System

Abstract

A system is provided.SOLUTION: The system includes means for collecting problems from residents, means for transmitting the collected problem data to generation artificial intelligence and obtaining an answer, means for providing the generated answer to the residents, means for accumulating and analyzing the collected data, means for requesting the generation artificial intelligence to make an improvement proposal for the whole community based on the analysis result, and means for providing the community leader with the generated improvement proposal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, residents and students in communities such as local governments and schools have a wide variety of worries, both big and small, but often have no one to talk to about them. In such situations, individual problems go unresolved, and the community as a whole does not improve. Furthermore, in order to propose collective improvement measures, it is necessary to analyze accumulated data and make specific improvement proposals, but there is a lack of effective ways to do this. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means.

[0006] First, a means is provided for collecting concerns from residents. This means allows residents to input and send their concerns and questions. Next, a means is provided for sending the collected concern data to a generative AI system and automatically obtaining answers. This generative AI system generates appropriate answers to various concerns. Finally, a means is provided for providing the generated answers to residents. This allows residents to receive answers to their concerns.

[0007] The present invention further provides a means for storing and analyzing collected data. This means makes it possible to identify common concerns and trends from the stored data. Then, it provides a means for requesting a generative artificial intelligence to generate improvement proposals for the entire community based on the analysis results. This generative artificial intelligence generates specific improvement proposals based on the analysis results. Finally, by providing a means for providing the generated improvement proposals to community leaders, the administrator can receive specific proposals for working on improving the entire community.

[0008] "Residents" refers to individual members of a community such as a local government or school.

[0009] "Problems" refer to the individual or collective problems and difficulties faced by residents.

[0010] "Collecting" refers to incorporating the concerns and questions provided by residents into the system.

[0011] "Generative AI" refers to AI technology that automatically generates appropriate answers and suggestions based on input data.

[0012] "Answer" refers to the solution or advice generated by generative artificial intelligence in response to a problem or question.

[0013] "Providing" refers to delivering information and services within the system to users in a usable form.

[0014] "Storing" refers to the process of continuously storing collected data in a database or other storage device.

[0015] "Analyzing" refers to the use of data analysis techniques to compile accumulated data and identify common patterns or trends.

[0016] "Improvement proposals" refer to improvement measures for the entire community created by generative artificial intelligence based on accumulated and analyzed data.

[0017] "Community leaders" refer to those responsible for management and decision-making in communities such as local governments and schools. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence, and then makes suggestions for improving the entire community based on the accumulated data.

[0040] Overall system configuration

[0041] The system includes a terminal for residents to input their concerns, a server that receives and processes the input data, a generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0042] Collecting user concerns

[0043] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[0044] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0045] Generative AI answer generation

[0046] The server receives the worry data sent from the device and passes it to the generative AI. Specifically, this data is appropriately formatted and sent as a request to the generative AI's API. The generative AI generates an appropriate answer based on the input worry content and returns the result to the server.

[0047] For example, in response to a problem such as "I can't stay motivated to study," a generative AI could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[0048] Providing answers

[0049] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[0050] Data accumulation and analysis

[0051] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[0052] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0053] Community-based improvement proposals

[0054] The server requests improvement proposals from the generative AI based on the analysis results. The generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a learning support system and holding regular learning consultation sessions."

[0055] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[0056] Specific examples

[0057] The user inputs and sends a concern such as "I'm worried about the safety of my neighborhood at night." The device sends this information to the server. The server sends this concern to the generative AI and receives a generated answer. The generative AI's answer is, "Please consider working with local governments to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user.

[0058] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify a trend of "high levels of anxiety about safety at night." It then requests specific improvement proposals from the generative AI, suggesting "increased nighttime patrols and the installation of security cameras." The server then notifies the local government administrator of these improvement proposals, which are then implemented.

[0059] In this way, the present invention provides a system that can address residents' concerns and improve the community as a whole.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The user enters their concerns or questions into the input form on the device and clicks the send button. The input information is then sent from the device to the server by the "send" action.

[0063] Step 2:

[0064] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[0065] Step 3:

[0066] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[0067] Step 4:

[0068] The server then sends the worry data, which has been confirmed to be in the correct format, to the generative AI API. The sent content includes the worry text data and related metadata (e.g., user ID, category, etc.).

[0069] Step 5:

[0070] The generative AI generates an appropriate answer based on the data it receives and sends it back to the server. For example, if the user says, "I'm not motivated to study," the generated answer might be, "It's effective to set detailed goals and accumulate small achievements. Try dividing your daily study time into 30-minute segments and concentrating on them."

[0071] Step 6:

[0072] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[0073] Step 7:

[0074] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[0075] Step 8:

[0076] The device displays the received answer data on the user interface, allowing the user to see the generative AI's answer to their problem.

[0077] Step 9:

[0078] The server stores the user's inquiry and the generated answer in a database, which includes the user ID, the content of the problem, the generated answer, and a timestamp.

[0079] Step 10:

[0080] The server periodically runs a batch process to analyze the accumulated data, which performs text analysis and clustering to identify common concerns and trends.

[0081] Step 11:

[0082] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study. Please propose improvements that can be implemented by the entire school."

[0083] Step 12:

[0084] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular learning consultation sessions."

[0085] Step 13:

[0086] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[0087] This series of processes allows us to address residents' concerns and provide suggestions for improving the community as a whole.

[0088] Example 1

[0089] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0090] Conventional methods for collecting and responding to residents' concerns in communities often lack specific advice for individual concerns, and there was no system in place to utilize the accumulated data on concerns to improve the community as a whole. As a result, individual concerns were not resolved, and the improvement of the community as a whole did not progress.

[0091] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0092] In this invention, the server includes a means for collecting worries from users, a means for transmitting the collected worry data to the generative AI model and obtaining an answer, and a means for providing the generated answer to the user. This makes it possible to provide prompt and specific advice for the user's worries. Furthermore, the server includes a means for accumulating and analyzing the collected data, a means for requesting the generative AI model to make improvement proposals for the entire community based on the analysis results, and a means for providing the generated improvement proposals to the community administrator. This makes it possible to effectively improve the entire community.

[0093] "User" refers to an individual user who uses the system to input their concerns and receive answers from the generative AI model.

[0094] "Worries" refer to problems or concerns that users input through the system and that should be resolved by the generative AI model.

[0095] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on collected problem data and then makes suggestions for improvements to the entire community based on the results of data analysis.

[0096] "Collection means" refers to a method or device for incorporating the worries and consultation details entered by users into the system.

[0097] "Transmission means" refers to the means by which collected data is sent to the generative AI model and an answer is obtained.

[0098] "Provision means" refers to a method or device for presenting answers and improvement suggestions obtained from a generative AI model to users and community administrators.

[0099] "Data storage means" refers to a method or device for storing collected problem data and answers obtained from the generative AI model in a database.

[0100] "Analysis tools" refers to methods or devices for analyzing accumulated data and identifying common patterns or trends.

[0101] "Means for requesting improvement proposals" refers to a means for requesting improvement proposals for the entire community from the generative AI model based on the analysis results.

[0102] "Community Manager" refers to a person or organization that has the authority to receive generated improvement suggestions and reflect them in the management and activities of the community.

[0103] Overall system configuration

[0104] This invention is a system that collects user concerns and provides answers to those concerns and improvement suggestions for the entire community using a generative AI model. The system includes a terminal where users input their concerns, a server that receives the input data and instructs other components to process it, a generative AI model that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0105] Collecting user concerns

[0106] The device provides an interface for users to input their concerns. The interface includes text boxes, options, a send button, etc. The user uses this interface to enter their concerns or questions and clicks the send button.

[0107] Specifically, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0108] Generative AI answer generation

[0109] The server receives the worry data sent from the device and passes it to the generative AI model. Specifically, this data is properly formatted and sent as a request to the generative AI model's API. The generative AI model generates an appropriate answer based on the input worry content and returns the result to the server.

[0110] For example, in response to a problem such as "I can't stay motivated to study," a generative AI model could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[0111] Example prompt: "A user expressed the following concern: 'I'm worried about safety at night.' Please provide specific advice on this concern."

[0112] Providing answers

[0113] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[0114] Data accumulation and analysis

[0115] The server stores the collected worry data and the answers from the generative AI model in a database. By recording each interaction, data analysis can be performed later.

[0116] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0117] Community-based improvement proposals

[0118] The server requests improvement proposals from the generative AI model based on the analysis results. The generative AI model generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it may suggest "introducing a learning support system and holding regular learning consultation sessions." This improvement proposal is provided to the administrator via the server.

[0119] This allows administrators to take concrete action to improve the operation and activities of the entire community based on the improvement suggestions provided.

[0120] Specific examples

[0121] The user inputs and submits a concern such as "I'm worried about safety at night." The device sends this information to the server. The server then sends this concern to the generative AI model and receives the generated answer. The generative AI model's answer is, "Please consider working with the local government to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user. Furthermore, if multiple residents raise the same concern, the server performs data analysis and identifies a trend of "many people are worried about safety at night." The server then requests specific improvement proposals from the generative AI model, proposing "strengthening nighttime patrols and installing security cameras." The server notifies the local government administrator of this improvement proposal, and specific improvement measures are implemented.

[0122] As described above, the present invention provides a system that can address users' concerns and improve the community as a whole.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1: User input of concerns

[0125] The terminal provides an interface for the user to input their worries. The user enters their worries in the text box and clicks the send button. For example, a student might enter "I can't get motivated to study" and click the send button. At this point, the terminal converts the input data into JSON format and prepares it for sending. Input data: The user's worries. Output data: Worry data in JSON format.

[0126] Step 2: Submit your problem data

[0127] The device sends the generated worry data to the server via the network. The HTTP protocol is used for transmission. Input data: Worry data in JSON format. Output data: Worry data sent to the server. Specific operations include generating a request header and encoding the data.

[0128] Step 3: Generative AI model generates answers

[0129] The server passes the worry data received from the device to the generative AI model. The server then formats the data appropriately and sends it to the generative AI model as an API request. Input data: The worry data sent to the server. Output data: The answer data from the generative AI model. Specific operations include data format conversion, sending a request to an API endpoint, and authentication processing.

[0130] Step 4: Receiving response data

[0131] The generative AI model generates an answer to the received problem data and returns the result to the server. The server receives the generated answer data. Input data: Request data to the generative AI model. Output data: Generated answer data. Specific operations include natural language processing, data analysis, and execution of answer generation algorithms within the AI ​​model.

[0132] Step 5: Submit your response data

[0133] The server reformats the generated response data and sends it back to the original terminal. Specifically, it converts the data into a format that is easy for the user to understand and sends it as an HTTP response. Input data: Generated response data. Output data: Formatted response data. Specific operations include data format conversion and response header generation.

[0134] Step 6: Display the answer to the user

[0135] The device receives the answer data sent from the server and displays it to the user. The user can check the answer displayed on the screen and get advice. Input data: Formatted answer data. Output data: Answer displayed to the user. Specific operations include updating the UI and executing notification functions.

[0136] Step 7: Data accumulation

[0137] The server stores the collected problem data and generated answer data in a database, which enables later data analysis. Input data: user problem data and generated answer data. Output data: data stored in the database. Specific operations include encoding data and executing database transactions.

[0138] Step 8: Analyze data and identify trends

[0139] The server periodically analyzes the accumulated data to identify common patterns and trends. Input data: accumulated worry data and answer data. Output data: trend data as the analysis result. Specific operations include running statistical analysis algorithms, cleansing the data, and generating analysis reports.

[0140] Step 9: Generate community-wide improvement suggestions

[0141] The server requests specific improvement proposals based on the analysis results and the generative AI model. The generative AI model generates specific improvement proposals for the entire community based on the analysis results. Input data: trend data as the analysis result. Output data: improvement proposals from the generative AI model. Specific operations include generating prompts to the AI ​​model and sending API requests.

[0142] Step 10: Notify administrators

[0143] The server notifies the generated improvement proposals through the administrator interface. The administrator receives the notification and plans and executes actions to specifically implement the proposed improvement measures. Input data: Generated improvement proposals. Output data: Improvement proposals notified to the administrator. Specific operations include generating notification messages and updating the administrator dashboard.

[0144] (Application example 1)

[0145] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] Conventional community support systems only collect residents' concerns and provide answers to them, but are insufficient in addressing public safety and security. It is also difficult to efficiently manage and analyze data collected from residents and quickly provide specific measures to improve public safety. As a result, residents' concerns remain unresolved, and the public safety of the entire community remains unimproved.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0148] In this invention, the server includes means for collecting concerns from residents, means for transmitting the collected concern data to the generative AI and obtaining a response, means for providing the generated response to residents, means for accumulating and analyzing the collected data, means for requesting the generative AI to propose improvements for the entire community based on the analysis results, means for providing the generated improvement proposals to the community leader, means for providing a smart device application for collecting concerns about public safety and security, and means for providing and recording the generated public safety improvement proposals. This makes it possible to efficiently collect residents' concerns about public safety and to quickly provide specific improvement measures using AI.

[0149] A "resident" is an individual who resides in or is enrolled in a particular community, such as a municipality or school.

[0150] The means for collecting "worries" are devices or applications that provide an interface for residents to input their problems and concerns and record them digitally.

[0151] "Generative AI" is an AI system that automatically generates appropriate answers and suggestions based on input concerns and data.

[0152] The "means of obtaining an answer" is the process of sending the collected data to generative artificial intelligence and obtaining an answer as the output result.

[0153] "Means of delivery" refers to the methods or devices by which the generated answers and improvement suggestions are displayed or communicated to residents and community leaders.

[0154] The "means for storing and analyzing data" is a mechanism for storing the collected worry data and generated answers in a database and later analyzing the data.

[0155] The "means for requesting improvement proposals" is a function that allows the server to instruct the generative artificial intelligence to create improvement proposals for the entire community based on the analysis results.

[0156] A "community leader" is an individual or organization that represents a community or group and is responsible for running and managing it.

[0157] A "smart device application" is a software application that runs on a mobile communication terminal such as a smartphone or tablet.

[0158] "Public Safety Improvement Proposals" are proposals for specific actions or measures to improve the safety of the community.

[0159] "Means of recording" refers to a function that stores the provided public safety improvement proposals and their implementation results in a database, making them available for later reference.

[0160] The present invention is a system that collects the concerns of residents in a community, provides answers using generative artificial intelligence, and makes suggestions for improving the entire community based on that data. Specific embodiments of the system are described below.

[0161] Overall system configuration

[0162] The system includes the following elements:

[0163] 1. A means of collecting residents' concerns

[0164] The system allows residents to input their concerns using an application installed on their smartphones, with an interface that includes text boxes, options, and a submit button.

[0165] Specifically, if a resident has concerns about public safety, they can enter something like "I'm worried about public safety at night" into the app and press the send button, which will send the information to the server.

[0166] 2. A means of sending collected worry data to generative AI and obtaining answers

[0167] The server receives the worry data sent from the device and sends it to the generative AI, which generates an appropriate answer based on the content of the worry and returns the result to the server.

[0168] For example, if a generative AI is sent a concern such as "I'm worried about the safety of the area at night," it will generate a response such as, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[0169] 3. A means of providing generated answers to residents

[0170] The server formats the generated answer and sends it back to the original terminal, which displays it to the user, allowing the resident to receive specific advice about their problem.

[0171] 4. Means of storing and analyzing collected data

[0172] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[0173] For example, if multiple residents express similar concerns about public safety, analyzing this data can identify that "there are many concerns about public safety at night in certain areas."

[0174] 5. A method to request generative AI to propose improvements for the entire community based on the analysis results

[0175] The server requests improvement proposals from the generative AI based on the analysis results, and the generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data.

[0176] For example, an improvement proposal such as "strengthening night patrols and installing security cameras" is generated.

[0177] 6. A means to provide generated improvement suggestions to community leaders

[0178] The server notifies the generated improvement proposal to the community leader, who can then implement specific safety measures based on the proposed improvement proposal.

[0179] Program processing and use of hardware and software

[0180] This system uses hardware and software such as a smartphone app, generative AI API, server, and database. Specifically, the following processes are performed:

[0181] Collecting residents' concerns

[0182] Residents' concern data is collected through the application interface and sent to the server in JSON format.

[0183] AI-powered answer generation

[0184] The collected data is sent to a generative artificial intelligence API, which generates appropriate answers.

[0185] Data accumulation and analysis

[0186] Analyze the accumulated data to identify common patterns and trends.

[0187] Providing improvement suggestions

[0188] Improvement suggestions generated by generative artificial intelligence are provided to community leaders.

[0189] Specific examples

[0190] Residents enter their concerns, such as "I'm worried about the safety at night," and send it.

[0191] Example prompt: "I'm worried about the safety of my family at night. Please tell me what specific measures I can take."

[0192] The server sends this information to the generative AI, which generates a response. The generative AI responds: "Consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[0193] The server then sends this response to the user's device and displays it to them. If multiple residents raise similar concerns, the server analyzes the data, identifies trends, and then requests a generative AI proposal for improvement. The proposal suggests "strengthening nighttime patrols and installing security cameras." The server notifies community leaders of this proposal, encouraging them to implement specific safety measures.

[0194] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] Residents use the smartphone application interface to input their concerns, for example, "I'm worried about the safety of the area at night," and then press the send button.

[0198] Input: User's problem text

[0199] Output: JSON formatted worries data

[0200] Step 2:

[0201] The device converts the user's input data into JSON format and sends it to the server, including metadata such as the user ID and timestamp.

[0202] Input: JSON formatted worries data

[0203] Output: Troubles data sent to the server

[0204] Step 3:

[0205] The server analyzes the received worry data and executes a process to send a request to the generative AI API. The server then formats the data appropriately and sends it to the AI.

[0206] Input: Worry data sent to the server

[0207] Output: The request sent to the generative AI API

[0208] Step 4:

[0209] The generative AI generates an appropriate answer based on the worry data received from the server. The prompt "I'm worried about the safety of my home at night. Please tell me what specific measures I can take" is input into the AI, and an answer is output.

[0210] Input: A request sent to the generative artificial intelligence API

[0211] Output: The generated answer

[0212] Step 5:

[0213] The server receives the answer returned by the generative AI and formats it before sending it back to the device, where it is provided to the user as specific advice.

[0214] Input: Generated Answer

[0215] Output: Formatted answer

[0216] Step 6:

[0217] The terminal receives the formatted response sent from the server and displays it to the user, who can then review the specific advice and take any necessary action.

[0218] Input: Formatted answer

[0219] Output: Advice displayed to the user

[0220] Step 7:

[0221] The server stores the collected worry data and generated answers in a database. The data includes the user ID, timestamp, content of the worry, and generated answers.

[0222] Input: Problem data and generated answers

[0223] Output: Records saved in the database

[0224] Step 8:

[0225] The accumulated data is periodically analyzed to identify trends and common problems. Based on the analysis results, the server sends multiple data sets to a generative AI system, which then generates improvement proposals for the entire community.

[0226] Input: Multiple records stored in a database

[0227] Output: Generated improvement suggestions

[0228] Step 9:

[0229] The server will notify community leaders of the generated improvement suggestions and encourage them to implement specific safety measures, either by email or via a specific administrator user interface.

