on the citizen's level of expertise. This allows appropriate guidance to be provided by adjusting the use of technical terminology in the guidance depending on the citizen's level of expertise. Some or all of the above-mentioned processing in the guidance unit can be performed using AI, for example, or without AI. For example, the guidance unit can input citizen's expertise level data into the generation AI and cause the generation AI to adjust the use of technical terminology based on the expertise level.

[0086] The support unit can estimate the citizen's emotions and adjust the support method based on the estimated citizen's emotions. For example, if the citizen is stressed, the generation AI can provide simple and quick support. If the citizen is relaxed, the generation AI can provide detailed support. If the citizen is in a hurry, the generation AI can provide concise and to-the-point support. This allows appropriate support to be provided by adjusting the support method based on the citizen's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the support unit can be performed using, for example, AI, or without AI. For example, the support unit can input citizen's emotion data into the generation AI and have the generation AI adjust the support method based on the emotion.

[0087] When providing support, the support unit can analyze the citizen's past problem-solving history and select the optimal support method. For example, the support unit allows the generation AI to select the optimal support method based on the citizen's past problem-solving history. The support unit can also analyze the citizen's past problem-solving history and allow the generation AI to provide the most effective support method. The support unit can also allow the generation AI to select the optimal support method by referring to the citizen's past problem-solving history. In this way, the optimal support method can be selected by analyzing the citizen's past problem-solving history. Some or all of the above-mentioned processing in the support unit may be performed, for example, using AI or may be performed without using AI. For example, the support unit can input the citizen's past problem-solving history data into the generation AI and have the generation AI select a support method based on the problem-solving history.

[0088] During support, the support unit can customize the support means based on the citizen's current living situation. For example, the support unit allows the generation AI to select the optimal support means based on the citizen's current living situation. The support unit can also analyze the citizen's current living situation and allow the generation AI to provide the most effective support means. The support unit can also allow the generation AI to select the optimal support means based on the citizen's current living situation. In this way, optimal support can be provided by customizing the support means based on the citizen's current living situation. Some or all of the above-described processing in the support unit may be performed, for example, using AI or without AI. For example, the support unit can input the citizen's living situation data into the generation AI and have the generation AI customize the support means based on the living situation.

[0089] The support unit can improve the support method by reflecting citizen feedback during support. For example, the support unit allows the generation AI to improve the support method based on citizen feedback. The support unit can also analyze citizen feedback and allow the generation AI to select the optimal support method. The support unit can also customize the support method by reflecting citizen feedback. In this way, the support method can be improved by reflecting citizen feedback. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input citizen feedback data into the generation AI and cause the generation AI to improve the support method based on the feedback.

[0090] The support unit can estimate the citizen's emotions and determine support priorities based on the estimated citizen's emotions. For example, if the citizen is feeling anxious, the support unit can have the generation AI provide support preferentially. Furthermore, if the citizen is relaxed, the support unit can have the generation AI provide detailed support. Furthermore, if the citizen is in a hurry, the support unit can have the generation AI provide concise and quick support. This allows important support to be provided preferentially by determining support priorities based on the citizen's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the support unit can be performed using, for example, AI, or without AI. For example, the support unit can input citizen's emotion data into the generation AI and have the generation AI determine support priorities based on emotions.

[0091] When providing support, the support unit can select the optimal support method by taking into account the citizen's geographical location information. In the support unit, for example, the generation AI selects the optimal support method based on the citizen's current location. The support unit can also analyze the citizen's geographical location information and have the generation AI provide the most effective support method. The support unit can also have the generation AI provide relevant support information based on the citizen's current location. This makes it possible to select the optimal support method by taking into account the citizen's geographical location information. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the citizen's geographical location data into the generation AI and have the generation AI select a support method based on the geographical location.

[0092] When providing support, the support unit can analyze the citizen's social media activity and suggest support methods. For example, the support unit analyzes the citizen's social media posts, and the generation AI suggests the optimal support method. The support unit can also refer to the activity of the citizen's friends on social media to have the generation AI provide relevant support information. The support unit can also have the generation AI suggest the optimal support method based on the citizen's social media check-in information. In this way, the optimal support method can be suggested by analyzing the citizen's social media activity. Some or all of the above-mentioned processing in the support unit may be performed, for example, using AI, or may be performed without using AI. For example, the support unit can input the citizen's social media data into the generation AI and have the generation AI suggest support methods based on the social media activity.

