System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring participation request information; means for acquiring volunteer request information; means for using a generation model that analyzes the acquired participation request information and volunteer request information and generates an optimal matching result; and means for performing notification based on the generated matching result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When accepting volunteers during disasters, participants are often randomly assigned to requested sites without considering their strengths and weaknesses. This results in problems with the acceptance system and work efficiency. The purpose of this invention is to quickly establish a volunteer acceptance system and improve work efficiency. [Means for solving the problem]

[0005] The present invention is a system that includes a means for acquiring volunteer request information, a means for acquiring volunteer request information, a means for analyzing the acquired volunteer request information and volunteer request information and using a generative model to generate optimal matching results, and a means for notifying based on the generated matching results. Specifically, the system acquires the areas of expertise and desired work content of volunteer applicants and analyzes this information with the volunteer request information to perform matching based on the areas of expertise and desired work content. Furthermore, the system stores information on volunteer applicants and the volunteer request information in a database, and periodically retrieves information from the database and passes it to the generative model, thereby achieving fast and effective volunteer allocation.

[0006] "Participation information" is information provided by volunteer applicants, such as their name, contact information, areas of expertise, desired work, and available dates and times.

[0007] "Volunteer request information" is information provided by a volunteer requester, such as the type of volunteer work required, the number of volunteers required, the location, and the date and time.

[0008] "Analysis" is the process of deriving optimal matching results based on the acquired participation request information and volunteer request information.

[0009] A "generative model" is an AI model that analyzes participation request information and volunteer request information to generate optimal matching results.

[0010] A "notification" is a message sent to both the person who wants to participate and the person who requests a volunteer, based on the matching results, to convey detailed work details and contact information.

[0011] A "database" is a storage device within the system that stores information on volunteer applicants and volunteer request information. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] This invention is a system that uses a generative AI model to analyze and match volunteer applicants with volunteer request tasks, and allocates volunteers appropriately. Below, we will explain the program processing of this system in natural language.

[0034] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[0035] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0036] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[0037] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results. Matching results are calculated taking into account the work content and the applicant's areas of expertise and preferences.

[0038] The server then sends notifications to both the person seeking participation and the person requesting the volunteer based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, contact information, etc. Upon receiving the notifications, the person seeking participation and the person requesting the volunteer can communicate with each other and gather at the appropriate time and place to complete the work.

[0039] Specific examples

[0040] A user (Ichiro Suzuki) enters the following information into a web form: "Ichiro Suzuki, mobile phone number, specializes in rescue operations, prefers weekends." The server stores this information in a database and manages it within the system.

[0041] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[0042] The server periodically retrieves information about Suzuki Ichiro from the database and passes it along with volunteer request information to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities and desired date and time match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[0043] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro will be participating."

[0044] This allows cooperation between those who wish to volunteer and those who request volunteers, enabling quick and efficient volunteer activities.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[0048] Step 2:

[0049] The server receives the volunteer participation request information entered by the user and stores it in a database, which can be accessed only by administrators with limited privileges.

[0050] Step 3:

[0051] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[0052] Step 4:

[0053] The server receives the volunteer request information entered by the user and stores it in a database. As with the participation request information, this information is also accessible only to the administrator.

[0054] Step 5:

[0055] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The frequency of this retrieval can be adjusted by system settings.

[0056] Step 6:

[0057] The server passes the acquired information on volunteer applicants and volunteer request information to the generative AI model, which then converts this information into the data format required for analysis.

[0058] Step 7:

[0059] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results and return them to the server.

[0060] Step 8:

[0061] The server receives the matching results output by the generative AI model and generates notifications to both the prospective participant and the volunteer requester, including the specific task, location, date and time, and contact information for both parties.

[0062] Step 9:

[0063] The server sends a notification to the volunteer requester containing details of the matched volunteer activity, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer, contact information, and the scheduled activity date and time.

[0064] Step 10:

[0065] Users (those wishing to volunteer and those requesting volunteers) communicate with each other based on the notifications received from the server, and efficiently carry out volunteer activities at the designated date, time and place.

[0066] Example 1

[0067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0068] Conventional volunteer matching systems have had the problem of being unable to properly analyze the information of those who wish to volunteer and those who request volunteers, and to efficiently match them. In particular, there is a demand for a system that can automatically and accurately match the areas of expertise, desired work content, and available dates and times of volunteers with the specific needs of the requester.

