system

Abstract

We provide the system. [Solution] Information gathering means for collecting activity information of local residents and organizations, Information analysis means for analyzing collected activity information to extract interest categories and abilities, Based on the analysis results, a means of matching the requirements of the regional plan with the profiles of residents or organizations, Information generation means for generating personalized information to invite prospective participants to participate in regional planning based on the results of the matching, A means of transmitting generated information to candidate participants, A display means that receives the generated information and provides an interface for residents or organizations to register to participate, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Activities in local communities are often carried out individually, making it difficult for residents and groups to cooperate and share resources. Therefore, when local governments promote regional projects, it has become an issue to quickly and efficiently find appropriate collaborators. In addition, it is necessary to increase the opportunities for local residents and groups to participate in projects by leveraging their interests and skills, and to activate the local community.

Means for Solving the Problems

[0005] This invention collects activity data from local residents and organizations, and analyzes the collected data to extract their areas of interest and skills. Based on the analysis results, it matches profiles that meet the requirements of local projects. Furthermore, it provides a system that generates individually optimized invitation documents based on the matching results and sends them to potential project participants. This system makes it possible to efficiently identify appropriate collaborators and revitalize local community activities.

[0006] "Local residents" refers to individuals who reside in a specific geographical area and participate in the social and cultural activities of that area.

[0007] The term "organization" refers to a group formed by the organization of multiple individuals who share common interests or goals.

[0008] "Activity data" refers to information about the past behavioral history, areas of interest, and skills of local residents and organizations.

[0009] "Data collection methods" refer to methods and technologies for obtaining activity data from local residents and organizations.

[0010] "Data analysis means" refers to technologies and methods for processing collected activity data and extracting or transforming relevant information.

[0011] "Matching method" refers to a method or technique for comparing analyzed profiles with project requirements and selecting the optimal combination.

[0012] "Document generation means" refers to a method or technology for creating individually optimized invitations or announcement documents based on matching results.

[0013] "Communication methods" refer to the technologies and means used to transmit generated documents to the target audience. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is implemented as a platform for building optimal collaborative relationships for local government projects based on activity data of local residents and organizations. Specifically, the program processes as follows:

[0036] First, the server collects data including the past activity history, areas of interest, and skills of local residents and organizations. This data is obtained from resident information systems and local community databases.

[0037] Next, the server analyzes the collected data using generative AI technology. During the analysis, the server uses natural language processing technology to accurately extract the interests and skills of residents and organizations from the text data.

[0038] Once the analysis is complete, the server compares the analyzed data with the requirements of the municipal project. Here, the generating AI understands the project content and selects residents and organizations that match the areas of interest and skills.

[0039] For selected residents or organizations, the server generates personalized invitations to encourage participation in the project. These invitations contain content designed to pique the participants' interest and encourage their involvement.

[0040] Finally, the terminal provides an interface for users to receive generated invitations. The terminal allows residents and organizations to easily register for projects they are interested in. This registration information is automatically sent to the server and used to facilitate project coordination.

[0041] As a concrete example, suppose a "local park beautification project" is being planned in a certain town. This project requires residents with experience participating in local environmental protection activities. The server identifies residents with similar activity histories and generates and sends them invitations that are likely to interest them. Residents can receive the invitations via their devices and consider whether or not to participate in the project.

[0042] In this way, the present invention promotes cooperation within local communities and enables efficient project management by local governments.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects data on the activity history, interests, and skills of local residents and organizations using relevant databases and external APIs. This information is formatted in JSON format and stored in the database.

[0046] Step 2:

[0047] The server applies natural language processing (NLP) to the collected data to extract areas of interest and skills of residents and organizations from the text. This systematizes each data entry as profile information.

[0048] Step 3:

[0049] The server collects project data from local governments and analyzes and extracts the necessary experience, skills, and recruitment conditions for each project. The project details are used as criteria for matching with profiles.

[0050] Step 4:

[0051] The server compares the extracted resident and organization profile information with project data and uses machine learning algorithms to calculate the similarity between the two. This generates a list of the best candidates that fit the project requirements.

[0052] Step 5:

[0053] The server generates personalized invitations for matched candidates. Using generation AI, it automatically creates engaging messages based on the participant's interests.

[0054] Step 6:

[0055] The device provides an interface for receiving invitations, allowing users to decide whether or not to participate. Through the interface, users can view project details and express their intention to participate.

[0056] Step 7:

[0057] The intention to participate, confirmed on the terminal, is automatically sent to the server via the system, allowing the project organizer to manage participant information.

[0058] This process allows for efficient recruitment of participants for local projects.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In local communities, there is a challenge in effectively leveraging the diverse skills and interests of individuals and organizations to promote their participation in municipal projects. In particular, the selection of appropriate personnel and efficient communication are essential.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes information gathering means for collecting behavioral information of individuals and organizations in the region, data analysis means for analyzing the collected behavioral information to extract areas of interest and skills, and matching means for matching the requirements of the regional project with the characteristics of individuals or organizations based on the analysis results. This makes it possible to make the most of the resources available in the community, promote participation, and operate projects effectively.

[0064] "Information gathering means" refers to technologies or devices for collecting information such as the behavioral history, areas of interest, and skills of individuals and organizations in a region.

[0065] "Data analysis means" refers to techniques or processes for analyzing collected information and, in particular, for extracting areas of interest and skills of individuals or organizations.

[0066] "Matching means" refers to a technology or process for comparing the characteristics of an analyzed individual or organization with the requirements of a local business to achieve the best possible match.

[0067] "Document generation means" refers to a technology or process for creating personalized documents based on the results of a comparison and encouraging participation.

[0068] "Communication means" refers to the technology or device used to distribute the generated documents to prospective participants.

[0069] A description of embodiments for carrying out this invention will be given.

[0070] The server collects behavioral information of individuals and organizations in the region. This information is obtained from sources such as resident information systems and local community databases. SQL databases are used for data collection, and the data is accessed using APIs.

[0071] Next, the server utilizes a generative AI model to analyze the collected information. In particular, it leverages natural language processing (NLP) techniques, using Python and NLP libraries such as spaCy to extract areas of interest and skills from text data. This analysis includes specific data processing such as text tokenization, part-of-speech tagging, and entity recognition.

[0072] Based on the analysis results, the server matches the requirements of the local project with the characteristics of individuals or organizations. Using a generative AI model, it identifies the most suitable personnel using prompt messages. For example, it might send a prompt message such as, "Please list residents who are eligible to participate in the environmental protection project."

[0073] The server then generates personalized invitations for each candidate based on the matching results. These invitations are created using a generation AI and contain content designed to pique the participant's interest.

[0074] Finally, the device provides an interface for prospective participants to receive invitations. Residents and organizations can view invitations through this interface and register to participate in projects that interest them. Operation on the device is provided using user-friendly widgets and forms.

[0075] An example of a prompt would be: "Identify the best candidates for the local park beautification project and generate personalized invitations for them."

[0076] In this way, the present invention can effectively build a regional cooperation system and support project management by local governments.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server collects behavioral information from individuals and organizations in the region. It uses APIs to access resident information systems and community databases to retrieve data such as activity history, areas of interest, and skills. Inputs include resident IDs and related information, while output is the collected raw data. Specific operations for extracting data are performed using SQL queries.

[0080] Step 2:

[0081] The server uses a generative AI model to analyze the collected raw data. Using Python and an NLP library (e.g., spaCy), it extracts areas of interest and skills from the text data using natural language processing techniques. The input is the raw data obtained in step 1, and the output is the analyzed text information. Specific operations include text tokenization, part-of-speech tagging, and entity recognition.

[0082] Step 3:

[0083] The server uses the analyzed data to match the requirements of the local project with the characteristics of individuals or organizations. It uses a generative AI model to generate prompts and identify the most suitable candidates. The input is the analyzed data and project requirements obtained in step 2, and the output is a list of suitable project candidates. A concrete example prompt would be, "Please list residents who are eligible to participate in the environmental protection project."

[0084] Step 4:

[0085] The server generates personalized invitations based on the matching results. It utilizes generation AI technology to create engaging wording. The input is the list of suitable candidates identified in step 3, and the output is the generated invitation. It uses template text and incorporates information relevant to the participants' interests.

[0086] Step 5:

[0087] The device provides an interface for users to receive generated invitations. Through this, users can consider participating in the project and register. The input is the invitation data generated in step 4, and the output is the user's intention to participate. The device provides a user-friendly UI, allowing interaction through forms and widgets.

[0088] Step 6:

[0089] Users register to participate in the project via their terminal. The registration information is sent to the server and used for project integration. Input is the user's registration information, and output is the information recorded on the server. The specific operation involves clicking a registration button and sending data via an HTTP request.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] Lack of collaboration within local communities and low participation rates in municipal projects are hindering community revitalization. While there is a need for mechanisms that allow local residents and organizations to efficiently participate in projects that match their interests and skills, traditional methods often fail to adequately disseminate project information, resulting in potential participants missing opportunities. These challenges need to be addressed.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes an information gathering means for collecting activity information of local residents and organizations, an information analysis means for analyzing the collected activity information to extract interest categories and capabilities, and a matching means for associating the requirements of the local plan with the profiles of residents or organizations based on the analysis results. This enables local residents and organizations to efficiently participate in projects that are suitable for their characteristics.

[0095] "Information gathering means" refers to methods for collecting information on the activities of local residents and organizations.

[0096] "Information analysis tools" are means for analyzing collected activity information and extracting the interest categories and capabilities of residents and organizations.

[0097] A "correspondence method" is a means of matching the requirements of a regional plan with the profiles of residents or organizations, based on the analysis results.

[0098] "Information generation means" refers to means of generating personalized information for participating candidates based on the results of the matching process.

[0099] "Information transmission means" refers to the means used to send generated information to potential participants.

[0100] "Display means" refers to means that receive generated information and provide an interface for residents or organizations to register their participation.

[0101] This invention provides a system that enables local residents and organizations to participate efficiently in municipal projects. Specific embodiments are described below.

[0102] First, the server collects activity information from local residents and organizations. The information collection method utilizes a cloud-based data management platform, retrieving information on past activity history, interest categories, and capabilities from local databases and online communities. The hardware used is Google® Cloud Platform, and the database is PostgreSQL.

[0103] Next, the server analyzes the collected data. Natural language processing (NLP) technology is used to extract interest categories and abilities from the text data. The software used includes spaCy as the NLP library and OpenAI's GPT-4® as the generative AI model. This process creates profiles of residents and organizations.

[0104] Subsequently, the server associates the requirements of the regional plan with the profiles of residents or organizations based on the analysis results, and generates personalized information. An automated email generation library using Node.js is used as the information generation method to create personalized information encouraging potential participants to join the project.

[0105] The generated information is sent to potential participants through various means of communication. For example, the information may be transmitted via email or mobile app.

[0106] Finally, the device receives the generated information and provides an interface that allows residents or organizations to easily register to participate in the project. This interface is developed using React Native for smartphones and smart glasses. The registration information is sent to the server in real time and used for project coordination.

[0107] As a concrete example, a resident interested in activities to preserve local traditional culture might receive a prompt message like the following:

[0108] "Hello, Resident Name. We have the perfect project for you, given your interest in local traditional culture! We need your help with the (Local Traditional Culture Preservation Project) taking place this summer. For more information and to register, please see this link: [link]"

[0109] In this way, it is possible to promote collaboration within local communities and increase opportunities for residents to contribute to their communities by utilizing their interests and abilities.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects activity information from local residents and organizations. This information collection involves retrieving data from local databases and online communities and storing it in cloud storage. The input is data about residents and organizations, and the output is an organized set of information.

[0113] Step 2:

[0114] The server analyzes the collected activity information. Using natural language processing techniques, it extracts the interest categories and capabilities of residents and organizations from the text data. The input is the organized information set from step 1, and the output is a profile of the residents and organizations.

[0115] Step 3:

[0116] The server associates the analyzed profile data with the requirements of the regional plan. A generative AI model analyzes the requirements and profiles and identifies appropriate residents and organizations based on this analysis. The input is the profiles of residents and organizations and the requirements of the regional plan, and the output is a list of potential candidates for project participation.

[0117] Step 4:

[0118] The server generates personalized information for potential candidates. An automated email generation program creates invitation emails based on the prompt text. The input is the list of participating candidates from step 3, and the output is the personalized invitation email.

[0119] Step 5:

[0120] The device receives the generated information, and the user registers to participate in the project. A mobile app developed using React Native notifies the user via email and displays a registration interface. The input is the invitation email from step 4, and the output is the participation registration information.

[0121] Step 6:

[0122] The server receives participant registration information and links it to the project management system. Information is received in real time and notified to the project administrator. The input is participant registration information submitted by users, and the output is the updated project participant list.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention combines a system that collects activity data from local residents and organizations, analyzes it to extract areas of interest and skills, and matches them with the requirements of local projects, with an emotion engine that recognizes users' emotions. This system utilizes emotion recognition to increase interest in participating in projects and enables more personalized invitations.

