system

Abstract

The system according to this embodiment aims to provide residents with easy-to-understand explanations of policies and to effectively collect and utilize residents' opinions. [Solution] The system according to the embodiment comprises an explanation unit, a multilingual unit, an event unit, a collection unit, an analysis unit, and an improvement unit. The explanation unit explains technical terms in response to residents' questions. The multilingual unit provides the information explained by the explanation unit in multiple languages. The event unit provides event information based on the information provided by the multilingual unit. The collection unit collects residents' opinions based on the information provided by the event unit. The analysis unit analyzes the opinions collected by the collection unit. The improvement unit improves policies based on the opinions analyzed by the analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult for local governments to convey policy explanations to residents, and it is difficult to effectively collect and utilize residents' opinions.

[0005] The system according to the embodiment aims to clearly explain policies to residents and effectively collect and utilize residents' opinions.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an explanation unit, a multilingual unit, an event unit, a collection unit, an analysis unit, and an improvement unit. The explanation unit explains technical terms in response to residents' questions. The multilingual unit provides the information explained by the explanation unit in multiple languages. The event unit provides event information based on the information provided by the multilingual unit. The collection unit collects residents' opinions based on the information provided by the event unit. The analysis unit analyzes the opinions collected by the collection unit. The improvement unit improves policies based on the opinions analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can explain policies to residents in an easy-to-understand manner and effectively collect and utilize residents' opinions. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The regional integrated AI agent system according to an embodiment of the present invention is a system for local governments and is an integrated system that improves the quality of life for citizens through the cooperation of six AI agents (citizen explanation, multilingual support, event coordination, citizen participation promotion, emotion recognition, and resident feedback). First, the regional integrated AI agent system has a citizen explanation agent that effectively explains the local government's policies to citizens and explains technical terms in an easy-to-understand manner in response to residents' questions. Next, the multilingual support agent explains the city's policies in multiple languages, making them easy to understand for foreign residents as well. Furthermore, the event coordination AI guide provides policy and event information at local events and information sessions, complementing resident support. The citizen participation promotion system provides functions that allow residents to give opinions on policy proposals, vote, and comment. The emotion recognition AI agent analyzes residents' emotions and adjusts the content of explanations in real time. Finally, the resident feedback AI report system aggregates questions and opinions from residents and automatically generates and provides reports for local government officials. Through this system, local governments aim to develop their regions together with local residents and build a sustainable and harmonious society. This enables regionally integrated AI agent systems to help local governments develop their communities together with residents and build sustainable and harmonious societies.

[0029] The regional integrated AI agent system according to this embodiment comprises an explanation unit, a multilingual unit, an event unit, a collection unit, an analysis unit, and an improvement unit. The explanation unit explains technical terms in response to residents' questions. The explanation unit can explain technical terms such as medical terms, legal terms, and technical terms. The explanation unit explains technical terms in an easy-to-understand manner in response to residents' questions. For example, when explaining medical terms, the explanation unit can explain specific symptoms and treatment methods. Also, when explaining legal terms, the explanation unit can explain specific legal procedures and rights and obligations. Furthermore, when explaining technical terms, the explanation unit can explain specific technological mechanisms and application examples. The multilingual unit provides the information explained by the explanation unit in multiple languages. The multilingual unit can provide information in multiple languages ​​such as English, Chinese, and Spanish. The multilingual unit provides information in multiple languages ​​according to the language of the residents. For example, when providing information in English, the multilingual unit can translate and explain technical terms in English. Furthermore, the Multilingual Department can translate and explain technical terms in Chinese when providing information in Chinese. Additionally, the Multilingual Department can translate and explain technical terms in Spanish when providing information in Spanish. The Events Department provides event information based on the information provided by the Multilingual Department. For example, the Events Department can provide information on local events, seminars, workshops, etc. The Events Department provides event information according to the interests of residents. For example, when providing information on local events, the Events Department can explain the date, time, location, and how to participate. Also, when providing information on seminars, the Events Department can explain the instructors, content, and participation fees. Furthermore, when providing information on workshops, the Events Department can explain the content, target audience, and application methods. The Collection Department collects residents' opinions based on the information provided by the Events Department. The Collection Department can collect residents' opinions in the form of questionnaires, feedback, and suggestions, for example. The Collection Department efficiently collects residents' opinions. For example, the Collection Department can collect residents' opinions by conducting questionnaires.Furthermore, the Collection Department can collect residents' opinions by setting up feedback forms. In addition, the Collection Department can collect residents' suggestions by setting up suggestion boxes. The Analysis Department analyzes the opinions collected by the Collection Department. The Analysis Department can, for example, compile survey results, analyze the content of feedback, and classify suggestions. The Analysis Department conducts a detailed analysis of residents' opinions. For example, the Analysis Department can compile survey results to grasp trends in residents' opinions. In addition, the Analysis Department can analyze the content of feedback to grasp the specific content of residents' opinions. Furthermore, the Analysis Department can classify suggestions to grasp the types and frequency of suggestions from residents. The Improvement Department improves policies based on the opinions analyzed by the Analysis Department. The Improvement Department can, for example, improve policies such as regional development policies, welfare policies, and environmental protection policies. The Improvement Department improves policies by reflecting residents' opinions. For example, when improving regional development policies, the Improvement Department can formulate specific policies by referring to residents' opinions. In addition, when improving welfare policies, the Improvement Department can formulate specific policies by referring to residents' opinions. Furthermore, the improvement department can formulate specific measures by taking residents' opinions into account when improving environmental protection policies. As a result, the regional integrated AI agent system according to this embodiment can explain technical terms in response to residents' questions, provide information in multiple languages, provide event information, collect residents' opinions, analyze those opinions, and improve policies.

[0030] The explanatory unit explains technical terms in response to residents' questions. For example, it can explain medical, legal, and technical terms. Specifically, if a resident asks a medical question, the unit will provide a detailed explanation of the disease, its symptoms, and treatment methods. For instance, it will explain the symptoms and treatment of a particular disease in easy-to-understand, general terms. If a legal question is asked, it will explain specific legal terms and procedures with concrete examples. For example, it will explain the contents of a contract and the rights and obligations of a resident using concrete examples to make them easy to understand. Furthermore, if a technical question is asked, it will explain specific technical terms and their applications using diagrams and videos. For example, it will explain the mechanisms of new technologies and their applications in a visually easy-to-understand way. To ensure that technical terms are explained clearly in response to residents' questions, the explanatory unit can utilize AI to grasp the residents' level of understanding in real time and adjust the explanation as needed. For example, if a resident finds something difficult to understand, the AI ​​will detect this reaction and provide simpler language or additional explanations. Furthermore, the explanatory unit can save residents' question history and refer to past questions to provide more appropriate answers. This allows the explanatory unit to flexibly and effectively explain technical terms in order to deepen residents' understanding.

[0031] The multilingual section provides information explained by the explanatory section in multiple languages. For example, the multilingual section can provide information in languages ​​such as English, Chinese, and Spanish. Specifically, the multilingual section uses AI to automatically translate information according to the user's language. For example, if a user selects English, the information explained by the explanatory section is translated into English, and technical terms are explained clearly in English. If a user selects Chinese, the information is translated into Chinese, and technical terms are explained clearly in Chinese. Furthermore, if a user selects Spanish, the information is translated into Spanish, and technical terms are explained clearly in Spanish. The multilingual section utilizes AI to accurately understand context and the meaning of technical terms, enabling it to provide natural translations tailored to the user's language. For example, to provide accurate translations of technical terms such as medical and legal terms, it uses AI models with specialized knowledge. The multilingual section can also provide information via audio using speech synthesis technology tailored to the user's language. For example, if a user prefers to receive information via audio, the AI ​​automatically translates the information and provides it in audio format. This allows the multilingual department to provide information flexibly and effectively in accordance with the language of the residents.

[0032] The Events Department provides event information based on information provided by the Multilingual Department. For example, the Events Department can provide information on local events, seminars, workshops, and other events. Specifically, the Events Department uses AI to analyze residents' interests and past participation history in order to provide event information tailored to their interests. For example, it provides relevant event information based on a resident's past event participation history. Furthermore, it can customize and individually provide event information according to residents' interests. For example, if a resident is interested in health, it provides information on health-related seminars and workshops. If a resident is interested in environmental protection, it provides information on environmental protection-related events. In addition, the Events Department can provide event information in multiple languages, depending on the resident's language. For example, it provides event information in multiple languages ​​such as English, Chinese, and Spanish, in a format that is easy for residents to understand. The Events Department can use AI to automatically collect, classify, and provide event information tailored to residents' interests and language. This allows the Events Department to flexibly and effectively provide event information that aligns with residents' interests.

[0033] The collection department collects residents' opinions based on information provided by the event department. The collection department can collect residents' opinions in various forms, such as questionnaire responses, feedback, and suggestions. Specifically, to collect feedback from residents who participated in an event, the collection department can use AI to automatically generate questionnaires and distribute them to residents. For example, it can automatically send questionnaires after the event to collect residents' opinions. The collection department can also collect residents' opinions by setting up a feedback form where residents can freely submit their opinions. For example, it can provide a form where residents can freely write their opinions and suggestions regarding the event. Furthermore, the collection department can collect residents' suggestions by setting up a suggestion box where residents can submit suggestions. For example, it can provide a suggestion box where residents can propose areas for improvement in the community or new ideas. The collection department can use AI to efficiently collect, classify, and store residents' opinions. For example, it can automatically classify the collected opinions and prioritize processing important opinions and suggestions. The collection department can also take measures to anonymize residents' opinions and protect their privacy. This allows the collection department to efficiently and effectively gather residents' opinions and use them to improve the entire system.

[0034] The Analysis Department analyzes the opinions collected by the Collection Department. For example, the Analysis Department can perform tasks such as aggregating survey results, analyzing the content of feedback, and classifying proposals. Specifically, the Analysis Department aggregates collected survey results and uses AI to automatically analyze the data in order to understand trends in residents' opinions. For example, it analyzes residents' satisfaction levels and areas of interest based on survey results. Furthermore, the Analysis Department utilizes natural language processing technology to analyze the content of feedback in detail and understand the specific content of residents' opinions. For example, it analyzes the text data of feedback to extract residents' opinions and feelings. In addition, the Analysis Department uses clustering technology to classify proposals and understand the types and frequency of residents' suggestions. For example, it automatically classifies the content of proposals and identifies common themes and trends. The Analysis Department can use AI to efficiently analyze collected opinions and extract important information. For example, it can identify local issues and areas for improvement based on residents' opinions and formulate specific countermeasures. The Analysis Department can also visualize the analysis results and provide tools for reporting them clearly to stakeholders. This allows the analysis department to thoroughly analyze the collected opinions and use them to improve the entire system.