[0230] Input: Generated improvement suggestions

[0231] Output: Improvement suggestions communicated to community leaders

[0232] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[0233] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0234] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence and an emotion engine, and further proposes improvements for the entire community based on the accumulated data.

[0235] Overall system configuration

[0236] The system includes a terminal for residents to input their concerns, a server that receives the input data and processes it in conjunction with an emotion engine that recognizes emotions, generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0237] Collecting user concerns and recognizing emotions

[0238] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[0239] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0240] Emotion Recognition and Answer Generation

[0241] The server receives the worry data sent from the device and passes it to the emotion engine, which analyzes the user's emotions from the input text data and identifies emotions such as "anxiety" or "disappointment."

[0242] The server passes the emotion data obtained from the emotion engine to the generative AI and instructs it to generate an answer along with the details of the problem. The generative AI generates an appropriate answer based on this data. For example, in response to the problem of "I can't get motivated to study," it generates an answer that is in tune with the person's emotions, such as "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax as you work."

[0243] Providing answers

[0244] The server receives the answer from the generative AI and sends it to the device in an appropriate format. The device then displays the answer to the user, allowing the user to receive specific, empathetic advice for their concerns.

[0245] Data accumulation and analysis

[0246] The server stores the collected worry data, generated answers, and emotional data generated by the emotion engine in a database. By recording each interaction, the data can be analyzed later.

[0247] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation and feeling anxious about their studies. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0248] Community-based improvement proposals

[0249] The server then requests improvement proposals from the generative AI based on the analysis results. The generative AI then generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a support system to improve motivation in learning and holding regular counseling sessions."

[0250] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[0251] Specific examples

[0252] The user types in "I'm worried about the safety at night" and sends it. The device sends this information to the server. The server sends this concern to the emotion engine, which recognizes it as "anxiety." The server then sends this to the generative AI and receives the generated answer. The generative AI's answer is, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective in reducing anxiety." The server sends this answer to the device and displays it to the user.

[0253] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify that there are many concerns about safety at night. It then asks the generative AI to propose specific improvements, suggesting strengthening nighttime patrols and installing security cameras. The server then notifies the local government administrator of these improvement proposals, and specific measures are implemented.

[0254] In this way, the present invention provides a system that can address the concerns of residents while being sensitive to their feelings, and can improve the community as a whole.

[0255] The processing flow will be explained below.

[0256] Step 1:

[0257] The user enters their concerns or questions into the input form on the device and clicks the send button. For example, they might enter, "I can't get motivated to study."

[0258] Step 2:

[0259] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[0260] Step 3:

[0261] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[0262] Step 4:

[0263] The server sends the properly formatted worry data to the emotion engine and asks it to extract emotion data from the text data entered by the user. The emotion engine analyzes the text and identifies emotions such as "anxiety" and "disappointment."

[0264] Step 5:

[0265] The emotion engine returns the analyzed emotion data to the server. For example, the emotion "anxiety" is recognized from the user's input.

[0266] Step 6:

[0267] The server combines the text data of the user's worries and emotion data and sends it to the generative AI. The transmitted content includes the user's worries and the emotions recognized.

[0268] Step 7:

[0269] The generative AI generates appropriate answers based on the worries and emotions it receives. For example, if it receives the worry of "I can't get motivated to study" and the emotion of "anxiety," it generates an answer that is in line with those emotions: "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax."

[0270] Step 8:

[0271] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[0272] Step 9:

[0273] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[0274] Step 10:

[0275] The device displays the generated answer to the user, allowing the user to receive specific advice that is in line with their own feelings about their troubles.

[0276] Step 11:

[0277] The server stores the user's consultation details, generated answers, and emotional data analyzed by the emotion engine in a database, including the user ID, the content of the problem, the generated answers, the recognized emotions, and a timestamp.

[0278] Step 12:

[0279] The server periodically runs a batch process that analyzes the accumulated data, performing text analysis and clustering to identify common concerns, trends, and associated sentiments.

[0280] Step 13:

[0281] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study and are feeling anxious. Please propose improvements that can be implemented by the entire school."

[0282] Step 14:

[0283] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular counseling sessions."

[0284] Step 15:

[0285] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[0286] Example 2

[0287] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0288] In modern society, communities such as local governments and schools are required to quickly and appropriately resolve the various concerns faced by residents and students. However, conventional systems require a lot of time and effort to collect and analyze concerns, provide appropriate advice, and accumulate data and generate improvement proposals, making it difficult to effectively utilize large amounts of data.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0290] In this invention, the server includes a means for collecting concerns from residents, a means for transmitting the collected concern data to an emotion analysis engine and identifying emotions, and a means for transmitting the emotion data and concern data identified by the emotion analysis engine to a generative AI model and obtaining answers. This makes it possible to provide quick and appropriate answers to residents' concerns that are sensitive to their emotions, and to generate improvement proposals for the entire community based on the accumulated data.

[0291] "Residents" refers to individuals who belong to a particular community, such as citizens, students, or staff.

[0292] "Worries" refers to specific information entered into the terminal, such as the problems, questions, and mental burdens residents face.

[0293] "Collection" refers to the process of centrally acquiring the concerns and data entered by residents through their devices and sending them to a server, etc.

[0294] An "emotion analysis engine" refers to a program or software that automatically analyzes the emotional state of residents from text data collected from them.

[0295] "Emotion Data" refers to data indicative of a user's emotional state as determined by an emotion analysis engine.

[0296] A "generative AI model" refers to an artificial intelligence system that automatically generates appropriate answers and improvement suggestions based on collected worry data and emotional data.

[0297] "Answer" refers to information provided by the generative AI model that offers advice or solutions to residents' concerns.

[0298] "Data accumulation" refers to the process of storing collected worry data, generated answers, emotional data, etc. in a database.

[0299] "Data analysis" refers to the process of analyzing accumulated data and identifying common patterns and trends.

[0300] "Improvement proposals" refer to proposals for effective measures and countermeasures for the entire community based on the results of data analysis.

[0301] "Community Leader" refers to an administrator or leader who is responsible for receiving improvement suggestions and taking concrete action based on them.

[0302] MODE FOR CARRYING OUT THE INVENTION

[0303] This invention is a system for improving the entire community by collecting and analyzing the concerns of residents in communities such as local governments and schools and providing appropriate advice. This system includes a terminal for residents to input their concerns, an emotion analysis engine, a generative AI model, a server including a database, and an interface for administrators.

[0304] System configuration and functions

[0305] 1. Terminal

[0306] It provides an interface for residents to input their concerns. The interface includes a text box and a submit button where users can write their concerns or questions and submit them. The submitted data is sent to the server in JSON format.

[0307] 2. Server

[0308] The server has several main functions.

[0309] Receiving and sending data

[0310] It receives worry data sent from the device and passes it to an emotion analysis engine. After emotion analysis, it sends the data to a generative AI model to obtain an answer.

[0311] Sentiment Analysis Engine

[0312] The sentiment analysis engine identifies the user's emotional state from collected text data, using natural language processing and machine learning techniques.

[0313] Generative AI Models

[0314] Based on the emotion data and concerns identified by the sentiment analysis engine, appropriate answers are generated using deep learning and large-scale language models.

[0315] Database

[0316] The collected worry data, emotion data, generated answers, etc. are stored, which allows for subsequent data analysis.

[0317] Data analysis

[0318] The accumulated data is analyzed to identify common patterns and trends, providing insights for generating community-wide improvement recommendations.

[0319] Admin Interface

[0320] It provides managers with improvement proposals generated based on the analysis results and provides an interface for planning and implementing specific countermeasures.

[0321] Specific examples

[0322] In a specific scenario, a student enters a concern such as "I can't get motivated to study" into their device and clicks the send button. This information is sent in JSON format to the server, which passes it to the emotion analysis engine. The emotion analysis engine analyzes it as "anxiety," and the server sends this emotion data to the generative AI model. The generative AI model generates the answer, "It's effective to set detailed goals and accumulate small feelings of accomplishment. Make sure to also take time to relax." The server sends this answer to the device and displays it to the user.

[0323] Prompt Sentence Examples

[0324] Examples of prompts provided to generative AI models include:

[0325] "User input: 'I'm not motivated to study'

[0326] Emotion engine analysis results: 'Anxiety'

[0327] Prompt for generative AI: 'If the user is worried about their motivation to study, please provide appropriate advice.'"

[0328] In this way, the system can provide quick and appropriate answers to specific concerns users have, and can also use the accumulated data to improve the community as a whole.

[0329] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0330] Step 1:

[0331] The user enters their concerns through the device interface and clicks the send button. The input is in a text box, for example, "I can't get motivated to study." The input here is raw text data. The device converts this text data into JSON format and prepares it for transmission.

[0332] Step 2:

[0333] The device sends the worry data entered by the user to the server. The sent data is in JSON format and specifically contains the text data "I can't get motivated to study." The server receives this JSON data.

[0334] Input: Text data of concerns from the device (JSON format)

[0335] Output: JSON data received by the server

[0336] Step 3:

[0337] The server analyzes the received worry data and prepares it for passing to the emotion analysis engine. Specifically, it extracts the text portion and converts it into a format that the emotion analysis engine can analyze. After the text analysis preparation is complete, the server sends the data to the emotion analysis engine.

[0338] Input: Received JSON data

[0339] Data processing: Extracting text and converting it into an analyzable format

[0340] Output: Text data to be sent to the sentiment analysis engine

[0341] Step 4:

[0342] The emotion analysis engine analyzes the text data sent from the server and identifies the user's emotion. For example, for the text "I'm not motivated to study," it identifies the emotion "anxiety." This identified emotion data is sent to the server.

[0343] Input: Text data for analysis

[0344] Data Computing: Sentiment Analysis, Identifying Emotional States

[0345] Output: Identified emotion data (e.g., anxiety)

[0346] Step 5:

[0347] The server receives the emotion data obtained from the emotion analysis engine and sends it along with the text data of the worries to the generative AI model. The data sent includes the details of the worries and the identified emotion data.

[0348] Input: Emotion data, worry text data

[0349] Data transmission: Send emotion and worry data to the generative AI model

[0350] Output: Data sent to the generative AI model completed

[0351] Step 6:

[0352] The generative AI model generates an appropriate answer based on the received emotion data and worry data. For example, in response to the worry "I can't get motivated to study" in response to the emotion "anxiety," the model generates the answer "It's effective to set detailed goals and accumulate small accomplishments. Make sure to also take time to relax." The generated answer is sent to the server.

[0353] Input: Emotion data, worry data

[0354] Data Computation: Generating Answers with Generative AI Models

[0355] Output: Generated response data

[0356] Step 7:

[0357] The server receives the answer from the generative AI model, converts it into an appropriate format (e.g., JSON), and sends it to the device.

[0358] Input: Answer data from the generative AI model

[0359] Data processing: converting to the appropriate format

[0360] Output: Response data sent to the device

[0361] Step 8:

[0362] The device displays the answers received from the server to the user, who can then check the displayed content to receive specific, empathetic advice about their concerns.

[0363] Input: Response data sent from the server

[0364] Output: The answer displayed to the user

[0365] Step 9:

[0366] The server stores the collected worry data, generated answers, and emotion data in a database, which enables subsequent data analysis.

[0367] Input: Worry data, emotion data, generated answers

[0368] Data storage: Saving to a database

[0369] Output: Accumulated data

[0370] Step 10:

[0371] The server analyzes the accumulated data and identifies common patterns and trends. For example, it reveals that many students struggle with motivation to study. This analysis results in the basis for suggesting improvements for the entire community.

[0372] Input: Accumulated data

[0373] Data analysis: identifying patterns and trends

[0374] Output: Analysis results (e.g., many students struggle with motivation to study)

[0375] Step 11:

[0376] The server requests improvement proposals from the generative AI model based on the analysis results, and the generative AI model generates specific improvement proposals based on the analysis results and sends them to the server.

[0377] Input: Analysis results

[0378] Data computation: generating improvement suggestions

[0379] Output: Generated improvement suggestions

[0380] Step 12:

[0381] The server provides the generated improvement proposals to community leaders through an administrator interface, who then plan and implement specific actions based on the proposals.

[0382] Input: Improvement suggestion

[0383] Data transmission: Transmission to the administrator interface

[0384] Output: Improvement suggestions provided to the administrator

[0385] This trend will lead to the realization of a system that can quickly and appropriately resolve residents' concerns while improving the community as a whole.

[0386] (Application example 2)

[0387] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0388] In electronic payment services, there is a need to effectively collect user complaints and provide tailored responses. Another challenge is to improve user satisfaction by accumulating and analyzing data on these complaints and issues and proposing improvements to the service as a whole.

[0389] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting worries from residents, means for analyzing the collected worry data using an emotion engine, and means for transmitting the analyzed emotion data and worry data to the generative AI and obtaining a response. This makes it possible to provide specific advice that is tailored to the user.

[0390] "Resident" refers to a user of the electronic payment service.

[0391] "Problems" refer to dissatisfaction or problems users experience while using electronic payment services.

[0392] "Collection means" refers to the interface and functions used to collect user concerns.

[0393] An "emotion engine" refers to software or a system for analyzing emotions from text data entered by the user.

[0394] "Generative artificial intelligence" refers to AI technology that generates appropriate answers based on analyzed emotional data and concerns.

[0395] "Collected data" refers to information collected from users regarding their concerns and complaints.

[0396] "Problem Data" is data collected from users regarding specific problems.

[0397] "Answer providing means" refers to the function or interface for providing the generated answer to the user.

[0398] "Data storage means" refers to a database or storage system for storing collected data.

[0399] "Analysis means" refers to the algorithms and software used to analyze the accumulated data.

[0400] "Improvement proposal generation means" refers to a function or system for generating improvement proposals for the entire service based on the analyzed data.

[0401] "Community leaders" refer to operators and managers of electronic payment services.

[0402] "Advice provision means" refers to functions and systems that use emotion engines and generative artificial intelligence to generate appropriate advice and provide it to users.

[0403] "Statistical analysis means" refers to software or systems for statistically analyzing accumulated data.

[0404] The components of the system for implementing this invention include a terminal for inputting worries, a server for processing data, an emotion engine, generative artificial intelligence, and necessary interfaces.

[0405] Hardware and Software Configuration

[0406] The server is operated using the following software and hardware:

[0407] Emotion Engine: IBM Watson(R) Tone Analyzer

[0408] Generative AI: OpenAI (registered trademark) GPT-3 (registered trademark)

[0409] Database: RDBMS such as MySQL (registered trademark) or PostgreSQL

[0410] Server hardware: powerful CPU, sufficient memory, and storage space

[0411] The device uses a smartphone or smart glasses to provide an interface for users to input their concerns, which may include text boxes, options, a submit button, etc.

[0412] Data processing flow

[0413] 1. Collecting user concerns

[0414] Users input and submit their concerns and complaints about electronic payment services using an input interface on their device, which may be provided by a mobile or web application.

[0415] 2. Sending data to the server

[0416] The worries entered by the user are sent to the server in JSON format, which then passes the received data to the emotion engine for analysis.

[0417] 3. Emotional Recognition

[0418] The emotion engine (IBM Watson Tone Analyzer) installed on the server analyzes the user's emotions from the input text data and identifies emotions such as "dissatisfaction" and "stress."

[0419] 4. Answer Generation

[0420] Based on the emotional data and worry data obtained from the emotion engine, the server uses generative artificial intelligence (OpenAI GPT-3) to generate appropriate answers tailored to the user.

[0421] 5. Providing answers to users

[0422] The server then sends the generated answer in an appropriate format to the device, which then displays it to the user, providing specific and emotionally relevant advice.

[0423] 6. Data accumulation and analysis

[0424] The server stores all interactions (input of worries, answers, emotional data) in a database, which is then subjected to statistical analysis.

[0425] 7. Suggestions for improving the overall service

[0426] The server statistically analyzes the accumulated data and generates suggestions for improving the overall service based on generative artificial intelligence. These suggestions are provided to the operator of the electronic payment service.

[0427] Specific examples

[0428] For example, a user might input and submit a complaint such as, "Smart payment isn't working in stores." The device then sends this data to the server. The server uses an emotion engine to recognize this as "dissatisfaction." The emotion data and complaint are then sent to a generative AI, which generates an answer such as: "If smart payment isn't working in stores, please make sure you're using the latest version of the app and that you always have a stable internet connection." The server then sends this answer to the device and displays it to the user.

[0429] Prompt Sentence Examples

[0430] "The user's emotion is dissatisfaction, and their problem is that smart payment in-store doesn't work. Please provide some advice to resolve this problem."

[0431] In this way, a system is provided that can provide specific advice that is sensitive to the user's feelings and improve the entire electronic payment service.

[0432] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0433] Step 1:

[0434] The user opens an interface on their device (smartphone or smart glasses) to input their concerns. They write their concerns or complaints in the input form and press the submit button. For example, they might enter "Smart payment isn't working properly at the store." The input data is sent to the server in JSON format.

[0435] Step 2:

[0436] The server receives JSON-formatted worry data sent by the user. The received data includes text entered by the user. The server prepares this text data to be passed to the emotion engine.

[0437] Step 3:

[0438] The server calls the emotion engine (IBM Watson Tone Analyzer) and sends the text data entered by the user. The emotion engine analyzes the user's emotions from the text data and identifies emotions such as "dissatisfaction" or "stress." The analysis results are returned to the server.

[0439] Step 4:

[0440] The server checks the emotion analysis results received from the emotion engine and sends the emotion data and the original concern data to the generative artificial intelligence (OpenAI GPT-3). The emotion data and concern data are sent along with a prompt. For example, "The emotion felt by the user is dissatisfaction, and the concern is that smart payment in stores is not working well. Please provide some advice to resolve this concern."

[0441] Step 5:

[0442] The generative artificial intelligence (OpenAI GPT-3) generates a response tailored to the user based on the prompt received. For example, it might generate advice such as, "If smart payment doesn't work in-store, please make sure you're using the latest version of the app and that you always have a secure internet connection." The generated advice is then returned to the server.

[0443] Step 6:

[0444] The server receives the answers from the generative AI and sends them to the device in an appropriate format. The server stores the answer data in a database. At the same time, all interactions (input of worries, emotion analysis results, generated answers) are accumulated in the database.

[0445] Step 7:

[0446] The device displays the answer received from the server to the user, who then checks the displayed advice and implements the solution to resolve the problem.

[0447] Step 8:

[0448] The server periodically performs statistical analysis of the accumulated data. This identifies common patterns and trends, and gathers data to generate service-wide improvement proposals. Based on this data, the server requests the generative AI to make service-wide improvement proposals.

[0449] Step 9:

[0450] The generative AI generates specific improvement proposals based on the received data. For example, it might generate an improvement proposal such as, "As part of a service-wide overhaul, we propose the introduction of a new connection protocol and the addition of an FAQ section." The server then provides this to the service administrator.

[0451] Through these steps, the system can provide specific advice that is sensitive to the user's emotions and improve the overall electronic payment service.

[0452] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0453] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0454] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0455] [Second embodiment]

[0456] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0457] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0458] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0459] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0460] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0461] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0462] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0463] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0464] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0465] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0466] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0467] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0468] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence, and then makes suggestions for improving the entire community based on the accumulated data.