[0125] The server first collects data on the activities of local residents and organizations. This utilizes resident information systems and local databases to obtain not only activity history, areas of interest, and skills, but also past emotional trend data. This makes it possible to understand what emotions participants experienced in different situations.

[0126] Next, the server utilizes natural language processing techniques to analyze the collected data. This analysis extracts the interests and skills of residents and organizations, and an emotion engine further analyzes emotional trends from past data. Through this data analysis, profiles of residents and organizations are formed, and these profiles are used to match them with project requirements.

[0127] The emotion engine estimates the user's current emotional state based on analyzed emotion trends. The server then adjusts the tone and content of the project invitation based on the information obtained, selecting the expression that best suits the user's current emotions. For example, an invitation to a project in which the user has shown positive emotions in the past will have a passionate and positive tone.

[0128] Additionally, potential participants receive personalized invitations on their devices. Users can review the invitations and express their interest in participating in projects that interest them. Once their intention to participate is confirmed, this information is sent to the server and recorded in the project management system.

[0129] For example, if there is a "health promotion program" held in a community, the emotional engine can identify residents who have given positive feedback at past health-related events and send them invitations that particularly emphasize their interest in health, thereby increasing their willingness to participate.

[0130] Thus, this invention makes it possible to more effectively encourage the participation of residents and organizations in local government projects. At the same time, by using emotion recognition, it is possible to improve the quality of invitations and help further deepen cooperation within the local community.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server collects activity data from local residents and organizations. This data is retrieved from local community portals and databases and includes information on activity history, areas of interest, skills, and past emotions. The data is converted into a structured format and stored for analysis.

[0134] Step 2:

[0135] The server analyzes the collected data using natural language processing technology. Specifically, it extracts the areas of interest and skills of residents and organizations from text data and creates profiles. At this stage, the emotional history of each resident regarding their activities is also analyzed.

[0136] Step 3:

[0137] The server uses an emotion engine to evaluate the user's emotional trends from the analyzed profile. It detects which past activities the user exhibited positive or negative emotions in and infers their current emotional state.

[0138] Step 4:

[0139] The server collects requirements data for local projects and matches it with user profiles. A machine learning algorithm evaluates whether the skills and interests required by the project match the profiles of the residents, and selects the best candidates.

[0140] Step 5:

[0141] The server uses the results of the emotion engine's analysis of the user's emotional state to generate personalized invitations. Specifically, it adjusts the tone and style of the invitation based on the user's emotional state and processes it using a document generation engine to make it more appealing.

[0142] Step 6:

[0143] The device provides an interface for receiving personalized invitations. Through this interface, users can view project details and register to participate if they are interested.

[0144] Step 7:

[0145] Participation intentions registered via the terminal are transferred to the server and recorded in the local government's project management system. This information is used to enable project managers to properly manage the project.

[0146] This processing flow aims to effectively promote participation in local projects and provide personalized experiences tailored to the sentiments of each resident and organization.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] Traditionally, systems designed to encourage participation from local residents and organizations have lacked personalized information, resulting in insufficient motivation to participate. Furthermore, the inability to provide invitations that consider participants' emotional states made it difficult to effectively motivate potential participants. Additionally, the inability to accurately match areas of interest and skills prevented the selection of appropriate participants who met project requirements.

[0150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0151] In this invention, the server includes information acquisition means for collecting activity data of local residents and organizations, information analysis means for analyzing the collected activity data to extract areas of interest and skills, and matching means for associating the requirements of local projects with characteristic information of residents or organizations based on the analysis results. This makes it possible to generate personalized documents based on participants' interests and feelings, and to invite appropriate participants according to project requirements.

[0152] "Information acquisition means" refers to functions for collecting activity data of local residents and organizations.

[0153] "Information analysis means" refers to a function that analyzes collected activity data to extract areas of interest and skills.

[0154] A "correspondence mechanism" is a function that associates the requirements of a regional project with the characteristics of residents or organizations based on the analysis results.

[0155] A "generative AI model" is an artificial intelligence-based system that creates prompt sentences from collected data and generates personalized documents.

[0156] "Document creation method" refers to a function that generates personalized documents to invite potential participants to join the project.

[0157] "Communication means" refers to the function for sending the generated document to the candidate participant.

[0158] "Expression adjustment means" refers to a function that allows the tone and content of an invitation to be adjusted based on sentiment analysis.

[0159] This invention is a system designed to promote the participation of local residents and organizations in activities. The system consists of a server, terminals, and users, each playing a specific role.

[0160] First, the server uses information acquisition methods to collect activity data from local residents and organizations. This data is collected using resident information systems and local databases and includes activity history, areas of interest, skills, and past sentiment trends. The basic process involves querying the databases and extracting the necessary data.

[0161] Next, the server uses information analysis tools to utilize natural language processing techniques to analyze the collected data. This process uses libraries such as Python's NLTK and spaCy to extract specific interests and skills from the text data, and an emotion engine further analyzes past emotion trends.

[0162] Next, the server uses a mapping mechanism to associate the profiles generated from the analyzed data with the requirements of the regional project. This mapping allows for the identification of the most suitable candidates for the project.

[0163] Furthermore, the server utilizes a generative AI model to create prompt messages and generate personalized invitations. The documents generated using a template engine (e.g., Jinja2) are customized based on each user's past sentiment data.

[0164] This invitation is received on the device. Users can view the invitation on their device and indicate their interest in participating in the project. Once participation in the project is decided, that information is sent from the device to the server and recorded in the project management system.

[0165] A concrete example is a "health promotion program" conducted in a local community. The emotion engine can identify residents who have previously given positive feedback at health-related events and deliver invitations that particularly emphasize their interest in health. This makes it possible to increase their willingness to participate.

[0166] An example of a prompt message is, "Use past sentiment data regarding local residents' participation in health events and utilize the sentiment engine to generate an invitation that will increase their motivation to participate." In this way, the entire system works together to enable more effective participation in local projects.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server collects activity data from local residents and organizations using information acquisition methods. Input requires activity history, areas of interest, skills, and historical sentiment trend data from resident information systems and local databases. By executing database queries, this data is extracted and output as a formatted dataset for use in subsequent analysis.

[0170] Step 2:

[0171] The server processes the collected data using information analysis tools. It uses the formatted dataset obtained in Step 1 as input. Using Python's NLTK and spaCy, it extracts areas of interest and skills from the text data, and analyzes past sentiment trends using a sentiment engine to output profiles of residents and organizations. These profiles include areas of interest, skills, and sentiment tendencies.

[0172] Step 3:

[0173] The server uses a mapping mechanism to associate the analyzed profiles with the requirements of the regional project. The inputs used are the profiles generated in step 2 and the pre-configured project requirements. The algorithm identifies suitable candidate participants for the project and outputs a list. This list is used to generate personalized invitations.

[0174] Step 4:

[0175] The server uses a generative AI model to create prompt messages and generate personalized invitations. The input requires the list of potential participants obtained in step 3 and each candidate's sentiment profile. A template engine (e.g., Jinja2) is used to generate invitations with appropriate tone and content, which are then provided as output.

[0176] Step 5:

[0177] The device receives personalized invitations sent from the server. Users can review the invitation content on the device and express their interest in participating in projects that interest them. The device retrieves the user's selection of projects they wish to participate in as input and sends this information to the server as output.

[0178] Step 6:

[0179] The server records user participation information in the project management system. Using the participation information received in step 5 as input, it records the information in the database necessary for project progress and outputs an updated participant list within the project management system.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] In modern local communities, effectively utilizing information about the activities of local members and organizations, and encouraging participation in local projects that appropriately reflect their interests and skills, is not easy. Furthermore, considering the emotional state of potential participants when making invitations is crucial for increasing their willingness to participate, but currently, systems with such capabilities are limited. Therefore, there is a need to analyze the activity information and emotional state of local members and organizations, and to provide participation invitations in the most optimal way.

[0183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0184] In this invention, the server includes an information gathering means for collecting activity information of local members and organizations, an information analysis means for analyzing the collected activity information and extracting areas of interest and technologies, and an emotion analysis means for analyzing the emotional state of the user. This enables the generation of personalized content tailored to the characteristics of local members and organizations, and adjustments to be made in accordance with the emotional state, thereby providing accurate and attractive participation guidance.

[0185] "Community members" refers to individuals who have their lives based in a specific area or residents belonging to that district.

[0186] An "organization" refers to a group or group that shares a common purpose and operates within a specific region.

[0187] "Activity information" refers to data about actions and events that local members or organizations have carried out in the past.

[0188] "Information gathering means" refers to methods and techniques for collecting information on the activities of local members and organizations.

[0189] "Information analysis means" refers to methods and techniques for analyzing collected activity information and extracting areas of interest and technologies.

[0190] "Areas of interest" refers to the fields or topics that local members or organizations are particularly interested in.

[0191] "Technology" refers to specific skills or expertise possessed by members or organizations within a community.

[0192] "Emotional analysis methods" refer to methods and techniques for analyzing and understanding the emotional state of participating candidates.

[0193] "Personalized content" refers to information or invitations that are customized based on the characteristics of specific local members or organizations.

[0194] "Adjustment methods" refer to methods and techniques for adjusting the tone and content of participation invitations based on emotional analysis.

[0195] This invention is a system aimed at promoting participation in local communities. The system consists primarily of a server, terminals, and users.

[0196] The server collects activity information from local members and organizations and stores it in a database using cloud services such as Google Cloud Platform. This database stores data on activity history, areas of interest, technologies, and emotional states. Google Cloud Natural Language API is used for information analysis, and natural language processing techniques are used to extract areas of interest and technologies from this data.

[0197] Furthermore, the server uses sentiment analysis engines such as Amazon Rekognition to analyze the emotional state of potential participants. The analyzed sentiment information is used to send personalized participation invitations with appropriate content and tone to the device using Firebase Cloud Messaging.

[0198] The device receives personalized guidance and notifications sent from the server. These notifications are customized according to the characteristics of local members and organizations and are designed to encourage participation.

[0199] Users view these notifications on their devices and clearly indicate their intention to participate based on their interests. This information is sent back to the server in real time and recorded in the regional project management system.

[0200] A concrete example is a local event called a "health promotion program." If candidate A has given positive feedback in past program participation, the server analyzes A's past emotional data and sends a passionate and positive message to the terminal, such as, "Would you like to experience a program that is beneficial to your health again?"

[0201] Example prompt for a generative AI model: "Based on participant sentiment analysis data, generate a personalized notification message to encourage participation in a walking event."

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The server collects activity information from local members and organizations and stores it in a database using Google Cloud Platform. Input data includes activity history, areas of interest, skills, and emotional state. This data is stored in cloud storage, formatted, and saved. The output is the saved data in a format usable for subsequent processing.

[0205] Step 2:

[0206] The server uses the Google Cloud Natural Language API to extract areas of interest and technologies from the collected text data. This process involves analyzing specific keywords and phrases from the input activity data to generate profile information indicating the interests of individuals and organizations. The output is a list of the analyzed areas of interest and technologies.

[0207] Step 3:

[0208] The server utilizes Amazon Rekognition to analyze emotional information from past image and video data related to the activities of participating candidates. The input is this past visual data. As a result of the analysis, the general emotional tendencies of the candidate are evaluated, and emotional data is obtained. The output is a quantitative profile of the emotional tendencies.

[0209] Step 4:

[0210] The server generates personalized invitations via Firebase Cloud Messaging, based on analyzed interest, technology, and sentiment data. These prompts are generated by a generative AI model and include details relevant to specific activities or events. The output is a customized invitation designed to capture the user's interest.

[0211] Step 5:

[0212] The terminal receives participation invitations sent from the server and notifies the user. The input is a customized message from the server. The terminal displays this notification in its user interface and presents event information relevant to the user. The output is a notification in a user-readable format.

[0213] Step 6:

[0214] The user checks notifications on their device and selects whether or not to participate in events they are interested in. The user makes their decision based on the information displayed on their device. Once a user indicates their intention to participate, this information is sent back to the server. The output is data regarding the user's intention to participate.

[0215] Step 7:

[0216] The server receives user participation confirmations and records them in the regional project management system. The input is participation confirmation information obtained from users. This information is entered into the management system and used for event planning and participant management. The output is the updated participant list in the management system.

[0217] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0233] This invention is implemented as a platform for building optimal collaborative relationships for local government projects based on activity data of local residents and organizations. Specifically, the program processes as follows:

[0234] First, the server collects data including the past activity history, areas of interest, and skills of local residents and organizations. This data is obtained from resident information systems and local community databases.