[0035] The Improvement Department improves policies based on feedback analyzed by the Analysis Department. The Improvement Department can improve policies such as regional development, welfare, and environmental protection. Specifically, the Improvement Department uses AI to formulate concrete policies that reflect residents' opinions. For example, when improving regional development policies, it plans new events and projects based on residents' opinions. Similarly, when improving welfare policies, it considers residents' opinions to enhance welfare services and introduce new support programs. Furthermore, when improving environmental protection policies, it considers residents' opinions to promote environmental protection activities and plan new environmental protection projects. The Improvement Department can use AI to evaluate the effectiveness of policies and modify them as needed, based on residents' opinions. For example, it can collect residents' opinions after the implementation of a policy and evaluate its effectiveness. The Improvement Department can also make the policy improvement process transparent and report the progress of policy improvements to residents. This allows the Improvement Department to flexibly and effectively improve policies that reflect residents' opinions, contributing to regional development and increased resident satisfaction.

[0036] The data collection unit can aggregate questions and opinions from residents and automatically generate and provide reports for local government officials. For example, the data collection unit can aggregate questions and opinions from residents into a database and generate reports using a report generation algorithm. The data collection unit analyzes the content of the questions and opinions, extracts important information, and compiles it into a report. For example, the data collection unit can classify questions and opinions from residents into categories and generate a report for each category. The data collection unit can also analyze the frequency and trends of questions and opinions and compile them into a report as statistical data. Furthermore, the data collection unit can summarize the content of the questions and opinions and compile the key points into a report. This allows for the efficient aggregation of questions and opinions from residents and the provision of reports to local government officials, which can be used to improve policies. Report generation may be performed using AI, for example, or without AI. For example, the data collection unit can input questions and opinions from residents into a database and generate reports using a report generation algorithm.

[0037] The explanation unit can analyze residents' past question history and select the most effective explanation method. For example, the explanation unit can store the content of questions residents have asked in the past in a database and analyze the question history. Based on the past question history, the explanation unit can provide relevant information in advance. For example, by providing information related to the content of questions residents have asked in the past in advance, the explanation unit can deepen residents' understanding. In addition, the explanation unit can prioritize using explanation methods that residents found easy to understand in the past. Furthermore, the explanation unit can provide a summary of frequently asked questions from the residents' question history. This allows the explanation unit to select the most effective explanation method and deepen residents' understanding by analyzing the residents' past question history. The analysis of the question history may be performed using AI, or it may be performed without AI. For example, the explanation unit can input residents' past question history into a database and have AI perform the analysis of the question history.

[0038] The explanatory unit can provide additional relevant information during the explanation based on the residents' areas of interest. For example, the explanatory unit can provide information related to policies that residents are interested in. The explanatory unit can provide additional relevant information based on the residents' areas of interest. For example, the explanatory unit can deepen residents' understanding by providing information related to policies that residents are interested in. The explanatory unit can also add detailed data on topics that residents have shown interest in. Furthermore, the explanatory unit can introduce relevant events and activities based on the residents' areas of interest. This allows for a deeper understanding of residents by providing additional relevant information based on their areas of interest. The identification of areas of interest may be done using AI, for example, or without using AI. For example, the explanatory unit can identify residents' areas of interest from survey results or past question history and provide relevant information.

[0039] The explanatory unit can provide region-specific information by considering the geographical location of residents during the explanation. For example, the explanatory unit can provide policy information related to the area where residents live. The explanatory unit provides region-specific information based on the geographical location of residents. For example, by providing policy information related to the area where residents live, the explanatory unit can deepen residents' understanding. The explanatory unit can also add information about events held in the residents' area. Furthermore, the explanatory unit can provide information about issues specific to the residents' area. In this way, by providing region-specific information while considering the geographical location of residents, residents' understanding can be deepened. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the explanatory unit can acquire residents' geographical location information from GPS data or address information and provide region-specific information.

[0040] The explanatory department can analyze residents' social media activity and provide relevant information during the explanation. For example, the explanatory department can provide information related to topics that residents have shown interest in on social media. The explanatory department can analyze residents' social media activity and provide relevant information. For example, by providing information related to topics that residents have shown interest in on social media, the explanatory department can deepen residents' understanding. The explanatory department can also provide information on issues that are frequently mentioned in residents' social media activity. Furthermore, the explanatory department can provide relevant policy information based on residents' social media activity. In this way, by analyzing residents' social media activity and providing relevant information, residents can deepen their understanding. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the explanatory department can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and provide relevant information.

[0041] The multilingual department can adjust the level of detail in explanations according to the language proficiency of the residents when providing multilingual support. For example, if the residents have a low language proficiency, the department can provide explanations in simple language. The multilingual department can adjust the level of detail in explanations according to the language proficiency of the residents. For example, if the residents have a low language proficiency, the department can provide explanations in simple language to deepen their understanding. Conversely, if the residents have a high language proficiency, the department can provide detailed explanations that include specialized terminology. Furthermore, the multilingual department can select an appropriate level of detail in explanations according to the language proficiency of the residents. In this way, by adjusting the level of detail in explanations according to the language proficiency of the residents, their understanding can be deepened. The evaluation of language proficiency may be performed using AI, for example, or without using AI. For example, the multilingual department can evaluate the language proficiency of residents from language test results or self-reported information and adjust the level of detail in explanations accordingly.

[0042] The multilingual department can select appropriate expressions according to the cultural background of the residents when providing multilingual support. For example, the multilingual department uses expressions that take into account the cultural background of the residents. The multilingual department selects appropriate expressions according to the cultural background of the residents. For example, by using expressions that take into account the cultural background of the residents, the multilingual department can deepen the understanding of the residents. In addition, the multilingual department can provide explanations that take into account the customs and values ​​unique to the culture of the residents. Furthermore, the multilingual department can select appropriate expressions based on the cultural background of the residents. This allows for a deeper understanding of the residents by selecting appropriate expressions according to their cultural background. Identifying cultural backgrounds may be done using AI, for example, or without using AI. For example, the multilingual department can identify the cultural background of residents from their nationality, religion, and customs, and select appropriate expressions.

[0043] The multilingual unit can provide region-specific information by considering the geographical location of residents when providing multilingual support. For example, the multilingual unit can provide policy information related to the area where residents live in multiple languages. The multilingual unit provides region-specific information based on the geographical location of residents. For example, by providing policy information related to the area where residents live in multiple languages, the multilingual unit can deepen residents' understanding. In addition, the multilingual unit can add information about events held in the residents' area in multiple languages. Furthermore, the multilingual unit can provide information about issues specific to the residents' area in multiple languages. This allows for a deeper understanding of residents by providing region-specific information while considering their geographical location. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the multilingual unit can acquire residents' geographical location information from GPS data or address information and provide region-specific information.

[0044] The multilingual department can analyze residents' social media activity and provide relevant information when providing multilingual support. For example, the multilingual department can provide information in multiple languages ​​related to topics that residents have shown interest in on social media. The multilingual department can analyze residents' social media activity and provide relevant information. For example, by providing information in multiple languages ​​related to topics that residents have shown interest in on social media, the multilingual department can deepen residents' understanding. The multilingual department can also provide information in multiple languages ​​about issues that are frequently mentioned in residents' social media activity. Furthermore, the multilingual department can provide information in multiple languages ​​based on residents' social media activity. In this way, by analyzing residents' social media activity and providing relevant information, residents' understanding can be deepened. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the multilingual department can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and provide relevant information.

[0045] The Events Department can analyze residents' past participation history when providing event information and suggest the most suitable events. For example, the Events Department can suggest related events based on events residents have previously attended. The Events Department can analyze residents' past participation history and suggest the most suitable events. For example, by suggesting related events based on events residents have previously attended, the Events Department can provide events that will interest residents. The Events Department can also suggest events that residents are likely to be interested in based on their past participation history. Furthermore, the Events Department can analyze residents' participation history and suggest the most suitable events. In this way, by analyzing residents' past participation history and suggesting the most suitable events, the Events Department can provide events that will interest residents. The analysis of participation history may be performed using AI, for example, or without AI. For example, the Events Department can input residents' past participation history into a database and have AI perform the analysis of the participation history.

[0046] The Events Department can suggest additional related events based on residents' areas of interest when providing event information. For example, the Events Department can suggest events related to areas that residents are interested in. The Events Department can suggest additional related events based on residents' areas of interest. For example, the Events Department can provide events that will attract residents' interest by suggesting events related to areas that residents are interested in. The Events Department can also add events on topics that will attract residents' interest. Furthermore, the Events Department can suggest related events based on residents' areas of interest. This allows the Events Department to provide events that will attract residents' interest by suggesting additional related events based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the Events Department can identify residents' areas of interest from survey results or past question history and suggest related events.

[0047] The Events Department can suggest additional related events based on residents' areas of interest when providing event information. For example, the Events Department can suggest events related to areas that residents are interested in. The Events Department can suggest additional related events based on residents' areas of interest. For example, the Events Department can provide events that will attract residents' interest by suggesting events related to areas that residents are interested in. The Events Department can also add events on topics that will attract residents' interest. Furthermore, the Events Department can suggest related events based on residents' areas of interest. This allows the Events Department to provide events that will attract residents' interest by suggesting additional related events based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the Events Department can identify residents' areas of interest from survey results or past question history and suggest related events.

[0048] The Events Department can provide region-specific events by considering residents' geographical location information when providing event information. For example, the Events Department can provide event information held in the area where residents live. The Events Department can provide region-specific events based on residents' geographical location information. For example, by providing event information held in the area where residents live, the Events Department can provide events that will interest residents. The Events Department can also add events specific to the area where residents live. Furthermore, the Events Department can provide region-specific events based on residents' geographical location information. This allows the Events Department to provide events that will interest residents by considering residents' geographical location information and providing region-specific events. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the Events Department can acquire residents' geographical location information from GPS data or address information and provide region-specific events.