[0093] The support unit can customize the support method by reflecting the citizen's past feedback when providing support. For example, the support unit allows the generation AI to select the optimal support method based on the citizen's past feedback. The support unit can also analyze the citizen's past feedback and allow the generation AI to provide the most effective support method. The support unit can also allow the generation AI to customize the support method by reflecting the citizen's past feedback. In this way, the support method can be customized by reflecting the citizen's past feedback. Some or all of the above-mentioned processing in the support unit may be performed using AI, for example, or may be performed without using AI. For example, the support unit can input the citizen's past feedback data into the generation AI and have the generation AI customize the support method based on the feedback.

[0094] The awareness raising unit can estimate the citizen's emotions and adjust the display method of the awareness message based on the estimated citizen's emotions. For example, if the citizen is nervous, the generation AI can provide a simple, highly visible display method. Furthermore, if the citizen is relaxed, the generation AI can provide a display method that includes detailed information. Furthermore, if the citizen is in a hurry, the generation AI can provide a concise, to-the-point display method. This allows for appropriate awareness to be provided by adjusting the display method of the awareness message based on the citizen's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the awareness raising unit can be performed using, for example, AI, or without AI. For example, the awareness raising unit can input citizen's emotion data into the generation AI and have the generation AI adjust the display method of the awareness message based on the emotion.

[0095] During enlightenment, the enlightenment unit can optimize the current enlightenment content by referring to past enlightenment data. For example, the enlightenment unit allows the generation AI to provide optimal enlightenment content based on past enlightenment data. The enlightenment unit can also analyze past enlightenment data and allow the generation AI to select the most effective enlightenment method. The enlightenment unit can also allow the generation AI to optimize the current enlightenment content by referring to past enlightenment data. In this way, the current enlightenment content can be optimized by referring to past enlightenment data. Some or all of the above-mentioned processing in the enlightenment unit may be performed, for example, using AI or may be performed without using AI. For example, the enlightenment unit can input past enlightenment data into the generation AI and cause the generation AI to optimize the enlightenment content.

[0096] The awareness department can apply different awareness methods to each category of measures and events during awareness generation. For example, in the case of awareness generation related to measures, the generation AI can apply a dedicated awareness method. In addition, in the case of awareness generation related to events, the awareness department can also have the generation AI apply a different awareness method. In addition, the awareness department can have the generation AI select the optimal awareness method depending on the category of the measures and events. In this way, optimal awareness can be provided by applying different awareness methods to each category of measures and events. Some or all of the above-mentioned processing in the awareness department may be performed using, for example, AI, or may be performed without using AI. For example, the awareness department can input category data of measures and events into the generation AI and have the generation AI apply an awareness method based on the category.

[0097] The awareness department can customize the awareness content by taking into account the citizen's attribute information when raising awareness. For example, the awareness department allows the generation AI to provide the most appropriate awareness content based on the citizen's age and gender. The awareness department can also allow the generation AI to provide the most appropriate awareness content based on the citizen's occupation and interests. The awareness department can also analyze the citizen's attribute information and customize the most appropriate awareness content based on the citizen's attribute information. In this way, the most appropriate awareness content can be customized by taking into account the citizen's attribute information. Some or all of the above-mentioned processing in the awareness department may be performed using AI, for example, or may be performed without using AI. For example, the awareness department can input citizen's attribute information data into the generation AI and have the generation AI customize the awareness content based on the attribute information.

[0098] The awareness raising unit can estimate citizens' emotions and adjust the importance of awareness content based on the estimated citizens' emotions. For example, if a citizen is feeling anxious, the awareness raising unit can have the generation AI prioritize providing important awareness content. Furthermore, if a citizen is relaxed, the awareness raising unit can have the generation AI provide detailed awareness content. Furthermore, if a citizen is in a hurry, the awareness raising unit can have the generation AI provide concise, to-the-point awareness content. This allows for adjusting the importance of awareness content based on citizens' emotions, thereby prioritizing the provision of important awareness content. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the awareness raising unit can be performed using, for example, AI, or without AI. For example, the awareness raising unit can input citizens' emotion data into the generation AI and have the generation AI adjust the importance of awareness content based on emotions.