[0235] Next, the server analyzes the collected data using generative AI technology. During the analysis, the server uses natural language processing technology to accurately extract the interests and skills of residents and organizations from the text data.

[0236] Once the analysis is complete, the server compares the analyzed data with the requirements of the municipal project. Here, the generating AI understands the project content and selects residents and organizations that match the areas of interest and skills.

[0237] For selected residents or organizations, the server generates personalized invitations to encourage participation in the project. These invitations contain content designed to pique the participants' interest and encourage their involvement.

[0238] Finally, the terminal provides an interface for users to receive generated invitations. The terminal allows residents and organizations to easily register for projects they are interested in. This registration information is automatically sent to the server and used to facilitate project coordination.

[0239] As a concrete example, suppose a "local park beautification project" is being planned in a certain town. This project requires residents with experience participating in local environmental protection activities. The server identifies residents with similar activity histories and generates and sends them invitations that are likely to interest them. Residents can receive the invitations via their devices and consider whether or not to participate in the project.

[0240] In this way, the present invention promotes cooperation within local communities and enables efficient project management by local governments.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The server collects data on the activity history, interests, and skills of local residents and organizations using relevant databases and external APIs. This information is formatted in JSON format and stored in the database.

[0244] Step 2:

[0245] The server applies natural language processing (NLP) to the collected data to extract areas of interest and skills of residents and organizations from the text. This systematizes each data entry as profile information.

[0246] Step 3:

[0247] The server collects project data from local governments and analyzes and extracts the necessary experience, skills, and recruitment conditions for each project. The project details are used as criteria for matching with profiles.

[0248] Step 4:

[0249] The server compares the extracted resident and organization profile information with project data and uses machine learning algorithms to calculate the similarity between the two. This generates a list of the best candidates that fit the project requirements.

[0250] Step 5:

[0251] The server generates personalized invitations for matched candidates. Using generation AI, it automatically creates engaging messages based on the participant's interests.

[0252] Step 6:

[0253] The device provides an interface for receiving invitations, allowing users to decide whether or not to participate. Through the interface, users can view project details and express their intention to participate.

[0254] Step 7:

[0255] The intention to participate, confirmed on the terminal, is automatically sent to the server via the system, allowing the project organizer to manage participant information.

[0256] This process allows for efficient recruitment of participants for local projects.

[0257] (Example 1)

[0258] Next, we will describe Example 1. 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".

[0259] In local communities, there is a challenge in effectively leveraging the diverse skills and interests of individuals and organizations to promote their participation in municipal projects. In particular, the selection of appropriate personnel and efficient communication are essential.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes information gathering means for collecting behavioral information of individuals and organizations in the region, data analysis means for analyzing the collected behavioral information to extract areas of interest and skills, and matching means for matching the requirements of the regional project with the characteristics of individuals or organizations based on the analysis results. This makes it possible to make the most of the resources available in the community, promote participation, and operate projects effectively.

[0262] "Information gathering means" refers to technologies or devices for collecting information such as the behavioral history, areas of interest, and skills of individuals and organizations in a region.

[0263] "Data analysis means" refers to techniques or processes for analyzing collected information and, in particular, for extracting areas of interest and skills of individuals or organizations.

[0264] "Matching means" refers to a technology or process for comparing the characteristics of an analyzed individual or organization with the requirements of a local business to achieve the best possible match.

[0265] "Document generation means" refers to a technology or process for creating personalized documents based on the results of a comparison and encouraging participation.

[0266] "Communication means" refers to the technology or device used to distribute the generated documents to prospective participants.

[0267] A description of embodiments for carrying out this invention will be given.

[0268] The server collects behavioral information of individuals and organizations in the region. This information is obtained from sources such as resident information systems and local community databases. SQL databases are used for data collection, and the data is accessed using APIs.

[0269] Next, the server utilizes a generative AI model to analyze the collected information. In particular, it leverages natural language processing (NLP) techniques, using Python and NLP libraries such as spaCy to extract areas of interest and skills from text data. This analysis includes specific data processing such as text tokenization, part-of-speech tagging, and entity recognition.

[0270] Based on the analysis results, the server matches the requirements of the local project with the characteristics of individuals or organizations. Using a generative AI model, it identifies the most suitable personnel using prompt messages. For example, it might send a prompt message such as, "Please list residents who are eligible to participate in the environmental protection project."

[0271] The server then generates personalized invitations for each candidate based on the matching results. These invitations are created using a generation AI and contain content designed to pique the participant's interest.

[0272] Finally, the device provides an interface for prospective participants to receive invitations. Residents and organizations can view invitations through this interface and register to participate in projects that interest them. Operation on the device is provided using user-friendly widgets and forms.

[0273] An example of a prompt would be: "Identify the best candidates for the local park beautification project and generate personalized invitations for them."

[0274] In this way, the present invention can effectively build a regional cooperation system and support project management by local governments.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The server collects behavioral information from individuals and organizations in the region. It uses APIs to access resident information systems and community databases to retrieve data such as activity history, areas of interest, and skills. Inputs include resident IDs and related information, while output is the collected raw data. Specific operations for extracting data are performed using SQL queries.

[0278] Step 2:

[0279] The server uses a generative AI model to analyze the collected raw data. Using Python and an NLP library (e.g., spaCy), it extracts areas of interest and skills from the text data using natural language processing techniques. The input is the raw data obtained in step 1, and the output is the analyzed text information. Specific operations include text tokenization, part-of-speech tagging, and entity recognition.

[0280] Step 3:

[0281] The server matches the requirements of the regional project with the characteristics of individuals or organizations using the analyzed data. It executes a process of generating prompt texts using a generative AI model to identify the optimal candidates. The input is the analyzed data obtained in step 2 and the project requirements, and the output is a list of project-fit candidates. As a specific example, a prompt text such as "Please list the residents who can participate in the environmental protection project" is used.

[0282] Step 4:

[0283] Based on the matching results, the server generates personalized invitations. It utilizes generative AI technology to create an appealing text. The input is the list of fit candidates identified in step 3, and the output is the generated invitation. It performs an operation of incorporating information related to the participants' interests by leveraging template texts.

[0284] Step 5:

[0285] The terminal provides an interface for the user to receive the generated invitation. Through this, the user can consider participating in the project and register. The input is the invitation data generated in step 4, and the output is the user's intention to participate. The terminal provides a user-friendly UI, enabling operations through forms and widgets.

[0286] Step 6:

[0287] The user registers for participation in the project through the terminal. The registration information is sent to the server and used for project coordination. The input is the user's participation registration information, and the output is the information recording on the server. The specific operation includes the process of clicking the registration button and sending data through an HTTP request.

[0288] (Application Example 1)

[0289] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0290] Lack of collaboration within local communities and low participation rates in municipal projects are hindering community revitalization. While there is a need for mechanisms that allow local residents and organizations to efficiently participate in projects that match their interests and skills, traditional methods often fail to adequately disseminate project information, resulting in potential participants missing opportunities. These challenges need to be addressed.

[0291] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0292] In this invention, the server includes an information gathering means for collecting activity information of local residents and organizations, an information analysis means for analyzing the collected activity information to extract interest categories and capabilities, and a matching means for associating the requirements of the local plan with the profiles of residents or organizations based on the analysis results. This enables local residents and organizations to efficiently participate in projects that are suitable for their characteristics.

[0293] "Information gathering means" refers to methods for collecting information on the activities of local residents and organizations.

[0294] "Information analysis tools" are means for analyzing collected activity information and extracting the interest categories and capabilities of residents and organizations.

[0295] A "correspondence method" is a means of matching the requirements of a regional plan with the profiles of residents or organizations, based on the analysis results.

[0296] "Information generation means" refers to means of generating personalized information for participating candidates based on the results of the matching process.

[0297] "Information transmission means" refers to the means used to send generated information to potential participants.

[0298] "Display means" refers to means that receive generated information and provide an interface for residents or organizations to register their participation.

[0299] This invention provides a system that enables local residents and organizations to participate efficiently in municipal projects. Specific embodiments are described below.

[0300] First, the server collects activity information from local residents and organizations. The information collection method utilizes a cloud-based data management platform, retrieving information on past activity history, interest categories, and capabilities from local databases and online communities. The hardware used is Google Cloud Platform, and PostgreSQL is used for the database.

[0301] Next, the server analyzes the collected data. Natural language processing (NLP) techniques are used to extract interest categories and abilities from the text data. The software used includes spaCy as the NLP library and OpenAI's GPT-4 as the generative AI model. This process creates profiles of residents and organizations.

[0302] Subsequently, the server associates the requirements of the regional plan with the profiles of residents or organizations based on the analysis results, and generates personalized information. An automated email generation library using Node.js is used as the information generation method to create personalized information encouraging potential participants to join the project.

[0303] The generated information is sent to potential participants through various means of communication. For example, the information may be transmitted via email or mobile app.

[0304] Finally, the terminal receives the generated information and provides an interface that allows residents or groups to easily register for participation in the project. This interface is developed for smartphones and smart glasses using React Native. The registration information is sent to the server in real time and utilized for project collaboration.

[0305] As a specific example, the following prompt text is sent to residents who are interested in activities to preserve the local traditional culture.

[0306] "Hello, [resident name]. There's a project that's perfect for you, as you're interested in the local traditional culture! The (Local Traditional Culture Protection Project) being held this summer requires your cooperation. For detailed information and registration, please click on this link. [Link]"

[0307] In this way, it is possible to promote cooperation within the local community and increase opportunities for residents to contribute to the community by leveraging their interests and abilities.

[0308] The flow of the specific process in Application Example 1 will be described using Figure 12.

[0309] Step 1:

[0310] The server collects activity information of local residents and groups. In this information collection, data is obtained from the local database and online communities and stored in cloud storage. The input is data related to residents and groups, and the output is an organized set of information.

[0311] Step 2:

[0312] The server analyzes the collected activity information. Using natural language processing technology, it extracts the interest categories and capabilities of residents and groups from the text data. The input is the organized set of information from Step 1, and the output is the profiles of residents and groups.

[0313] Step 3:

[0314] The server associates the analyzed profile data with the requirements of the regional plan. A generative AI model analyzes the requirements and profiles and identifies appropriate residents and organizations based on this analysis. The input is the profiles of residents and organizations and the requirements of the regional plan, and the output is a list of potential candidates for project participation.

[0315] Step 4:

[0316] The server generates personalized information for potential candidates. An automated email generation program creates invitation emails based on the prompt text. The input is the list of participating candidates from step 3, and the output is the personalized invitation email.

[0317] Step 5:

[0318] The device receives the generated information, and the user registers to participate in the project. A mobile app developed using React Native notifies the user via email and displays a registration interface. The input is the invitation email from step 4, and the output is the participation registration information.

[0319] Step 6:

[0320] The server receives participant registration information and links it to the project management system. Information is received in real time and notified to the project administrator. The input is participant registration information submitted by users, and the output is the updated project participant list.

[0321] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0322] This invention combines a system that collects activity data from local residents and organizations, analyzes it to extract areas of interest and skills, and matches them with the requirements of local projects, with an emotion engine that recognizes users' emotions. This system utilizes emotion recognition to increase interest in participating in projects and enables more personalized invitations.

[0323] The server first collects data on the activities of local residents and organizations. This utilizes resident information systems and local databases to obtain not only activity history, areas of interest, and skills, but also past emotional trend data. This makes it possible to understand what emotions participants experienced in different situations.

[0324] Next, the server utilizes natural language processing techniques to analyze the collected data. This analysis extracts the interests and skills of residents and organizations, and an emotion engine further analyzes emotional trends from past data. Through this data analysis, profiles of residents and organizations are formed, and these profiles are used to match them with project requirements.

[0325] The emotion engine estimates the user's current emotional state based on analyzed emotion trends. The server then adjusts the tone and content of the project invitation based on the information obtained, selecting the expression that best suits the user's current emotions. For example, an invitation to a project in which the user has shown positive emotions in the past will have a passionate and positive tone.

[0326] Additionally, potential participants receive personalized invitations on their devices. Users can review the invitations and express their interest in participating in projects that interest them. Once their intention to participate is confirmed, this information is sent to the server and recorded in the project management system.

[0327] For example, if there is a "health promotion program" held in a community, the emotional engine can identify residents who have given positive feedback at past health-related events and send them invitations that particularly emphasize their interest in health, thereby increasing their willingness to participate.

[0328] Thus, this invention makes it possible to more effectively encourage the participation of residents and organizations in local government projects. At the same time, by using emotion recognition, it is possible to improve the quality of invitations and help further deepen cooperation within the local community.

[0329] The following describes the processing flow.

[0330] Step 1:

[0331] The server collects activity data from local residents and organizations. This data is retrieved from local community portals and databases and includes information on activity history, areas of interest, skills, and past emotions. The data is converted into a structured format and stored for analysis.