[0049] The Events Department can analyze residents' social media activity when providing event information and suggest relevant events. For example, the Events Department can provide information related to events that residents have shown interest in on social media. The Events Department can analyze residents' social media activity and suggest relevant events. For example, the Events Department can provide events that will interest residents by providing information related to events that residents have shown interest in on social media. The Events Department can also suggest events that are frequently mentioned based on residents' social media activity. Furthermore, the Events Department can suggest relevant events based on residents' social media activity. In this way, by analyzing residents' social media activity and suggesting relevant events, the Events Department can provide events that will interest residents. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the Events Department can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and suggest relevant events.

[0050] The collection unit can analyze residents' past opinion submission history to select the optimal collection method when collecting opinions. For example, the collection unit can provide relevant questions based on opinions previously submitted by residents. The collection unit analyzes residents' past opinion submission history and selects the optimal collection method. For example, the collection unit can effectively collect residents' opinions by providing relevant questions based on opinions previously submitted by residents. The collection unit can also select the optimal collection method from residents' past opinion submission history. Furthermore, the collection unit can analyze residents' opinion submission history and propose the most effective collection method. This makes it possible to collect opinions more effectively by analyzing residents' past opinion submission history and selecting the optimal collection method. The analysis of opinion submission history may be performed using AI, for example, or without AI. For example, the collection unit can input residents' past opinion submission history into a database and have AI perform the analysis of the opinion submission history.

[0051] The collection unit can collect additional relevant questions based on residents' areas of interest when gathering opinions. For example, the collection unit can provide questions related to policies that residents are interested in. The collection unit collects additional relevant questions based on residents' areas of interest. For example, the collection unit can effectively collect residents' opinions by providing questions related to policies that residents are interested in. The collection unit can also add questions on topics that are of interest to residents. Furthermore, the collection unit can collect relevant questions based on residents' areas of interest. This makes it possible to collect opinions more effectively by collecting additional relevant questions based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the collection unit can identify residents' areas of interest from survey results or past question history and collect relevant questions.

[0052] The collection unit can collect region-specific opinions by considering residents' geographical location information when collecting opinions. For example, the collection unit can collect opinions related to the area where residents live. The collection unit collects region-specific opinions based on residents' geographical location information. For example, by collecting opinions related to the area where residents live, the collection unit can effectively collect residents' opinions. The collection unit can also collect opinions on problems occurring in residents' areas. Furthermore, the collection unit can collect region-specific opinions based on residents' geographical location information. This makes opinion collection more effective by considering residents' geographical location information when collecting region-specific opinions. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the collection unit can acquire residents' geographical location information from GPS data or address information and collect region-specific opinions.

[0053] The data collection unit can analyze residents' social media activity and collect relevant opinions when gathering opinions. For example, the data collection unit can collect opinions related to topics that residents have shown interest in on social media. The data collection unit can analyze residents' social media activity and collect relevant opinions. For example, the data collection unit can effectively collect residents' opinions by collecting opinions related to topics that residents have shown interest in on social media. The data collection unit can also collect opinions on frequently mentioned issues from residents' social media activity. Furthermore, the data collection unit can collect relevant opinions based on residents' social media activity. This makes it possible to collect opinions more effectively by analyzing residents' social media activity and collecting relevant opinions. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the data collection unit can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and collect relevant opinions.

[0054] The analysis unit can optimize its analysis algorithm by referring to past analysis data during opinion analysis. For example, the analysis unit can select the optimal analysis algorithm based on past analysis data. The analysis unit optimizes the analysis algorithm by referring to past analysis data. For example, the analysis unit can improve the accuracy of opinion analysis by selecting the optimal analysis algorithm based on past analysis data. Furthermore, the analysis unit can improve the analysis algorithm by referring to past analysis results. In addition, the analysis unit can improve the accuracy of the analysis by utilizing past data. As a result, more effective opinion analysis becomes possible by optimizing the analysis algorithm by referring to past analysis data. The reference to past analysis data may be performed using AI, for example, or without using AI. For example, the analysis unit can input past analysis data into a database and have AI perform the optimization of the analysis algorithm.

[0055] The analysis unit can apply different analytical methods to each category of opinion during opinion analysis. For example, the analysis unit can select an appropriate analytical method according to the category of opinion. The analysis unit can apply different analytical methods to each category of opinion. For example, by selecting an appropriate analytical method according to the category of opinion, the analysis unit can improve the accuracy of opinion analysis. Furthermore, the analysis unit can analyze opinions by applying different analytical methods to each category. In addition, the analysis unit can select the optimal analytical method based on the category of opinion. This makes it possible to perform more effective opinion analysis by applying different analytical methods to each category of opinion. The classification of opinion categories may be done using AI, for example, or without using AI. For example, the analysis unit can classify opinion categories by theme or importance and apply an appropriate analytical method.

[0056] The analysis unit can weight opinions based on when they were submitted. For example, the analysis unit can adjust the weighting of opinions according to when they were submitted. The analysis unit can weight opinions based on when they were submitted. For example, by adjusting the weighting of opinions according to when they were submitted, the analysis unit can improve the accuracy of opinion analysis. The analysis unit can also prioritize the analysis of opinions that have been submitted recently. Furthermore, the analysis unit can evaluate the importance of opinions based on when they were submitted. This makes it possible to perform more effective opinion analysis by weighting opinions based on when they were submitted. The acquisition of opinion submission dates may be done using AI, for example, or without using AI. For example, the analysis unit can input opinion submission dates into a database and have AI perform the weighting of the analysis.

[0057] The analysis department can improve the accuracy of its opinion analysis by referring to relevant literature. For example, the analysis department can improve the accuracy of its opinion analysis by referring to relevant literature. The analysis department can improve the accuracy of its opinion analysis by referring to relevant literature. For example, the analysis department can increase the reliability of its opinion analysis by improving the accuracy of its opinion analysis by referring to relevant literature. Furthermore, the analysis department can provide background information on the opinion based on the relevant literature. In addition, the analysis department can increase the reliability of its analysis by utilizing the relevant literature. This makes it possible to perform more effective opinion analysis by improving the accuracy of the analysis by referring to relevant literature. The referencing of relevant literature may be done using AI, or it may be done without using AI. For example, the analysis department can input relevant literature into a database and have AI perform the analysis to improve accuracy.

[0058] The improvement department can optimize improvement algorithms by referring to past improvement data when improving policies. For example, the improvement department can select the optimal improvement algorithm based on past improvement data. The improvement department optimizes the improvement algorithm by referring to past improvement data. For example, by selecting the optimal improvement algorithm based on past improvement data, the improvement department can improve the accuracy of policy improvements. Furthermore, the improvement department can improve the improvement algorithm by referring to past improvement results. In addition, the improvement department can improve the accuracy of improvements by utilizing past data. As a result, by optimizing the improvement algorithm by referring to past improvement data, more effective policy improvements become possible. The reference to past improvement data may be done using AI, for example, or without using AI. For example, the improvement department can input past improvement data into a database and have AI perform the optimization of the improvement algorithm.

[0059] The improvement department can determine the priority of improvements based on residents' areas of interest when improving policies. For example, the improvement department can prioritize improvements related to policies that residents are interested in. The improvement department can determine the priority of improvements based on residents' areas of interest. For example, by prioritizing improvements related to policies that residents are interested in, the improvement department can enhance the effectiveness of policy improvements. The improvement department can also prioritize improvements on topics that are of interest to residents. Furthermore, the improvement department can determine the priority of improvements based on residents' areas of interest. This makes it possible to improve policies more effectively by determining the priority of improvements based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the improvement department can identify residents' areas of interest from survey results or past question history and determine the priority of improvements.

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

[0061] The explanation unit can analyze residents' past question history and select the most effective explanation method. For example, the explanation unit can store the content of questions residents have asked in the past in a database and analyze the question history. Based on the past question history, the explanation unit can provide relevant information in advance. For example, by providing information related to the content of questions residents have asked in the past in advance, the explanation unit can deepen residents' understanding. In addition, the explanation unit can prioritize using explanation methods that residents found easy to understand in the past. Furthermore, the explanation unit can provide a summary of frequently asked questions from the residents' question history. This allows the explanation unit to select the most effective explanation method and deepen residents' understanding by analyzing the residents' past question history. The analysis of the question history may be performed using AI, or it may be performed without AI. For example, the explanation unit can input residents' past question history into a database and have AI perform the analysis of the question history.

[0062] The data collection unit can aggregate questions and opinions from residents and automatically generate and provide reports for local government officials. For example, the data collection unit can aggregate questions and opinions from residents into a database and generate reports using a report generation algorithm. The data collection unit analyzes the content of the questions and opinions, extracts important information, and compiles it into a report. For example, the data collection unit can classify questions and opinions from residents into categories and generate a report for each category. The data collection unit can also analyze the frequency and trends of questions and opinions and compile them into a report as statistical data. Furthermore, the data collection unit can summarize the content of the questions and opinions and compile the key points into a report. This allows for the efficient aggregation of questions and opinions from residents and the provision of reports to local government officials, which can be used to improve policies. Report generation may be performed using AI, for example, or without AI. For example, the data collection unit can input questions and opinions from residents into a database and generate reports using a report generation algorithm.

[0063] The explanatory unit can provide additional relevant information during the explanation based on the residents' areas of interest. For example, the explanatory unit can provide information related to policies that residents are interested in. The explanatory unit can provide additional relevant information based on the residents' areas of interest. For example, the explanatory unit can deepen residents' understanding by providing information related to policies that residents are interested in. The explanatory unit can also add detailed data on topics that residents have shown interest in. Furthermore, the explanatory unit can introduce relevant events and activities based on the residents' areas of interest. This allows for a deeper understanding of residents by providing additional relevant information based on their areas of interest. The identification of areas of interest may be done using AI, for example, or without using AI. For example, the explanatory unit can identify residents' areas of interest from survey results or past question history and provide relevant information.

[0064] The explanation unit can analyze residents' past question history and select the most effective explanation method. For example, the explanation unit can store the content of questions residents have asked in the past in a database and analyze the question history. Based on the past question history, the explanation unit can provide relevant information in advance. For example, by providing information related to the content of questions residents have asked in the past in advance, the explanation unit can deepen residents' understanding. In addition, the explanation unit can prioritize using explanation methods that residents found easy to understand in the past. Furthermore, the explanation unit can provide a summary of frequently asked questions from the residents' question history. This allows the explanation unit to select the most effective explanation method and deepen residents' understanding by analyzing the residents' past question history. The analysis of the question history may be performed using AI, or it may be performed without AI. For example, the explanation unit can input residents' past question history into a database and have AI perform the analysis of the question history.