[0069] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0070] In this invention, the server includes a means for acquiring participation request information, a means for acquiring volunteer request information, a means for analyzing the acquired participation request information and volunteer request information and using a generation AI model to generate optimal matching results, and a means for notifying based on the generated matching results. This enables efficient and highly accurate matching by appropriately analyzing the areas of expertise, desired work content, and available dates and times of volunteer applicants and volunteer requesters.

[0071] "Participation information" is information such as areas of expertise, desired work content, and available dates and times provided by individuals who wish to participate in volunteer activities.

[0072] "Volunteer request information" is information provided by individuals or organizations in need of volunteer activities, such as the type of work required, the number of people required, the location, and the date and time.

[0073] A "generative AI model" is an artificial intelligence model that uses collected data to analyze and generate optimal matching results.

[0074] "Notification" refers to the act of communicating specific work content, location, date and time, contact information, etc. to those wishing to volunteer and those requesting volunteers based on the generated matching results.

[0075] "Database" refers to an information storage system built on a server for efficiently and safely storing and managing participation request information and volunteer request information.

[0076] A "prompt sentence" is a specific formatted piece of information that is input to a generative AI model for analysis and matching.

[0077] This invention is a system that uses a generative AI model to efficiently match volunteer applicants with those requesting volunteers, and allocates volunteers appropriately.

[0078] System Overview

[0079] This system consists of three main components: a server, a device, and a user. Users (those who wish to participate and those who request) access the website from their own device (PC or smartphone) and enter the necessary information. The server receives this information and stores it in a database. Periodically, the server retrieves the necessary information from the database and inputs it as a prompt sentence into the generative AI model.

[0080] The generative AI model analyzes the input information and generates optimal matching results. Based on the results, the server sends notifications, enabling efficient implementation of volunteer activities.

[0081] Hardware and software used

[0082] Server: Use cloud servers with high-performance data processing capabilities (e.g., Amazon Web Services, Google Cloud Platform).

[0083] Database: A relational database (e.g., MySQL, PostgreSQL) is used to manage data.

[0084] Generative AI models: Use generative AI models built using machine learning frameworks (e.g., TensorFlow, PyTorch).

[0085] Website: Use modern front-end frameworks (e.g. React, Angular) and back-end frameworks (e.g. Node.js, Django) to create web forms and send and receive data.

[0086] Specific operation of the system

[0087] 1. Enter user information

[0088] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[0089] 2. Enter your request information

[0090] Another user (the volunteer requester) accesses a form on the same or another website and opens a volunteer request registration form. The volunteer requester enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0091] 3. Data Processing and Analysis

[0092] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The server then passes this information to the generative AI model as prompts. The generative AI model analyzes the volunteer applicant's areas of expertise, desired work, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results.

[0093] Prompt Sentence Examples

[0094] Information for potential volunteers:

[0095] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[0096] Volunteer Request Information:

[0097] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[0098] 4. Sending notifications

[0099] The server sends notifications to both the volunteer applicant and the volunteer requester based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, and contact information. Upon receiving the notifications, the volunteer applicant and requester will communicate based on the notifications and meet at the designated place and time to complete the work.

[0100] This will enable efficient cooperation between those who wish to volunteer and those who request volunteers, resulting in prompt and effective volunteer activities.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Step 1:

[0103] A user (a person wishing to participate as a volunteer) accesses the website and enters information into the volunteer participation registration form.

[0104] Input: Name, contact details, skills, desired work, available dates and times

[0105] What happens: A user visits a web form, fills in the required information, and clicks the submit button.

[0106] Output: The entered information is sent to the server.

[0107] Step 2:

[0108] The server receives the participation request information and stores it in a database.

[0109] Input: Information of the person who wants to participate (name, contact information, skills, desired work, available date and time)

[0110] What it does: The server formats the information it receives and stores it in a database.

[0111] Output: Participation preferences stored in a database

[0112] Step 3:

[0113] A user (volunteer requester) accesses the same or another website and enters information into a volunteer request registration form.

[0114] Input: Volunteer work required, number required, location, date and time

[0115] How it works: A volunteer requester visits a web form, fills in the required information, and clicks submit.

[0116] Output: The requested information is sent to the server.

[0117] Step 4:

[0118] The server receives the requested information and stores it in a database.