[0332] Step 2:

[0333] The server analyzes the collected data using natural language processing technology. Specifically, it extracts the areas of interest and skills of residents and organizations from text data and creates profiles. At this stage, the emotional history of each resident regarding their activities is also analyzed.

[0334] Step 3:

[0335] The server uses an emotion engine to evaluate the user's emotional trends from the analyzed profile. It detects which past activities the user exhibited positive or negative emotions in and infers their current emotional state.

[0336] Step 4:

[0337] The server collects requirements data for local projects and matches it with user profiles. A machine learning algorithm evaluates whether the skills and interests required by the project match the profiles of the residents, and selects the best candidates.

[0338] Step 5:

[0339] The server uses the results of the emotion engine's analysis of the user's emotional state to generate personalized invitations. Specifically, it adjusts the tone and style of the invitation based on the user's emotional state and processes it using a document generation engine to make it more appealing.

[0340] Step 6:

[0341] The device provides an interface for receiving personalized invitations. Through this interface, users can view project details and register to participate if they are interested.

[0342] Step 7:

[0343] Participation intentions registered via the terminal are transferred to the server and recorded in the local government's project management system. This information is used to enable project managers to properly manage the project.

[0344] This processing flow aims to effectively promote participation in local projects and provide personalized experiences tailored to the sentiments of each resident and organization.

[0345] (Example 2)

[0346] Next, we will describe Example 2. 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".

[0347] Traditionally, systems designed to encourage participation from local residents and organizations have lacked personalized information, resulting in insufficient motivation to participate. Furthermore, the inability to provide invitations that consider participants' emotional states made it difficult to effectively motivate potential participants. Additionally, the inability to accurately match areas of interest and skills prevented the selection of appropriate participants who met project requirements.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes information acquisition means for collecting activity data of local residents and organizations, information analysis means for analyzing the collected activity data to extract areas of interest and skills, and matching means for associating the requirements of local projects with characteristic information of residents or organizations based on the analysis results. This makes it possible to generate personalized documents based on participants' interests and feelings, and to invite appropriate participants according to project requirements.

[0350] "Information acquisition means" refers to functions for collecting activity data of local residents and organizations.

[0351] "Information analysis means" refers to a function that analyzes collected activity data to extract areas of interest and skills.

[0352] A "correspondence mechanism" is a function that associates the requirements of a regional project with the characteristics of residents or organizations based on the analysis results.

[0353] A "generative AI model" is an artificial intelligence-based system that creates prompt sentences from collected data and generates personalized documents.

[0354] "Document creation method" refers to a function that generates personalized documents to invite potential participants to join the project.

[0355] "Communication means" refers to the function for sending the generated document to the candidate participant.

[0356] "Expression adjustment means" refers to a function that allows the tone and content of an invitation to be adjusted based on sentiment analysis.

[0357] This invention is a system designed to promote the participation of local residents and organizations in activities. The system consists of a server, terminals, and users, each playing a specific role.

[0358] First, the server uses information acquisition methods to collect activity data from local residents and organizations. This data is collected using resident information systems and local databases and includes activity history, areas of interest, skills, and past sentiment trends. The basic process involves querying the databases and extracting the necessary data.

[0359] Next, the server uses information analysis tools to utilize natural language processing techniques to analyze the collected data. This process uses libraries such as Python's NLTK and spaCy to extract specific interests and skills from the text data, and an emotion engine further analyzes past emotion trends.

[0360] Next, the server uses a mapping mechanism to associate the profiles generated from the analyzed data with the requirements of the regional project. This mapping allows for the identification of the most suitable candidates for the project.

[0361] Furthermore, the server utilizes a generative AI model to create prompt messages and generate personalized invitations. The documents generated using a template engine (e.g., Jinja2) are customized based on each user's past sentiment data.

[0362] This invitation is received on the device. Users can view the invitation on their device and indicate their interest in participating in the project. Once participation in the project is decided, that information is sent from the device to the server and recorded in the project management system.

[0363] A concrete example is a "health promotion program" conducted in a local community. The emotion engine can identify residents who have previously given positive feedback at health-related events and deliver invitations that particularly emphasize their interest in health. This makes it possible to increase their willingness to participate.

[0364] An example of a prompt message is, "Use past sentiment data regarding local residents' participation in health events and utilize the sentiment engine to generate an invitation that will increase their motivation to participate." In this way, the entire system works together to enable more effective participation in local projects.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The server collects activity data from local residents and organizations using information acquisition methods. Input requires activity history, areas of interest, skills, and historical sentiment trend data from resident information systems and local databases. By executing database queries, this data is extracted and output as a formatted dataset for use in subsequent analysis.

[0368] Step 2:

[0369] The server processes the collected data using information analysis tools. It uses the formatted dataset obtained in Step 1 as input. Using Python's NLTK and spaCy, it extracts areas of interest and skills from the text data, and analyzes past sentiment trends using a sentiment engine to output profiles of residents and organizations. These profiles include areas of interest, skills, and sentiment tendencies.

[0370] Step 3:

[0371] The server uses a mapping mechanism to associate the analyzed profiles with the requirements of the regional project. The inputs used are the profiles generated in step 2 and the pre-configured project requirements. The algorithm identifies suitable candidate participants for the project and outputs a list. This list is used to generate personalized invitations.

[0372] Step 4:

[0373] The server uses a generative AI model to create prompt messages and generate personalized invitations. The input requires the list of potential participants obtained in step 3 and each candidate's sentiment profile. A template engine (e.g., Jinja2) is used to generate invitations with appropriate tone and content, which are then provided as output.

[0374] Step 5:

[0375] The device receives personalized invitations sent from the server. Users can review the invitation content on the device and express their interest in participating in projects that interest them. The device retrieves the user's selection of projects they wish to participate in as input and sends this information to the server as output.

[0376] Step 6:

[0377] The server records user participation information in the project management system. Using the participation information received in step 5 as input, it records the information in the database necessary for project progress and outputs an updated participant list within the project management system.

[0378] (Application Example 2)

[0379] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0380] In modern local communities, effectively utilizing information about the activities of local members and organizations, and encouraging participation in local projects that appropriately reflect their interests and skills, is not easy. Furthermore, considering the emotional state of potential participants when making invitations is crucial for increasing their willingness to participate, but currently, systems with such capabilities are limited. Therefore, there is a need to analyze the activity information and emotional state of local members and organizations, and to provide participation invitations in the most optimal way.

[0381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0382] In this invention, the server includes an information gathering means for collecting activity information of local members and organizations, an information analysis means for analyzing the collected activity information and extracting areas of interest and technologies, and an emotion analysis means for analyzing the emotional state of the user. This enables the generation of personalized content tailored to the characteristics of local members and organizations, and adjustments to be made in accordance with the emotional state, thereby providing accurate and attractive participation guidance.

[0383] "Community members" refers to individuals who have their lives based in a specific area or residents belonging to that district.

[0384] An "organization" refers to a group or group that shares a common purpose and operates within a specific region.

[0385] "Activity information" refers to data about actions and events that local members or organizations have carried out in the past.

[0386] "Information gathering means" refers to methods and techniques for collecting information on the activities of local members and organizations.

[0387] "Information analysis means" refers to methods and techniques for analyzing collected activity information and extracting areas of interest and technologies.

[0388] "Areas of interest" refers to the fields or topics that local members or organizations are particularly interested in.

[0389] "Technology" refers to specific skills or expertise possessed by members or organizations within a community.

[0390] "Emotional analysis methods" refer to methods and techniques for analyzing and understanding the emotional state of participating candidates.

[0391] "Personalized content" refers to information or invitations that are customized based on the characteristics of specific local members or organizations.

[0392] "Adjustment methods" refer to methods and techniques for adjusting the tone and content of participation invitations based on emotional analysis.

[0393] This invention is a system aimed at promoting participation in local communities. The system consists primarily of a server, terminals, and users.

[0394] The server collects activity information from local members and organizations and stores it in a database using cloud services such as Google Cloud Platform. This database stores data on activity history, areas of interest, technologies, and emotional states. Google Cloud Natural Language API is used for information analysis, and natural language processing techniques are used to extract areas of interest and technologies from this data.

[0395] Furthermore, the server uses sentiment analysis engines such as Amazon Rekognition to analyze the emotional state of potential participants. The analyzed sentiment information is used to send personalized participation invitations with appropriate content and tone to the device using Firebase Cloud Messaging.

[0396] The device receives personalized guidance and notifications sent from the server. These notifications are customized according to the characteristics of local members and organizations and are designed to encourage participation.

[0397] Users view these notifications on their devices and clearly indicate their intention to participate based on their interests. This information is sent back to the server in real time and recorded in the regional project management system.

[0398] A concrete example is a local event called a "health promotion program." If candidate A has given positive feedback in past program participation, the server analyzes A's past emotional data and sends a passionate and positive message to the terminal, such as, "Would you like to experience a program that is beneficial to your health again?"

[0399] Example prompt for a generative AI model: "Based on participant sentiment analysis data, generate a personalized notification message to encourage participation in a walking event."

[0400] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0401] Step 1:

[0402] The server collects activity information from local members and organizations and stores it in a database using Google Cloud Platform. Input data includes activity history, areas of interest, skills, and emotional state. This data is stored in cloud storage, formatted, and saved. The output is the saved data in a format usable for subsequent processing.

[0403] Step 2:

[0404] The server uses the Google Cloud Natural Language API to extract areas of interest and technologies from the collected text data. This process involves analyzing specific keywords and phrases from the input activity data to generate profile information indicating the interests of individuals and organizations. The output is a list of the analyzed areas of interest and technologies.

[0405] Step 3:

[0406] The server utilizes Amazon Rekognition to analyze emotional information from past image and video data related to the activities of participating candidates. The input is this past visual data. As a result of the analysis, the general emotional tendencies of the candidate are evaluated, and emotional data is obtained. The output is a quantitative profile of the emotional tendencies.

[0407] Step 4:

[0408] The server generates personalized invitations via Firebase Cloud Messaging, based on analyzed interest, technology, and sentiment data. These prompts are generated by a generative AI model and include details relevant to specific activities or events. The output is a customized invitation designed to capture the user's interest.

[0409] Step 5:

[0410] The terminal receives participation invitations sent from the server and notifies the user. The input is a customized message from the server. The terminal displays this notification in its user interface and presents event information relevant to the user. The output is a notification in a user-readable format.

[0411] Step 6:

[0412] The user checks notifications on their device and selects whether or not to participate in events they are interested in. The user makes their decision based on the information displayed on their device. Once a user indicates their intention to participate, this information is sent back to the server. The output is data regarding the user's intention to participate.

[0413] Step 7:

[0414] The server receives user participation confirmations and records them in the regional project management system. The input is participation confirmation information obtained from users. This information is entered into the management system and used for event planning and participant management. The output is the updated participant list in the management system.

[0415] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0416] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0417] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0418] [Third Embodiment]

[0419] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0420] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0421] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0422] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0423] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0424] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0425] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0426] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0427] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0428] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0429] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0430] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0431] This invention is implemented as a platform for building optimal collaborative relationships for local government projects based on activity data of local residents and organizations. Specifically, the program processes as follows:

[0432] First, the server collects data including the past activity history, areas of interest, and skills of local residents and organizations. This data is obtained from resident information systems and local community databases.

[0433] Next, the server analyzes the collected data using generative AI technology. During the analysis, the server uses natural language processing technology to accurately extract the interests and skills of residents and organizations from the text data.

[0434] Once the analysis is complete, the server compares the analyzed data with the requirements of the municipal project. Here, the generating AI understands the project content and selects residents and organizations that match the areas of interest and skills.

[0435] For selected residents or organizations, the server generates personalized invitations to encourage participation in the project. These invitations contain content designed to pique the participants' interest and encourage their involvement.

[0436] Finally, the terminal provides an interface for users to receive generated invitations. The terminal allows residents and organizations to easily register for projects they are interested in. This registration information is automatically sent to the server and used to facilitate project coordination.

[0437] As a concrete example, suppose a "local park beautification project" is being planned in a certain town. This project requires residents with experience participating in local environmental protection activities. The server identifies residents with similar activity histories and generates and sends them invitations that are likely to interest them. Residents can receive the invitations via their devices and consider whether or not to participate in the project.

[0438] In this way, the present invention promotes cooperation within local communities and enables efficient project management by local governments.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The server collects data on the activity history, interests, and skills of local residents and organizations using relevant databases and external APIs. This information is formatted in JSON format and stored in the database.

[0442] Step 2:

[0443] The server applies natural language processing (NLP) to the collected data to extract areas of interest and skills of residents and organizations from the text. This systematizes each data entry as profile information.

[0444] Step 3:

[0445] The server collects project data from local governments and analyzes and extracts the necessary experience, skills, and recruitment conditions for each project. The project details are used as criteria for matching with profiles.