[0065] The explanatory unit can provide additional relevant information during the explanation based on the residents' areas of interest. For example, the explanatory unit can provide information related to policies that residents are interested in. The explanatory unit can provide additional relevant information based on the residents' areas of interest. For example, the explanatory unit can deepen residents' understanding by providing information related to policies that residents are interested in. The explanatory unit can also add detailed data on topics that residents have shown interest in. Furthermore, the explanatory unit can introduce relevant events and activities based on the residents' areas of interest. This allows for a deeper understanding of residents by providing additional relevant information based on their areas of interest. The identification of areas of interest may be done using AI, for example, or without using AI. For example, the explanatory unit can identify residents' areas of interest from survey results or past question history and provide relevant information.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The explanatory section explains technical terms in response to residents' questions. For example, it can explain medical terms, legal terms, technical terms, etc. The explanatory section explains technical terms in an easy-to-understand manner in response to residents' questions. Step 2: The multilingual section provides the information explained by the explanatory section in multiple languages. For example, information can be provided in multiple languages ​​such as English, Chinese, and Spanish. The multilingual section provides information in multiple languages ​​according to the language of the residents. Step 3: The Events Department provides event information based on the information provided by the Multilingual Department. For example, they can provide information on local events, seminars, workshops, etc. The Events Department provides event information according to the interests of the residents. Step 4: The collection team gathers residents' opinions based on the information provided by the event team. For example, residents' opinions can be collected in the form of questionnaire responses, feedback, suggestions, etc. Step 5: The analysis department analyzes the opinions collected by the collection department. For example, this can involve compiling survey results, analyzing the content of feedback, and classifying suggestions. Step 6: The Improvement Department improves policies based on the opinions analyzed by the Analysis Department. For example, policies such as regional development policies, welfare policies, and environmental protection policies can be improved.

[0068] (Example of form 2) The regional integrated AI agent system according to an embodiment of the present invention is a system for local governments and is an integrated system that improves the quality of life for citizens through the cooperation of six AI agents (citizen explanation, multilingual support, event coordination, citizen participation promotion, emotion recognition, and resident feedback). First, the regional integrated AI agent system has a citizen explanation agent that effectively explains the local government's policies to citizens and explains technical terms in an easy-to-understand manner in response to residents' questions. Next, the multilingual support agent explains the city's policies in multiple languages, making them easy to understand for foreign residents as well. Furthermore, the event coordination AI guide provides policy and event information at local events and information sessions, complementing resident support. The citizen participation promotion system provides functions that allow residents to give opinions on policy proposals, vote, and comment. The emotion recognition AI agent analyzes residents' emotions and adjusts the content of explanations in real time. Finally, the resident feedback AI report system aggregates questions and opinions from residents and automatically generates and provides reports for local government officials. Through this system, local governments aim to develop their regions together with local residents and build a sustainable and harmonious society. This enables regionally integrated AI agent systems to help local governments develop their communities together with residents and build sustainable and harmonious societies.

[0069] The regional integrated AI agent system according to this embodiment comprises an explanation unit, a multilingual unit, an event unit, a collection unit, an analysis unit, and an improvement unit. The explanation unit explains technical terms in response to residents' questions. The explanation unit can explain technical terms such as medical terms, legal terms, and technical terms. The explanation unit explains technical terms in an easy-to-understand manner in response to residents' questions. For example, when explaining medical terms, the explanation unit can explain specific symptoms and treatment methods. Also, when explaining legal terms, the explanation unit can explain specific legal procedures and rights and obligations. Furthermore, when explaining technical terms, the explanation unit can explain specific technological mechanisms and application examples. The multilingual unit provides the information explained by the explanation unit in multiple languages. The multilingual unit can provide information in multiple languages ​​such as English, Chinese, and Spanish. The multilingual unit provides information in multiple languages ​​according to the language of the residents. For example, when providing information in English, the multilingual unit can translate and explain technical terms in English. Furthermore, the Multilingual Department can translate and explain technical terms in Chinese when providing information in Chinese. Additionally, the Multilingual Department can translate and explain technical terms in Spanish when providing information in Spanish. The Events Department provides event information based on the information provided by the Multilingual Department. For example, the Events Department can provide information on local events, seminars, workshops, etc. The Events Department provides event information according to the interests of residents. For example, when providing information on local events, the Events Department can explain the date, time, location, and how to participate. Also, when providing information on seminars, the Events Department can explain the instructors, content, and participation fees. Furthermore, when providing information on workshops, the Events Department can explain the content, target audience, and application methods. The Collection Department collects residents' opinions based on the information provided by the Events Department. The Collection Department can collect residents' opinions in the form of questionnaires, feedback, and suggestions, for example. The Collection Department efficiently collects residents' opinions. For example, the Collection Department can collect residents' opinions by conducting questionnaires.Furthermore, the Collection Department can collect residents' opinions by setting up feedback forms. In addition, the Collection Department can collect residents' suggestions by setting up suggestion boxes. The Analysis Department analyzes the opinions collected by the Collection Department. The Analysis Department can, for example, compile survey results, analyze the content of feedback, and classify suggestions. The Analysis Department conducts a detailed analysis of residents' opinions. For example, the Analysis Department can compile survey results to grasp trends in residents' opinions. In addition, the Analysis Department can analyze the content of feedback to grasp the specific content of residents' opinions. Furthermore, the Analysis Department can classify suggestions to grasp the types and frequency of suggestions from residents. The Improvement Department improves policies based on the opinions analyzed by the Analysis Department. The Improvement Department can, for example, improve policies such as regional development policies, welfare policies, and environmental protection policies. The Improvement Department improves policies by reflecting residents' opinions. For example, when improving regional development policies, the Improvement Department can formulate specific policies by referring to residents' opinions. In addition, when improving welfare policies, the Improvement Department can formulate specific policies by referring to residents' opinions. Furthermore, the improvement department can formulate specific measures by taking residents' opinions into account when improving environmental protection policies. As a result, the regional integrated AI agent system according to this embodiment can explain technical terms in response to residents' questions, provide information in multiple languages, provide event information, collect residents' opinions, analyze those opinions, and improve policies.

[0070] The explanatory unit explains technical terms in response to residents' questions. For example, it can explain medical, legal, and technical terms. Specifically, if a resident asks a medical question, the unit will provide a detailed explanation of the disease, its symptoms, and treatment methods. For instance, it will explain the symptoms and treatment of a particular disease in easy-to-understand, general terms. If a legal question is asked, it will explain specific legal terms and procedures with concrete examples. For example, it will explain the contents of a contract and the rights and obligations of a resident using concrete examples to make them easy to understand. Furthermore, if a technical question is asked, it will explain specific technical terms and their applications using diagrams and videos. For example, it will explain the mechanisms of new technologies and their applications in a visually easy-to-understand way. To ensure that technical terms are explained clearly in response to residents' questions, the explanatory unit can utilize AI to grasp the residents' level of understanding in real time and adjust the explanation as needed. For example, if a resident finds something difficult to understand, the AI ​​will detect this reaction and provide simpler language or additional explanations. Furthermore, the explanatory unit can save residents' question history and refer to past questions to provide more appropriate answers. This allows the explanatory unit to flexibly and effectively explain technical terms in order to deepen residents' understanding.

[0071] The multilingual section provides information explained by the explanatory section in multiple languages. For example, the multilingual section can provide information in languages ​​such as English, Chinese, and Spanish. Specifically, the multilingual section uses AI to automatically translate information according to the user's language. For example, if a user selects English, the information explained by the explanatory section is translated into English, and technical terms are explained clearly in English. If a user selects Chinese, the information is translated into Chinese, and technical terms are explained clearly in Chinese. Furthermore, if a user selects Spanish, the information is translated into Spanish, and technical terms are explained clearly in Spanish. The multilingual section utilizes AI to accurately understand context and the meaning of technical terms, enabling it to provide natural translations tailored to the user's language. For example, to provide accurate translations of technical terms such as medical and legal terms, it uses AI models with specialized knowledge. The multilingual section can also provide information via audio using speech synthesis technology tailored to the user's language. For example, if a user prefers to receive information via audio, the AI ​​automatically translates the information and provides it in audio format. This allows the multilingual department to provide information flexibly and effectively in accordance with the language of the residents.

[0072] The Events Department provides event information based on information provided by the Multilingual Department. For example, the Events Department can provide information on local events, seminars, workshops, and other events. Specifically, the Events Department uses AI to analyze residents' interests and past participation history in order to provide event information tailored to their interests. For example, it provides relevant event information based on a resident's past event participation history. Furthermore, it can customize and individually provide event information according to residents' interests. For example, if a resident is interested in health, it provides information on health-related seminars and workshops. If a resident is interested in environmental protection, it provides information on environmental protection-related events. In addition, the Events Department can provide event information in multiple languages, depending on the resident's language. For example, it provides event information in multiple languages ​​such as English, Chinese, and Spanish, in a format that is easy for residents to understand. The Events Department can use AI to automatically collect, classify, and provide event information tailored to residents' interests and language. This allows the Events Department to flexibly and effectively provide event information that aligns with residents' interests.

[0073] The collection department collects residents' opinions based on information provided by the event department. The collection department can collect residents' opinions in various forms, such as questionnaire responses, feedback, and suggestions. Specifically, to collect feedback from residents who participated in an event, the collection department can use AI to automatically generate questionnaires and distribute them to residents. For example, it can automatically send questionnaires after the event to collect residents' opinions. The collection department can also collect residents' opinions by setting up a feedback form where residents can freely submit their opinions. For example, it can provide a form where residents can freely write their opinions and suggestions regarding the event. Furthermore, the collection department can collect residents' suggestions by setting up a suggestion box where residents can submit suggestions. For example, it can provide a suggestion box where residents can propose areas for improvement in the community or new ideas. The collection department can use AI to efficiently collect, classify, and store residents' opinions. For example, it can automatically classify the collected opinions and prioritize processing important opinions and suggestions. The collection department can also take measures to anonymize residents' opinions and protect their privacy. This allows the collection department to efficiently and effectively gather residents' opinions and use them to improve the entire system.