[0469] Overall system configuration

[0470] The system includes a terminal for residents to input their concerns, a server that receives and processes the input data, a generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0471] Collecting user concerns

[0472] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[0473] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0474] Generative AI answer generation

[0475] The server receives the worry data sent from the device and passes it to the generative AI. Specifically, this data is appropriately formatted and sent as a request to the generative AI's API. The generative AI generates an appropriate answer based on the input worry content and returns the result to the server.

[0476] For example, in response to a problem such as "I can't stay motivated to study," a generative AI could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[0477] Providing answers

[0478] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[0479] Data accumulation and analysis

[0480] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[0481] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0482] Community-based improvement proposals

[0483] The server requests improvement proposals from the generative AI based on the analysis results. The generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a learning support system and holding regular learning consultation sessions."

[0484] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[0485] Specific examples

[0486] The user inputs and sends a concern such as "I'm worried about the safety of my neighborhood at night." The device sends this information to the server. The server sends this concern to the generative AI and receives a generated answer. The generative AI's answer is, "Please consider working with local governments to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user.

[0487] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify a trend of "high levels of anxiety about safety at night." It then requests specific improvement proposals from the generative AI, suggesting "increased nighttime patrols and the installation of security cameras." The server then notifies the local government administrator of these improvement proposals, which are then implemented.

[0488] In this way, the present invention provides a system that can address residents' concerns and improve the community as a whole.

[0489] The processing flow will be explained below.

[0490] Step 1:

[0491] The user enters their concerns or questions into the input form on the device and clicks the send button. The input information is then sent from the device to the server by the "send" action.

[0492] Step 2:

[0493] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[0494] Step 3:

[0495] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[0496] Step 4:

[0497] The server then sends the worry data, which has been confirmed to be in the correct format, to the generative AI API. The sent content includes the worry text data and related metadata (e.g., user ID, category, etc.).

[0498] Step 5:

[0499] The generative AI generates an appropriate answer based on the data it receives and sends it back to the server. For example, if the user says, "I'm not motivated to study," the generated answer might be, "It's effective to set detailed goals and accumulate small achievements. Try dividing your daily study time into 30-minute segments and concentrating on them."

[0500] Step 6:

[0501] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[0502] Step 7:

[0503] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[0504] Step 8:

[0505] The device displays the received answer data on the user interface, allowing the user to see the generative AI's answer to their problem.

[0506] Step 9:

[0507] The server stores the user's inquiry and the generated answer in a database, which includes the user ID, the content of the problem, the generated answer, and a timestamp.

[0508] Step 10:

[0509] The server periodically runs a batch process to analyze the accumulated data, which performs text analysis and clustering to identify common concerns and trends.

[0510] Step 11:

[0511] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study. Please propose improvements that can be implemented by the entire school."

[0512] Step 12:

[0513] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular learning consultation sessions."

[0514] Step 13:

[0515] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[0516] This series of processes allows us to address residents' concerns and provide suggestions for improving the community as a whole.

[0517] Example 1

[0518] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0519] Conventional methods for collecting and responding to residents' concerns in communities often lack specific advice for individual concerns, and there was no system in place to utilize the accumulated data on concerns to improve the community as a whole. As a result, individual concerns were not resolved, and the improvement of the community as a whole did not progress.

[0520] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0521] In this invention, the server includes a means for collecting worries from users, a means for transmitting the collected worry data to the generative AI model and obtaining an answer, and a means for providing the generated answer to the user. This makes it possible to provide prompt and specific advice for the user's worries. Furthermore, the server includes a means for accumulating and analyzing the collected data, a means for requesting the generative AI model to make improvement proposals for the entire community based on the analysis results, and a means for providing the generated improvement proposals to the community administrator. This makes it possible to effectively improve the entire community.

[0522] "User" refers to an individual user who uses the system to input their concerns and receive answers from the generative AI model.

[0523] "Worries" refer to problems or concerns that users input through the system and that should be resolved by the generative AI model.

[0524] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on collected problem data and then makes suggestions for improvements to the entire community based on the results of data analysis.

[0525] "Collection means" refers to a method or device for incorporating the worries and consultation details entered by users into the system.

[0526] "Transmission means" refers to the means by which collected data is sent to the generative AI model and an answer is obtained.

[0527] "Provision means" refers to a method or device for presenting answers and improvement suggestions obtained from a generative AI model to users and community administrators.

[0528] "Data storage means" refers to a method or device for storing collected problem data and answers obtained from the generative AI model in a database.

[0529] "Analysis tools" refers to methods or devices for analyzing accumulated data and identifying common patterns or trends.

[0530] "Means for requesting improvement proposals" refers to a means for requesting improvement proposals for the entire community from the generative AI model based on the analysis results.

[0531] "Community Manager" refers to a person or organization that has the authority to receive generated improvement suggestions and reflect them in the management and activities of the community.

[0532] Overall system configuration

[0533] This invention is a system that collects user concerns and provides answers to those concerns and improvement suggestions for the entire community using a generative AI model. The system includes a terminal where users input their concerns, a server that receives the input data and instructs other components to process it, a generative AI model that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0534] Collecting user concerns

[0535] The device provides an interface for users to input their concerns. The interface includes text boxes, options, a send button, etc. The user uses this interface to enter their concerns or questions and clicks the send button.

[0536] Specifically, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0537] Generative AI answer generation

[0538] The server receives the worry data sent from the device and passes it to the generative AI model. Specifically, this data is properly formatted and sent as a request to the generative AI model's API. The generative AI model generates an appropriate answer based on the input worry content and returns the result to the server.

[0539] For example, in response to a problem such as "I can't stay motivated to study," a generative AI model could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[0540] Example prompt: "A user expressed the following concern: 'I'm worried about safety at night.' Please provide specific advice on this concern."

[0541] Providing answers

[0542] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[0543] Data accumulation and analysis

[0544] The server stores the collected worry data and the answers from the generative AI model in a database. By recording each interaction, data analysis can be performed later.

[0545] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0546] Community-based improvement proposals

[0547] The server requests improvement proposals from the generative AI model based on the analysis results. The generative AI model generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it may suggest "introducing a learning support system and holding regular learning consultation sessions." This improvement proposal is provided to the administrator via the server.

[0548] This allows administrators to take concrete action to improve the operation and activities of the entire community based on the improvement suggestions provided.

[0549] Specific examples

[0550] The user inputs and submits a concern such as "I'm worried about safety at night." The device sends this information to the server. The server then sends this concern to the generative AI model and receives the generated answer. The generative AI model's answer is, "Please consider working with the local government to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user. Furthermore, if multiple residents raise the same concern, the server performs data analysis and identifies a trend of "many people are worried about safety at night." The server then requests specific improvement proposals from the generative AI model, proposing "strengthening nighttime patrols and installing security cameras." The server notifies the local government administrator of this improvement proposal, and specific improvement measures are implemented.

[0551] As described above, the present invention provides a system that can address users' concerns and improve the community as a whole.

[0552] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0553] Step 1: User input of concerns

[0554] The terminal provides an interface for the user to input their worries. The user enters their worries in the text box and clicks the send button. For example, a student might enter "I can't get motivated to study" and click the send button. At this point, the terminal converts the input data into JSON format and prepares it for sending. Input data: The user's worries. Output data: Worry data in JSON format.

[0555] Step 2: Submit your problem data

[0556] The device sends the generated worry data to the server via the network. The HTTP protocol is used for transmission. Input data: Worry data in JSON format. Output data: Worry data sent to the server. Specific operations include generating a request header and encoding the data.

[0557] Step 3: Generative AI model generates answers

[0558] The server passes the worry data received from the device to the generative AI model. The server then formats the data appropriately and sends it to the generative AI model as an API request. Input data: The worry data sent to the server. Output data: The answer data from the generative AI model. Specific operations include data format conversion, sending a request to an API endpoint, and authentication processing.

[0559] Step 4: Receiving response data

[0560] The generative AI model generates an answer to the received problem data and returns the result to the server. The server receives the generated answer data. Input data: Request data to the generative AI model. Output data: Generated answer data. Specific operations include natural language processing, data analysis, and execution of answer generation algorithms within the AI ​​model.

[0561] Step 5: Submit your response data

[0562] The server reformats the generated response data and sends it back to the original terminal. Specifically, it converts the data into a format that is easy for the user to understand and sends it as an HTTP response. Input data: Generated response data. Output data: Formatted response data. Specific operations include data format conversion and response header generation.

[0563] Step 6: Display the answer to the user

[0564] The device receives the answer data sent from the server and displays it to the user. The user can check the answer displayed on the screen and get advice. Input data: Formatted answer data. Output data: Answer displayed to the user. Specific operations include updating the UI and executing notification functions.

[0565] Step 7: Data accumulation

[0566] The server stores the collected problem data and generated answer data in a database, which enables later data analysis. Input data: user problem data and generated answer data. Output data: data stored in the database. Specific operations include encoding data and executing database transactions.

[0567] Step 8: Analyze data and identify trends

[0568] The server periodically analyzes the accumulated data to identify common patterns and trends. Input data: accumulated worry data and answer data. Output data: trend data as the analysis result. Specific operations include running statistical analysis algorithms, cleansing the data, and generating analysis reports.

[0569] Step 9: Generate community-wide improvement suggestions

[0570] The server requests specific improvement proposals based on the analysis results and the generative AI model. The generative AI model generates specific improvement proposals for the entire community based on the analysis results. Input data: trend data as the analysis result. Output data: improvement proposals from the generative AI model. Specific operations include generating prompts to the AI ​​model and sending API requests.

[0571] Step 10: Notify administrators

[0572] The server notifies the generated improvement proposals through the administrator interface. The administrator receives the notification and plans and executes actions to specifically implement the proposed improvement measures. Input data: Generated improvement proposals. Output data: Improvement proposals notified to the administrator. Specific operations include generating notification messages and updating the administrator dashboard.

[0573] (Application example 1)

[0574] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0575] Conventional community support systems only collect residents' concerns and provide answers to them, but are insufficient in addressing public safety and security. It is also difficult to efficiently manage and analyze data collected from residents and quickly provide specific measures to improve public safety. As a result, residents' concerns remain unresolved, and the public safety of the entire community remains unimproved.

[0576] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0577] In this invention, the server includes means for collecting concerns from residents, means for transmitting the collected concern data to the generative AI and obtaining a response, means for providing the generated response to residents, means for accumulating and analyzing the collected data, means for requesting the generative AI to propose improvements for the entire community based on the analysis results, means for providing the generated improvement proposals to the community leader, means for providing a smart device application for collecting concerns about public safety and security, and means for providing and recording the generated public safety improvement proposals. This makes it possible to efficiently collect residents' concerns about public safety and to quickly provide specific improvement measures using AI.

[0578] A "resident" is an individual who resides in or is enrolled in a particular community, such as a municipality or school.

[0579] The means for collecting "worries" are devices or applications that provide an interface for residents to input their problems and concerns and record them digitally.

[0580] "Generative AI" is an AI system that automatically generates appropriate answers and suggestions based on input concerns and data.

[0581] The "means of obtaining an answer" is the process of sending the collected data to generative artificial intelligence and obtaining an answer as the output result.

[0582] "Means of delivery" refers to the methods or devices by which the generated answers and improvement suggestions are displayed or communicated to residents and community leaders.

[0583] The "means for storing and analyzing data" is a mechanism for storing the collected worry data and generated answers in a database and later analyzing the data.

[0584] The "means for requesting improvement proposals" is a function that allows the server to instruct the generative artificial intelligence to create improvement proposals for the entire community based on the analysis results.

[0585] A "community leader" is an individual or organization that represents a community or group and is responsible for running and managing it.

[0586] A "smart device application" is a software application that runs on a mobile communication terminal such as a smartphone or tablet.

[0587] "Public Safety Improvement Proposals" are proposals for specific actions or measures to improve the safety of the community.

[0588] "Means of recording" refers to a function that stores the provided public safety improvement proposals and their implementation results in a database, making them available for later reference.

[0589] The present invention is a system that collects the concerns of residents in a community, provides answers using generative artificial intelligence, and makes suggestions for improving the entire community based on that data. Specific embodiments of the system are described below.

[0590] Overall system configuration

[0591] The system includes the following elements:

[0592] 1. A means of collecting residents' concerns

[0593] The system allows residents to input their concerns using an application installed on their smartphones, with an interface that includes text boxes, options, and a submit button.

[0594] Specifically, if a resident has concerns about public safety, they can enter something like "I'm worried about public safety at night" into the app and press the send button, which will send the information to the server.

[0595] 2. A means of sending collected worry data to generative AI and obtaining answers

[0596] The server receives the worry data sent from the device and sends it to the generative AI, which generates an appropriate answer based on the content of the worry and returns the result to the server.

[0597] For example, if a generative AI is sent a concern such as "I'm worried about the safety of the area at night," it will generate a response such as, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[0598] 3. A means of providing generated answers to residents

[0599] The server formats the generated answer and sends it back to the original terminal, which displays it to the user, allowing the resident to receive specific advice about their problem.

[0600] 4. Means of storing and analyzing collected data

[0601] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[0602] For example, if multiple residents express similar concerns about public safety, analyzing this data can identify that "there are many concerns about public safety at night in certain areas."

[0603] 5. A method to request generative AI to propose improvements for the entire community based on the analysis results

[0604] The server requests improvement proposals from the generative AI based on the analysis results, and the generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data.

[0605] For example, an improvement proposal such as "strengthening night patrols and installing security cameras" is generated.

[0606] 6. A means to provide generated improvement suggestions to community leaders

[0607] The server notifies the generated improvement proposal to the community leader, who can then implement specific safety measures based on the proposed improvement proposal.

[0608] Program processing and use of hardware and software

[0609] This system uses hardware and software such as a smartphone app, generative AI API, server, and database. Specifically, the following processes are performed:

[0610] Collecting residents' concerns

[0611] Residents' concern data is collected through the application interface and sent to the server in JSON format.

[0612] AI-powered answer generation

[0613] The collected data is sent to a generative artificial intelligence API, which generates appropriate answers.

[0614] Data accumulation and analysis

[0615] Analyze the accumulated data to identify common patterns and trends.

[0616] Providing improvement suggestions

[0617] Improvement suggestions generated by generative artificial intelligence are provided to community leaders.

[0618] Specific examples

[0619] Residents enter their concerns, such as "I'm worried about the safety at night," and send it.

[0620] Example prompt: "I'm worried about the safety of my family at night. Please tell me what specific measures I can take."

[0621] The server sends this information to the generative AI, which generates a response. The generative AI responds: "Consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[0622] The server then sends this response to the user's device and displays it to them. If multiple residents raise similar concerns, the server analyzes the data, identifies trends, and then requests a generative AI proposal for improvement. The proposal suggests "strengthening nighttime patrols and installing security cameras." The server notifies community leaders of this proposal, encouraging them to implement specific safety measures.

[0623] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[0624] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0625] Step 1:

[0626] Residents use the smartphone application interface to input their concerns, for example, "I'm worried about the safety of the area at night," and then press the send button.

[0627] Input: User's problem text

[0628] Output: JSON formatted worries data

[0629] Step 2:

[0630] The device converts the user's input data into JSON format and sends it to the server, including metadata such as the user ID and timestamp.

[0631] Input: JSON formatted worries data

[0632] Output: Troubles data sent to the server

[0633] Step 3:

[0634] The server analyzes the received worry data and executes a process to send a request to the generative AI API. The server then formats the data appropriately and sends it to the AI.

[0635] Input: Worry data sent to the server

[0636] Output: The request sent to the generative AI API

[0637] Step 4:

[0638] The generative AI generates an appropriate answer based on the worry data received from the server. The prompt "I'm worried about the safety of my home at night. Please tell me what specific measures I can take" is input into the AI, and an answer is output.

[0639] Input: A request sent to the generative artificial intelligence API

[0640] Output: The generated answer

[0641] Step 5:

[0642] The server receives the answer returned by the generative AI and formats it before sending it back to the device, where it is provided to the user as specific advice.

[0643] Input: Generated Answer

[0644] Output: Formatted answer

[0645] Step 6:

[0646] The terminal receives the formatted response sent from the server and displays it to the user, who can then review the specific advice and take any necessary action.

[0647] Input: Formatted answer

[0648] Output: Advice displayed to the user

[0649] Step 7:

[0650] The server stores the collected worry data and generated answers in a database. The data includes the user ID, timestamp, content of the worry, and generated answers.

[0651] Input: Problem data and generated answers

[0652] Output: Records saved in the database

[0653] Step 8:

[0654] The accumulated data is periodically analyzed to identify trends and common problems. Based on the analysis results, the server sends multiple data sets to a generative AI system, which then generates improvement proposals for the entire community.

[0655] Input: Multiple records stored in a database

[0656] Output: Generated improvement suggestions

[0657] Step 9:

[0658] The server will notify community leaders of the generated improvement suggestions and encourage them to implement specific safety measures, either by email or via a specific administrator user interface.

[0659] Input: Generated improvement suggestions

[0660] Output: Improvement suggestions communicated to community leaders

[0661] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[0662] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0663] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence and an emotion engine, and further proposes improvements for the entire community based on the accumulated data.

[0664] Overall system configuration

[0665] The system includes a terminal for residents to input their concerns, a server that receives the input data and processes it in conjunction with an emotion engine that recognizes emotions, generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0666] Collecting user concerns and recognizing emotions

[0667] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[0668] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0669] Emotion Recognition and Answer Generation

[0670] The server receives the worry data sent from the device and passes it to the emotion engine, which analyzes the user's emotions from the input text data and identifies emotions such as "anxiety" or "disappointment."

[0671] The server passes the emotion data obtained from the emotion engine to the generative AI and instructs it to generate an answer along with the details of the problem. The generative AI generates an appropriate answer based on this data. For example, in response to the problem of "I can't get motivated to study," it generates an answer that is in tune with the person's emotions, such as "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax as you work."

[0672] Providing answers

[0673] The server receives the answer from the generative AI and sends it to the device in an appropriate format. The device then displays the answer to the user, allowing the user to receive specific, empathetic advice for their concerns.

[0674] Data accumulation and analysis

[0675] The server stores the collected worry data, generated answers, and emotional data generated by the emotion engine in a database. By recording each interaction, the data can be analyzed later.

[0676] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation and feeling anxious about their studies. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0677] Community-based improvement proposals

[0678] The server then requests improvement proposals from the generative AI based on the analysis results. The generative AI then generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a support system to improve motivation in learning and holding regular counseling sessions."

[0679] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[0680] Specific examples

[0681] The user types in "I'm worried about the safety at night" and sends it. The device sends this information to the server. The server sends this concern to the emotion engine, which recognizes it as "anxiety." The server then sends this to the generative AI and receives the generated answer. The generative AI's answer is, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective in reducing anxiety." The server sends this answer to the device and displays it to the user.

[0682] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify that there are many concerns about safety at night. It then asks the generative AI to propose specific improvements, suggesting strengthening nighttime patrols and installing security cameras. The server then notifies the local government administrator of these improvement proposals, and specific measures are implemented.

[0683] In this way, the present invention provides a system that can address the concerns of residents while being sensitive to their feelings, and can improve the community as a whole.

[0684] The processing flow will be explained below.