[0446] Step 4:

[0447] The server compares the extracted resident and organization profile information with project data and uses machine learning algorithms to calculate the similarity between the two. This generates a list of the best candidates that fit the project requirements.

[0448] Step 5:

[0449] The server generates personalized invitations for matched candidates. Using generation AI, it automatically creates engaging messages based on the participant's interests.

[0450] Step 6:

[0451] The device provides an interface for receiving invitations, allowing users to decide whether or not to participate. Through the interface, users can view project details and express their intention to participate.

[0452] Step 7:

[0453] The intention to participate, confirmed on the terminal, is automatically sent to the server via the system, allowing the project organizer to manage participant information.

[0454] This process allows for efficient recruitment of participants for local projects.

[0455] (Example 1)

[0456] Next, we will describe Example 1. 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."

[0457] In local communities, there is a challenge in effectively leveraging the diverse skills and interests of individuals and organizations to promote their participation in municipal projects. In particular, the selection of appropriate personnel and efficient communication are essential.

[0458] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0459] In this invention, the server includes information gathering means for collecting behavioral information of individuals and organizations in the region, data analysis means for analyzing the collected behavioral information to extract areas of interest and skills, and matching means for matching the requirements of the regional project with the characteristics of individuals or organizations based on the analysis results. This makes it possible to make the most of the resources available in the community, promote participation, and operate projects effectively.

[0460] "Information gathering means" refers to technologies or devices for collecting information such as the behavioral history, areas of interest, and skills of individuals and organizations in a region.

[0461] "Data analysis means" refers to techniques or processes for analyzing collected information and, in particular, for extracting areas of interest and skills of individuals or organizations.

[0462] "Matching means" refers to a technology or process for comparing the characteristics of an analyzed individual or organization with the requirements of a local business to achieve the best possible match.

[0463] "Document generation means" refers to a technology or process for creating personalized documents based on the results of a comparison and encouraging participation.

[0464] "Communication means" refers to the technology or device used to distribute the generated documents to prospective participants.

[0465] A description of embodiments for carrying out this invention will be given.

[0466] The server collects behavioral information of individuals and organizations in the region. This information is obtained from sources such as resident information systems and local community databases. SQL databases are used for data collection, and the data is accessed using APIs.

[0467] Next, the server utilizes a generative AI model to analyze the collected information. In particular, it leverages natural language processing (NLP) techniques, using Python and NLP libraries such as spaCy to extract areas of interest and skills from text data. This analysis includes specific data processing such as text tokenization, part-of-speech tagging, and entity recognition.

[0468] Based on the analysis results, the server matches the requirements of the local project with the characteristics of individuals or organizations. Using a generative AI model, it identifies the most suitable personnel using prompt messages. For example, it might send a prompt message such as, "Please list residents who are eligible to participate in the environmental protection project."

[0469] The server then generates personalized invitations for each candidate based on the matching results. These invitations are created using a generation AI and contain content designed to pique the participant's interest.

[0470] Finally, the device provides an interface for prospective participants to receive invitations. Residents and organizations can view invitations through this interface and register to participate in projects that interest them. Operation on the device is provided using user-friendly widgets and forms.

[0471] An example of a prompt would be: "Identify the best candidates for the local park beautification project and generate personalized invitations for them."

[0472] In this way, the present invention can effectively build a regional cooperation system and support project management by local governments.

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The server collects behavioral information from individuals and organizations in the region. It uses APIs to access resident information systems and community databases to retrieve data such as activity history, areas of interest, and skills. Inputs include resident IDs and related information, while output is the collected raw data. Specific operations for extracting data are performed using SQL queries.

[0476] Step 2:

[0477] The server uses a generative AI model to analyze the collected raw data. Using Python and an NLP library (e.g., spaCy), it extracts areas of interest and skills from the text data using natural language processing techniques. The input is the raw data obtained in step 1, and the output is the analyzed text information. Specific operations include text tokenization, part-of-speech tagging, and entity recognition.

[0478] Step 3:

[0479] The server uses the analyzed data to match the requirements of the local project with the characteristics of individuals or organizations. It uses a generative AI model to generate prompts and identify the most suitable candidates. The input is the analyzed data and project requirements obtained in step 2, and the output is a list of suitable project candidates. A concrete example prompt would be, "Please list residents who are eligible to participate in the environmental protection project."

[0480] Step 4:

[0481] The server generates personalized invitations based on the matching results. It utilizes generation AI technology to create engaging wording. The input is the list of suitable candidates identified in step 3, and the output is the generated invitation. It uses template text and incorporates information relevant to the participants' interests.

[0482] Step 5:

[0483] The device provides an interface for users to receive generated invitations. Through this, users can consider participating in the project and register. The input is the invitation data generated in step 4, and the output is the user's intention to participate. The device provides a user-friendly UI, allowing interaction through forms and widgets.

[0484] Step 6:

[0485] Users register to participate in the project via their terminal. The registration information is sent to the server and used for project integration. Input is the user's registration information, and output is the information recorded on the server. The specific operation involves clicking a registration button and sending data via an HTTP request.

[0486] (Application Example 1)

[0487] Next, we will explain Application Example 1. In the following explanation, 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."

[0488] Lack of collaboration within local communities and low participation rates in municipal projects are hindering community revitalization. While there is a need for mechanisms that allow local residents and organizations to efficiently participate in projects that match their interests and skills, traditional methods often fail to adequately disseminate project information, resulting in potential participants missing opportunities. These challenges need to be addressed.

[0489] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0490] In this invention, the server includes an information gathering means for collecting activity information of local residents and organizations, an information analysis means for analyzing the collected activity information to extract interest categories and capabilities, and a matching means for associating the requirements of the local plan with the profiles of residents or organizations based on the analysis results. This enables local residents and organizations to efficiently participate in projects that are suitable for their characteristics.

[0491] "Information gathering means" refers to methods for collecting information on the activities of local residents and organizations.

[0492] "Information analysis tools" are means for analyzing collected activity information and extracting the interest categories and capabilities of residents and organizations.

[0493] A "correspondence method" is a means of matching the requirements of a regional plan with the profiles of residents or organizations, based on the analysis results.

[0494] "Information generation means" refers to means of generating personalized information for participating candidates based on the results of the matching process.

[0495] "Information transmission means" refers to the means used to send generated information to potential participants.

[0496] "Display means" refers to means that receive generated information and provide an interface for residents or organizations to register their participation.

[0497] This invention provides a system that enables local residents and organizations to participate efficiently in municipal projects. Specific embodiments are described below.

[0498] First, the server collects activity information from local residents and organizations. The information collection method utilizes a cloud-based data management platform, retrieving information on past activity history, interest categories, and capabilities from local databases and online communities. The hardware used is Google Cloud Platform, and PostgreSQL is used for the database.

[0499] Next, the server analyzes the collected data. Natural language processing (NLP) techniques are used to extract interest categories and abilities from the text data. The software used includes spaCy as the NLP library and OpenAI's GPT-4 as the generative AI model. This process creates profiles of residents and organizations.

[0500] Subsequently, the server associates the requirements of the regional plan with the profiles of residents or organizations based on the analysis results, and generates personalized information. An automated email generation library using Node.js is used as the information generation method to create personalized information encouraging potential participants to join the project.

[0501] The generated information is sent to potential participants through various means of communication. For example, the information may be transmitted via email or mobile app.

[0502] Finally, the device receives the generated information and provides an interface that allows residents or organizations to easily register to participate in the project. This interface is developed using React Native for smartphones and smart glasses. The registration information is sent to the server in real time and used for project coordination.

[0503] As a concrete example, a resident interested in activities to preserve local traditional culture might receive a prompt message like the following:

[0504] "Hello, Resident Name. We have the perfect project for you, given your interest in local traditional culture! We need your help with the (Local Traditional Culture Preservation Project) taking place this summer. For more information and to register, please see this link: [link]"

[0505] In this way, it is possible to promote collaboration within local communities and increase opportunities for residents to contribute to their communities by utilizing their interests and abilities.

[0506] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0507] Step 1:

[0508] The server collects activity information from local residents and organizations. This information collection involves retrieving data from local databases and online communities and storing it in cloud storage. The input is data about residents and organizations, and the output is an organized set of information.

[0509] Step 2:

[0510] The server analyzes the collected activity information. Using natural language processing techniques, it extracts the interest categories and capabilities of residents and organizations from the text data. The input is the organized information set from step 1, and the output is a profile of the residents and organizations.

[0511] Step 3:

[0512] The server associates the analyzed profile data with the requirements of the regional plan. A generative AI model analyzes the requirements and profiles and identifies appropriate residents and organizations based on this analysis. The input is the profiles of residents and organizations and the requirements of the regional plan, and the output is a list of potential candidates for project participation.

[0513] Step 4:

[0514] The server generates personalized information for potential candidates. An automated email generation program creates invitation emails based on the prompt text. The input is the list of participating candidates from step 3, and the output is the personalized invitation email.

[0515] Step 5:

[0516] The device receives the generated information, and the user registers to participate in the project. A mobile app developed using React Native notifies the user via email and displays a registration interface. The input is the invitation email from step 4, and the output is the participation registration information.

[0517] Step 6:

[0518] The server receives participant registration information and links it to the project management system. Information is received in real time and notified to the project administrator. The input is participant registration information submitted by users, and the output is the updated project participant list.

[0519] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0520] This invention combines a system that collects activity data from local residents and organizations, analyzes it to extract areas of interest and skills, and matches them with the requirements of local projects, with an emotion engine that recognizes users' emotions. This system utilizes emotion recognition to increase interest in participating in projects and enables more personalized invitations.

[0521] The server first collects data on the activities of local residents and organizations. This utilizes resident information systems and local databases to obtain not only activity history, areas of interest, and skills, but also past emotional trend data. This makes it possible to understand what emotions participants experienced in different situations.

[0522] Next, the server utilizes natural language processing techniques to analyze the collected data. This analysis extracts the interests and skills of residents and organizations, and an emotion engine further analyzes emotional trends from past data. Through this data analysis, profiles of residents and organizations are formed, and these profiles are used to match them with project requirements.

[0523] The emotion engine estimates the user's current emotional state based on analyzed emotion trends. The server then adjusts the tone and content of the project invitation based on the information obtained, selecting the expression that best suits the user's current emotions. For example, an invitation to a project in which the user has shown positive emotions in the past will have a passionate and positive tone.

[0524] Additionally, potential participants receive personalized invitations on their devices. Users can review the invitations and express their interest in participating in projects that interest them. Once their intention to participate is confirmed, this information is sent to the server and recorded in the project management system.

[0525] For example, if there is a "health promotion program" held in a community, the emotional engine can identify residents who have given positive feedback at past health-related events and send them invitations that particularly emphasize their interest in health, thereby increasing their willingness to participate.

[0526] Thus, this invention makes it possible to more effectively encourage the participation of residents and organizations in local government projects. At the same time, by using emotion recognition, it is possible to improve the quality of invitations and help further deepen cooperation within the local community.

[0527] The following describes the processing flow.

[0528] Step 1:

[0529] The server collects activity data from local residents and organizations. This data is retrieved from local community portals and databases and includes information on activity history, areas of interest, skills, and past emotions. The data is converted into a structured format and stored for analysis.

[0530] Step 2:

[0531] The server analyzes the collected data using natural language processing technology. Specifically, it extracts the areas of interest and skills of residents and organizations from text data and creates profiles. At this stage, the emotional history of each resident regarding their activities is also analyzed.

[0532] Step 3:

[0533] The server uses an emotion engine to evaluate the user's emotional trends from the analyzed profile. It detects which past activities the user exhibited positive or negative emotions in and infers their current emotional state.

[0534] Step 4:

[0535] The server collects requirements data for local projects and matches it with user profiles. A machine learning algorithm evaluates whether the skills and interests required by the project match the profiles of the residents, and selects the best candidates.

[0536] Step 5:

[0537] The server uses the results of the emotion engine's analysis of the user's emotional state to generate personalized invitations. Specifically, it adjusts the tone and style of the invitation based on the user's emotional state and processes it using a document generation engine to make it more appealing.

[0538] Step 6:

[0539] The device provides an interface for receiving personalized invitations. Through this interface, users can view project details and register to participate if they are interested.

[0540] Step 7:

[0541] Participation intentions registered via the terminal are transferred to the server and recorded in the local government's project management system. This information is used to enable project managers to properly manage the project.

[0542] This processing flow aims to effectively promote participation in local projects and provide personalized experiences tailored to the sentiments of each resident and organization.

[0543] (Example 2)

[0544] Next, we will describe Example 2. 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."

[0545] Traditionally, systems designed to encourage participation from local residents and organizations have lacked personalized information, resulting in insufficient motivation to participate. Furthermore, the inability to provide invitations that consider participants' emotional states made it difficult to effectively motivate potential participants. Additionally, the inability to accurately match areas of interest and skills prevented the selection of appropriate participants who met project requirements.