[0074] The Analysis Department analyzes the opinions collected by the Collection Department. For example, the Analysis Department can perform tasks such as aggregating survey results, analyzing the content of feedback, and classifying proposals. Specifically, the Analysis Department aggregates collected survey results and uses AI to automatically analyze the data in order to understand trends in residents' opinions. For example, it analyzes residents' satisfaction levels and areas of interest based on survey results. Furthermore, the Analysis Department utilizes natural language processing technology to analyze the content of feedback in detail and understand the specific content of residents' opinions. For example, it analyzes the text data of feedback to extract residents' opinions and feelings. In addition, the Analysis Department uses clustering technology to classify proposals and understand the types and frequency of residents' suggestions. For example, it automatically classifies the content of proposals and identifies common themes and trends. The Analysis Department can use AI to efficiently analyze collected opinions and extract important information. For example, it can identify local issues and areas for improvement based on residents' opinions and formulate specific countermeasures. The Analysis Department can also visualize the analysis results and provide tools for reporting them clearly to stakeholders. This allows the analysis department to thoroughly analyze the collected opinions and use them to improve the entire system.

[0075] The Improvement Department improves policies based on feedback analyzed by the Analysis Department. The Improvement Department can improve policies such as regional development, welfare, and environmental protection. Specifically, the Improvement Department uses AI to formulate concrete policies that reflect residents' opinions. For example, when improving regional development policies, it plans new events and projects based on residents' opinions. Similarly, when improving welfare policies, it considers residents' opinions to enhance welfare services and introduce new support programs. Furthermore, when improving environmental protection policies, it considers residents' opinions to promote environmental protection activities and plan new environmental protection projects. The Improvement Department can use AI to evaluate the effectiveness of policies and modify them as needed, based on residents' opinions. For example, it can collect residents' opinions after the implementation of a policy and evaluate its effectiveness. The Improvement Department can also make the policy improvement process transparent and report the progress of policy improvements to residents. This allows the Improvement Department to flexibly and effectively improve policies that reflect residents' opinions, contributing to regional development and increased resident satisfaction.

[0076] The explanation unit can analyze residents' emotions and adjust the explanation content in real time. For example, the unit can capture residents' facial expressions with a camera and analyze their emotions using an emotion estimation algorithm. Based on changes in facial expressions, the unit calculates an emotion score and adjusts the explanation content accordingly. For example, if a resident is feeling anxious, the unit will provide the explanation in a gentle and polite tone. If a resident is agitated, the unit can provide the explanation in a calm and composed tone. Furthermore, if a resident has questions, the unit can add detailed explanations to deepen their understanding. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by adjusting the explanation content according to the residents' emotions.

[0077] The data collection unit can aggregate questions and opinions from residents and automatically generate and provide reports for local government officials. For example, the data collection unit can aggregate questions and opinions from residents into a database and generate reports using a report generation algorithm. The data collection unit analyzes the content of the questions and opinions, extracts important information, and compiles it into a report. For example, the data collection unit can classify questions and opinions from residents into categories and generate a report for each category. The data collection unit can also analyze the frequency and trends of questions and opinions and compile them into a report as statistical data. Furthermore, the data collection unit can summarize the content of the questions and opinions and compile the key points into a report. This allows for the efficient aggregation of questions and opinions from residents and the provision of reports to local government officials, which can be used to improve policies. Report generation may be performed using AI, for example, or without AI. For example, the data collection unit can input questions and opinions from residents into a database and generate reports using a report generation algorithm.

[0078] The explanatory unit can estimate the emotions of residents and adjust the tone and expression of the explanation based on the estimated emotions. For example, the explanatory unit can capture the resident's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The explanatory unit calculates an emotion score based on the changes in facial expression and adjusts the tone and expression of the explanation. For example, if the resident is feeling anxious, the explanatory unit will provide the explanation in a gentle and polite tone. Also, if the resident is excited, the explanatory unit can provide the explanation in a calm and composed tone. Furthermore, if the resident has questions, the explanatory unit can add detailed explanations to deepen their understanding. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by adjusting the tone and expression of the explanation according to the resident's emotions.

[0079] The explanation unit can analyze residents' past question history and select the most effective explanation method. For example, the explanation unit can store the content of questions residents have asked in the past in a database and analyze the question history. Based on the past question history, the explanation unit can provide relevant information in advance. For example, by providing information related to the content of questions residents have asked in the past in advance, the explanation unit can deepen residents' understanding. In addition, the explanation unit can prioritize using explanation methods that residents found easy to understand in the past. Furthermore, the explanation unit can provide a summary of frequently asked questions from the residents' question history. This allows the explanation unit to select the most effective explanation method and deepen residents' understanding by analyzing the residents' past question history. The analysis of the question history may be performed using AI, or it may be performed without AI. For example, the explanation unit can input residents' past question history into a database and have AI perform the analysis of the question history.

[0080] The explanatory unit can provide additional relevant information during the explanation based on the residents' areas of interest. For example, the explanatory unit can provide information related to policies that residents are interested in. The explanatory unit can provide additional relevant information based on the residents' areas of interest. For example, the explanatory unit can deepen residents' understanding by providing information related to policies that residents are interested in. The explanatory unit can also add detailed data on topics that residents have shown interest in. Furthermore, the explanatory unit can introduce relevant events and activities based on the residents' areas of interest. This allows for a deeper understanding of residents by providing additional relevant information based on their areas of interest. The identification of areas of interest may be done using AI, for example, or without using AI. For example, the explanatory unit can identify residents' areas of interest from survey results or past question history and provide relevant information.

[0081] The explanation unit can estimate the emotions of residents and determine the priority of explanations based on the estimated emotions. For example, the explanation unit can capture the facial expressions of residents with a camera and estimate their emotions using an emotion estimation algorithm. The explanation unit calculates an emotion score based on the changes in facial expressions and determines the priority of explanations. For example, if a resident is feeling anxious, the explanation unit will prioritize explanations that provide reassurance. Also, if a resident is agitated, the explanation unit can prioritize calm explanations. Furthermore, if a resident has questions, the explanation unit can prioritize explanations that address those questions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by determining the priority of explanations according to the emotions of residents.

[0082] The explanatory unit can provide region-specific information by considering the geographical location of residents during the explanation. For example, the explanatory unit can provide policy information related to the area where residents live. The explanatory unit provides region-specific information based on the geographical location of residents. For example, by providing policy information related to the area where residents live, the explanatory unit can deepen residents' understanding. The explanatory unit can also add information about events held in the residents' area. Furthermore, the explanatory unit can provide information about issues specific to the residents' area. In this way, by providing region-specific information while considering the geographical location of residents, residents' understanding can be deepened. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the explanatory unit can acquire residents' geographical location information from GPS data or address information and provide region-specific information.

[0083] The explanatory department can analyze residents' social media activity and provide relevant information during the explanation. For example, the explanatory department can provide information related to topics that residents have shown interest in on social media. The explanatory department can analyze residents' social media activity and provide relevant information. For example, by providing information related to topics that residents have shown interest in on social media, the explanatory department can deepen residents' understanding. The explanatory department can also provide information on issues that are frequently mentioned in residents' social media activity. Furthermore, the explanatory department can provide relevant policy information based on residents' social media activity. In this way, by analyzing residents' social media activity and providing relevant information, residents can deepen their understanding. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the explanatory department can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and provide relevant information.

[0084] The multilingual unit can estimate the emotions of residents and adjust the tone and expression of the multilingual explanation based on the estimated emotions. For example, the multilingual unit can capture the facial expressions of residents with a camera and estimate their emotions using an emotion estimation algorithm. The multilingual unit calculates an emotion score based on changes in facial expressions and adjusts the tone and expression of the multilingual explanation. For example, if a resident is feeling anxious, the multilingual unit can provide a multilingual explanation in a gentle tone. Also, if a resident is excited, the multilingual unit can provide a multilingual explanation in a calm tone. Furthermore, if a resident has questions, the multilingual unit can add detailed multilingual explanations. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by adjusting the tone and expression of the multilingual explanation according to the emotions of the residents.

[0085] The multilingual department can adjust the level of detail in explanations according to the language proficiency of the residents when providing multilingual support. For example, if the residents have a low language proficiency, the department can provide explanations in simple language. The multilingual department can adjust the level of detail in explanations according to the language proficiency of the residents. For example, if the residents have a low language proficiency, the department can provide explanations in simple language to deepen their understanding. Conversely, if the residents have a high language proficiency, the department can provide detailed explanations that include specialized terminology. Furthermore, the multilingual department can select an appropriate level of detail in explanations according to the language proficiency of the residents. In this way, by adjusting the level of detail in explanations according to the language proficiency of the residents, their understanding can be deepened. The evaluation of language proficiency may be performed using AI, for example, or without using AI. For example, the multilingual department can evaluate the language proficiency of residents from language test results or self-reported information and adjust the level of detail in explanations accordingly.

[0086] The multilingual department can select appropriate expressions according to the cultural background of the residents when providing multilingual support. For example, the multilingual department uses expressions that take into account the cultural background of the residents. The multilingual department selects appropriate expressions according to the cultural background of the residents. For example, by using expressions that take into account the cultural background of the residents, the multilingual department can deepen the understanding of the residents. In addition, the multilingual department can provide explanations that take into account the customs and values ​​unique to the culture of the residents. Furthermore, the multilingual department can select appropriate expressions based on the cultural background of the residents. This allows for a deeper understanding of the residents by selecting appropriate expressions according to their cultural background. Identifying cultural backgrounds may be done using AI, for example, or without using AI. For example, the multilingual department can identify the cultural background of residents from their nationality, religion, and customs, and select appropriate expressions.

[0087] The multilingual unit can estimate residents' emotions and determine the priority of multilingual explanations based on the estimated emotions. For example, the multilingual unit can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The multilingual unit calculates an emotion score based on changes in facial expressions and determines the priority of multilingual explanations. For example, if a resident is feeling anxious, the multilingual unit will prioritize explanations that provide reassurance. Also, if a resident is agitated, the multilingual unit can prioritize calm explanations. Furthermore, if a resident has questions, the multilingual unit can prioritize explanations that resolve those questions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by determining the priority of multilingual explanations according to residents' emotions.