[0685] Step 1:

[0686] The user enters their concerns or questions into the input form on the device and clicks the send button. For example, they might enter, "I can't get motivated to study."

[0687] Step 2:

[0688] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[0689] Step 3:

[0690] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[0691] Step 4:

[0692] The server sends the properly formatted worry data to the emotion engine and asks it to extract emotion data from the text data entered by the user. The emotion engine analyzes the text and identifies emotions such as "anxiety" and "disappointment."

[0693] Step 5:

[0694] The emotion engine returns the analyzed emotion data to the server. For example, the emotion "anxiety" is recognized from the user's input.

[0695] Step 6:

[0696] The server combines the text data of the user's worries and emotion data and sends it to the generative AI. The transmitted content includes the user's worries and the emotions recognized.

[0697] Step 7:

[0698] The generative AI generates appropriate answers based on the worries and emotions it receives. For example, if it receives the worry of "I can't get motivated to study" and the emotion of "anxiety," it generates an answer that is in line with those emotions: "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax."

[0699] Step 8:

[0700] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[0701] Step 9:

[0702] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[0703] Step 10:

[0704] The device displays the generated answer to the user, allowing the user to receive specific advice that is in line with their own feelings about their troubles.

[0705] Step 11:

[0706] The server stores the user's consultation details, generated answers, and emotional data analyzed by the emotion engine in a database, including the user ID, the content of the problem, the generated answers, the recognized emotions, and a timestamp.

[0707] Step 12:

[0708] The server periodically runs a batch process that analyzes the accumulated data, performing text analysis and clustering to identify common concerns, trends, and associated sentiments.

[0709] Step 13:

[0710] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study and are feeling anxious. Please propose improvements that can be implemented by the entire school."

[0711] Step 14:

[0712] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular counseling sessions."

[0713] Step 15:

[0714] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[0715] Example 2

[0716] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0717] In modern society, communities such as local governments and schools are required to quickly and appropriately resolve the various concerns faced by residents and students. However, conventional systems require a lot of time and effort to collect and analyze concerns, provide appropriate advice, and accumulate data and generate improvement proposals, making it difficult to effectively utilize large amounts of data.

[0718] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0719] In this invention, the server includes a means for collecting concerns from residents, a means for transmitting the collected concern data to an emotion analysis engine and identifying emotions, and a means for transmitting the emotion data and concern data identified by the emotion analysis engine to a generative AI model and obtaining answers. This makes it possible to provide quick and appropriate answers to residents' concerns that are sensitive to their emotions, and to generate improvement proposals for the entire community based on the accumulated data.

[0720] "Residents" refers to individuals who belong to a particular community, such as citizens, students, or staff.

[0721] "Worries" refers to specific information entered into the terminal, such as the problems, questions, and mental burdens residents face.

[0722] "Collection" refers to the process of centrally acquiring the concerns and data entered by residents through their devices and sending them to a server, etc.

[0723] An "emotion analysis engine" refers to a program or software that automatically analyzes the emotional state of residents from text data collected from them.

[0724] "Emotion Data" refers to data indicative of a user's emotional state as determined by an emotion analysis engine.

[0725] A "generative AI model" refers to an artificial intelligence system that automatically generates appropriate answers and improvement suggestions based on collected worry data and emotional data.

[0726] "Answer" refers to information provided by the generative AI model that offers advice or solutions to residents' concerns.

[0727] "Data accumulation" refers to the process of storing collected worry data, generated answers, emotional data, etc. in a database.

[0728] "Data analysis" refers to the process of analyzing accumulated data and identifying common patterns and trends.

[0729] "Improvement proposals" refer to proposals for effective measures and countermeasures for the entire community based on the results of data analysis.

[0730] "Community Leader" refers to an administrator or leader who is responsible for receiving improvement suggestions and taking concrete action based on them.

[0731] MODE FOR CARRYING OUT THE INVENTION

[0732] This invention is a system for improving the entire community by collecting and analyzing the concerns of residents in communities such as local governments and schools and providing appropriate advice. This system includes a terminal for residents to input their concerns, an emotion analysis engine, a generative AI model, a server including a database, and an interface for administrators.

[0733] System configuration and functions

[0734] 1. Terminal

[0735] It provides an interface for residents to input their concerns. The interface includes a text box and a submit button where users can write their concerns or questions and submit them. The submitted data is sent to the server in JSON format.

[0736] 2. Server

[0737] The server has several main functions.

[0738] Receiving and sending data

[0739] It receives worry data sent from the device and passes it to an emotion analysis engine. After emotion analysis, it sends the data to a generative AI model to obtain an answer.

[0740] Sentiment Analysis Engine

[0741] The sentiment analysis engine identifies the user's emotional state from collected text data, using natural language processing and machine learning techniques.

[0742] Generative AI Models

[0743] Based on the emotion data and concerns identified by the sentiment analysis engine, appropriate answers are generated using deep learning and large-scale language models.

[0744] Database

[0745] The collected worry data, emotion data, generated answers, etc. are stored, which allows for subsequent data analysis.

[0746] Data analysis

[0747] The accumulated data is analyzed to identify common patterns and trends, providing insights for generating community-wide improvement recommendations.

[0748] Admin Interface

[0749] It provides managers with improvement proposals generated based on the analysis results and provides an interface for planning and implementing specific countermeasures.

[0750] Specific examples

[0751] In a specific scenario, a student enters a concern such as "I can't get motivated to study" into their device and clicks the send button. This information is sent in JSON format to the server, which passes it to the emotion analysis engine. The emotion analysis engine analyzes it as "anxiety," and the server sends this emotion data to the generative AI model. The generative AI model generates the answer, "It's effective to set detailed goals and accumulate small feelings of accomplishment. Make sure to also take time to relax." The server sends this answer to the device and displays it to the user.

[0752] Prompt Sentence Examples

[0753] Examples of prompts provided to generative AI models include:

[0754] "User input: 'I'm not motivated to study'

[0755] Emotion engine analysis results: 'Anxiety'

[0756] Prompt for generative AI: 'If the user is worried about their motivation to study, please provide appropriate advice.'"

[0757] In this way, the system can provide quick and appropriate answers to specific concerns users have, and can also use the accumulated data to improve the community as a whole.

[0758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0759] Step 1:

[0760] The user enters their concerns through the device interface and clicks the send button. The input is in a text box, for example, "I can't get motivated to study." The input here is raw text data. The device converts this text data into JSON format and prepares it for transmission.

[0761] Step 2:

[0762] The device sends the worry data entered by the user to the server. The sent data is in JSON format and specifically contains the text data "I can't get motivated to study." The server receives this JSON data.

[0763] Input: Text data of concerns from the device (JSON format)

[0764] Output: JSON data received by the server

[0765] Step 3:

[0766] The server analyzes the received worry data and prepares it for passing to the emotion analysis engine. Specifically, it extracts the text portion and converts it into a format that the emotion analysis engine can analyze. After the text analysis preparation is complete, the server sends the data to the emotion analysis engine.

[0767] Input: Received JSON data

[0768] Data processing: Extracting text and converting it into an analyzable format

[0769] Output: Text data to be sent to the sentiment analysis engine

[0770] Step 4:

[0771] The emotion analysis engine analyzes the text data sent from the server and identifies the user's emotion. For example, for the text "I'm not motivated to study," it identifies the emotion "anxiety." This identified emotion data is sent to the server.

[0772] Input: Text data for analysis

[0773] Data Computing: Sentiment Analysis, Identifying Emotional States

[0774] Output: Identified emotion data (e.g., anxiety)

[0775] Step 5:

[0776] The server receives the emotion data obtained from the emotion analysis engine and sends it along with the text data of the worries to the generative AI model. The data sent includes the details of the worries and the identified emotion data.

[0777] Input: Emotion data, worry text data

[0778] Data transmission: Send emotion and worry data to the generative AI model

[0779] Output: Data sent to the generative AI model completed

[0780] Step 6:

[0781] The generative AI model generates an appropriate answer based on the received emotion data and worry data. For example, in response to the worry "I can't get motivated to study" in response to the emotion "anxiety," the model generates the answer "It's effective to set detailed goals and accumulate small accomplishments. Make sure to also take time to relax." The generated answer is sent to the server.

[0782] Input: Emotion data, worry data

[0783] Data Computation: Generating Answers with Generative AI Models

[0784] Output: Generated response data

[0785] Step 7:

[0786] The server receives the answer from the generative AI model, converts it into an appropriate format (e.g., JSON), and sends it to the device.

[0787] Input: Answer data from the generative AI model

[0788] Data processing: converting to the appropriate format

[0789] Output: Response data sent to the device

[0790] Step 8:

[0791] The device displays the answers received from the server to the user, who can then check the displayed content to receive specific, empathetic advice about their concerns.

[0792] Input: Response data sent from the server

[0793] Output: The answer displayed to the user

[0794] Step 9:

[0795] The server stores the collected worry data, generated answers, and emotion data in a database, which enables subsequent data analysis.

[0796] Input: Worry data, emotion data, generated answers

[0797] Data storage: Saving to a database

[0798] Output: Accumulated data

[0799] Step 10:

[0800] The server analyzes the accumulated data and identifies common patterns and trends. For example, it reveals that many students struggle with motivation to study. This analysis results in the basis for suggesting improvements for the entire community.

[0801] Input: Accumulated data

[0802] Data analysis: identifying patterns and trends

[0803] Output: Analysis results (e.g., many students struggle with motivation to study)

[0804] Step 11:

[0805] The server requests improvement proposals from the generative AI model based on the analysis results, and the generative AI model generates specific improvement proposals based on the analysis results and sends them to the server.

[0806] Input: Analysis results

[0807] Data computation: generating improvement suggestions

[0808] Output: Generated improvement suggestions

[0809] Step 12:

[0810] The server provides the generated improvement proposals to community leaders through an administrator interface, who then plan and implement specific actions based on the proposals.

[0811] Input: Improvement suggestion

[0812] Data transmission: Transmission to the administrator interface

[0813] Output: Improvement suggestions provided to the administrator

[0814] This trend will lead to the realization of a system that can quickly and appropriately resolve residents' concerns while improving the community as a whole.

[0815] (Application example 2)

[0816] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0817] In electronic payment services, there is a need to effectively collect user complaints and provide tailored responses. Another challenge is to improve user satisfaction by accumulating and analyzing data on these complaints and issues and proposing improvements to the service as a whole.

[0818] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting worries from residents, means for analyzing the collected worry data using an emotion engine, and means for transmitting the analyzed emotion data and worry data to the generative AI and obtaining a response. This makes it possible to provide specific advice that is tailored to the user.

[0819] "Resident" refers to a user of the electronic payment service.

[0820] "Problems" refer to dissatisfaction or problems users experience while using electronic payment services.

[0821] "Collection means" refers to the interface and functions used to collect user concerns.

[0822] An "emotion engine" refers to software or a system for analyzing emotions from text data entered by the user.

[0823] "Generative artificial intelligence" refers to AI technology that generates appropriate answers based on analyzed emotional data and concerns.

[0824] "Collected data" refers to information collected from users regarding their concerns and complaints.

[0825] "Problem Data" is data collected from users regarding specific problems.

[0826] "Answer providing means" refers to the function or interface for providing the generated answer to the user.

[0827] "Data storage means" refers to a database or storage system for storing collected data.

[0828] "Analysis means" refers to the algorithms and software used to analyze the accumulated data.

[0829] "Improvement proposal generation means" refers to a function or system for generating improvement proposals for the entire service based on the analyzed data.

[0830] "Community leaders" refer to operators and managers of electronic payment services.

[0831] "Advice provision means" refers to functions and systems that use emotion engines and generative artificial intelligence to generate appropriate advice and provide it to users.

[0832] "Statistical analysis means" refers to software or systems for statistically analyzing accumulated data.

[0833] The components of the system for implementing this invention include a terminal for inputting worries, a server for processing data, an emotion engine, generative artificial intelligence, and necessary interfaces.

[0834] Hardware and Software Configuration

[0835] The server is operated using the following software and hardware:

[0836] Emotion engine: IBM Watson Tone Analyzer

[0837] Generative artificial intelligence: OpenAI GPT-3

[0838] Database: RDBMS such as MySQL or PostgreSQL

[0839] Server hardware: powerful CPU, sufficient memory, and storage space

[0840] The device uses a smartphone or smart glasses to provide an interface for users to input their concerns, which may include text boxes, options, a submit button, etc.

[0841] Data processing flow

[0842] 1. Collecting user concerns

[0843] Users input and submit their concerns and complaints about electronic payment services using an input interface on their device, which may be provided by a mobile or web application.

[0844] 2. Sending data to the server

[0845] The worries entered by the user are sent to the server in JSON format, which then passes the received data to the emotion engine for analysis.

[0846] 3. Emotional Recognition

[0847] The emotion engine (IBM Watson Tone Analyzer) installed on the server analyzes the user's emotions from the input text data and identifies emotions such as "dissatisfaction" and "stress."

[0848] 4. Answer Generation

[0849] Based on the emotional data and worry data obtained from the emotion engine, the server uses generative artificial intelligence (OpenAI GPT-3) to generate appropriate answers tailored to the user.

[0850] 5. Providing answers to users

[0851] The server then sends the generated answer in an appropriate format to the device, which then displays it to the user, providing specific and emotionally relevant advice.

[0852] 6. Data accumulation and analysis

[0853] The server stores all interactions (input of worries, answers, emotional data) in a database, which is then subjected to statistical analysis.

[0854] 7. Suggestions for improving the overall service

[0855] The server statistically analyzes the accumulated data and generates suggestions for improving the overall service based on generative artificial intelligence. These suggestions are provided to the operator of the electronic payment service.

[0856] Specific examples

[0857] For example, a user might input and submit a complaint such as, "Smart payment isn't working in stores." The device then sends this data to the server. The server uses an emotion engine to recognize this as "dissatisfaction." The emotion data and complaint are then sent to a generative AI, which generates an answer such as: "If smart payment isn't working in stores, please make sure you're using the latest version of the app and that you always have a stable internet connection." The server then sends this answer to the device and displays it to the user.

[0858] Prompt Sentence Examples

[0859] "The user's emotion is dissatisfaction, and their problem is that smart payment in-store doesn't work. Please provide some advice to resolve this problem."

[0860] In this way, a system is provided that can provide specific advice that is sensitive to the user's feelings and improve the entire electronic payment service.

[0861] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0862] Step 1:

[0863] The user opens an interface on their device (smartphone or smart glasses) to input their concerns. They write their concerns or complaints in the input form and press the submit button. For example, they might enter "Smart payment isn't working properly at the store." The input data is sent to the server in JSON format.

[0864] Step 2:

[0865] The server receives JSON-formatted worry data sent by the user. The received data includes text entered by the user. The server prepares this text data to be passed to the emotion engine.

[0866] Step 3:

[0867] The server calls the emotion engine (IBM Watson Tone Analyzer) and sends the text data entered by the user. The emotion engine analyzes the user's emotions from the text data and identifies emotions such as "dissatisfaction" or "stress." The analysis results are returned to the server.

[0868] Step 4:

[0869] The server checks the emotion analysis results received from the emotion engine and sends the emotion data and the original concern data to the generative artificial intelligence (OpenAI GPT-3). The emotion data and concern data are sent along with a prompt. For example, "The emotion felt by the user is dissatisfaction, and the concern is that smart payment in stores is not working well. Please provide some advice to resolve this concern."

[0870] Step 5:

[0871] The generative artificial intelligence (OpenAI GPT-3) generates a response tailored to the user based on the prompt received. For example, it might generate advice such as, "If smart payment doesn't work in-store, please make sure you're using the latest version of the app and that you always have a secure internet connection." The generated advice is then returned to the server.

[0872] Step 6:

[0873] The server receives the answers from the generative AI and sends them to the device in an appropriate format. The server stores the answer data in a database. At the same time, all interactions (input of worries, emotion analysis results, generated answers) are accumulated in the database.

[0874] Step 7:

[0875] The device displays the answer received from the server to the user, who then checks the displayed advice and implements the solution to resolve the problem.

[0876] Step 8:

[0877] The server periodically performs statistical analysis of the accumulated data. This identifies common patterns and trends, and gathers data to generate service-wide improvement proposals. Based on this data, the server requests the generative AI to make service-wide improvement proposals.

[0878] Step 9:

[0879] The generative AI generates specific improvement proposals based on the received data. For example, it might generate an improvement proposal such as, "As part of a service-wide overhaul, we propose the introduction of a new connection protocol and the addition of an FAQ section." The server then provides this to the service administrator.

[0880] Through these steps, the system can provide specific advice that is sensitive to the user's emotions and improve the overall electronic payment service.

[0881] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0882] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0883] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0884] [Third embodiment]

[0885] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0886] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0887] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0888] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0889] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0890] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0891] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0892] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0893] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0894] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0895] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0896] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0897] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence, and then makes suggestions for improving the entire community based on the accumulated data.

[0898] Overall system configuration

[0899] The system includes a terminal for residents to input their concerns, a server that receives and processes the input data, a generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0900] Collecting user concerns

[0901] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[0902] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0903] Generative AI answer generation

[0904] The server receives the worry data sent from the device and passes it to the generative AI. Specifically, this data is appropriately formatted and sent as a request to the generative AI's API. The generative AI generates an appropriate answer based on the input worry content and returns the result to the server.

[0905] For example, in response to a problem such as "I can't stay motivated to study," a generative AI could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[0906] Providing answers

[0907] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[0908] Data accumulation and analysis

[0909] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[0910] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0911] Community-based improvement proposals

[0912] The server requests improvement proposals from the generative AI based on the analysis results. The generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a learning support system and holding regular learning consultation sessions."

[0913] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[0914] Specific examples

[0915] The user inputs and sends a concern such as "I'm worried about the safety of my neighborhood at night." The device sends this information to the server. The server sends this concern to the generative AI and receives a generated answer. The generative AI's answer is, "Please consider working with local governments to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user.

[0916] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify a trend of "high levels of anxiety about safety at night." It then requests specific improvement proposals from the generative AI, suggesting "increased nighttime patrols and the installation of security cameras." The server then notifies the local government administrator of these improvement proposals, which are then implemented.

[0917] In this way, the present invention provides a system that can address residents' concerns and improve the community as a whole.

[0918] The processing flow will be explained below.

[0919] Step 1:

[0920] The user enters their concerns or questions into the input form on the device and clicks the send button. The input information is then sent from the device to the server by the "send" action.

[0921] Step 2:

[0922] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[0923] Step 3:

[0924] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[0925] Step 4:

[0926] The server then sends the worry data, which has been confirmed to be in the correct format, to the generative AI API. The sent content includes the worry text data and related metadata (e.g., user ID, category, etc.).

[0927] Step 5:

[0928] The generative AI generates an appropriate answer based on the data it receives and sends it back to the server. For example, if the user says, "I'm not motivated to study," the generated answer might be, "It's effective to set detailed goals and accumulate small achievements. Try dividing your daily study time into 30-minute segments and concentrating on them."

[0929] Step 6:

[0930] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[0931] Step 7:

[0932] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[0933] Step 8:

[0934] The device displays the received answer data on the user interface, allowing the user to see the generative AI's answer to their problem.

[0935] Step 9:

[0936] The server stores the user's inquiry and the generated answer in a database, which includes the user ID, the content of the problem, the generated answer, and a timestamp.