[0546] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0547] In this invention, the server includes information acquisition means for collecting activity data of local residents and organizations, information analysis means for analyzing the collected activity data to extract areas of interest and skills, and matching means for associating the requirements of local projects with characteristic information of residents or organizations based on the analysis results. This makes it possible to generate personalized documents based on participants' interests and feelings, and to invite appropriate participants according to project requirements.

[0548] "Information acquisition means" refers to functions for collecting activity data of local residents and organizations.

[0549] "Information analysis means" refers to a function that analyzes collected activity data to extract areas of interest and skills.

[0550] A "correspondence mechanism" is a function that associates the requirements of a regional project with the characteristics of residents or organizations based on the analysis results.

[0551] A "generative AI model" is an artificial intelligence-based system that creates prompt sentences from collected data and generates personalized documents.

[0552] "Document creation method" refers to a function that generates personalized documents to invite potential participants to join the project.

[0553] "Communication means" refers to the function for sending the generated document to the candidate participant.

[0554] "Expression adjustment means" refers to a function that allows the tone and content of an invitation to be adjusted based on sentiment analysis.

[0555] This invention is a system designed to promote the participation of local residents and organizations in activities. The system consists of a server, terminals, and users, each playing a specific role.

[0556] First, the server uses information acquisition methods to collect activity data from local residents and organizations. This data is collected using resident information systems and local databases and includes activity history, areas of interest, skills, and past sentiment trends. The basic process involves querying the databases and extracting the necessary data.

[0557] Next, the server uses information analysis tools to utilize natural language processing techniques to analyze the collected data. This process uses libraries such as Python's NLTK and spaCy to extract specific interests and skills from the text data, and an emotion engine further analyzes past emotion trends.

[0558] Next, the server uses a mapping mechanism to associate the profiles generated from the analyzed data with the requirements of the regional project. This mapping allows for the identification of the most suitable candidates for the project.

[0559] Furthermore, the server utilizes a generative AI model to create prompt messages and generate personalized invitations. The documents generated using a template engine (e.g., Jinja2) are customized based on each user's past sentiment data.

[0560] This invitation is received on the device. Users can view the invitation on their device and indicate their interest in participating in the project. Once participation in the project is decided, that information is sent from the device to the server and recorded in the project management system.

[0561] A concrete example is a "health promotion program" conducted in a local community. The emotion engine can identify residents who have previously given positive feedback at health-related events and deliver invitations that particularly emphasize their interest in health. This makes it possible to increase their willingness to participate.

[0562] An example of a prompt message is, "Use past sentiment data regarding local residents' participation in health events and utilize the sentiment engine to generate an invitation that will increase their motivation to participate." In this way, the entire system works together to enable more effective participation in local projects.

[0563] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0564] Step 1:

[0565] The server collects activity data from local residents and organizations using information acquisition methods. Input requires activity history, areas of interest, skills, and historical sentiment trend data from resident information systems and local databases. By executing database queries, this data is extracted and output as a formatted dataset for use in subsequent analysis.

[0566] Step 2:

[0567] The server processes the collected data using information analysis tools. It uses the formatted dataset obtained in Step 1 as input. Using Python's NLTK and spaCy, it extracts areas of interest and skills from the text data, and analyzes past sentiment trends using a sentiment engine to output profiles of residents and organizations. These profiles include areas of interest, skills, and sentiment tendencies.

[0568] Step 3:

[0569] The server uses a mapping mechanism to associate the analyzed profiles with the requirements of the regional project. The inputs used are the profiles generated in step 2 and the pre-configured project requirements. The algorithm identifies suitable candidate participants for the project and outputs a list. This list is used to generate personalized invitations.

[0570] Step 4:

[0571] The server uses a generative AI model to create prompt messages and generate personalized invitations. The input requires the list of potential participants obtained in step 3 and each candidate's sentiment profile. A template engine (e.g., Jinja2) is used to generate invitations with appropriate tone and content, which are then provided as output.

[0572] Step 5:

[0573] The device receives personalized invitations sent from the server. Users can review the invitation content on the device and express their interest in participating in projects that interest them. The device retrieves the user's selection of projects they wish to participate in as input and sends this information to the server as output.

[0574] Step 6:

[0575] The server records user participation information in the project management system. Using the participation information received in step 5 as input, it records the information in the database necessary for project progress and outputs an updated participant list within the project management system.

[0576] (Application Example 2)

[0577] Next, we will explain application example 2. In the following explanation, 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."

[0578] In modern local communities, effectively utilizing information about the activities of local members and organizations, and encouraging participation in local projects that appropriately reflect their interests and skills, is not easy. Furthermore, considering the emotional state of potential participants when making invitations is crucial for increasing their willingness to participate, but currently, systems with such capabilities are limited. Therefore, there is a need to analyze the activity information and emotional state of local members and organizations, and to provide participation invitations in the most optimal way.

[0579] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0580] In this invention, the server includes an information gathering means for collecting activity information of local members and organizations, an information analysis means for analyzing the collected activity information and extracting areas of interest and technologies, and an emotion analysis means for analyzing the emotional state of the user. This enables the generation of personalized content tailored to the characteristics of local members and organizations, and adjustments to be made in accordance with the emotional state, thereby providing accurate and attractive participation guidance.

[0581] "Community members" refers to individuals who have their lives based in a specific area or residents belonging to that district.

[0582] An "organization" refers to a group or group that shares a common purpose and operates within a specific region.

[0583] "Activity information" refers to data about actions and events that local members or organizations have carried out in the past.

[0584] "Information gathering means" refers to methods and techniques for collecting information on the activities of local members and organizations.

[0585] "Information analysis means" refers to methods and techniques for analyzing collected activity information and extracting areas of interest and technologies.

[0586] "Areas of interest" refers to the fields or topics that local members or organizations are particularly interested in.

[0587] "Technology" refers to specific skills or expertise possessed by members or organizations within a community.

[0588] "Emotional analysis methods" refer to methods and techniques for analyzing and understanding the emotional state of participating candidates.

[0589] "Personalized content" refers to information or invitations that are customized based on the characteristics of specific local members or organizations.

[0590] "Adjustment methods" refer to methods and techniques for adjusting the tone and content of participation invitations based on emotional analysis.

[0591] This invention is a system aimed at promoting participation in local communities. The system consists primarily of a server, terminals, and users.

[0592] The server collects activity information from local members and organizations and stores it in a database using cloud services such as Google Cloud Platform. This database stores data on activity history, areas of interest, technologies, and emotional states. Google Cloud Natural Language API is used for information analysis, and natural language processing techniques are used to extract areas of interest and technologies from this data.

[0593] Furthermore, the server uses sentiment analysis engines such as Amazon Rekognition to analyze the emotional state of potential participants. The analyzed sentiment information is used to send personalized participation invitations with appropriate content and tone to the device using Firebase Cloud Messaging.

[0594] The device receives personalized guidance and notifications sent from the server. These notifications are customized according to the characteristics of local members and organizations and are designed to encourage participation.

[0595] Users view these notifications on their devices and clearly indicate their intention to participate based on their interests. This information is sent back to the server in real time and recorded in the regional project management system.

[0596] A concrete example is a local event called a "health promotion program." If candidate A has given positive feedback in past program participation, the server analyzes A's past emotional data and sends a passionate and positive message to the terminal, such as, "Would you like to experience a program that is beneficial to your health again?"

[0597] Example prompt for a generative AI model: "Based on participant sentiment analysis data, generate a personalized notification message to encourage participation in a walking event."

[0598] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0599] Step 1:

[0600] The server collects activity information from local members and organizations and stores it in a database using Google Cloud Platform. Input data includes activity history, areas of interest, skills, and emotional state. This data is stored in cloud storage, formatted, and saved. The output is the saved data in a format usable for subsequent processing.

[0601] Step 2:

[0602] The server uses the Google Cloud Natural Language API to extract areas of interest and technologies from the collected text data. This process involves analyzing specific keywords and phrases from the input activity data to generate profile information indicating the interests of individuals and organizations. The output is a list of the analyzed areas of interest and technologies.

[0603] Step 3:

[0604] The server utilizes Amazon Rekognition to analyze emotional information from past image and video data related to the activities of participating candidates. The input is this past visual data. As a result of the analysis, the general emotional tendencies of the candidate are evaluated, and emotional data is obtained. The output is a quantitative profile of the emotional tendencies.

[0605] Step 4:

[0606] The server generates personalized invitations via Firebase Cloud Messaging, based on analyzed interest, technology, and sentiment data. These prompts are generated by a generative AI model and include details relevant to specific activities or events. The output is a customized invitation designed to capture the user's interest.

[0607] Step 5:

[0608] The terminal receives participation invitations sent from the server and notifies the user. The input is a customized message from the server. The terminal displays this notification in its user interface and presents event information relevant to the user. The output is a notification in a user-readable format.

[0609] Step 6:

[0610] The user checks notifications on their device and selects whether or not to participate in events they are interested in. The user makes their decision based on the information displayed on their device. Once a user indicates their intention to participate, this information is sent back to the server. The output is data regarding the user's intention to participate.

[0611] Step 7:

[0612] The server receives user participation confirmations and records them in the regional project management system. The input is participation confirmation information obtained from users. This information is entered into the management system and used for event planning and participant management. The output is the updated participant list in the management system.

[0613] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0614] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0615] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0619] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0620] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0621] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0622] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0623] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0624] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0625] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0626] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0627] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0628] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0629] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0630] This invention is implemented as a platform for building optimal collaborative relationships for local government projects based on activity data of local residents and organizations. Specifically, the program processes as follows:

[0631] First, the server collects data including the past activity history, areas of interest, and skills of local residents and organizations. This data is obtained from resident information systems and local community databases.

[0632] Next, the server analyzes the collected data using generative AI technology. During the analysis, the server uses natural language processing technology to accurately extract the interests and skills of residents and organizations from the text data.

[0633] Once the analysis is complete, the server compares the analyzed data with the requirements of the municipal project. Here, the generating AI understands the project content and selects residents and organizations that match the areas of interest and skills.

[0634] For selected residents or organizations, the server generates personalized invitations to encourage participation in the project. These invitations contain content designed to pique the participants' interest and encourage their involvement.

[0635] Finally, the terminal provides an interface for users to receive generated invitations. The terminal allows residents and organizations to easily register for projects they are interested in. This registration information is automatically sent to the server and used to facilitate project coordination.

[0636] As a concrete example, suppose a "local park beautification project" is being planned in a certain town. This project requires residents with experience participating in local environmental protection activities. The server identifies residents with similar activity histories and generates and sends them invitations that are likely to interest them. Residents can receive the invitations via their devices and consider whether or not to participate in the project.

[0637] In this way, the present invention promotes cooperation within local communities and enables efficient project management by local governments.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] The server collects data on the activity history, interests, and skills of local residents and organizations using relevant databases and external APIs. This information is formatted in JSON format and stored in the database.

[0641] Step 2:

[0642] The server applies natural language processing (NLP) to the collected data to extract areas of interest and skills of residents and organizations from the text. This systematizes each data entry as profile information.

[0643] Step 3:

[0644] The server collects project data from local governments and analyzes and extracts the necessary experience, skills, and recruitment conditions for each project. The project details are used as criteria for matching with profiles.

[0645] Step 4:

[0646] The server compares the extracted resident and organization profile information with project data and uses machine learning algorithms to calculate the similarity between the two. This generates a list of the best candidates that fit the project requirements.

[0647] Step 5:

[0648] The server generates personalized invitations for matched candidates. Using generation AI, it automatically creates engaging messages based on the participant's interests.

[0649] Step 6:

[0650] The device provides an interface for receiving invitations, allowing users to decide whether or not to participate. Through the interface, users can view project details and express their intention to participate.

[0651] Step 7:

[0652] The intention to participate, confirmed on the terminal, is automatically sent to the server via the system, allowing the project organizer to manage participant information.

[0653] This process allows for efficient recruitment of participants for local projects.

[0654] (Example 1)

[0655] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0656] In local communities, there is a challenge in effectively leveraging the diverse skills and interests of individuals and organizations to promote their participation in municipal projects. In particular, the selection of appropriate personnel and efficient communication are essential.

[0657] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0658] In this invention, the server includes information gathering means for collecting behavioral information of individuals and organizations in the region, data analysis means for analyzing the collected behavioral information to extract areas of interest and skills, and matching means for matching the requirements of the regional project with the characteristics of individuals or organizations based on the analysis results. This makes it possible to make the most of the resources available in the community, promote participation, and operate projects effectively.

[0659] "Information gathering means" refers to technologies or devices for collecting information such as the behavioral history, areas of interest, and skills of individuals and organizations in a region.