[0099] The awareness department can determine the priority of awareness based on the timing of measures and events during awareness raising. For example, in the case of an upcoming event, the awareness department can have the generation AI prioritize awareness raising. In addition, in the case of an event that is far away, the awareness department can have the generation AI postpone awareness raising. In addition, the awareness department can have the generation AI determine the priority of awareness raising based on the timing of measures and events. In this way, appropriate awareness raising can be provided by determining the priority of awareness raising based on the timing of measures and events. Some or all of the above-mentioned processing in the awareness department can be performed using, for example, AI, or can be performed without using AI. For example, the awareness department can input data on the timing of measures and events into the generation AI and have the generation AI determine the priority of awareness raising based on the timing.

[0100] The enlightenment unit can optimize the enlightenment content by referring to relevant market data during enlightenment. For example, the enlightenment unit allows the generation AI to provide optimal enlightenment content based on relevant market data. The enlightenment unit can also analyze the relevant market data and allow the generation AI to select the most effective enlightenment method. The enlightenment unit can also allow the generation AI to optimize the current enlightenment content by referring to the relevant market data. In this way, the enlightenment content can be optimized by referring to the relevant market data. Some or all of the above-mentioned processing in the enlightenment unit may be performed, for example, using AI or may be performed without using AI. For example, the enlightenment unit can input relevant market data into the generation AI and cause the generation AI to optimize the enlightenment content.

[0101] The awareness department can adjust the awareness content during awareness raising, taking into account the technical maturity of the measures and events. For example, in the case of a technically mature measure, the awareness department can have the generation AI provide detailed awareness content. In addition, in the case of a technically immature measure, the awareness department can have the generation AI provide concise awareness content. In addition, the awareness department can have the generation AI adjust the awareness content based on the technical maturity of the measure or event. This makes it possible to provide appropriate awareness content by taking into account the technical maturity of the measure or event. Some or all of the above-mentioned processing in the awareness department can be performed, for example, using AI, or can be performed without using AI. For example, the awareness department can input technical maturity data of the measure or event into the generation AI, and have the generation AI adjust the awareness content based on the technical maturity.

[0102] The feedback collection unit can estimate the citizen's emotions and adjust the feedback collection method based on the estimated citizen's emotions. For example, if the citizen is feeling anxious, the generation AI can provide a simple and quick feedback collection method. Alternatively, if the citizen is relaxed, the generation AI can provide a detailed feedback collection method. Alternatively, if the citizen is in a hurry, the generation AI can provide a concise and to-the-point feedback collection method. This allows appropriate feedback to be collected by adjusting the feedback collection method based on the citizen's emotions. The emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the feedback collection unit can be performed using AI, for example, or without AI. For example, the feedback collection unit can input citizen's emotion data into the generation AI and cause the generation AI to adjust the feedback collection method based on the emotion.

[0103] When collecting feedback, the feedback collection unit can analyze the citizen's past feedback history and select the optimal collection method. In the feedback collection unit, for example, the generation AI selects the optimal collection method based on the citizen's past feedback history. The feedback collection unit can also analyze the citizen's past feedback history and provide the generation AI with the most effective collection method. The feedback collection unit can also select the optimal collection method by referring to the citizen's past feedback history. In this way, the optimal collection method can be selected by analyzing the citizen's past feedback history. Some or all of the above-mentioned processing in the feedback collection unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback collection unit can input the citizen's past feedback history data into the generation AI and cause the generation AI to select a collection method based on the feedback history.

[0104] The feedback collection unit can customize the collection means based on the citizen's current living situation when collecting feedback. In the feedback collection unit, for example, the generation AI selects the optimal collection means based on the citizen's current living situation. The feedback collection unit can also analyze the citizen's current living situation and have the generation AI provide the most effective collection means. The feedback collection unit can also have the generation AI select the optimal collection means based on the citizen's current living situation. In this way, optimal feedback can be collected by customizing the collection means based on the citizen's current living situation. Some or all of the above-mentioned processing in the feedback collection unit may be performed, for example, using AI or may be performed without using AI. For example, the feedback collection unit can input citizen's living situation data into the generation AI and have the generation AI customize the collection means based on the living situation.