[0937] Step 10:

[0938] The server periodically runs a batch process to analyze the accumulated data, which performs text analysis and clustering to identify common concerns and trends.

[0939] Step 11:

[0940] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study. Please propose improvements that can be implemented by the entire school."

[0941] Step 12:

[0942] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular learning consultation sessions."

[0943] Step 13:

[0944] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[0945] This series of processes allows us to address residents' concerns and provide suggestions for improving the community as a whole.

[0946] Example 1

[0947] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0948] Conventional methods for collecting and responding to residents' concerns in communities often lack specific advice for individual concerns, and there was no system in place to utilize the accumulated data on concerns to improve the community as a whole. As a result, individual concerns were not resolved, and the improvement of the community as a whole did not progress.

[0949] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0950] In this invention, the server includes a means for collecting worries from users, a means for transmitting the collected worry data to the generative AI model and obtaining an answer, and a means for providing the generated answer to the user. This makes it possible to provide prompt and specific advice for the user's worries. Furthermore, the server includes a means for accumulating and analyzing the collected data, a means for requesting the generative AI model to make improvement proposals for the entire community based on the analysis results, and a means for providing the generated improvement proposals to the community administrator. This makes it possible to effectively improve the entire community.

[0951] "User" refers to an individual user who uses the system to input their concerns and receive answers from the generative AI model.

[0952] "Worries" refer to problems or concerns that users input through the system and that should be resolved by the generative AI model.

[0953] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on collected problem data and then makes suggestions for improvements to the entire community based on the results of data analysis.

[0954] "Collection means" refers to a method or device for incorporating the worries and consultation details entered by users into the system.

[0955] "Transmission means" refers to the means by which collected data is sent to the generative AI model and an answer is obtained.

[0956] "Provision means" refers to a method or device for presenting answers and improvement suggestions obtained from a generative AI model to users and community administrators.

[0957] "Data storage means" refers to a method or device for storing collected problem data and answers obtained from the generative AI model in a database.

[0958] "Analysis tools" refers to methods or devices for analyzing accumulated data and identifying common patterns or trends.

[0959] "Means for requesting improvement proposals" refers to a means for requesting improvement proposals for the entire community from the generative AI model based on the analysis results.

[0960] "Community Manager" refers to a person or organization that has the authority to receive generated improvement suggestions and reflect them in the management and activities of the community.

[0961] Overall system configuration

[0962] This invention is a system that collects user concerns and provides answers to those concerns and improvement suggestions for the entire community using a generative AI model. The system includes a terminal where users input their concerns, a server that receives the input data and instructs other components to process it, a generative AI model that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[0963] Collecting user concerns

[0964] The device provides an interface for users to input their concerns. The interface includes text boxes, options, a send button, etc. The user uses this interface to enter their concerns or questions and clicks the send button.

[0965] Specifically, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[0966] Generative AI answer generation

[0967] The server receives the worry data sent from the device and passes it to the generative AI model. Specifically, this data is properly formatted and sent as a request to the generative AI model's API. The generative AI model generates an appropriate answer based on the input worry content and returns the result to the server.

[0968] For example, in response to a problem such as "I can't stay motivated to study," a generative AI model could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[0969] Example prompt: "A user expressed the following concern: 'I'm worried about safety at night.' Please provide specific advice on this concern."

[0970] Providing answers

[0971] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[0972] Data accumulation and analysis

[0973] The server stores the collected worry data and the answers from the generative AI model in a database. By recording each interaction, data analysis can be performed later.

[0974] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[0975] Community-based improvement proposals

[0976] The server requests improvement proposals from the generative AI model based on the analysis results. The generative AI model generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it may suggest "introducing a learning support system and holding regular learning consultation sessions." This improvement proposal is provided to the administrator via the server.

[0977] This allows administrators to take concrete action to improve the operation and activities of the entire community based on the improvement suggestions provided.

[0978] Specific examples

[0979] The user inputs and submits a concern such as "I'm worried about safety at night." The device sends this information to the server. The server then sends this concern to the generative AI model and receives the generated answer. The generative AI model's answer is, "Please consider working with the local government to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user. Furthermore, if multiple residents raise the same concern, the server performs data analysis and identifies a trend of "many people are worried about safety at night." The server then requests specific improvement proposals from the generative AI model, proposing "strengthening nighttime patrols and installing security cameras." The server notifies the local government administrator of this improvement proposal, and specific improvement measures are implemented.

[0980] As described above, the present invention provides a system that can address users' concerns and improve the community as a whole.

[0981] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0982] Step 1: User input of concerns

[0983] The terminal provides an interface for the user to input their worries. The user enters their worries in the text box and clicks the send button. For example, a student might enter "I can't get motivated to study" and click the send button. At this point, the terminal converts the input data into JSON format and prepares it for sending. Input data: The user's worries. Output data: Worry data in JSON format.

[0984] Step 2: Submit your problem data

[0985] The device sends the generated worry data to the server via the network. The HTTP protocol is used for transmission. Input data: Worry data in JSON format. Output data: Worry data sent to the server. Specific operations include generating a request header and encoding the data.

[0986] Step 3: Generative AI model generates answers

[0987] The server passes the worry data received from the device to the generative AI model. The server then formats the data appropriately and sends it to the generative AI model as an API request. Input data: The worry data sent to the server. Output data: The answer data from the generative AI model. Specific operations include data format conversion, sending a request to an API endpoint, and authentication processing.

[0988] Step 4: Receiving response data

[0989] The generative AI model generates an answer to the received problem data and returns the result to the server. The server receives the generated answer data. Input data: Request data to the generative AI model. Output data: Generated answer data. Specific operations include natural language processing, data analysis, and execution of answer generation algorithms within the AI ​​model.

[0990] Step 5: Submit your response data

[0991] The server reformats the generated response data and sends it back to the original terminal. Specifically, it converts the data into a format that is easy for the user to understand and sends it as an HTTP response. Input data: Generated response data. Output data: Formatted response data. Specific operations include data format conversion and response header generation.

[0992] Step 6: Display the answer to the user

[0993] The device receives the answer data sent from the server and displays it to the user. The user can check the answer displayed on the screen and get advice. Input data: Formatted answer data. Output data: Answer displayed to the user. Specific operations include updating the UI and executing notification functions.

[0994] Step 7: Data accumulation

[0995] The server stores the collected problem data and generated answer data in a database, which enables later data analysis. Input data: user problem data and generated answer data. Output data: data stored in the database. Specific operations include encoding data and executing database transactions.

[0996] Step 8: Analyze data and identify trends

[0997] The server periodically analyzes the accumulated data to identify common patterns and trends. Input data: accumulated worry data and answer data. Output data: trend data as the analysis result. Specific operations include running statistical analysis algorithms, cleansing the data, and generating analysis reports.

[0998] Step 9: Generate community-wide improvement suggestions

[0999] The server requests specific improvement proposals based on the analysis results and the generative AI model. The generative AI model generates specific improvement proposals for the entire community based on the analysis results. Input data: trend data as the analysis result. Output data: improvement proposals from the generative AI model. Specific operations include generating prompts to the AI ​​model and sending API requests.

[1000] Step 10: Notify administrators

[1001] The server notifies the generated improvement proposals through the administrator interface. The administrator receives the notification and plans and executes actions to specifically implement the proposed improvement measures. Input data: Generated improvement proposals. Output data: Improvement proposals notified to the administrator. Specific operations include generating notification messages and updating the administrator dashboard.

[1002] (Application example 1)

[1003] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1004] Conventional community support systems only collect residents' concerns and provide answers to them, but are insufficient in addressing public safety and security. It is also difficult to efficiently manage and analyze data collected from residents and quickly provide specific measures to improve public safety. As a result, residents' concerns remain unresolved, and the public safety of the entire community remains unimproved.

[1005] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1006] In this invention, the server includes means for collecting concerns from residents, means for transmitting the collected concern data to the generative AI and obtaining a response, means for providing the generated response to residents, means for accumulating and analyzing the collected data, means for requesting the generative AI to propose improvements for the entire community based on the analysis results, means for providing the generated improvement proposals to the community leader, means for providing a smart device application for collecting concerns about public safety and security, and means for providing and recording the generated public safety improvement proposals. This makes it possible to efficiently collect residents' concerns about public safety and to quickly provide specific improvement measures using AI.

[1007] A "resident" is an individual who resides in or is enrolled in a particular community, such as a municipality or school.

[1008] The means for collecting "worries" are devices or applications that provide an interface for residents to input their problems and concerns and record them digitally.

[1009] "Generative AI" is an AI system that automatically generates appropriate answers and suggestions based on input concerns and data.

[1010] The "means of obtaining an answer" is the process of sending the collected data to generative artificial intelligence and obtaining an answer as the output result.

[1011] "Means of delivery" refers to the methods or devices by which the generated answers and improvement suggestions are displayed or communicated to residents and community leaders.

[1012] The "means for storing and analyzing data" is a mechanism for storing the collected worry data and generated answers in a database and later analyzing the data.

[1013] The "means for requesting improvement proposals" is a function that allows the server to instruct the generative artificial intelligence to create improvement proposals for the entire community based on the analysis results.

[1014] A "community leader" is an individual or organization that represents a community or group and is responsible for running and managing it.

[1015] A "smart device application" is a software application that runs on a mobile communication terminal such as a smartphone or tablet.

[1016] "Public Safety Improvement Proposals" are proposals for specific actions or measures to improve the safety of the community.

[1017] "Means of recording" refers to a function that stores the provided public safety improvement proposals and their implementation results in a database, making them available for later reference.

[1018] The present invention is a system that collects the concerns of residents in a community, provides answers using generative artificial intelligence, and makes suggestions for improving the entire community based on that data. Specific embodiments of the system are described below.

[1019] Overall system configuration

[1020] The system includes the following elements:

[1021] 1. A means of collecting residents' concerns

[1022] The system allows residents to input their concerns using an application installed on their smartphones, with an interface that includes text boxes, options, and a submit button.

[1023] Specifically, if a resident has concerns about public safety, they can enter something like "I'm worried about public safety at night" into the app and press the send button, which will send the information to the server.

[1024] 2. A means of sending collected worry data to generative AI and obtaining answers

[1025] The server receives the worry data sent from the device and sends it to the generative AI, which generates an appropriate answer based on the content of the worry and returns the result to the server.

[1026] For example, if a generative AI is sent a concern such as "I'm worried about the safety of the area at night," it will generate a response such as, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[1027] 3. A means of providing generated answers to residents

[1028] The server formats the generated answer and sends it back to the original terminal, which displays it to the user, allowing the resident to receive specific advice about their problem.

[1029] 4. Means of storing and analyzing collected data

[1030] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[1031] For example, if multiple residents express similar concerns about public safety, analyzing this data can identify that "there are many concerns about public safety at night in certain areas."

[1032] 5. A method to request generative AI to propose improvements for the entire community based on the analysis results

[1033] The server requests improvement proposals from the generative AI based on the analysis results, and the generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data.

[1034] For example, an improvement proposal such as "strengthening night patrols and installing security cameras" is generated.

[1035] 6. A means to provide generated improvement suggestions to community leaders

[1036] The server notifies the generated improvement proposal to the community leader, who can then implement specific safety measures based on the proposed improvement proposal.

[1037] Program processing and use of hardware and software

[1038] This system uses hardware and software such as a smartphone app, generative AI API, server, and database. Specifically, the following processes are performed:

[1039] Collecting residents' concerns

[1040] Residents' concern data is collected through the application interface and sent to the server in JSON format.

[1041] AI-powered answer generation

[1042] The collected data is sent to a generative artificial intelligence API, which generates appropriate answers.

[1043] Data accumulation and analysis

[1044] Analyze the accumulated data to identify common patterns and trends.

[1045] Providing improvement suggestions

[1046] Improvement suggestions generated by generative artificial intelligence are provided to community leaders.

[1047] Specific examples

[1048] Residents enter their concerns, such as "I'm worried about the safety at night," and send it.

[1049] Example prompt: "I'm worried about the safety of my family at night. Please tell me what specific measures I can take."

[1050] The server sends this information to the generative AI, which generates a response. The generative AI responds: "Consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[1051] The server then sends this response to the user's device and displays it to them. If multiple residents raise similar concerns, the server analyzes the data, identifies trends, and then requests a generative AI proposal for improvement. The proposal suggests "strengthening nighttime patrols and installing security cameras." The server notifies community leaders of this proposal, encouraging them to implement specific safety measures.

[1052] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[1053] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1054] Step 1:

[1055] Residents use the smartphone application interface to input their concerns, for example, "I'm worried about the safety of the area at night," and then press the send button.

[1056] Input: User's problem text

[1057] Output: JSON formatted worries data

[1058] Step 2:

[1059] The device converts the user's input data into JSON format and sends it to the server, including metadata such as the user ID and timestamp.

[1060] Input: JSON formatted worries data

[1061] Output: Troubles data sent to the server

[1062] Step 3:

[1063] The server analyzes the received worry data and executes a process to send a request to the generative AI API. The server then formats the data appropriately and sends it to the AI.

[1064] Input: Worry data sent to the server

[1065] Output: The request sent to the generative AI API

[1066] Step 4:

[1067] The generative AI generates an appropriate answer based on the worry data received from the server. The prompt "I'm worried about the safety of my home at night. Please tell me what specific measures I can take" is input into the AI, and an answer is output.

[1068] Input: A request sent to the generative artificial intelligence API

[1069] Output: The generated answer

[1070] Step 5:

[1071] The server receives the answer returned by the generative AI and formats it before sending it back to the device, where it is provided to the user as specific advice.

[1072] Input: Generated Answer

[1073] Output: Formatted answer

[1074] Step 6:

[1075] The terminal receives the formatted response sent from the server and displays it to the user, who can then review the specific advice and take any necessary action.

[1076] Input: Formatted answer

[1077] Output: Advice displayed to the user

[1078] Step 7:

[1079] The server stores the collected worry data and generated answers in a database. The data includes the user ID, timestamp, content of the worry, and generated answers.

[1080] Input: Problem data and generated answers

[1081] Output: Records saved in the database

[1082] Step 8:

[1083] The accumulated data is periodically analyzed to identify trends and common problems. Based on the analysis results, the server sends multiple data sets to a generative AI system, which then generates improvement proposals for the entire community.

[1084] Input: Multiple records stored in a database

[1085] Output: Generated improvement suggestions

[1086] Step 9:

[1087] The server will notify community leaders of the generated improvement suggestions and encourage them to implement specific safety measures, either by email or via a specific administrator user interface.

[1088] Input: Generated improvement suggestions

[1089] Output: Improvement suggestions communicated to community leaders

[1090] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[1091] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1092] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence and an emotion engine, and further proposes improvements for the entire community based on the accumulated data.

[1093] Overall system configuration

[1094] The system includes a terminal for residents to input their concerns, a server that receives the input data and processes it in conjunction with an emotion engine that recognizes emotions, generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[1095] Collecting user concerns and recognizing emotions

[1096] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[1097] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[1098] Emotion Recognition and Answer Generation

[1099] The server receives the worry data sent from the device and passes it to the emotion engine, which analyzes the user's emotions from the input text data and identifies emotions such as "anxiety" or "disappointment."

[1100] The server passes the emotion data obtained from the emotion engine to the generative AI and instructs it to generate an answer along with the details of the problem. The generative AI generates an appropriate answer based on this data. For example, in response to the problem of "I can't get motivated to study," it generates an answer that is in tune with the person's emotions, such as "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax as you work."

[1101] Providing answers

[1102] The server receives the answer from the generative AI and sends it to the device in an appropriate format. The device then displays the answer to the user, allowing the user to receive specific, empathetic advice for their concerns.

[1103] Data accumulation and analysis

[1104] The server stores the collected worry data, generated answers, and emotional data generated by the emotion engine in a database. By recording each interaction, the data can be analyzed later.

[1105] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation and feeling anxious about their studies. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[1106] Community-based improvement proposals

[1107] The server then requests improvement proposals from the generative AI based on the analysis results. The generative AI then generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a support system to improve motivation in learning and holding regular counseling sessions."

[1108] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[1109] Specific examples

[1110] The user types in "I'm worried about the safety at night" and sends it. The device sends this information to the server. The server sends this concern to the emotion engine, which recognizes it as "anxiety." The server then sends this to the generative AI and receives the generated answer. The generative AI's answer is, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective in reducing anxiety." The server sends this answer to the device and displays it to the user.

[1111] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify that there are many concerns about safety at night. It then asks the generative AI to propose specific improvements, suggesting strengthening nighttime patrols and installing security cameras. The server then notifies the local government administrator of these improvement proposals, and specific measures are implemented.

[1112] In this way, the present invention provides a system that can address the concerns of residents while being sensitive to their feelings, and can improve the community as a whole.

[1113] The processing flow will be explained below.

[1114] Step 1:

[1115] The user enters their concerns or questions into the input form on the device and clicks the send button. For example, they might enter, "I can't get motivated to study."

[1116] Step 2:

[1117] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[1118] Step 3:

[1119] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[1120] Step 4:

[1121] The server sends the properly formatted worry data to the emotion engine and asks it to extract emotion data from the text data entered by the user. The emotion engine analyzes the text and identifies emotions such as "anxiety" and "disappointment."

[1122] Step 5:

[1123] The emotion engine returns the analyzed emotion data to the server. For example, the emotion "anxiety" is recognized from the user's input.

[1124] Step 6:

[1125] The server combines the text data of the user's worries and emotion data and sends it to the generative AI. The transmitted content includes the user's worries and the emotions recognized.

[1126] Step 7:

[1127] The generative AI generates appropriate answers based on the worries and emotions it receives. For example, if it receives the worry of "I can't get motivated to study" and the emotion of "anxiety," it generates an answer that is in line with those emotions: "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax."

[1128] Step 8:

[1129] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[1130] Step 9:

[1131] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[1132] Step 10:

[1133] The device displays the generated answer to the user, allowing the user to receive specific advice that is in line with their own feelings about their troubles.

[1134] Step 11:

[1135] The server stores the user's consultation details, generated answers, and emotional data analyzed by the emotion engine in a database, including the user ID, the content of the problem, the generated answers, the recognized emotions, and a timestamp.

[1136] Step 12:

[1137] The server periodically runs a batch process that analyzes the accumulated data, performing text analysis and clustering to identify common concerns, trends, and associated sentiments.

[1138] Step 13:

[1139] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study and are feeling anxious. Please propose improvements that can be implemented by the entire school."

[1140] Step 14:

[1141] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular counseling sessions."

[1142] Step 15:

[1143] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[1144] Example 2

[1145] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1146] In modern society, communities such as local governments and schools are required to quickly and appropriately resolve the various concerns faced by residents and students. However, conventional systems require a lot of time and effort to collect and analyze concerns, provide appropriate advice, and accumulate data and generate improvement proposals, making it difficult to effectively utilize large amounts of data.

[1147] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1148] In this invention, the server includes a means for collecting concerns from residents, a means for transmitting the collected concern data to an emotion analysis engine and identifying emotions, and a means for transmitting the emotion data and concern data identified by the emotion analysis engine to a generative AI model and obtaining answers. This makes it possible to provide quick and appropriate answers to residents' concerns that are sensitive to their emotions, and to generate improvement proposals for the entire community based on the accumulated data.