[0660] "Data analysis means" refers to techniques or processes for analyzing collected information and, in particular, for extracting areas of interest and skills of individuals or organizations.

[0661] "Matching means" refers to a technology or process for comparing the characteristics of an analyzed individual or organization with the requirements of a local business to achieve the best possible match.

[0662] "Document generation means" refers to a technology or process for creating personalized documents based on the results of a comparison and encouraging participation.

[0663] "Communication means" refers to the technology or device used to distribute the generated documents to prospective participants.

[0664] A description of embodiments for carrying out this invention will be given.

[0665] The server collects behavioral information of individuals and organizations in the region. This information is obtained from sources such as resident information systems and local community databases. SQL databases are used for data collection, and the data is accessed using APIs.

[0666] Next, the server utilizes a generative AI model to analyze the collected information. In particular, it leverages natural language processing (NLP) techniques, using Python and NLP libraries such as spaCy to extract areas of interest and skills from text data. This analysis includes specific data processing such as text tokenization, part-of-speech tagging, and entity recognition.

[0667] Based on the analysis results, the server matches the requirements of the local project with the characteristics of individuals or organizations. Using a generative AI model, it identifies the most suitable personnel using prompt messages. For example, it might send a prompt message such as, "Please list residents who are eligible to participate in the environmental protection project."

[0668] The server then generates personalized invitations for each candidate based on the matching results. These invitations are created using a generation AI and contain content designed to pique the participant's interest.

[0669] Finally, the device provides an interface for prospective participants to receive invitations. Residents and organizations can view invitations through this interface and register to participate in projects that interest them. Operation on the device is provided using user-friendly widgets and forms.

[0670] An example of a prompt would be: "Identify the best candidates for the local park beautification project and generate personalized invitations for them."

[0671] In this way, the present invention can effectively build a regional cooperation system and support project management by local governments.

[0672] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0673] Step 1:

[0674] The server collects behavioral information from individuals and organizations in the region. It uses APIs to access resident information systems and community databases to retrieve data such as activity history, areas of interest, and skills. Inputs include resident IDs and related information, while output is the collected raw data. Specific operations for extracting data are performed using SQL queries.

[0675] Step 2:

[0676] The server uses a generative AI model to analyze the collected raw data. Using Python and an NLP library (e.g., spaCy), it extracts areas of interest and skills from the text data using natural language processing techniques. The input is the raw data obtained in step 1, and the output is the analyzed text information. Specific operations include text tokenization, part-of-speech tagging, and entity recognition.

[0677] Step 3:

[0678] The server uses the analyzed data to match the requirements of the local project with the characteristics of individuals or organizations. It uses a generative AI model to generate prompts and identify the most suitable candidates. The input is the analyzed data and project requirements obtained in step 2, and the output is a list of suitable project candidates. A concrete example prompt would be, "Please list residents who are eligible to participate in the environmental protection project."

[0679] Step 4:

[0680] The server generates personalized invitations based on the matching results. It utilizes generation AI technology to create engaging wording. The input is the list of suitable candidates identified in step 3, and the output is the generated invitation. It uses template text and incorporates information relevant to the participants' interests.

[0681] Step 5:

[0682] The device provides an interface for users to receive generated invitations. Through this, users can consider participating in the project and register. The input is the invitation data generated in step 4, and the output is the user's intention to participate. The device provides a user-friendly UI, allowing interaction through forms and widgets.

[0683] Step 6:

[0684] Users register to participate in the project via their terminal. The registration information is sent to the server and used for project integration. Input is the user's registration information, and output is the information recorded on the server. The specific operation involves clicking a registration button and sending data via an HTTP request.

[0685] (Application Example 1)

[0686] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0687] Lack of collaboration within local communities and low participation rates in municipal projects are hindering community revitalization. While there is a need for mechanisms that allow local residents and organizations to efficiently participate in projects that match their interests and skills, traditional methods often fail to adequately disseminate project information, resulting in potential participants missing opportunities. These challenges need to be addressed.

[0688] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0689] In this invention, the server includes an information gathering means for collecting activity information of local residents and organizations, an information analysis means for analyzing the collected activity information to extract interest categories and capabilities, and a matching means for associating the requirements of the local plan with the profiles of residents or organizations based on the analysis results. This enables local residents and organizations to efficiently participate in projects that are suitable for their characteristics.

[0690] "Information gathering means" refers to methods for collecting information on the activities of local residents and organizations.

[0691] "Information analysis tools" are means for analyzing collected activity information and extracting the interest categories and capabilities of residents and organizations.

[0692] A "correspondence method" is a means of matching the requirements of a regional plan with the profiles of residents or organizations, based on the analysis results.

[0693] "Information generation means" refers to means of generating personalized information for participating candidates based on the results of the matching process.

[0694] "Information transmission means" refers to the means used to send generated information to potential participants.

[0695] "Display means" refers to means that receive generated information and provide an interface for residents or organizations to register their participation.

[0696] This invention provides a system that enables local residents and organizations to participate efficiently in municipal projects. Specific embodiments are described below.

[0697] First, the server collects activity information from local residents and organizations. The information collection method utilizes a cloud-based data management platform, retrieving information on past activity history, interest categories, and capabilities from local databases and online communities. The hardware used is Google Cloud Platform, and PostgreSQL is used for the database.

[0698] Next, the server analyzes the collected data. Natural language processing (NLP) techniques are used to extract interest categories and abilities from the text data. The software used includes spaCy as the NLP library and OpenAI's GPT-4 as the generative AI model. This process creates profiles of residents and organizations.

[0699] Subsequently, the server associates the requirements of the regional plan with the profiles of residents or organizations based on the analysis results, and generates personalized information. An automated email generation library using Node.js is used as the information generation method to create personalized information encouraging potential participants to join the project.

[0700] The generated information is sent to potential participants through various means of communication. For example, the information may be transmitted via email or mobile app.

[0701] Finally, the device receives the generated information and provides an interface that allows residents or organizations to easily register to participate in the project. This interface is developed using React Native for smartphones and smart glasses. The registration information is sent to the server in real time and used for project coordination.

[0702] As a concrete example, a resident interested in activities to preserve local traditional culture might receive a prompt message like the following:

[0703] "Hello, Resident Name. We have the perfect project for you, given your interest in local traditional culture! We need your help with the (Local Traditional Culture Preservation Project) taking place this summer. For more information and to register, please see this link: [link]"

[0704] In this way, it is possible to promote collaboration within local communities and increase opportunities for residents to contribute to their communities by utilizing their interests and abilities.

[0705] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0706] Step 1:

[0707] The server collects activity information from local residents and organizations. This information collection involves retrieving data from local databases and online communities and storing it in cloud storage. The input is data about residents and organizations, and the output is an organized set of information.

[0708] Step 2:

[0709] The server analyzes the collected activity information. Using natural language processing techniques, it extracts the interest categories and capabilities of residents and organizations from the text data. The input is the organized information set from step 1, and the output is a profile of the residents and organizations.

[0710] Step 3:

[0711] The server associates the analyzed profile data with the requirements of the regional plan. A generative AI model analyzes the requirements and profiles and identifies appropriate residents and organizations based on this analysis. The input is the profiles of residents and organizations and the requirements of the regional plan, and the output is a list of potential candidates for project participation.

[0712] Step 4:

[0713] The server generates personalized information for potential candidates. An automated email generation program creates invitation emails based on the prompt text. The input is the list of participating candidates from step 3, and the output is the personalized invitation email.

[0714] Step 5:

[0715] The device receives the generated information, and the user registers to participate in the project. A mobile app developed using React Native notifies the user via email and displays a registration interface. The input is the invitation email from step 4, and the output is the participation registration information.

[0716] Step 6:

[0717] The server receives participant registration information and links it to the project management system. Information is received in real time and notified to the project administrator. The input is participant registration information submitted by users, and the output is the updated project participant list.

[0718] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0719] This invention combines a system that collects activity data from local residents and organizations, analyzes it to extract areas of interest and skills, and matches them with the requirements of local projects, with an emotion engine that recognizes users' emotions. This system utilizes emotion recognition to increase interest in participating in projects and enables more personalized invitations.

[0720] The server first collects data on the activities of local residents and organizations. This utilizes resident information systems and local databases to obtain not only activity history, areas of interest, and skills, but also past emotional trend data. This makes it possible to understand what emotions participants experienced in different situations.

[0721] Next, the server utilizes natural language processing techniques to analyze the collected data. This analysis extracts the interests and skills of residents and organizations, and an emotion engine further analyzes emotional trends from past data. Through this data analysis, profiles of residents and organizations are formed, and these profiles are used to match them with project requirements.

[0722] The emotion engine estimates the user's current emotional state based on analyzed emotion trends. The server then adjusts the tone and content of the project invitation based on the information obtained, selecting the expression that best suits the user's current emotions. For example, an invitation to a project in which the user has shown positive emotions in the past will have a passionate and positive tone.

[0723] Additionally, potential participants receive personalized invitations on their devices. Users can review the invitations and express their interest in participating in projects that interest them. Once their intention to participate is confirmed, this information is sent to the server and recorded in the project management system.

[0724] For example, if there is a "health promotion program" held in a community, the emotional engine can identify residents who have given positive feedback at past health-related events and send them invitations that particularly emphasize their interest in health, thereby increasing their willingness to participate.

[0725] Thus, this invention makes it possible to more effectively encourage the participation of residents and organizations in local government projects. At the same time, by using emotion recognition, it is possible to improve the quality of invitations and help further deepen cooperation within the local community.

[0726] The following describes the processing flow.

[0727] Step 1:

[0728] The server collects activity data from local residents and organizations. This data is retrieved from local community portals and databases and includes information on activity history, areas of interest, skills, and past emotions. The data is converted into a structured format and stored for analysis.

[0729] Step 2:

[0730] The server analyzes the collected data using natural language processing technology. Specifically, it extracts the areas of interest and skills of residents and organizations from text data and creates profiles. At this stage, the emotional history of each resident regarding their activities is also analyzed.

[0731] Step 3:

[0732] The server uses an emotion engine to evaluate the user's emotional trends from the analyzed profile. It detects which past activities the user exhibited positive or negative emotions in and infers their current emotional state.

[0733] Step 4:

[0734] The server collects requirements data for local projects and matches it with user profiles. A machine learning algorithm evaluates whether the skills and interests required by the project match the profiles of the residents, and selects the best candidates.

[0735] Step 5:

[0736] The server uses the results of the emotion engine's analysis of the user's emotional state to generate personalized invitations. Specifically, it adjusts the tone and style of the invitation based on the user's emotional state and processes it using a document generation engine to make it more appealing.

[0737] Step 6:

[0738] The device provides an interface for receiving personalized invitations. Through this interface, users can view project details and register to participate if they are interested.

[0739] Step 7:

[0740] Participation intentions registered via the terminal are transferred to the server and recorded in the local government's project management system. This information is used to enable project managers to properly manage the project.

[0741] This processing flow aims to effectively promote participation in local projects and provide personalized experiences tailored to the sentiments of each resident and organization.

[0742] (Example 2)

[0743] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0744] Traditionally, systems designed to encourage participation from local residents and organizations have lacked personalized information, resulting in insufficient motivation to participate. Furthermore, the inability to provide invitations that consider participants' emotional states made it difficult to effectively motivate potential participants. Additionally, the inability to accurately match areas of interest and skills prevented the selection of appropriate participants who met project requirements.

[0745] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0746] In this invention, the server includes information acquisition means for collecting activity data of local residents and organizations, information analysis means for analyzing the collected activity data to extract areas of interest and skills, and matching means for associating the requirements of local projects with characteristic information of residents or organizations based on the analysis results. This makes it possible to generate personalized documents based on participants' interests and feelings, and to invite appropriate participants according to project requirements.

[0747] "Information acquisition means" refers to functions for collecting activity data of local residents and organizations.

[0748] "Information analysis means" refers to a function that analyzes collected activity data to extract areas of interest and skills.

[0749] A "correspondence mechanism" is a function that associates the requirements of a regional project with the characteristics of residents or organizations based on the analysis results.

[0750] A "generative AI model" is an artificial intelligence-based system that creates prompt sentences from collected data and generates personalized documents.

[0751] "Document creation method" refers to a function that generates personalized documents to invite potential participants to join the project.

[0752] "Communication means" refers to the function for sending the generated document to the candidate participant.

[0753] "Expression adjustment means" refers to a function that allows the tone and content of an invitation to be adjusted based on sentiment analysis.

[0754] This invention is a system designed to promote the participation of local residents and organizations in activities. The system consists of a server, terminals, and users, each playing a specific role.

[0755] First, the server uses information acquisition methods to collect activity data from local residents and organizations. This data is collected using resident information systems and local databases and includes activity history, areas of interest, skills, and past sentiment trends. The basic process involves querying the databases and extracting the necessary data.