[0105] The feedback collection unit can improve the collection method by reflecting citizen feedback when collecting feedback. In the feedback collection unit, for example, the generation AI improves the collection method based on citizen feedback. The feedback collection unit can also analyze citizen feedback and the generation AI can select the optimal collection method. The feedback collection unit can also customize the collection method by reflecting citizen feedback. In this way, the collection method can be improved by reflecting citizen feedback. Some or all of the above-mentioned processing in the feedback collection unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback collection unit can input citizen feedback data into the generation AI and cause the generation AI to improve the collection method based on the feedback.

[0106] The feedback collection unit can estimate the citizen's emotions and determine the priority of feedback collection based on the estimated citizen's emotions. For example, if the citizen is feeling anxious, the feedback collection unit can cause the generation AI to prioritize feedback collection. Furthermore, if the citizen is relaxed, the feedback collection unit can cause the generation AI to collect detailed feedback. Furthermore, if the citizen is in a hurry, the feedback collection unit can cause the generation AI to collect concise and to-the-point feedback. Thus, by determining the priority of feedback collection based on the citizen's emotions, important feedback can be collected preferentially. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the feedback collection unit can be performed using, for example, AI, or without AI. For example, the feedback collection unit can input citizen's emotion data into the generation AI and cause the generation AI to determine the priority of feedback collection based on emotions.

[0107] When collecting feedback, the feedback collection unit can select the optimal collection method by taking into account the citizen's geographical location information. In the feedback collection unit, for example, the generation AI selects the optimal collection method based on the citizen's current location. The feedback collection unit can also analyze the citizen's geographical location information and have the generation AI provide the most effective collection method. The feedback collection unit can also provide the generation AI with a relevant feedback collection method based on the citizen's current location. This allows the optimal collection method to be selected by taking into account the citizen's geographical location information. Some or all of the above-mentioned processing in the feedback collection unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback collection unit can input the citizen's geographical location data into the generation AI and have the generation AI select a collection method based on the geographical location.

[0108] When collecting feedback, the feedback collection unit can analyze the citizen's social media activity and suggest a collection method. For example, the feedback collection unit analyzes the content of the citizen's social media posts, and the generation AI suggests the optimal collection method. The feedback collection unit can also refer to the activity of the citizen's friends on social media to provide a relevant feedback collection method. The feedback collection unit can also have the generation AI suggest the optimal collection method based on the citizen's social media check-in information. In this way, the optimal collection method can be suggested by analyzing the citizen's social media activity. Some or all of the above-mentioned processing in the feedback collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback collection unit can input the citizen's social media data into the generation AI and have the generation AI suggest collection methods based on the social media activity.

[0109] When collecting feedback, the feedback collection unit can customize the collection method by reflecting citizens' past feedback. In the feedback collection unit, for example, the generation AI selects the optimal collection method based on citizens' past feedback. The feedback collection unit can also analyze citizens' past feedback and have the generation AI provide the most effective collection method. In addition, the feedback collection unit can also have the generation AI customize the collection method by reflecting citizens' past feedback. In this way, the collection method can be customized by reflecting citizens' past feedback. Some or all of the above-mentioned processing in the feedback collection unit may be performed using AI, for example, or may be performed without using AI. For example, the feedback collection unit can input citizens' past feedback data into the generation AI and have the generation AI customize the collection method based on the feedback. === Hard Collateral 1-1 === For example, each of a plurality of elements including an information providing unit, a guidance unit, a support unit, an education unit, and a feedback collecting unit is realized by at least one of the smart device 14 and the data processing device 12. For example, the information providing unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The guidance unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The support unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The education unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The feedback collecting unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === For example, each of a plurality of elements including an information providing unit, a guidance unit, a support unit, an enlightenment unit, and a feedback collecting unit is realized by at least one of the smart glasses 214 and the data processing device 12. For example, the information providing unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The guidance unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The support unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The enlightenment unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The feedback collecting unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === For example, each of a plurality of elements including an information providing unit, a guidance unit, a support unit, an education unit, and a feedback collecting unit is realized by at least one of the headset type terminal 314 and the data processing device 12. For example, the information providing unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The guidance unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The support unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The education unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The feedback collecting unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === For example, each of a plurality of elements including an information providing unit, a guidance unit, a support unit, an education unit, and a feedback collecting unit is realized by at least one of the robot 414 and the data processing device 12. For example, the information providing unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The guidance unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The support unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The education unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The feedback collecting unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] The information provision unit can adjust the content of the information provided taking into account the citizen's health condition. For example, if a citizen asks a question about health, the generation AI will prioritize providing health-related information. The information provision unit can also have the generation AI provide appropriate health advice based on the citizen's health condition. Furthermore, the information provision unit can analyze the citizen's health data and have the generation AI provide optimal health information. This allows the provision of more appropriate information by adjusting the content of the information provided based on the citizen's health condition.