[1149] "Residents" refers to individuals who belong to a particular community, such as citizens, students, or staff.

[1150] "Worries" refers to specific information entered into the terminal, such as the problems, questions, and mental burdens residents face.

[1151] "Collection" refers to the process of centrally acquiring the concerns and data entered by residents through their devices and sending them to a server, etc.

[1152] An "emotion analysis engine" refers to a program or software that automatically analyzes the emotional state of residents from text data collected from them.

[1153] "Emotion Data" refers to data indicative of a user's emotional state as determined by an emotion analysis engine.

[1154] A "generative AI model" refers to an artificial intelligence system that automatically generates appropriate answers and improvement suggestions based on collected worry data and emotional data.

[1155] "Answer" refers to information provided by the generative AI model that offers advice or solutions to residents' concerns.

[1156] "Data accumulation" refers to the process of storing collected worry data, generated answers, emotional data, etc. in a database.

[1157] "Data analysis" refers to the process of analyzing accumulated data and identifying common patterns and trends.

[1158] "Improvement proposals" refer to proposals for effective measures and countermeasures for the entire community based on the results of data analysis.

[1159] "Community Leader" refers to an administrator or leader who is responsible for receiving improvement suggestions and taking concrete action based on them.

[1160] MODE FOR CARRYING OUT THE INVENTION

[1161] This invention is a system for improving the entire community by collecting and analyzing the concerns of residents in communities such as local governments and schools and providing appropriate advice. This system includes a terminal for residents to input their concerns, an emotion analysis engine, a generative AI model, a server including a database, and an interface for administrators.

[1162] System configuration and functions

[1163] 1. Terminal

[1164] It provides an interface for residents to input their concerns. The interface includes a text box and a submit button where users can write their concerns or questions and submit them. The submitted data is sent to the server in JSON format.

[1165] 2. Server

[1166] The server has several main functions.

[1167] Receiving and sending data

[1168] It receives worry data sent from the device and passes it to an emotion analysis engine. After emotion analysis, it sends the data to a generative AI model to obtain an answer.

[1169] Sentiment Analysis Engine

[1170] The sentiment analysis engine identifies the user's emotional state from collected text data, using natural language processing and machine learning techniques.

[1171] Generative AI Models

[1172] Based on the emotion data and concerns identified by the sentiment analysis engine, appropriate answers are generated using deep learning and large-scale language models.

[1173] Database

[1174] The collected worry data, emotion data, generated answers, etc. are stored, which allows for subsequent data analysis.

[1175] Data analysis

[1176] The accumulated data is analyzed to identify common patterns and trends, providing insights for generating community-wide improvement recommendations.

[1177] Admin Interface

[1178] It provides managers with improvement proposals generated based on the analysis results and provides an interface for planning and implementing specific countermeasures.

[1179] Specific examples

[1180] In a specific scenario, a student enters a concern such as "I can't get motivated to study" into their device and clicks the send button. This information is sent in JSON format to the server, which passes it to the emotion analysis engine. The emotion analysis engine analyzes it as "anxiety," and the server sends this emotion data to the generative AI model. The generative AI model generates the answer, "It's effective to set detailed goals and accumulate small feelings of accomplishment. Make sure to also take time to relax." The server sends this answer to the device and displays it to the user.

[1181] Prompt Sentence Examples

[1182] Examples of prompts provided to generative AI models include:

[1183] "User input: 'I'm not motivated to study'

[1184] Emotion engine analysis results: 'Anxiety'

[1185] Prompt for generative AI: 'If the user is worried about their motivation to study, please provide appropriate advice.'"

[1186] In this way, the system can provide quick and appropriate answers to specific concerns users have, and can also use the accumulated data to improve the community as a whole.

[1187] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1188] Step 1:

[1189] The user enters their concerns through the device interface and clicks the send button. The input is in a text box, for example, "I can't get motivated to study." The input here is raw text data. The device converts this text data into JSON format and prepares it for transmission.

[1190] Step 2:

[1191] The device sends the worry data entered by the user to the server. The sent data is in JSON format and specifically contains the text data "I can't get motivated to study." The server receives this JSON data.

[1192] Input: Text data of concerns from the device (JSON format)

[1193] Output: JSON data received by the server

[1194] Step 3:

[1195] The server analyzes the received worry data and prepares it for passing to the emotion analysis engine. Specifically, it extracts the text portion and converts it into a format that the emotion analysis engine can analyze. After the text analysis preparation is complete, the server sends the data to the emotion analysis engine.

[1196] Input: Received JSON data

[1197] Data processing: Extracting text and converting it into an analyzable format

[1198] Output: Text data to be sent to the sentiment analysis engine

[1199] Step 4:

[1200] The emotion analysis engine analyzes the text data sent from the server and identifies the user's emotion. For example, for the text "I'm not motivated to study," it identifies the emotion "anxiety." This identified emotion data is sent to the server.

[1201] Input: Text data for analysis

[1202] Data Computing: Sentiment Analysis, Identifying Emotional States

[1203] Output: Identified emotion data (e.g., anxiety)

[1204] Step 5:

[1205] The server receives the emotion data obtained from the emotion analysis engine and sends it along with the text data of the worries to the generative AI model. The data sent includes the details of the worries and the identified emotion data.

[1206] Input: Emotion data, worry text data

[1207] Data transmission: Send emotion and worry data to the generative AI model

[1208] Output: Data sent to the generative AI model completed

[1209] Step 6:

[1210] The generative AI model generates an appropriate answer based on the received emotion data and worry data. For example, in response to the worry "I can't get motivated to study" in response to the emotion "anxiety," the model generates the answer "It's effective to set detailed goals and accumulate small accomplishments. Make sure to also take time to relax." The generated answer is sent to the server.

[1211] Input: Emotion data, worry data

[1212] Data Computation: Generating Answers with Generative AI Models

[1213] Output: Generated response data

[1214] Step 7:

[1215] The server receives the answer from the generative AI model, converts it into an appropriate format (e.g., JSON), and sends it to the device.

[1216] Input: Answer data from the generative AI model

[1217] Data processing: converting to the appropriate format

[1218] Output: Response data sent to the device

[1219] Step 8:

[1220] The device displays the answers received from the server to the user, who can then check the displayed content to receive specific, empathetic advice about their concerns.

[1221] Input: Response data sent from the server

[1222] Output: The answer displayed to the user

[1223] Step 9:

[1224] The server stores the collected worry data, generated answers, and emotion data in a database, which enables subsequent data analysis.

[1225] Input: Worry data, emotion data, generated answers

[1226] Data storage: Saving to a database

[1227] Output: Accumulated data

[1228] Step 10:

[1229] The server analyzes the accumulated data and identifies common patterns and trends. For example, it reveals that many students struggle with motivation to study. This analysis results in the basis for suggesting improvements for the entire community.

[1230] Input: Accumulated data

[1231] Data analysis: identifying patterns and trends

[1232] Output: Analysis results (e.g., many students struggle with motivation to study)

[1233] Step 11:

[1234] The server requests improvement proposals from the generative AI model based on the analysis results, and the generative AI model generates specific improvement proposals based on the analysis results and sends them to the server.

[1235] Input: Analysis results

[1236] Data computation: generating improvement suggestions

[1237] Output: Generated improvement suggestions

[1238] Step 12:

[1239] The server provides the generated improvement proposals to community leaders through an administrator interface, who then plan and implement specific actions based on the proposals.

[1240] Input: Improvement suggestion

[1241] Data transmission: Transmission to the administrator interface

[1242] Output: Improvement suggestions provided to the administrator

[1243] This trend will lead to the realization of a system that can quickly and appropriately resolve residents' concerns while improving the community as a whole.

[1244] (Application example 2)

[1245] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1246] In electronic payment services, there is a need to effectively collect user complaints and provide tailored responses. Another challenge is to improve user satisfaction by accumulating and analyzing data on these complaints and issues and proposing improvements to the service as a whole.

[1247] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting worries from residents, means for analyzing the collected worry data using an emotion engine, and means for transmitting the analyzed emotion data and worry data to the generative AI and obtaining a response. This makes it possible to provide specific advice that is tailored to the user.

[1248] "Resident" refers to a user of the electronic payment service.

[1249] "Problems" refer to dissatisfaction or problems users experience while using electronic payment services.

[1250] "Collection means" refers to the interface and functions used to collect user concerns.

[1251] An "emotion engine" refers to software or a system for analyzing emotions from text data entered by the user.

[1252] "Generative artificial intelligence" refers to AI technology that generates appropriate answers based on analyzed emotional data and concerns.

[1253] "Collected data" refers to information collected from users regarding their concerns and complaints.

[1254] "Problem Data" is data collected from users regarding specific problems.

[1255] "Answer providing means" refers to the function or interface for providing the generated answer to the user.

[1256] "Data storage means" refers to a database or storage system for storing collected data.

[1257] "Analysis means" refers to the algorithms and software used to analyze the accumulated data.

[1258] "Improvement proposal generation means" refers to a function or system for generating improvement proposals for the entire service based on the analyzed data.

[1259] "Community leaders" refer to operators and managers of electronic payment services.

[1260] "Advice provision means" refers to functions and systems that use emotion engines and generative artificial intelligence to generate appropriate advice and provide it to users.

[1261] "Statistical analysis means" refers to software or systems for statistically analyzing accumulated data.

[1262] The components of the system for implementing this invention include a terminal for inputting worries, a server for processing data, an emotion engine, generative artificial intelligence, and necessary interfaces.

[1263] Hardware and Software Configuration

[1264] The server is operated using the following software and hardware:

[1265] Emotion engine: IBM Watson Tone Analyzer

[1266] Generative artificial intelligence: OpenAI GPT-3

[1267] Database: RDBMS such as MySQL or PostgreSQL

[1268] Server hardware: powerful CPU, sufficient memory, and storage space

[1269] The device uses a smartphone or smart glasses to provide an interface for users to input their concerns, which may include text boxes, options, a submit button, etc.

[1270] Data processing flow

[1271] 1. Collecting user concerns

[1272] Users input and submit their concerns and complaints about electronic payment services using an input interface on their device, which may be provided by a mobile or web application.

[1273] 2. Sending data to the server

[1274] The worries entered by the user are sent to the server in JSON format, which then passes the received data to the emotion engine for analysis.

[1275] 3. Emotional Recognition

[1276] The emotion engine (IBM Watson Tone Analyzer) installed on the server analyzes the user's emotions from the input text data and identifies emotions such as "dissatisfaction" and "stress."

[1277] 4. Answer Generation

[1278] Based on the emotional data and worry data obtained from the emotion engine, the server uses generative artificial intelligence (OpenAI GPT-3) to generate appropriate answers tailored to the user.

[1279] 5. Providing answers to users

[1280] The server then sends the generated answer in an appropriate format to the device, which then displays it to the user, providing specific and emotionally relevant advice.

[1281] 6. Data accumulation and analysis

[1282] The server stores all interactions (input of worries, answers, emotional data) in a database, which is then subjected to statistical analysis.

[1283] 7. Suggestions for improving the overall service

[1284] The server statistically analyzes the accumulated data and generates suggestions for improving the overall service based on generative artificial intelligence. These suggestions are provided to the operator of the electronic payment service.

[1285] Specific examples

[1286] For example, a user might input and submit a complaint such as, "Smart payment isn't working in stores." The device then sends this data to the server. The server uses an emotion engine to recognize this as "dissatisfaction." The emotion data and complaint are then sent to a generative AI, which generates an answer such as: "If smart payment isn't working in stores, please make sure you're using the latest version of the app and that you always have a stable internet connection." The server then sends this answer to the device and displays it to the user.

[1287] Prompt Sentence Examples

[1288] "The user's emotion is dissatisfaction, and their problem is that smart payment in-store doesn't work. Please provide some advice to resolve this problem."

[1289] In this way, a system is provided that can provide specific advice that is sensitive to the user's feelings and improve the entire electronic payment service.

[1290] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1291] Step 1:

[1292] The user opens an interface on their device (smartphone or smart glasses) to input their concerns. They write their concerns or complaints in the input form and press the submit button. For example, they might enter "Smart payment isn't working properly at the store." The input data is sent to the server in JSON format.

[1293] Step 2:

[1294] The server receives JSON-formatted worry data sent by the user. The received data includes text entered by the user. The server prepares this text data to be passed to the emotion engine.

[1295] Step 3:

[1296] The server calls the emotion engine (IBM Watson Tone Analyzer) and sends the text data entered by the user. The emotion engine analyzes the user's emotions from the text data and identifies emotions such as "dissatisfaction" or "stress." The analysis results are returned to the server.

[1297] Step 4:

[1298] The server checks the emotion analysis results received from the emotion engine and sends the emotion data and the original concern data to the generative artificial intelligence (OpenAI GPT-3). The emotion data and concern data are sent along with a prompt. For example, "The emotion felt by the user is dissatisfaction, and the concern is that smart payment in stores is not working well. Please provide some advice to resolve this concern."

[1299] Step 5:

[1300] The generative artificial intelligence (OpenAI GPT-3) generates a response tailored to the user based on the prompt received. For example, it might generate advice such as, "If smart payment doesn't work in-store, please make sure you're using the latest version of the app and that you always have a secure internet connection." The generated advice is then returned to the server.

[1301] Step 6:

[1302] The server receives the answers from the generative AI and sends them to the device in an appropriate format. The server stores the answer data in a database. At the same time, all interactions (input of worries, emotion analysis results, generated answers) are accumulated in the database.

[1303] Step 7:

[1304] The device displays the answer received from the server to the user, who then checks the displayed advice and implements the solution to resolve the problem.

[1305] Step 8:

[1306] The server periodically performs statistical analysis of the accumulated data. This identifies common patterns and trends, and gathers data to generate service-wide improvement proposals. Based on this data, the server requests the generative AI to make service-wide improvement proposals.

[1307] Step 9:

[1308] The generative AI generates specific improvement proposals based on the received data. For example, it might generate an improvement proposal such as, "As part of a service-wide overhaul, we propose the introduction of a new connection protocol and the addition of an FAQ section." The server then provides this to the service administrator.

[1309] Through these steps, the system can provide specific advice that is sensitive to the user's emotions and improve the overall electronic payment service.

[1310] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1311] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1312] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1313] [Fourth embodiment]

[1314] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1315] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1316] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1317] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1318] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1319] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1320] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1321] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1322] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1323] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1324] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1325] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1326] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1327] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence, and then makes suggestions for improving the entire community based on the accumulated data.

[1328] Overall system configuration

[1329] The system includes a terminal for residents to input their concerns, a server that receives and processes the input data, a generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[1330] Collecting user concerns

[1331] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[1332] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[1333] Generative AI answer generation

[1334] The server receives the worry data sent from the device and passes it to the generative AI. Specifically, this data is appropriately formatted and sent as a request to the generative AI's API. The generative AI generates an appropriate answer based on the input worry content and returns the result to the server.

[1335] For example, in response to a problem such as "I can't stay motivated to study," a generative AI could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[1336] Providing answers

[1337] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[1338] Data accumulation and analysis

[1339] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[1340] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[1341] Community-based improvement proposals

[1342] The server requests improvement proposals from the generative AI based on the analysis results. The generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a learning support system and holding regular learning consultation sessions."

[1343] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[1344] Specific examples

[1345] The user inputs and sends a concern such as "I'm worried about the safety of my neighborhood at night." The device sends this information to the server. The server sends this concern to the generative AI and receives a generated answer. The generative AI's answer is, "Please consider working with local governments to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user.

[1346] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify a trend of "high levels of anxiety about safety at night." It then requests specific improvement proposals from the generative AI, suggesting "increased nighttime patrols and the installation of security cameras." The server then notifies the local government administrator of these improvement proposals, which are then implemented.

[1347] In this way, the present invention provides a system that can address residents' concerns and improve the community as a whole.

[1348] The processing flow will be explained below.

[1349] Step 1:

[1350] The user enters their concerns or questions into the input form on the device and clicks the send button. The input information is then sent from the device to the server by the "send" action.

[1351] Step 2:

[1352] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[1353] Step 3:

[1354] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[1355] Step 4:

[1356] The server then sends the worry data, which has been confirmed to be in the correct format, to the generative AI API. The sent content includes the worry text data and related metadata (e.g., user ID, category, etc.).

[1357] Step 5:

[1358] The generative AI generates an appropriate answer based on the data it receives and sends it back to the server. For example, if the user says, "I'm not motivated to study," the generated answer might be, "It's effective to set detailed goals and accumulate small achievements. Try dividing your daily study time into 30-minute segments and concentrating on them."

[1359] Step 6:

[1360] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[1361] Step 7:

[1362] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[1363] Step 8:

[1364] The device displays the received answer data on the user interface, allowing the user to see the generative AI's answer to their problem.

[1365] Step 9:

[1366] The server stores the user's inquiry and the generated answer in a database, which includes the user ID, the content of the problem, the generated answer, and a timestamp.

[1367] Step 10:

[1368] The server periodically runs a batch process to analyze the accumulated data, which performs text analysis and clustering to identify common concerns and trends.

[1369] Step 11:

[1370] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study. Please propose improvements that can be implemented by the entire school."

[1371] Step 12:

[1372] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular learning consultation sessions."

[1373] Step 13:

[1374] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[1375] This series of processes allows us to address residents' concerns and provide suggestions for improving the community as a whole.

[1376] Example 1

[1377] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1378] Conventional methods for collecting and responding to residents' concerns in communities often lack specific advice for individual concerns, and there was no system in place to utilize the accumulated data on concerns to improve the community as a whole. As a result, individual concerns were not resolved, and the improvement of the community as a whole did not progress.

[1379] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1380] In this invention, the server includes a means for collecting worries from users, a means for transmitting the collected worry data to the generative AI model and obtaining an answer, and a means for providing the generated answer to the user. This makes it possible to provide prompt and specific advice for the user's worries. Furthermore, the server includes a means for accumulating and analyzing the collected data, a means for requesting the generative AI model to make improvement proposals for the entire community based on the analysis results, and a means for providing the generated improvement proposals to the community administrator. This makes it possible to effectively improve the entire community.

[1381] "User" refers to an individual user who uses the system to input their concerns and receive answers from the generative AI model.

[1382] "Worries" refer to problems or concerns that users input through the system and that should be resolved by the generative AI model.

[1383] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on collected problem data and then makes suggestions for improvements to the entire community based on the results of data analysis.

[1384] "Collection means" refers to a method or device for incorporating the worries and consultation details entered by users into the system.

[1385] "Transmission means" refers to the means by which collected data is sent to the generative AI model and an answer is obtained.

[1386] "Provision means" refers to a method or device for presenting answers and improvement suggestions obtained from a generative AI model to users and community administrators.

[1387] "Data storage means" refers to a method or device for storing collected problem data and answers obtained from the generative AI model in a database.

[1388] "Analysis tools" refers to methods or devices for analyzing accumulated data and identifying common patterns or trends.

[1389] "Means for requesting improvement proposals" refers to a means for requesting improvement proposals for the entire community from the generative AI model based on the analysis results.

[1390] "Community Manager" refers to a person or organization that has the authority to receive generated improvement suggestions and reflect them in the management and activities of the community.