[0756] Next, the server uses information analysis tools to utilize natural language processing techniques to analyze the collected data. This process uses libraries such as Python's NLTK and spaCy to extract specific interests and skills from the text data, and an emotion engine further analyzes past emotion trends.

[0757] Next, the server uses a mapping mechanism to associate the profiles generated from the analyzed data with the requirements of the regional project. This mapping allows for the identification of the most suitable candidates for the project.

[0758] Furthermore, the server utilizes a generative AI model to create prompt messages and generate personalized invitations. The documents generated using a template engine (e.g., Jinja2) are customized based on each user's past sentiment data.

[0759] This invitation is received on the device. Users can view the invitation on their device and indicate their interest in participating in the project. Once participation in the project is decided, that information is sent from the device to the server and recorded in the project management system.

[0760] A concrete example is a "health promotion program" conducted in a local community. The emotion engine can identify residents who have previously given positive feedback at health-related events and deliver invitations that particularly emphasize their interest in health. This makes it possible to increase their willingness to participate.

[0761] An example of a prompt message is, "Use past sentiment data regarding local residents' participation in health events and utilize the sentiment engine to generate an invitation that will increase their motivation to participate." In this way, the entire system works together to enable more effective participation in local projects.

[0762] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0763] Step 1:

[0764] The server collects activity data from local residents and organizations using information acquisition methods. Input requires activity history, areas of interest, skills, and historical sentiment trend data from resident information systems and local databases. By executing database queries, this data is extracted and output as a formatted dataset for use in subsequent analysis.

[0765] Step 2:

[0766] The server processes the collected data using information analysis tools. It uses the formatted dataset obtained in Step 1 as input. Using Python's NLTK and spaCy, it extracts areas of interest and skills from the text data, and analyzes past sentiment trends using a sentiment engine to output profiles of residents and organizations. These profiles include areas of interest, skills, and sentiment tendencies.

[0767] Step 3:

[0768] The server uses a mapping mechanism to associate the analyzed profiles with the requirements of the regional project. The inputs used are the profiles generated in step 2 and the pre-configured project requirements. The algorithm identifies suitable candidate participants for the project and outputs a list. This list is used to generate personalized invitations.

[0769] Step 4:

[0770] The server uses a generative AI model to create prompt messages and generate personalized invitations. The input requires the list of potential participants obtained in step 3 and each candidate's sentiment profile. A template engine (e.g., Jinja2) is used to generate invitations with appropriate tone and content, which are then provided as output.

[0771] Step 5:

[0772] The device receives personalized invitations sent from the server. Users can review the invitation content on the device and express their interest in participating in projects that interest them. The device retrieves the user's selection of projects they wish to participate in as input and sends this information to the server as output.

[0773] Step 6:

[0774] The server records user participation information in the project management system. Using the participation information received in step 5 as input, it records the information in the database necessary for project progress and outputs an updated participant list within the project management system.

[0775] (Application Example 2)

[0776] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0777] In modern local communities, effectively utilizing information about the activities of local members and organizations, and encouraging participation in local projects that appropriately reflect their interests and skills, is not easy. Furthermore, considering the emotional state of potential participants when making invitations is crucial for increasing their willingness to participate, but currently, systems with such capabilities are limited. Therefore, there is a need to analyze the activity information and emotional state of local members and organizations, and to provide participation invitations in the most optimal way.

[0778] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0779] In this invention, the server includes an information gathering means for collecting activity information of local members and organizations, an information analysis means for analyzing the collected activity information and extracting areas of interest and technologies, and an emotion analysis means for analyzing the emotional state of the user. This enables the generation of personalized content tailored to the characteristics of local members and organizations, and adjustments to be made in accordance with the emotional state, thereby providing accurate and attractive participation guidance.

[0780] "Community members" refers to individuals who have their lives based in a specific area or residents belonging to that district.

[0781] An "organization" refers to a group or group that shares a common purpose and operates within a specific region.

[0782] "Activity information" refers to data about actions and events that local members or organizations have carried out in the past.

[0783] "Information gathering means" refers to methods and techniques for collecting information on the activities of local members and organizations.

[0784] "Information analysis means" refers to methods and techniques for analyzing collected activity information and extracting areas of interest and technologies.

[0785] "Areas of interest" refers to the fields or topics that local members or organizations are particularly interested in.

[0786] "Technology" refers to specific skills or expertise possessed by members or organizations within a community.

[0787] "Emotional analysis methods" refer to methods and techniques for analyzing and understanding the emotional state of participating candidates.

[0788] "Personalized content" refers to information or invitations that are customized based on the characteristics of specific local members or organizations.

[0789] "Adjustment methods" refer to methods and techniques for adjusting the tone and content of participation invitations based on emotional analysis.

[0790] This invention is a system aimed at promoting participation in local communities. The system consists primarily of a server, terminals, and users.

[0791] The server collects activity information from local members and organizations and stores it in a database using cloud services such as Google Cloud Platform. This database stores data on activity history, areas of interest, technologies, and emotional states. Google Cloud Natural Language API is used for information analysis, and natural language processing techniques are used to extract areas of interest and technologies from this data.

[0792] Furthermore, the server uses sentiment analysis engines such as Amazon Rekognition to analyze the emotional state of potential participants. The analyzed sentiment information is used to send personalized participation invitations with appropriate content and tone to the device using Firebase Cloud Messaging.

[0793] The device receives personalized guidance and notifications sent from the server. These notifications are customized according to the characteristics of local members and organizations and are designed to encourage participation.

[0794] Users view these notifications on their devices and clearly indicate their intention to participate based on their interests. This information is sent back to the server in real time and recorded in the regional project management system.

[0795] A concrete example is a local event called a "health promotion program." If candidate A has given positive feedback in past program participation, the server analyzes A's past emotional data and sends a passionate and positive message to the terminal, such as, "Would you like to experience a program that is beneficial to your health again?"

[0796] Example prompt for a generative AI model: "Based on participant sentiment analysis data, generate a personalized notification message to encourage participation in a walking event."

[0797] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0798] Step 1:

[0799] The server collects activity information from local members and organizations and stores it in a database using Google Cloud Platform. Input data includes activity history, areas of interest, skills, and emotional state. This data is stored in cloud storage, formatted, and saved. The output is the saved data in a format usable for subsequent processing.

[0800] Step 2:

[0801] The server uses the Google Cloud Natural Language API to extract areas of interest and technologies from the collected text data. This process involves analyzing specific keywords and phrases from the input activity data to generate profile information indicating the interests of individuals and organizations. The output is a list of the analyzed areas of interest and technologies.

[0802] Step 3:

[0803] The server utilizes Amazon Rekognition to analyze emotional information from past image and video data related to the activities of participating candidates. The input is this past visual data. As a result of the analysis, the general emotional tendencies of the candidate are evaluated, and emotional data is obtained. The output is a quantitative profile of the emotional tendencies.

[0804] Step 4:

[0805] The server generates personalized invitations via Firebase Cloud Messaging, based on analyzed interest, technology, and sentiment data. These prompts are generated by a generative AI model and include details relevant to specific activities or events. The output is a customized invitation designed to capture the user's interest.

[0806] Step 5:

[0807] The terminal receives participation invitations sent from the server and notifies the user. The input is a customized message from the server. The terminal displays this notification in its user interface and presents event information relevant to the user. The output is a notification in a user-readable format.

[0808] Step 6:

[0809] The user checks notifications on their device and selects whether or not to participate in events they are interested in. The user makes their decision based on the information displayed on their device. Once a user indicates their intention to participate, this information is sent back to the server. The output is data regarding the user's intention to participate.

[0810] Step 7:

[0811] The server receives user participation confirmations and records them in the regional project management system. The input is participation confirmation information obtained from users. This information is entered into the management system and used for event planning and participant management. The output is the updated participant list in the management system.

[0812] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0813] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0814] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0815] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0816] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0817] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0818] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0819] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0820] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0821] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0822] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0823] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0824] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0825] 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.

[0826] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0827] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0828] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0829] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0830] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0831] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0832] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0833] The following is further disclosed regarding the embodiments described above.

[0834] (Claim 1)

[0835] A data collection method for collecting activity data of local residents and organizations,

[0836] A data analysis means for analyzing collected activity data to extract areas of interest and skills,

[0837] Based on the analysis results, a matching mechanism is provided to match the requirements of a regional project with the profiles of residents or organizations.

[0838] A document generation means that generates a personalized document to invite candidate participants to join the project based on the matching results,

[0839] A means of communication to send the generated document to the candidate participant,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, wherein the data collection means extracts activity history, interests, and skills from a database of local residents and organizations.

[0843] (Claim 3)

[0844] The system according to claim 1, wherein the data analysis means extracts areas of interest and skills from text data using natural language processing technology.

[0845] "Example 1"

[0846] (Claim 1)

[0847] Information gathering means for collecting information on the behavior of individuals and organizations in the region,

[0848] A data analysis means for analyzing collected behavioral information to extract areas of interest and skills,

[0849] Based on the analysis results, a matching means is provided to match the requirements of the regional project with the characteristics of an individual or organization.

[0850] A document generation means that generates personalized documents to invite prospective participants to participate in the project based on the results of the matching process,

[0851] A means of communication for distributing the generated documents to the candidate participants,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, wherein the means of information gathering is to extract behavioral history, interests, and skills from local individual and organizational information sources.

[0855] (Claim 3)

[0856] The system according to claim 1, wherein the data analysis means extracts areas of interest and skills from text information using natural language processing technology.

[0857] "Application Example 1"

[0858] (Claim 1)

[0859] Information gathering means for collecting activity information of local residents and organizations,

[0860] Information analysis means for analyzing collected activity information to extract interest categories and abilities,

[0861] Based on the analysis results, a means of matching the requirements of the regional plan with the profiles of residents or organizations,

[0862] Information generation means for generating personalized information to invite prospective participants to participate in regional planning based on the results of the matching,

[0863] A means of transmitting generated information to candidate participants,

[0864] A display means that receives the generated information and provides an interface for residents or organizations to register to participate,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, wherein the means of information gathering is to extract activity history, interests, and capabilities from an information base of local residents and organizations.

[0868] (Claim 3)

[0869] The system according to claim 1, wherein the information analysis means extracts interest categories and abilities from text information using natural language processing technology.

[0870] "Example 2 of combining an emotion engine"

[0871] (Claim 1)

[0872] A means of acquiring information to collect activity data of local residents and organizations,

[0873] Information analysis means for analyzing collected activity data to extract areas of interest and skills,

[0874] Based on the analysis results, a means of matching the requirements of a regional project with the characteristics information of residents or organizations,

[0875] A document creation method that generates personalized documents to invite potential participants to join a project by creating prompt sentences using a generative AI model based on the results of the mapping,

[0876] A means of communication to send the generated document to the candidate participant,

[0877] A means of adjusting the tone and content of invitations sent to participants based on sentiment analysis,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, wherein the means for acquiring information is to extract activity history, interests, and skills from the collection of information of local residents and organizations.

[0881] (Claim 3)

[0882] The system according to claim 1, wherein the information analysis means extracts areas of interest and skills from textual information using natural language processing technology, and analyzes emotional trends through sentiment analysis.

[0883] "Application example 2 when combining with an emotional engine"

[0884] (Claim 1)

[0885] Information gathering means for collecting information on the activities of local members and organizations,

[0886] Information analysis means for analyzing collected activity information to extract areas of interest and technologies,

[0887] Based on the analysis results, a means of matching the requirements of the regional project with the characteristics of its members or organization,

[0888] Content generation means for generating personalized content to invite prospective participants to participate in the project based on the matching results,

[0889] A means of communication to send the generated content to the candidate participants,

[0890] A means of analyzing the emotional state of a user,

[0891] An adjustment mechanism that adjusts the tone of participation invitations and provides personalized business notifications based on the analysis results from emotion analysis tools,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, wherein the means of information gathering is to extract activity history, interests, and skills from data storage locations of local members and organizations.

[0895] (Claim 3)

[0896] The system according to claim 1, wherein the information analysis means extracts fields of interest and technologies from linguistic information using natural language processing technology. [Explanation of symbols]

[0897] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information gathering means for collecting activity information of local residents and organizations, Information analysis means for analyzing collected activity information to extract interest categories and abilities, Based on the analysis results, a means of matching the requirements of the regional plan with the profiles of residents or organizations, Information generation means for generating personalized information to invite prospective participants to participate in regional planning based on the results of the matching, A means of transmitting generated information to candidate participants, A display means that receives the generated information and provides an interface for residents or organizations to register to participate, A system that includes this.

2. The system according to claim 1, wherein the means of information gathering is to extract activity history, interests, and capabilities from an information base of local residents and organizations.

3. The system according to claim 1, wherein the information analysis means extracts interest categories and abilities from text information using natural language processing technology.

Images