[0112] The information provision unit can estimate citizens' emotions and adjust the format of information provision based on the estimated citizens' emotions. For example, if a citizen is feeling anxious, the generation AI can provide information in a visually reassuring design. If a citizen is relaxed, the generation AI can provide information in a format that includes detailed information. Furthermore, if a citizen is in a hurry, the generation AI can provide information in a concise and to-the-point format. This allows for more effective information provision by adjusting the format of information provision based on citizens' emotions.

[0113] The guidance unit can analyze the citizen's past behavior history and select the optimal guidance method. For example, based on what procedures the citizen has performed in the past, the generation AI will prioritize providing guidance on related procedures. The guidance unit can also analyze the citizen's past behavior history and the generation AI can select the most effective guidance method. Furthermore, the guidance unit can refer to the citizen's past behavior history and the generation AI can provide guidance at the optimal timing. In this way, the optimal guidance method can be selected by analyzing the citizen's past behavior history.

[0114] The guidance section can estimate the citizen's emotions and adjust the order of guidance based on the estimated citizen's emotions. For example, if the citizen is nervous, the generation AI can guide them through important procedures first. Alternatively, if the citizen is relaxed, the generation AI can guide them through detailed procedures in an orderly manner. Furthermore, if the citizen is in a hurry, the generation AI can prioritize simple procedures that focus on the main points. This allows the provision of more appropriate guidance by adjusting the order of guidance based on the citizen's emotions.

[0115] The support department can customize the content of support based on the citizen's living environment. For example, if the citizen lives in an urban area, the generation AI can provide support information specialized for urban areas. Also, if the citizen lives in a rural area, the generation AI can provide support information specialized for rural areas. Furthermore, the support department can analyze the citizen's living environment, and the generation AI can select the optimal support method. This allows the support content to be customized based on the citizen's living environment, making it possible to provide more appropriate support.

[0116] The support department can estimate the emotions of citizens and prioritize support based on the estimated emotions of citizens. For example, if a citizen is feeling anxious, the generation AI can provide support first. If a citizen is relaxed, the generation AI can also provide detailed support. Furthermore, if a citizen is in a hurry, the generation AI can provide concise and quick support. This allows support prioritization based on citizens' emotions, enabling important support to be provided first.

[0117] The Public Awareness Department can customize the public awareness content based on the hobbies and interests of citizens. For example, if a citizen is interested in sports, the generation AI can prioritize providing sports-related public awareness content. Also, if a citizen is interested in cultural activities, the generation AI can provide public awareness content related to cultural activities. Furthermore, the Public Awareness Department can analyze citizens' hobbies and interests, and the generation AI can provide the most appropriate public awareness content. This allows for more effective public awareness by customizing the public awareness content based on citizens' hobbies and interests.

[0118] The Public Awareness Department can estimate citizens' emotions and adjust the way public awareness is displayed based on the estimated emotions. For example, if a citizen is nervous, the generation AI can provide a simple, highly visible display. If a citizen is relaxed, the generation AI can provide a display that includes detailed information. Furthermore, if a citizen is in a hurry, the generation AI can provide a concise, to-the-point display. This allows appropriate public awareness to be provided by adjusting the way public awareness is displayed based on citizens' emotions.