[1391] Overall system configuration

[1392] This invention is a system that collects user concerns and provides answers to those concerns and improvement suggestions for the entire community using a generative AI model. The system includes a terminal where users input their concerns, a server that receives the input data and instructs other components to process it, a generative AI model that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[1393] Collecting user concerns

[1394] The device provides an interface for users to input their concerns. The interface includes text boxes, options, a send button, etc. The user uses this interface to enter their concerns or questions and clicks the send button.

[1395] Specifically, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[1396] Generative AI answer generation

[1397] The server receives the worry data sent from the device and passes it to the generative AI model. Specifically, this data is properly formatted and sent as a request to the generative AI model's API. The generative AI model generates an appropriate answer based on the input worry content and returns the result to the server.

[1398] For example, in response to a problem such as "I can't stay motivated to study," a generative AI model could generate the following answer: "It's effective to set detailed goals and accumulate small feelings of accomplishment. Try starting by dividing your daily study time into 30-minute segments and concentrating on them."

[1399] Example prompt: "A user expressed the following concern: 'I'm worried about safety at night.' Please provide specific advice on this concern."

[1400] Providing answers

[1401] The server reformats the generated answer and sends it back to the device, which displays it to the user, who can then receive specific advice about their problem.

[1402] Data accumulation and analysis

[1403] The server stores the collected worry data and the answers from the generative AI model in a database. By recording each interaction, data analysis can be performed later.

[1404] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation to study. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[1405] Community-based improvement proposals

[1406] The server requests improvement proposals from the generative AI model based on the analysis results. The generative AI model generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it may suggest "introducing a learning support system and holding regular learning consultation sessions." This improvement proposal is provided to the administrator via the server.

[1407] This allows administrators to take concrete action to improve the operation and activities of the entire community based on the improvement suggestions provided.

[1408] Specific examples

[1409] The user inputs and submits a concern such as "I'm worried about safety at night." The device sends this information to the server. The server then sends this concern to the generative AI model and receives the generated answer. The generative AI model's answer is, "Please consider working with the local government to strengthen nighttime patrols. Installing security cameras would also be effective." The server sends this answer to the device and displays it to the user. Furthermore, if multiple residents raise the same concern, the server performs data analysis and identifies a trend of "many people are worried about safety at night." The server then requests specific improvement proposals from the generative AI model, proposing "strengthening nighttime patrols and installing security cameras." The server notifies the local government administrator of this improvement proposal, and specific improvement measures are implemented.

[1410] As described above, the present invention provides a system that can address users' concerns and improve the community as a whole.

[1411] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1412] Step 1: User input of concerns

[1413] The terminal provides an interface for the user to input their worries. The user enters their worries in the text box and clicks the send button. For example, a student might enter "I can't get motivated to study" and click the send button. At this point, the terminal converts the input data into JSON format and prepares it for sending. Input data: The user's worries. Output data: Worry data in JSON format.

[1414] Step 2: Submit your problem data

[1415] The device sends the generated worry data to the server via the network. The HTTP protocol is used for transmission. Input data: Worry data in JSON format. Output data: Worry data sent to the server. Specific operations include generating a request header and encoding the data.

[1416] Step 3: Generative AI model generates answers

[1417] The server passes the worry data received from the device to the generative AI model. The server then formats the data appropriately and sends it to the generative AI model as an API request. Input data: The worry data sent to the server. Output data: The answer data from the generative AI model. Specific operations include data format conversion, sending a request to an API endpoint, and authentication processing.

[1418] Step 4: Receiving response data

[1419] The generative AI model generates an answer to the received problem data and returns the result to the server. The server receives the generated answer data. Input data: Request data to the generative AI model. Output data: Generated answer data. Specific operations include natural language processing, data analysis, and execution of answer generation algorithms within the AI ​​model.

[1420] Step 5: Submit your response data

[1421] The server reformats the generated response data and sends it back to the original terminal. Specifically, it converts the data into a format that is easy for the user to understand and sends it as an HTTP response. Input data: Generated response data. Output data: Formatted response data. Specific operations include data format conversion and response header generation.

[1422] Step 6: Display the answer to the user

[1423] The device receives the answer data sent from the server and displays it to the user. The user can check the answer displayed on the screen and get advice. Input data: Formatted answer data. Output data: Answer displayed to the user. Specific operations include updating the UI and executing notification functions.

[1424] Step 7: Data accumulation

[1425] The server stores the collected problem data and generated answer data in a database, which enables later data analysis. Input data: user problem data and generated answer data. Output data: data stored in the database. Specific operations include encoding data and executing database transactions.

[1426] Step 8: Analyze data and identify trends

[1427] The server periodically analyzes the accumulated data to identify common patterns and trends. Input data: accumulated worry data and answer data. Output data: trend data as the analysis result. Specific operations include running statistical analysis algorithms, cleansing the data, and generating analysis reports.

[1428] Step 9: Generate community-wide improvement suggestions

[1429] The server requests specific improvement proposals based on the analysis results and the generative AI model. The generative AI model generates specific improvement proposals for the entire community based on the analysis results. Input data: trend data as the analysis result. Output data: improvement proposals from the generative AI model. Specific operations include generating prompts to the AI ​​model and sending API requests.

[1430] Step 10: Notify administrators

[1431] The server notifies the generated improvement proposals through the administrator interface. The administrator receives the notification and plans and executes actions to specifically implement the proposed improvement measures. Input data: Generated improvement proposals. Output data: Improvement proposals notified to the administrator. Specific operations include generating notification messages and updating the administrator dashboard.

[1432] (Application example 1)

[1433] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1434] Conventional community support systems only collect residents' concerns and provide answers to them, but are insufficient in addressing public safety and security. It is also difficult to efficiently manage and analyze data collected from residents and quickly provide specific measures to improve public safety. As a result, residents' concerns remain unresolved, and the public safety of the entire community remains unimproved.

[1435] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1436] In this invention, the server includes means for collecting concerns from residents, means for transmitting the collected concern data to the generative AI and obtaining a response, means for providing the generated response to residents, means for accumulating and analyzing the collected data, means for requesting the generative AI to propose improvements for the entire community based on the analysis results, means for providing the generated improvement proposals to the community leader, means for providing a smart device application for collecting concerns about public safety and security, and means for providing and recording the generated public safety improvement proposals. This makes it possible to efficiently collect residents' concerns about public safety and to quickly provide specific improvement measures using AI.

[1437] A "resident" is an individual who resides in or is enrolled in a particular community, such as a municipality or school.

[1438] The means for collecting "worries" are devices or applications that provide an interface for residents to input their problems and concerns and record them digitally.

[1439] "Generative AI" is an AI system that automatically generates appropriate answers and suggestions based on input concerns and data.

[1440] The "means of obtaining an answer" is the process of sending the collected data to generative artificial intelligence and obtaining an answer as the output result.

[1441] "Means of delivery" refers to the methods or devices by which the generated answers and improvement suggestions are displayed or communicated to residents and community leaders.

[1442] The "means for storing and analyzing data" is a mechanism for storing the collected worry data and generated answers in a database and later analyzing the data.

[1443] The "means for requesting improvement proposals" is a function that allows the server to instruct the generative artificial intelligence to create improvement proposals for the entire community based on the analysis results.

[1444] A "community leader" is an individual or organization that represents a community or group and is responsible for running and managing it.

[1445] A "smart device application" is a software application that runs on a mobile communication terminal such as a smartphone or tablet.

[1446] "Public Safety Improvement Proposals" are proposals for specific actions or measures to improve the safety of the community.

[1447] "Means of recording" refers to a function that stores the provided public safety improvement proposals and their implementation results in a database, making them available for later reference.

[1448] The present invention is a system that collects the concerns of residents in a community, provides answers using generative artificial intelligence, and makes suggestions for improving the entire community based on that data. Specific embodiments of the system are described below.

[1449] Overall system configuration

[1450] The system includes the following elements:

[1451] 1. A means of collecting residents' concerns

[1452] The system allows residents to input their concerns using an application installed on their smartphones, with an interface that includes text boxes, options, and a submit button.

[1453] Specifically, if a resident has concerns about public safety, they can enter something like "I'm worried about public safety at night" into the app and press the send button, which will send the information to the server.

[1454] 2. A means of sending collected worry data to generative AI and obtaining answers

[1455] The server receives the worry data sent from the device and sends it to the generative AI, which generates an appropriate answer based on the content of the worry and returns the result to the server.

[1456] For example, if a generative AI is sent a concern such as "I'm worried about the safety of the area at night," it will generate a response such as, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[1457] 3. A means of providing generated answers to residents

[1458] The server formats the generated answer and sends it back to the original terminal, which displays it to the user, allowing the resident to receive specific advice about their problem.

[1459] 4. Means of storing and analyzing collected data

[1460] The server stores the collected worry data and generated answers in a database. By recording each interaction, data analysis becomes possible later.

[1461] For example, if multiple residents express similar concerns about public safety, analyzing this data can identify that "there are many concerns about public safety at night in certain areas."

[1462] 5. A method to request generative AI to propose improvements for the entire community based on the analysis results

[1463] The server requests improvement proposals from the generative AI based on the analysis results, and the generative AI generates specific improvement proposals for the entire community based on the collected and analyzed data.

[1464] For example, an improvement proposal such as "strengthening night patrols and installing security cameras" is generated.

[1465] 6. A means to provide generated improvement suggestions to community leaders

[1466] The server notifies the generated improvement proposal to the community leader, who can then implement specific safety measures based on the proposed improvement proposal.

[1467] Program processing and use of hardware and software

[1468] This system uses hardware and software such as a smartphone app, generative AI API, server, and database. Specifically, the following processes are performed:

[1469] Collecting residents' concerns

[1470] Residents' concern data is collected through the application interface and sent to the server in JSON format.

[1471] AI-powered answer generation

[1472] The collected data is sent to a generative artificial intelligence API, which generates appropriate answers.

[1473] Data accumulation and analysis

[1474] Analyze the accumulated data to identify common patterns and trends.

[1475] Providing improvement suggestions

[1476] Improvement suggestions generated by generative artificial intelligence are provided to community leaders.

[1477] Specific examples

[1478] Residents enter their concerns, such as "I'm worried about the safety at night," and send it.

[1479] Example prompt: "I'm worried about the safety of my family at night. Please tell me what specific measures I can take."

[1480] The server sends this information to the generative AI, which generates a response. The generative AI responds: "Consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective."

[1481] The server then sends this response to the user's device and displays it to them. If multiple residents raise similar concerns, the server analyzes the data, identifies trends, and then requests a generative AI proposal for improvement. The proposal suggests "strengthening nighttime patrols and installing security cameras." The server notifies community leaders of this proposal, encouraging them to implement specific safety measures.

[1482] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[1483] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1484] Step 1:

[1485] Residents use the smartphone application interface to input their concerns, for example, "I'm worried about the safety of the area at night," and then press the send button.

[1486] Input: User's problem text

[1487] Output: JSON formatted worries data

[1488] Step 2:

[1489] The device converts the user's input data into JSON format and sends it to the server, including metadata such as the user ID and timestamp.

[1490] Input: JSON formatted worries data

[1491] Output: Troubles data sent to the server

[1492] Step 3:

[1493] The server analyzes the received worry data and executes a process to send a request to the generative AI API. The server then formats the data appropriately and sends it to the AI.

[1494] Input: Worry data sent to the server

[1495] Output: The request sent to the generative AI API

[1496] Step 4:

[1497] The generative AI generates an appropriate answer based on the worry data received from the server. The prompt "I'm worried about the safety of my home at night. Please tell me what specific measures I can take" is input into the AI, and an answer is output.

[1498] Input: A request sent to the generative artificial intelligence API

[1499] Output: The generated answer

[1500] Step 5:

[1501] The server receives the answer returned by the generative AI and formats it before sending it back to the device, where it is provided to the user as specific advice.

[1502] Input: Generated Answer

[1503] Output: Formatted answer

[1504] Step 6:

[1505] The terminal receives the formatted response sent from the server and displays it to the user, who can then review the specific advice and take any necessary action.

[1506] Input: Formatted answer

[1507] Output: Advice displayed to the user

[1508] Step 7:

[1509] The server stores the collected worry data and generated answers in a database. The data includes the user ID, timestamp, content of the worry, and generated answers.

[1510] Input: Problem data and generated answers

[1511] Output: Records saved in the database

[1512] Step 8:

[1513] The accumulated data is periodically analyzed to identify trends and common problems. Based on the analysis results, the server sends multiple data sets to a generative AI system, which then generates improvement proposals for the entire community.

[1514] Input: Multiple records stored in a database

[1515] Output: Generated improvement suggestions

[1516] Step 9:

[1517] The server will notify community leaders of the generated improvement suggestions and encourage them to implement specific safety measures, either by email or via a specific administrator user interface.

[1518] Input: Generated improvement suggestions

[1519] Output: Improvement suggestions communicated to community leaders

[1520] This will enable efficient collection of residents' concerns about public safety and rapid provision of concrete improvement measures using AI.

[1521] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1522] This invention is a system that collects the concerns of residents in communities such as local governments and schools, provides appropriate answers using generative artificial intelligence and an emotion engine, and further proposes improvements for the entire community based on the accumulated data.

[1523] Overall system configuration

[1524] The system includes a terminal for residents to input their concerns, a server that receives the input data and processes it in conjunction with an emotion engine that recognizes emotions, generative artificial intelligence that generates answers and improvement suggestions, and an interface for administrators that provides analysis results and improvement suggestions.

[1525] Collecting user concerns and recognizing emotions

[1526] The terminal provides an interface for residents to input their concerns. The interface includes text boxes, options, a send button, etc. Users can enter their concerns or questions through this interface and send them.

[1527] For example, if a student is worried about not being motivated to study, they can enter that information into an input form on their device and click the send button. This information is sent to the server in JSON format or similar.

[1528] Emotion Recognition and Answer Generation

[1529] The server receives the worry data sent from the device and passes it to the emotion engine, which analyzes the user's emotions from the input text data and identifies emotions such as "anxiety" or "disappointment."

[1530] The server passes the emotion data obtained from the emotion engine to the generative AI and instructs it to generate an answer along with the details of the problem. The generative AI generates an appropriate answer based on this data. For example, in response to the problem of "I can't get motivated to study," it generates an answer that is in tune with the person's emotions, such as "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax as you work."

[1531] Providing answers

[1532] The server receives the answer from the generative AI and sends it to the device in an appropriate format. The device then displays the answer to the user, allowing the user to receive specific, empathetic advice for their concerns.

[1533] Data accumulation and analysis

[1534] The server stores the collected worry data, generated answers, and emotional data generated by the emotion engine in a database. By recording each interaction, the data can be analyzed later.

[1535] For example, by analyzing the accumulated data, it can be determined that many students are struggling with motivation and feeling anxious about their studies. Based on this information, the server can then perform further analysis to identify common patterns and trends.

[1536] Community-based improvement proposals

[1537] The server then requests improvement proposals from the generative AI based on the analysis results. The generative AI then generates specific improvement proposals for the entire community based on the collected and analyzed data. For example, it suggests "introducing a support system to improve motivation in learning and holding regular counseling sessions."

[1538] These improvement suggestions are provided to the administrator via the server, who can then take specific actions based on the suggestions to improve the operation and activities of the entire community.

[1539] Specific examples

[1540] The user types in "I'm worried about the safety at night" and sends it. The device sends this information to the server. The server sends this concern to the emotion engine, which recognizes it as "anxiety." The server then sends this to the generative AI and receives the generated answer. The generative AI's answer is, "Please consider working with local governments to increase nighttime patrols. Installing security cameras would also be effective in reducing anxiety." The server sends this answer to the device and displays it to the user.

[1541] Furthermore, if multiple residents express similar concerns, the server will conduct data analysis and identify that there are many concerns about safety at night. It then asks the generative AI to propose specific improvements, suggesting strengthening nighttime patrols and installing security cameras. The server then notifies the local government administrator of these improvement proposals, and specific measures are implemented.

[1542] In this way, the present invention provides a system that can address the concerns of residents while being sensitive to their feelings, and can improve the community as a whole.

[1543] The processing flow will be explained below.

[1544] Step 1:

[1545] The user enters their concerns or questions into the input form on the device and clicks the send button. For example, they might enter, "I can't get motivated to study."

[1546] Step 2:

[1547] The device packages the user's input worry data in an appropriate format, such as JSON, and sends it to the server as an HTTP request.

[1548] Step 3:

[1549] The server parses the received problem data to ensure it is in the correct format, which includes validating the data (e.g., text length and category matching).

[1550] Step 4:

[1551] The server sends the properly formatted worry data to the emotion engine and asks it to extract emotion data from the text data entered by the user. The emotion engine analyzes the text and identifies emotions such as "anxiety" and "disappointment."

[1552] Step 5:

[1553] The emotion engine returns the analyzed emotion data to the server. For example, the emotion "anxiety" is recognized from the user's input.

[1554] Step 6:

[1555] The server combines the text data of the user's worries and emotion data and sends it to the generative AI. The transmitted content includes the user's worries and the emotions recognized.

[1556] Step 7:

[1557] The generative AI generates appropriate answers based on the worries and emotions it receives. For example, if it receives the worry of "I can't get motivated to study" and the emotion of "anxiety," it generates an answer that is in line with those emotions: "It's effective to set detailed goals and accumulate small accomplishments. Also, make sure to take time to relax."

[1558] Step 8:

[1559] The server receives the answers returned by the generative AI and converts them into the appropriate format, which includes organizing the answer data and formatting the text.

[1560] Step 9:

[1561] The server then sends the converted response to the terminal. The response data is sent again in JSON format or similar.

[1562] Step 10:

[1563] The device displays the generated answer to the user, allowing the user to receive specific advice that is in line with their own feelings about their troubles.

[1564] Step 11:

[1565] The server stores the user's consultation details, generated answers, and emotional data analyzed by the emotion engine in a database, including the user ID, the content of the problem, the generated answers, the recognized emotions, and a timestamp.

[1566] Step 12:

[1567] The server periodically runs a batch process that analyzes the accumulated data, performing text analysis and clustering to identify common concerns, trends, and associated sentiments.

[1568] Step 13:

[1569] Based on the analysis results, the server requests the generative AI to propose improvements for the entire community. For example, it sends a request such as, "Many students are struggling with motivation to study and are feeling anxious. Please propose improvements that can be implemented by the entire school."

[1570] Step 14:

[1571] The generative AI generates specific improvement proposals based on the analysis results and sends them back to the server. For example, a proposal might be generated that reads, "We propose introducing a learning support system and holding regular counseling sessions."

[1572] Step 15:

[1573] The server formats the generated improvement proposals for administrators and provides them to community leaders via dashboards, emails, etc. This allows administrators to obtain information for specific implementation of improvement measures.

[1574] Example 2

[1575] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1576] In modern society, communities such as local governments and schools are required to quickly and appropriately resolve the various concerns faced by residents and students. However, conventional systems require a lot of time and effort to collect and analyze concerns, provide appropriate advice, and accumulate data and generate improvement proposals, making it difficult to effectively utilize large amounts of data.