[0088] The multilingual unit can provide region-specific information by considering the geographical location of residents when providing multilingual support. For example, the multilingual unit can provide policy information related to the area where residents live in multiple languages. The multilingual unit provides region-specific information based on the geographical location of residents. For example, by providing policy information related to the area where residents live in multiple languages, the multilingual unit can deepen residents' understanding. In addition, the multilingual unit can add information about events held in the residents' area in multiple languages. Furthermore, the multilingual unit can provide information about issues specific to the residents' area in multiple languages. This allows for a deeper understanding of residents by providing region-specific information while considering their geographical location. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the multilingual unit can acquire residents' geographical location information from GPS data or address information and provide region-specific information.

[0089] The multilingual department can analyze residents' social media activity and provide relevant information when providing multilingual support. For example, the multilingual department can provide information in multiple languages ​​related to topics that residents have shown interest in on social media. The multilingual department can analyze residents' social media activity and provide relevant information. For example, by providing information in multiple languages ​​related to topics that residents have shown interest in on social media, the multilingual department can deepen residents' understanding. The multilingual department can also provide information in multiple languages ​​about issues that are frequently mentioned in residents' social media activity. Furthermore, the multilingual department can provide information in multiple languages ​​based on residents' social media activity. In this way, by analyzing residents' social media activity and providing relevant information, residents' understanding can be deepened. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the multilingual department can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and provide relevant information.

[0090] The Events Department can estimate residents' emotions and adjust how event information is provided based on those estimated emotions. For example, the Events Department can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Based on the changes in facial expressions, the Events Department calculates an emotion score and adjusts how event information is provided. For example, if a resident is feeling anxious, the Events Department can provide reassuring event information. Also, if a resident is excited, the Events Department can provide event information in a calm tone. Furthermore, if a resident has questions, the Events Department can add more detailed event information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective information provision by adjusting how event information is provided according to residents' emotions.

[0091] The Events Department can analyze residents' past participation history when providing event information and suggest the most suitable events. For example, the Events Department can suggest related events based on events residents have previously attended. The Events Department can analyze residents' past participation history and suggest the most suitable events. For example, by suggesting related events based on events residents have previously attended, the Events Department can provide events that will interest residents. The Events Department can also suggest events that residents are likely to be interested in based on their past participation history. Furthermore, the Events Department can analyze residents' participation history and suggest the most suitable events. In this way, by analyzing residents' past participation history and suggesting the most suitable events, the Events Department can provide events that will interest residents. The analysis of participation history may be performed using AI, for example, or without AI. For example, the Events Department can input residents' past participation history into a database and have AI perform the analysis of the participation history.

[0092] The Events Department can suggest additional related events based on residents' areas of interest when providing event information. For example, the Events Department can suggest events related to areas that residents are interested in. The Events Department can suggest additional related events based on residents' areas of interest. For example, the Events Department can provide events that will attract residents' interest by suggesting events related to areas that residents are interested in. The Events Department can also add events on topics that will attract residents' interest. Furthermore, the Events Department can suggest related events based on residents' areas of interest. This allows the Events Department to provide events that will attract residents' interest by suggesting additional related events based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the Events Department can identify residents' areas of interest from survey results or past question history and suggest related events.

[0093] The Events Department can suggest additional related events based on residents' areas of interest when providing event information. For example, the Events Department can suggest events related to areas that residents are interested in. The Events Department can suggest additional related events based on residents' areas of interest. For example, the Events Department can provide events that will attract residents' interest by suggesting events related to areas that residents are interested in. The Events Department can also add events on topics that will attract residents' interest. Furthermore, the Events Department can suggest related events based on residents' areas of interest. This allows the Events Department to provide events that will attract residents' interest by suggesting additional related events based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the Events Department can identify residents' areas of interest from survey results or past question history and suggest related events.

[0094] The Events Department can estimate residents' emotions and prioritize event information based on those estimated emotions. For example, the Events Department can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Based on the changes in facial expressions, the Events Department calculates an emotion score and determines the priority of event information. For example, if a resident is feeling anxious, the Events Department will prioritize event information that provides a sense of security. Also, if a resident is excited, the Events Department can prioritize calming event information. Furthermore, if a resident has questions, the Events Department can prioritize event information that answers those questions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective information provision by prioritizing event information according to residents' emotions.

[0095] The Events Department can provide region-specific events by considering residents' geographical location information when providing event information. For example, the Events Department can provide event information held in the area where residents live. The Events Department can provide region-specific events based on residents' geographical location information. For example, by providing event information held in the area where residents live, the Events Department can provide events that will interest residents. The Events Department can also add events specific to the area where residents live. Furthermore, the Events Department can provide region-specific events based on residents' geographical location information. This allows the Events Department to provide events that will interest residents by considering residents' geographical location information and providing region-specific events. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the Events Department can acquire residents' geographical location information from GPS data or address information and provide region-specific events.

[0096] The Events Department can analyze residents' social media activity when providing event information and suggest relevant events. For example, the Events Department can provide information related to events that residents have shown interest in on social media. The Events Department can analyze residents' social media activity and suggest relevant events. For example, the Events Department can provide events that will interest residents by providing information related to events that residents have shown interest in on social media. The Events Department can also suggest events that are frequently mentioned based on residents' social media activity. Furthermore, the Events Department can suggest relevant events based on residents' social media activity. In this way, by analyzing residents' social media activity and suggesting relevant events, the Events Department can provide events that will interest residents. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the Events Department can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and suggest relevant events.

[0097] The collection unit can estimate residents' emotions and adjust the method of collecting opinions based on the estimated emotions. For example, the collection unit can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The collection unit calculates an emotion score based on changes in facial expressions and adjusts the method of collecting opinions. For example, if a resident is feeling anxious, the collection unit can provide an opinion-collecting method that provides reassurance. Also, if a resident is agitated, the collection unit can collect opinions in a calm tone. Furthermore, if a resident has questions, the collection unit can collect opinions by adding detailed explanations. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This makes it possible to collect opinions more effectively by adjusting the method of collecting opinions according to the emotions of the residents.

[0098] The collection unit can analyze residents' past opinion submission history to select the optimal collection method when collecting opinions. For example, the collection unit can provide relevant questions based on opinions previously submitted by residents. The collection unit analyzes residents' past opinion submission history and selects the optimal collection method. For example, the collection unit can effectively collect residents' opinions by providing relevant questions based on opinions previously submitted by residents. The collection unit can also select the optimal collection method from residents' past opinion submission history. Furthermore, the collection unit can analyze residents' opinion submission history and propose the most effective collection method. This makes it possible to collect opinions more effectively by analyzing residents' past opinion submission history and selecting the optimal collection method. The analysis of opinion submission history may be performed using AI, for example, or without AI. For example, the collection unit can input residents' past opinion submission history into a database and have AI perform the analysis of the opinion submission history.

[0099] The collection unit can collect additional relevant questions based on residents' areas of interest when gathering opinions. For example, the collection unit can provide questions related to policies that residents are interested in. The collection unit collects additional relevant questions based on residents' areas of interest. For example, the collection unit can effectively collect residents' opinions by providing questions related to policies that residents are interested in. The collection unit can also add questions on topics that are of interest to residents. Furthermore, the collection unit can collect relevant questions based on residents' areas of interest. This makes it possible to collect opinions more effectively by collecting additional relevant questions based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the collection unit can identify residents' areas of interest from survey results or past question history and collect relevant questions.

[0100] The data collection unit can estimate residents' emotions and determine the priority of opinion collection based on the estimated emotions. For example, the data collection unit can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The data collection unit calculates an emotion score based on changes in facial expressions and determines the priority of opinion collection. For example, if a resident is feeling anxious, the data collection unit will prioritize collecting opinions that provide reassurance. Also, if a resident is agitated, the data collection unit can prioritize collecting calm opinions. Furthermore, if a resident has questions, the data collection unit can prioritize collecting opinions that address those questions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective opinion collection by determining the priority of opinion collection according to residents' emotions.

[0101] The collection unit can collect region-specific opinions by considering residents' geographical location information when collecting opinions. For example, the collection unit can collect opinions related to the area where residents live. The collection unit collects region-specific opinions based on residents' geographical location information. For example, by collecting opinions related to the area where residents live, the collection unit can effectively collect residents' opinions. The collection unit can also collect opinions on problems occurring in residents' areas. Furthermore, the collection unit can collect region-specific opinions based on residents' geographical location information. This makes opinion collection more effective by considering residents' geographical location information when collecting region-specific opinions. The acquisition of geographical location information may be done using AI, for example, or without using AI. For example, the collection unit can acquire residents' geographical location information from GPS data or address information and collect region-specific opinions.

[0102] The data collection unit can analyze residents' social media activity and collect relevant opinions when gathering opinions. For example, the data collection unit can collect opinions related to topics that residents have shown interest in on social media. The data collection unit can analyze residents' social media activity and collect relevant opinions. For example, the data collection unit can effectively collect residents' opinions by collecting opinions related to topics that residents have shown interest in on social media. The data collection unit can also collect opinions on frequently mentioned issues from residents' social media activity. Furthermore, the data collection unit can collect relevant opinions based on residents' social media activity. This makes it possible to collect opinions more effectively by analyzing residents' social media activity and collecting relevant opinions. The analysis of social media activity may be performed using AI, for example, or without AI. For example, the data collection unit can analyze residents' social media activity from the content of posts, the number of followers, the number of likes, etc., and collect relevant opinions.

[0103] The analysis unit can estimate residents' emotions and adjust the opinion analysis method based on the estimated emotions. For example, the analysis unit can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit calculates an emotion score based on changes in facial expressions and adjusts the opinion analysis method accordingly. For example, if a resident is feeling anxious, the analysis unit can provide an analysis method that provides reassurance. Also, if a resident is agitated, the analysis unit can conduct opinion analysis in a calm tone. Furthermore, if a resident has questions, the analysis unit can add detailed explanations to analyze their opinions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective opinion analysis by adjusting the opinion analysis method according to the emotions of the residents.