[0119] The feedback collection unit can analyze citizens' past feedback history and select the optimal collection method. For example, the generation AI selects the optimal collection method based on citizens' past feedback history. The feedback collection unit can also analyze citizens' past feedback history and the generation AI can provide the most effective collection method. Furthermore, the feedback collection unit can also refer to citizens' past feedback history and the generation AI can select the optimal collection method. In this way, the optimal collection method can be selected by analyzing citizens' past feedback history.

[0120] The feedback collection unit can estimate citizens' emotions and adjust the feedback collection method based on the estimated citizens' emotions. For example, if citizens are feeling anxious, the generation AI can provide a simple and quick feedback collection method. If citizens are relaxed, the generation AI can provide a detailed feedback collection method. Furthermore, if citizens are in a hurry, the generation AI can provide a concise and to-the-point feedback collection method. In this way, appropriate feedback can be collected by adjusting the feedback collection method based on citizens' emotions.

[0121] The processing flow of the second embodiment will be briefly explained below.

[0122] Step 1: The information provision department answers citizens' questions and provides them with the necessary information. For example, it uses generative AI to generate appropriate answers to citizens' questions and provides information on procedures for obtaining a resident registration card and notifying a change of address. It also analyzes citizens' past question history and selects the most appropriate method of providing information. Step 2: The guidance section provides guidance on the necessary documents and procedures based on the information provided by the information provision section. For example, it uses generation AI to guide citizens through the necessary documents and procedural steps to proceed with a procedure, adjusting the level of detail in the guidance based on the importance of the procedure. It also estimates the citizen's emotions and adjusts the way the guidance is presented based on the estimated emotions. Step 3: The support department solves the citizen's questions and problems based on the information provided by the information department. For example, it uses generative AI to provide appropriate solutions and analyzes the citizen's past problem-solving history to select the most appropriate support method. It also estimates the citizen's emotions and adjusts the support method based on the estimated emotions. Step 4: The Public Awareness Department provides information on local government policies, events, important notices, etc. based on the information resolved by the Support Department. For example, they use generative AI to provide information on policies and events, estimate citizen sentiment, and adjust the display method. They also refer to past public awareness data to optimize current public awareness content. Step 5: The Feedback Collection Department collects feedback and requests from citizens based on the information provided by the Public Awareness Department. For example, it uses generative AI to collect opinions and requests from citizens, estimates their sentiments, and adjusts the collection method. It also analyzes citizens' past feedback history to select the optimal collection method.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 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.

[0129] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0143] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0144] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0146] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0147] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0150] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0153] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0159] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0160] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0163] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0165] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0166] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0167] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0168] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0169] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0170] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0171] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0173] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0175] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0176] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0178] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0179] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0180] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0184] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0185] 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.

[0186] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0187] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0188] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0189] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0191] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0192] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0193] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0194] [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. The Information Department answers questions from citizens and provides information. a guidance unit that provides guidance on necessary documents or procedures based on the information provided by the information providing unit; a support department that solves questions and problems of citizens based on the information provided by the information providing department; an awareness department that provides information on local government policies, events, and important notices based on the information resolved by the support department; a feedback collection unit that collects feedback and requests from citizens based on the information provided by the awareness-raising unit. A system characterized by:

2. The information providing unit Estimate public sentiment and adjust the timing of information provision based on the estimated public sentiment 2. The system of claim 1.

3. The information providing unit Analyze citizens' past question history and select the method of providing information 2. The system of claim 1.

4. The information providing unit Filter information based on current citizen interests at the time of submission 2. The system of claim 1.

5. The information providing unit When providing information, the means of providing it will be selected according to the citizen's input method.

2. The system of claim 1.

6. The information providing unit Estimate public sentiment and prioritize information based on the estimated public sentiment 2. The system of claim 1.

7. The information providing unit Prioritize relevant information based on citizens' geographic location when providing information 2. The system of claim 1.

8. The information providing unit When providing information, analyze citizens' social media activity and provide relevant information 2. The system of claim 1.

Images