[1577] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1578] In this invention, the server includes a means for collecting concerns from residents, a means for transmitting the collected concern data to an emotion analysis engine and identifying emotions, and a means for transmitting the emotion data and concern data identified by the emotion analysis engine to a generative AI model and obtaining answers. This makes it possible to provide quick and appropriate answers to residents' concerns that are sensitive to their emotions, and to generate improvement proposals for the entire community based on the accumulated data.

[1579] "Residents" refers to individuals who belong to a particular community, such as citizens, students, or staff.

[1580] "Worries" refers to specific information entered into the terminal, such as the problems, questions, and mental burdens residents face.

[1581] "Collection" refers to the process of centrally acquiring the concerns and data entered by residents through their devices and sending them to a server, etc.

[1582] An "emotion analysis engine" refers to a program or software that automatically analyzes the emotional state of residents from text data collected from them.

[1583] "Emotion Data" refers to data indicative of a user's emotional state as determined by an emotion analysis engine.

[1584] A "generative AI model" refers to an artificial intelligence system that automatically generates appropriate answers and improvement suggestions based on collected worry data and emotional data.

[1585] "Answer" refers to information provided by the generative AI model that offers advice or solutions to residents' concerns.

[1586] "Data accumulation" refers to the process of storing collected worry data, generated answers, emotional data, etc. in a database.

[1587] "Data analysis" refers to the process of analyzing accumulated data and identifying common patterns and trends.

[1588] "Improvement proposals" refer to proposals for effective measures and countermeasures for the entire community based on the results of data analysis.

[1589] "Community Leader" refers to an administrator or leader who is responsible for receiving improvement suggestions and taking concrete action based on them.

[1590] MODE FOR CARRYING OUT THE INVENTION

[1591] This invention is a system for improving the entire community by collecting and analyzing the concerns of residents in communities such as local governments and schools and providing appropriate advice. This system includes a terminal for residents to input their concerns, an emotion analysis engine, a generative AI model, a server including a database, and an interface for administrators.

[1592] System configuration and functions

[1593] 1. Terminal

[1594] It provides an interface for residents to input their concerns. The interface includes a text box and a submit button where users can write their concerns or questions and submit them. The submitted data is sent to the server in JSON format.

[1595] 2. Server

[1596] The server has several main functions.

[1597] Receiving and sending data

[1598] It receives worry data sent from the device and passes it to an emotion analysis engine. After emotion analysis, it sends the data to a generative AI model to obtain an answer.

[1599] Sentiment Analysis Engine

[1600] The sentiment analysis engine identifies the user's emotional state from collected text data, using natural language processing and machine learning techniques.

[1601] Generative AI Models

[1602] Based on the emotion data and concerns identified by the sentiment analysis engine, appropriate answers are generated using deep learning and large-scale language models.

[1603] Database

[1604] The collected worry data, emotion data, generated answers, etc. are stored, which allows for subsequent data analysis.

[1605] Data analysis

[1606] The accumulated data is analyzed to identify common patterns and trends, providing insights for generating community-wide improvement recommendations.

[1607] Admin Interface

[1608] It provides managers with improvement proposals generated based on the analysis results and provides an interface for planning and implementing specific countermeasures.

[1609] Specific examples

[1610] In a specific scenario, a student enters a concern such as "I can't get motivated to study" into their device and clicks the send button. This information is sent in JSON format to the server, which passes it to the emotion analysis engine. The emotion analysis engine analyzes it as "anxiety," and the server sends this emotion data to the generative AI model. The generative AI model generates the answer, "It's effective to set detailed goals and accumulate small feelings of accomplishment. Make sure to also take time to relax." The server sends this answer to the device and displays it to the user.

[1611] Prompt Sentence Examples

[1612] Examples of prompts provided to generative AI models include:

[1613] "User input: 'I'm not motivated to study'

[1614] Emotion engine analysis results: 'Anxiety'

[1615] Prompt for generative AI: 'If the user is worried about their motivation to study, please provide appropriate advice.'"

[1616] In this way, the system can provide quick and appropriate answers to specific concerns users have, and can also use the accumulated data to improve the community as a whole.

[1617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1618] Step 1:

[1619] The user enters their concerns through the device interface and clicks the send button. The input is in a text box, for example, "I can't get motivated to study." The input here is raw text data. The device converts this text data into JSON format and prepares it for transmission.

[1620] Step 2:

[1621] The device sends the worry data entered by the user to the server. The sent data is in JSON format and specifically contains the text data "I can't get motivated to study." The server receives this JSON data.

[1622] Input: Text data of concerns from the device (JSON format)

[1623] Output: JSON data received by the server

[1624] Step 3:

[1625] The server analyzes the received worry data and prepares it for passing to the emotion analysis engine. Specifically, it extracts the text portion and converts it into a format that the emotion analysis engine can analyze. After the text analysis preparation is complete, the server sends the data to the emotion analysis engine.

[1626] Input: Received JSON data

[1627] Data processing: Extracting text and converting it into an analyzable format

[1628] Output: Text data to be sent to the sentiment analysis engine

[1629] Step 4:

[1630] The emotion analysis engine analyzes the text data sent from the server and identifies the user's emotion. For example, for the text "I'm not motivated to study," it identifies the emotion "anxiety." This identified emotion data is sent to the server.

[1631] Input: Text data for analysis

[1632] Data Computing: Sentiment Analysis, Identifying Emotional States

[1633] Output: Identified emotion data (e.g., anxiety)

[1634] Step 5:

[1635] The server receives the emotion data obtained from the emotion analysis engine and sends it along with the text data of the worries to the generative AI model. The data sent includes the details of the worries and the identified emotion data.

[1636] Input: Emotion data, worry text data

[1637] Data transmission: Send emotion and worry data to the generative AI model

[1638] Output: Data sent to the generative AI model completed

[1639] Step 6:

[1640] The generative AI model generates an appropriate answer based on the received emotion data and worry data. For example, in response to the worry "I can't get motivated to study" in response to the emotion "anxiety," the model generates the answer "It's effective to set detailed goals and accumulate small accomplishments. Make sure to also take time to relax." The generated answer is sent to the server.

[1641] Input: Emotion data, worry data

[1642] Data Computation: Generating Answers with Generative AI Models

[1643] Output: Generated response data

[1644] Step 7:

[1645] The server receives the answer from the generative AI model, converts it into an appropriate format (e.g., JSON), and sends it to the device.

[1646] Input: Answer data from the generative AI model

[1647] Data processing: converting to the appropriate format

[1648] Output: Response data sent to the device

[1649] Step 8:

[1650] The device displays the answers received from the server to the user, who can then check the displayed content to receive specific, empathetic advice about their concerns.

[1651] Input: Response data sent from the server

[1652] Output: The answer displayed to the user

[1653] Step 9:

[1654] The server stores the collected worry data, generated answers, and emotion data in a database, which enables subsequent data analysis.

[1655] Input: Worry data, emotion data, generated answers

[1656] Data storage: Saving to a database

[1657] Output: Accumulated data

[1658] Step 10:

[1659] The server analyzes the accumulated data and identifies common patterns and trends. For example, it reveals that many students struggle with motivation to study. This analysis results in the basis for suggesting improvements for the entire community.

[1660] Input: Accumulated data

[1661] Data analysis: identifying patterns and trends

[1662] Output: Analysis results (e.g., many students struggle with motivation to study)

[1663] Step 11:

[1664] The server requests improvement proposals from the generative AI model based on the analysis results, and the generative AI model generates specific improvement proposals based on the analysis results and sends them to the server.

[1665] Input: Analysis results

[1666] Data computation: generating improvement suggestions

[1667] Output: Generated improvement suggestions

[1668] Step 12:

[1669] The server provides the generated improvement proposals to community leaders through an administrator interface, who then plan and implement specific actions based on the proposals.

[1670] Input: Improvement suggestion

[1671] Data transmission: Transmission to the administrator interface

[1672] Output: Improvement suggestions provided to the administrator

[1673] This trend will lead to the realization of a system that can quickly and appropriately resolve residents' concerns while improving the community as a whole.

[1674] (Application example 2)

[1675] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1676] In electronic payment services, there is a need to effectively collect user complaints and provide tailored responses. Another challenge is to improve user satisfaction by accumulating and analyzing data on these complaints and issues and proposing improvements to the service as a whole.

[1677] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting worries from residents, means for analyzing the collected worry data using an emotion engine, and means for transmitting the analyzed emotion data and worry data to the generative AI and obtaining a response. This makes it possible to provide specific advice that is tailored to the user.

[1678] "Resident" refers to a user of the electronic payment service.

[1679] "Problems" refer to dissatisfaction or problems users experience while using electronic payment services.

[1680] "Collection means" refers to the interface and functions used to collect user concerns.

[1681] An "emotion engine" refers to software or a system for analyzing emotions from text data entered by the user.

[1682] "Generative artificial intelligence" refers to AI technology that generates appropriate answers based on analyzed emotional data and concerns.

[1683] "Collected data" refers to information collected from users regarding their concerns and complaints.

[1684] "Problem Data" is data collected from users regarding specific problems.

[1685] "Answer providing means" refers to the function or interface for providing the generated answer to the user.

[1686] "Data storage means" refers to a database or storage system for storing collected data.

[1687] "Analysis means" refers to the algorithms and software used to analyze the accumulated data.

[1688] "Improvement proposal generation means" refers to a function or system for generating improvement proposals for the entire service based on the analyzed data.

[1689] "Community leaders" refer to operators and managers of electronic payment services.

[1690] "Advice provision means" refers to functions and systems that use emotion engines and generative artificial intelligence to generate appropriate advice and provide it to users.

[1691] "Statistical analysis means" refers to software or systems for statistically analyzing accumulated data.

[1692] The components of the system for implementing this invention include a terminal for inputting worries, a server for processing data, an emotion engine, generative artificial intelligence, and necessary interfaces.

[1693] Hardware and Software Configuration

[1694] The server is operated using the following software and hardware:

[1695] Emotion engine: IBM Watson Tone Analyzer

[1696] Generative artificial intelligence: OpenAI GPT-3

[1697] Database: RDBMS such as MySQL or PostgreSQL

[1698] Server hardware: powerful CPU, sufficient memory, and storage space

[1699] The device uses a smartphone or smart glasses to provide an interface for users to input their concerns, which may include text boxes, options, a submit button, etc.

[1700] Data processing flow

[1701] 1. Collecting user concerns

[1702] Users input and submit their concerns and complaints about electronic payment services using an input interface on their device, which may be provided by a mobile or web application.

[1703] 2. Sending data to the server

[1704] The worries entered by the user are sent to the server in JSON format, which then passes the received data to the emotion engine for analysis.

[1705] 3. Emotional Recognition

[1706] The emotion engine (IBM Watson Tone Analyzer) installed on the server analyzes the user's emotions from the input text data and identifies emotions such as "dissatisfaction" and "stress."

[1707] 4. Answer Generation

[1708] Based on the emotional data and worry data obtained from the emotion engine, the server uses generative artificial intelligence (OpenAI GPT-3) to generate appropriate answers tailored to the user.

[1709] 5. Providing answers to users

[1710] The server then sends the generated answer in an appropriate format to the device, which then displays it to the user, providing specific and emotionally relevant advice.

[1711] 6. Data accumulation and analysis

[1712] The server stores all interactions (input of worries, answers, emotional data) in a database, which is then subjected to statistical analysis.

[1713] 7. Suggestions for improving the overall service

[1714] The server statistically analyzes the accumulated data and generates suggestions for improving the overall service based on generative artificial intelligence. These suggestions are provided to the operator of the electronic payment service.

[1715] Specific examples

[1716] For example, a user might input and submit a complaint such as, "Smart payment isn't working in stores." The device then sends this data to the server. The server uses an emotion engine to recognize this as "dissatisfaction." The emotion data and complaint are then sent to a generative AI, which generates an answer such as: "If smart payment isn't working in stores, please make sure you're using the latest version of the app and that you always have a stable internet connection." The server then sends this answer to the device and displays it to the user.

[1717] Prompt Sentence Examples

[1718] "The user's emotion is dissatisfaction, and their problem is that smart payment in-store doesn't work. Please provide some advice to resolve this problem."

[1719] In this way, a system is provided that can provide specific advice that is sensitive to the user's feelings and improve the entire electronic payment service.

[1720] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1721] Step 1:

[1722] The user opens an interface on their device (smartphone or smart glasses) to input their concerns. They write their concerns or complaints in the input form and press the submit button. For example, they might enter "Smart payment isn't working properly at the store." The input data is sent to the server in JSON format.

[1723] Step 2:

[1724] The server receives JSON-formatted worry data sent by the user. The received data includes text entered by the user. The server prepares this text data to be passed to the emotion engine.

[1725] Step 3:

[1726] The server calls the emotion engine (IBM Watson Tone Analyzer) and sends the text data entered by the user. The emotion engine analyzes the user's emotions from the text data and identifies emotions such as "dissatisfaction" or "stress." The analysis results are returned to the server.

[1727] Step 4:

[1728] The server checks the emotion analysis results received from the emotion engine and sends the emotion data and the original concern data to the generative artificial intelligence (OpenAI GPT-3). The emotion data and concern data are sent along with a prompt. For example, "The emotion felt by the user is dissatisfaction, and the concern is that smart payment in stores is not working well. Please provide some advice to resolve this concern."

[1729] Step 5:

[1730] The generative artificial intelligence (OpenAI GPT-3) generates a response tailored to the user based on the prompt received. For example, it might generate advice such as, "If smart payment doesn't work in-store, please make sure you're using the latest version of the app and that you always have a secure internet connection." The generated advice is then returned to the server.

[1731] Step 6:

[1732] The server receives the answers from the generative AI and sends them to the device in an appropriate format. The server stores the answer data in a database. At the same time, all interactions (input of worries, emotion analysis results, generated answers) are accumulated in the database.

[1733] Step 7:

[1734] The device displays the answer received from the server to the user, who then checks the displayed advice and implements the solution to resolve the problem.

[1735] Step 8:

[1736] The server periodically performs statistical analysis of the accumulated data. This identifies common patterns and trends, and gathers data to generate service-wide improvement proposals. Based on this data, the server requests the generative AI to make service-wide improvement proposals.

[1737] Step 9:

[1738] The generative AI generates specific improvement proposals based on the received data. For example, it might generate an improvement proposal such as, "As part of a service-wide overhaul, we propose the introduction of a new connection protocol and the addition of an FAQ section." The server then provides this to the service administrator.

[1739] Through these steps, the system can provide specific advice that is sensitive to the user's emotions and improve the overall electronic payment service.

[1740] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1741] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1742] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1743] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1744] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1745] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1746] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1747] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1748] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1749] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1750] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1751] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1752] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1753] 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.

[1754] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1755] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1756] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1757] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1758] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1759] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1760] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1761] The following is further disclosed regarding the above embodiment.

[1762] (Claim 1)

[1763] A means of collecting concerns from residents,

[1764] A means of sending the collected worry data to a generative AI and receiving an answer;

[1765] a means of providing the generated answers to residents;

[1766] a means for storing and analyzing the collected data;

[1767] A method to request generative artificial intelligence to propose improvements for the entire community based on the analysis results, and

[1768] The system includes a means for providing generated improvement suggestions to a community leader.

[1769] (Claim 2)

[1770] 10. The system of claim 1, further comprising means for providing an interface for residents to input their concerns.

[1771] (Claim 3)

[1772] 10. The system of claim 1, further comprising means for storing answers and analysis results obtained from the generative artificial intelligence in a database.

[1773] "Example 1"

[1774] (Claim 1)

[1775] A means for collecting concerns from users;

[1776] A means to send the collected worry data to the generative AI model and obtain answers;

[1777] means for providing the generated answer to the user;

[1778] a means for storing and analyzing the collected data;

[1779] A means to request a generative AI model to propose improvements for the entire community based on the analysis results, and

[1780] The system includes a means for providing the generated improvement suggestions to a community administrator.

[1781] (Claim 2)

[1782] 10. The system of claim 1, further comprising means for providing an interface for a user to input a concern.

[1783] (Claim 3)

[1784] 10. The system of claim 1, further comprising means for storing answers and analysis results obtained from the generative AI model in a database.

[1785] "Application Example 1"

[1786] (Claim 1)

[1787] A means of collecting concerns from residents,

[1788] A means of sending the collected worry data to a generative AI and receiving an answer;

[1789] a means of providing the generated answers to residents;

[1790] a means for storing and analyzing the collected data;

[1791] A method to request generative artificial intelligence to propose improvements for the entire community based on the analysis results, and

[1792] a means for providing generated improvement suggestions to community leaders;

[1793] A means for providing a smart device application for collecting concerns about public safety and security;

[1794] a means for providing and recording generated public safety improvement proposals;

[1795] A system including:

[1796] (Claim 2)

[1797] 10. The system of claim 1, further comprising means for providing an interface for residents to input their concerns.

[1798] (Claim 3)

[1799] 10. The system of claim 1, further comprising means for storing answers and analysis results obtained from the generative artificial intelligence in a database.

[1800] "Example 2: Combining Emotion Engines"

[1801] (Claim 1)

[1802] A means of collecting concerns from residents,

[1803] A means for transmitting the collected worry data to an emotion analysis engine to identify emotions;

[1804] A means for sending the emotion data and worry data identified by the emotion analysis engine to the generative AI model to obtain an answer;

[1805] a means of providing the generated answers to residents;

[1806] a means for storing and analyzing the collected data and emotion data;

[1807] A means to request a generative AI model to propose improvements for the entire community based on the analysis results, and

[1808] a means for providing generated improvement suggestions to community leaders;

[1809] A system including:

[1810] (Claim 2)

[1811] 10. The system of claim 1, further comprising means for providing an interface for residents to input their concerns.

[1812] (Claim 3)

[1813] 10. The system of claim 1, further comprising means for storing answers and analysis results obtained from the generative AI model in a database.

[1814] "Application example 2 when combining emotion engines"

[1815] (Claim 1)

[1816] A means of collecting concerns from residents,

[1817] A means for analyzing the collected worry data using an emotion engine;

[1818] A means to send the analyzed emotion data and worry data to the generative AI and obtain an answer;

[1819] a means of providing the generated answers to residents;

[1820] a means for storing and analyzing the collected data;

[1821] A method to request generative artificial intelligence to propose improvements for the entire community based on the analysis results, and

[1822] a means for providing generated improvement suggestions to community leaders;

[1823] A means for generating and providing user-specific advice using an emotion engine and generative artificial intelligence;

[1824] A system that includes a means for statistically analyzing accumulated data and generating improvement proposals for the entire service.

[1825] (Claim 2)

[1826] 10. The system of claim 1, further comprising means for providing an interface for residents to input their concerns.

[1827] (Claim 3)

[1828] 10. The system of claim 1, further comprising means for storing answers and analysis results obtained from the generative artificial intelligence in a database. [Explanation of symbols]

[1829] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting concerns from residents, A means of sending the collected worry data to a generative AI and receiving an answer; a means of providing the generated answers to residents; a means for storing and analyzing the collected data; A method to request generative artificial intelligence to propose improvements for the entire community based on the analysis results, and The system includes a means for providing generated improvement suggestions to a community leader.

2. The system of claim 1 further comprising means for providing an interface for residents to input their concerns.

3. 10. The system of claim 1, further comprising means for storing answers and analysis results obtained from the generative artificial intelligence in a database.

Images