[0104] The analysis unit can optimize its analysis algorithm by referring to past analysis data during opinion analysis. For example, the analysis unit can select the optimal analysis algorithm based on past analysis data. The analysis unit optimizes the analysis algorithm by referring to past analysis data. For example, the analysis unit can improve the accuracy of opinion analysis by selecting the optimal analysis algorithm based on past analysis data. Furthermore, the analysis unit can improve the analysis algorithm by referring to past analysis results. In addition, the analysis unit can improve the accuracy of the analysis by utilizing past data. As a result, more effective opinion analysis becomes possible by optimizing the analysis algorithm by referring to past analysis data. The reference to past analysis data may be performed using AI, for example, or without using AI. For example, the analysis unit can input past analysis data into a database and have AI perform the optimization of the analysis algorithm.

[0105] The analysis unit can apply different analytical methods to each category of opinion during opinion analysis. For example, the analysis unit can select an appropriate analytical method according to the category of opinion. The analysis unit can apply different analytical methods to each category of opinion. For example, by selecting an appropriate analytical method according to the category of opinion, the analysis unit can improve the accuracy of opinion analysis. Furthermore, the analysis unit can analyze opinions by applying different analytical methods to each category. In addition, the analysis unit can select the optimal analytical method based on the category of opinion. This makes it possible to perform more effective opinion analysis by applying different analytical methods to each category of opinion. The classification of opinion categories may be done using AI, for example, or without using AI. For example, the analysis unit can classify opinion categories by theme or importance and apply an appropriate analytical method.

[0106] The analysis unit can estimate residents' emotions and determine the priority of opinion analysis based on the estimated emotions. For example, the analysis unit can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. The analysis unit calculates an emotion score based on changes in facial expressions and determines the priority of opinion analysis. For example, if a resident is feeling anxious, the analysis unit will prioritize opinion analysis that provides reassurance. Also, if a resident is agitated, the analysis unit can prioritize calm opinion analysis. Furthermore, if a resident has questions, the analysis unit can prioritize opinion analysis that resolves those questions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective opinion analysis by determining the priority of opinion analysis according to residents' emotions.

[0107] The analysis unit can weight opinions based on when they were submitted. For example, the analysis unit can adjust the weighting of opinions according to when they were submitted. The analysis unit can weight opinions based on when they were submitted. For example, by adjusting the weighting of opinions according to when they were submitted, the analysis unit can improve the accuracy of opinion analysis. The analysis unit can also prioritize the analysis of opinions that have been submitted recently. Furthermore, the analysis unit can evaluate the importance of opinions based on when they were submitted. This makes it possible to perform more effective opinion analysis by weighting opinions based on when they were submitted. The acquisition of opinion submission dates may be done using AI, for example, or without using AI. For example, the analysis unit can input opinion submission dates into a database and have AI perform the weighting of the analysis.

[0108] The analysis department can improve the accuracy of its opinion analysis by referring to relevant literature. For example, the analysis department can improve the accuracy of its opinion analysis by referring to relevant literature. The analysis department can improve the accuracy of its opinion analysis by referring to relevant literature. For example, the analysis department can increase the reliability of its opinion analysis by improving the accuracy of its opinion analysis by referring to relevant literature. Furthermore, the analysis department can provide background information on the opinion based on the relevant literature. In addition, the analysis department can increase the reliability of its analysis by utilizing the relevant literature. This makes it possible to perform more effective opinion analysis by improving the accuracy of the analysis by referring to relevant literature. The referencing of relevant literature may be done using AI, or it may be done without using AI. For example, the analysis department can input relevant literature into a database and have AI perform the analysis to improve accuracy.

[0109] The improvement department can estimate residents' emotions and adjust policy improvements based on those estimated emotions. For example, the improvement department can capture residents' facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. Based on the changes in facial expressions, the improvement department calculates an emotion score and adjusts policy improvements accordingly. For example, if a resident is feeling anxious, the improvement department can implement policy improvements that provide a sense of security. If a resident is agitated, the improvement department can implement calm policy improvements. Furthermore, if a resident has questions, the improvement department can implement policy improvements that address those questions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective policy improvements by adjusting policy improvements according to residents' emotions.

[0110] The improvement department can optimize improvement algorithms by referring to past improvement data when improving policies. For example, the improvement department can select the optimal improvement algorithm based on past improvement data. The improvement department optimizes the improvement algorithm by referring to past improvement data. For example, by selecting the optimal improvement algorithm based on past improvement data, the improvement department can improve the accuracy of policy improvements. Furthermore, the improvement department can improve the improvement algorithm by referring to past improvement results. In addition, the improvement department can improve the accuracy of improvements by utilizing past data. As a result, by optimizing the improvement algorithm by referring to past improvement data, more effective policy improvements become possible. The reference to past improvement data may be done using AI, for example, or without using AI. For example, the improvement department can input past improvement data into a database and have AI perform the optimization of the improvement algorithm.

[0111] The improvement department can determine the priority of improvements based on residents' areas of interest when improving policies. For example, the improvement department can prioritize improvements related to policies that residents are interested in. The improvement department can determine the priority of improvements based on residents' areas of interest. For example, by prioritizing improvements related to policies that residents are interested in, the improvement department can enhance the effectiveness of policy improvements. The improvement department can also prioritize improvements on topics that are of interest to residents. Furthermore, the improvement department can determine the priority of improvements based on residents' areas of interest. This makes it possible to improve policies more effectively by determining the priority of improvements based on residents' areas of interest. The identification of areas of interest may be done using AI, for example, or not. For example, the improvement department can identify residents' areas of interest from survey results or past question history and determine the priority of improvements.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The explanation unit can analyze residents' past question history and select the most effective explanation method. For example, the explanation unit can store the content of questions residents have asked in the past in a database and analyze the question history. Based on the past question history, the explanation unit can provide relevant information in advance. For example, by providing information related to the content of questions residents have asked in the past in advance, the explanation unit can deepen residents' understanding. In addition, the explanation unit can prioritize using explanation methods that residents found easy to understand in the past. Furthermore, the explanation unit can provide a summary of frequently asked questions from the residents' question history. This allows the explanation unit to select the most effective explanation method and deepen residents' understanding by analyzing the residents' past question history. The analysis of the question history may be performed using AI, or it may be performed without AI. For example, the explanation unit can input residents' past question history into a database and have AI perform the analysis of the question history.

[0114] The explanatory unit can estimate the emotions of residents and adjust the tone and expression of the explanation based on the estimated emotions. For example, the explanatory unit can capture the resident's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The explanatory unit calculates an emotion score based on the changes in facial expression and adjusts the tone and expression of the explanation. For example, if the resident is feeling anxious, the explanatory unit will provide the explanation in a gentle and polite tone. Also, if the resident is excited, the explanatory unit can provide the explanation in a calm and composed tone. Furthermore, if the resident has questions, the explanatory unit can add detailed explanations to deepen their understanding. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by adjusting the tone and expression of the explanation according to the resident's emotions.

[0115] The data collection unit can aggregate questions and opinions from residents and automatically generate and provide reports for local government officials. For example, the data collection unit can aggregate questions and opinions from residents into a database and generate reports using a report generation algorithm. The data collection unit analyzes the content of the questions and opinions, extracts important information, and compiles it into a report. For example, the data collection unit can classify questions and opinions from residents into categories and generate a report for each category. The data collection unit can also analyze the frequency and trends of questions and opinions and compile them into a report as statistical data. Furthermore, the data collection unit can summarize the content of the questions and opinions and compile the key points into a report. This allows for the efficient aggregation of questions and opinions from residents and the provision of reports to local government officials, which can be used to improve policies. Report generation may be performed using AI, for example, or without AI. For example, the data collection unit can input questions and opinions from residents into a database and generate reports using a report generation algorithm.

[0116] The explanation unit can estimate the emotions of residents and determine the priority of explanations based on the estimated emotions. For example, the explanation unit can capture the facial expressions of residents with a camera and estimate their emotions using an emotion estimation algorithm. The explanation unit calculates an emotion score based on the changes in facial expressions and determines the priority of explanations. For example, if a resident is feeling anxious, the explanation unit will prioritize explanations that provide reassurance. Also, if a resident is agitated, the explanation unit can prioritize calm explanations. Furthermore, if a resident has questions, the explanation unit can prioritize explanations that address those questions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by determining the priority of explanations according to the emotions of residents.

[0117] The explanatory unit can provide additional relevant information during the explanation based on the residents' areas of interest. For example, the explanatory unit can provide information related to policies that residents are interested in. The explanatory unit can provide additional relevant information based on the residents' areas of interest. For example, the explanatory unit can deepen residents' understanding by providing information related to policies that residents are interested in. The explanatory unit can also add detailed data on topics that residents have shown interest in. Furthermore, the explanatory unit can introduce relevant events and activities based on the residents' areas of interest. This allows for a deeper understanding of residents by providing additional relevant information based on their areas of interest. The identification of areas of interest may be done using AI, for example, or without using AI. For example, the explanatory unit can identify residents' areas of interest from survey results or past question history and provide relevant information.

[0118] The explanatory unit can estimate the emotions of residents and adjust the tone and expression of the explanation based on the estimated emotions. For example, the explanatory unit can capture the resident's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The explanatory unit calculates an emotion score based on the changes in facial expression and adjusts the tone and expression of the explanation. For example, if the resident is feeling anxious, the explanatory unit will provide the explanation in a gentle and polite tone. Also, if the resident is excited, the explanatory unit can provide the explanation in a calm and composed tone. Furthermore, if the resident has questions, the explanatory unit can add detailed explanations to deepen their understanding. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by adjusting the tone and expression of the explanation according to the resident's emotions.

[0119] The explanation unit can analyze residents' past question history and select the most effective explanation method. For example, the explanation unit can store the content of questions residents have asked in the past in a database and analyze the question history. Based on the past question history, the explanation unit can provide relevant information in advance. For example, by providing information related to the content of questions residents have asked in the past in advance, the explanation unit can deepen residents' understanding. In addition, the explanation unit can prioritize using explanation methods that residents found easy to understand in the past. Furthermore, the explanation unit can provide a summary of frequently asked questions from the residents' question history. This allows the explanation unit to select the most effective explanation method and deepen residents' understanding by analyzing the residents' past question history. The analysis of the question history may be performed using AI, or it may be performed without AI. For example, the explanation unit can input residents' past question history into a database and have AI perform the analysis of the question history.

[0120] The explanation unit can estimate the emotions of residents and determine the priority of explanations based on the estimated emotions. For example, the explanation unit can capture the facial expressions of residents with a camera and estimate their emotions using an emotion estimation algorithm. The explanation unit calculates an emotion score based on the changes in facial expressions and determines the priority of explanations. For example, if a resident is feeling anxious, the explanation unit will prioritize explanations that provide reassurance. Also, if a resident is agitated, the explanation unit can prioritize calm explanations. Furthermore, if a resident has questions, the explanation unit can prioritize explanations that address those questions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by determining the priority of explanations according to the emotions of residents.

[0121] The explanatory unit can provide additional relevant information during the explanation based on the residents' areas of interest. For example, the explanatory unit can provide information related to policies that residents are interested in. The explanatory unit can provide additional relevant information based on the residents' areas of interest. For example, the explanatory unit can deepen residents' understanding by providing information related to policies that residents are interested in. The explanatory unit can also add detailed data on topics that residents have shown interest in. Furthermore, the explanatory unit can introduce relevant events and activities based on the residents' areas of interest. This allows for a deeper understanding of residents by providing additional relevant information based on their areas of interest. The identification of areas of interest may be done using AI, for example, or without using AI. For example, the explanatory unit can identify residents' areas of interest from survey results or past question history and provide relevant information.

[0122] The explanatory unit can estimate the emotions of residents and adjust the tone and expression of the explanation based on the estimated emotions. For example, the explanatory unit can capture the resident's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. The explanatory unit calculates an emotion score based on the changes in facial expression and adjusts the tone and expression of the explanation. For example, if the resident is feeling anxious, the explanatory unit will provide the explanation in a gentle and polite tone. Also, if the resident is excited, the explanatory unit can provide the explanation in a calm and composed tone. Furthermore, if the resident has questions, the explanatory unit can add detailed explanations to deepen their understanding. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is not limited to, but may include, text generation AI (e.g., LLM) or multimodal generation AI. This allows for more effective explanations by adjusting the tone and expression of the explanation according to the resident's emotions.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The explanatory section explains technical terms in response to residents' questions. For example, it can explain medical terms, legal terms, technical terms, etc. The explanatory section explains technical terms in an easy-to-understand manner in response to residents' questions. Step 2: The multilingual section provides the information explained by the explanatory section in multiple languages. For example, information can be provided in multiple languages ​​such as English, Chinese, and Spanish. The multilingual section provides information in multiple languages ​​according to the language of the residents. Step 3: The Events Department provides event information based on the information provided by the Multilingual Department. For example, they can provide information on local events, seminars, workshops, etc. The Events Department provides event information according to the interests of the residents. Step 4: The collection team gathers residents' opinions based on the information provided by the event team. For example, residents' opinions can be collected in the form of questionnaire responses, feedback, suggestions, etc. Step 5: The analysis department analyzes the opinions collected by the collection department. For example, this can involve compiling survey results, analyzing the content of feedback, and classifying suggestions. Step 6: The Improvement Department improves policies based on the opinions analyzed by the Analysis Department. For example, policies such as regional development policies, welfare policies, and environmental protection policies can be improved.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the explanation unit, multilingual unit, event unit, collection unit, analysis unit, and improvement unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the explanation unit is implemented by the control unit 46A of the smart device 14 and explains technical terms in response to residents' questions. The multilingual unit is also implemented by the control unit 46A of the smart device 14 and provides the information explained by the explanation unit in multiple languages. The event unit is implemented by the control unit 46A of the smart device 14 and provides information on local events and seminars. The collection unit is implemented by the control unit 46A of the smart device 14 and collects residents' opinions. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The improvement unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves policies based on the analyzed opinions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the explanation unit, multilingual unit, event unit, collection unit, analysis unit, and improvement unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the explanation unit is implemented by the control unit 46A of the smart glasses 214 and explains technical terms in response to residents' questions. The multilingual unit is also implemented by the control unit 46A of the smart glasses 214 and provides the information explained by the explanation unit in multiple languages. The event unit is implemented by the control unit 46A of the smart glasses 214 and provides information on local events and seminars. The collection unit is implemented by the control unit 46A of the smart glasses 214 and collects residents' opinions. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The improvement unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves policies based on the analyzed opinions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the explanation unit, multilingual unit, event unit, collection unit, analysis unit, and improvement unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the explanation unit is implemented by the control unit 46A of the headset terminal 314 and explains technical terms in response to residents' questions. The multilingual unit is implemented by the control unit 46A of the headset terminal 314 and provides the information explained by the explanation unit in multiple languages. The event unit is implemented by the control unit 46A of the headset terminal 314 and provides information on local events and seminars. The collection unit is implemented by the control unit 46A of the headset terminal 314 and collects residents' opinions. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The improvement unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves policies based on the analyzed opinions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the explanation unit, multilingual unit, event unit, collection unit, analysis unit, and improvement unit, is implemented by at least one of the robot 414 and the data processing unit 12. For example, the explanation unit is implemented by the control unit 46A of the robot 414 and explains technical terms in response to residents' questions. The multilingual unit is also implemented by the control unit 46A of the robot 414 and provides the information explained by the explanation unit in multiple languages. The event unit is implemented by the control unit 46A of the robot 414 and provides information on local events and seminars. The collection unit is implemented by the control unit 46A of the robot 414 and collects residents' opinions. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the collected opinions. The improvement unit is implemented by the specific processing unit 290 of the data processing unit 12 and improves policies based on the analyzed opinions. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0178] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] 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.

[0188] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] (Note 1) An explanatory section that answers residents' questions and explains technical terms, A multilingual unit that provides the information explained by the explanatory unit in multiple languages, The event department provides event information based on the information provided by the aforementioned multilingual department, A collection department collects residents' opinions based on the information provided by the aforementioned event department, An analysis unit analyzes the opinions collected by the aforementioned collection unit, The system includes an improvement unit that improves policies based on the opinions analyzed by the aforementioned analysis unit. A system characterized by the following features. (Note 2) The above explanatory section is, Analyze residents' sentiments and adjust explanations in real time. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is It collects questions and opinions from residents and automatically generates and provides reports for local government officials. The system described in Appendix 1, characterized by the features described herein. (Note 4) The above explanatory section is, We estimate the residents' feelings and adjust the tone and expression of the explanation based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 5) The above explanatory section is, Analyze residents' past question history to select the most effective explanation method. The system described in Appendix 1, characterized by the features described herein. (Note 6) The above explanatory section is, During the explanation, provide additional relevant information based on the residents' areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 7) The above explanatory section is, We estimate the residents' feelings and determine the priority of explanations based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 8) The above explanatory section is, When providing explanations, take into account the geographical location information of residents and provide region-specific information. The system described in Appendix 1, characterized by the features described herein. (Note 9) The above explanatory section is, During the explanation, we will analyze residents' social media activity and provide relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned multilingual unit is The system estimates the residents' feelings and adjusts the tone and expression of multilingual explanations based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned multilingual unit is When providing multilingual support, adjust the level of detail in explanations according to the language proficiency of the residents. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned multilingual unit is When providing multilingual support, select appropriate expressions according to the cultural background of the residents. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned multilingual unit is The system estimates residents' sentiments and prioritizes multilingual explanations based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned multilingual unit is When providing multilingual support, regionally specific information is provided, taking into account the geographical location of residents. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned multilingual unit is When providing multilingual support, analyze residents' social media activity and provide relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned event section, We estimate residents' sentiments and adjust how event information is provided based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned event section, When providing event information, we analyze residents' past participation history to suggest the most suitable events. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned event section, When providing event information, additional related events will be suggested based on residents' areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned event section, When providing event information, additional related events will be suggested based on residents' areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned event section, The system estimates residents' sentiments and prioritizes event information based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned event section, When providing event information, we will consider the geographical location of residents to offer events specific to their region. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned event section, When providing event information, we analyze residents' social media activity and suggest relevant events. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned collection unit is We estimate the sentiments of the residents and adjust the methods of collecting opinions based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned collection unit is When collecting opinions, we analyze residents' past opinion submission history to select the most suitable collection method. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned collection unit is When collecting opinions, additional questions will be collected based on the residents' areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned collection unit is We estimate the sentiments of the residents and determine the priority of opinion gathering based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned collection unit is When collecting opinions, consider the geographical location information of residents to gather opinions specific to the region. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned collection unit is When gathering opinions, analyze residents' social media activity and collect relevant opinions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned analysis unit is We estimate the residents' sentiments and adjust the opinion analysis method based on the estimated residents' sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned analysis unit is When analyzing opinions, we optimize the analysis algorithm by referring to past analysis data. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned analysis unit is When analyzing opinions, different analytical methods are applied to each category of opinion. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned analysis unit is We estimate the sentiments of the residents and determine the priority of opinion analysis based on the estimated sentiments of the residents. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned analysis unit is When analyzing opinions, weight the analysis based on when the opinions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned analysis unit is When analyzing opinions, referencing relevant literature improves the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned improvement unit is, We estimate the sentiments of residents and adjust the methods for improving policies based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned improvement unit is, When improving policies, refer to past improvement data to optimize the improvement algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned improvement unit is, When improving policies, prioritize improvements based on areas of interest to residents. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An explanatory section that answers residents' questions and explains technical terms, A multilingual unit that provides the information explained by the explanatory unit in multiple languages, The event department provides event information based on the information provided by the aforementioned multilingual department, A collection department collects residents' opinions based on the information provided by the aforementioned event department, An analysis unit analyzes the opinions collected by the aforementioned collection unit, The system includes an improvement unit that improves policies based on the opinions analyzed by the aforementioned analysis unit. A system characterized by the following features.

2. The above explanatory section is, Analyze residents' sentiments and adjust explanations in real time. The system according to feature 1.

3. The aforementioned collection unit is It collects questions and opinions from residents and automatically generates and provides reports for local government officials. The system according to feature 1.

4. The above explanatory section is, We estimate the residents' feelings and adjust the tone and expression of the explanation based on those estimated feelings. The system according to feature 1.

5. The above explanatory section is, Analyze residents' past question history to select the most effective explanation method. The system according to feature 1.

6. The above explanatory section is, During the explanation, provide additional relevant information based on the residents' areas of interest. The system according to feature 1.

7. The above explanatory section is, We estimate the residents' feelings and determine the priority of explanations based on those estimated feelings. The system according to feature 1.

8. The above explanatory section is, When providing explanations, take into account the geographical location information of residents and provide region-specific information. The system according to feature 1.

Images