[0119] Input: Volunteer request information (task details, number of people required, location, date and time)

[0120] What it does: The server formats the information it receives and stores it in a database.

[0121] Output: Request information stored in the database

[0122] Step 5:

[0123] The server periodically retrieves participation information and request information from the database.

[0124] Input: Participation preferences and request information stored in the database

[0125] How it works: A scheduled task on the server periodically accesses the database to retrieve the necessary information.

[0126] Output: Acquired participation request information and request information

[0127] Step 6:

[0128] The information obtained by the server is used to input prompt sentences into the generative AI model.

[0129] Input: Acquired participation request information and request information

[0130] Example prompt sentence:

[0131] Information for potential volunteers:

[0132] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[0133] Volunteer Request Information:

[0134] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[0135] How it works: The server converts the information it obtains into a prompt sentence and inputs it into the generative AI model.

[0136] Output: The prompt passed to the generative AI model

[0137] Step 7:

[0138] The generative AI model analyzes the prompt and generates the best matching result.

[0139] Input: The prompt passed to the generative AI model

[0140] How it works: The generative AI model analyzes data based on the prompt text and matches the optimal combination of participants and requested information.

[0141] Output: The generated matching results

[0142] Step 8:

[0143] The server receives the matching results output from the generative AI model and notifies them.

[0144] Input: Generated matching results

[0145] How it works: Based on the matching results, the server notifies the participants and volunteer requesters of the tasks, including the location, date, time, and contact information.

[0146] Output: Notifications sent to applicants and requesters

[0147] Step 9:

[0148] Users (those wishing to participate and those making the request) will communicate based on the notification and work at the specified date, time and place.

[0149] Input: Notification sent (task, location, date, time, contact)

[0150] How it works: Users who receive the notification will contact each other and actually volunteer at the specified date, time and place.

[0151] Output: Volunteer activity performed

[0152] (Application example 1)

[0153] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0154] Conventional delivery systems have issues with inefficient matching of delivery personnel with delivery requests, leading to delays and errors in delivery operations. In particular, matching is performed without taking into account the delivery personnel's areas of expertise or desired work content, which often results in unnecessary travel and inappropriate delivery assignments. Therefore, there is a need for a system that can improve the efficiency of delivery operations and efficiently match delivery personnel with delivery requests.

[0155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0156] In this invention, the server includes a means for acquiring participation desire information, a means for acquiring delivery request information, a means for analyzing the acquired participation desire information and delivery request information and using a generation model to generate an optimal matching result, and a means for notifying based on the generated matching result. This makes it possible to match the optimal delivery person with the delivery request, taking into account the delivery person's area of ​​expertise and the desired work content.

[0157] "Participation information" is information submitted by a delivery person when they wish to participate in a delivery, and includes their name, contact information, area of ​​expertise, desired work content, available dates and times, etc.

[0158] "Delivery request information" refers to information submitted by a restaurant or store when requesting delivery, and includes the required delivery details, number of people requested, location, date and time, etc.

[0159] A "generative model" is an artificial intelligence model that analyzes participation request information and delivery request information and generates optimal matching results based on that information.

[0160] "Notification" is a means of sending communication and instructions to delivery personnel and delivery requesters based on the matching results generated by the generative model.

[0161] "Specialty area" refers to an area in which a delivery person is good at making deliveries, and indicates an area in which deliveries can be made efficiently.

[0162] "Desired work content" refers to the specific work content that a delivery person desires when they apply to participate in a delivery, and what type of delivery work they would like to do.

[0163] "Matching" is the process of comparing participation request information with delivery request information and selecting the best combination.

[0164] The "database" is a system that organizes and stores data such as participation requests and delivery requests, and allows efficient search and retrieval of information as needed.

[0165] The present invention provides a system for efficiently matching delivery personnel with delivery requests in a delivery service, which is implemented by utilizing a server, a terminal of the delivery personnel, and a terminal of the delivery requester.

[0166] Overall system overview

[0167] The server acquires participation request information and delivery request information. To collect this information, data entered into a web form from the terminals of the delivery person and the delivery requester is used. The server stores this acquired information in a database and updates the information periodically.

[0168] Hardware and software used

[0169] 1. Server:

[0170] The server is implemented as a web application using Flask.

[0171] The database uses SQLite to store and manage information.

[0172] The generative AI model used is OpenAI's GPT-3.

[0173] 2. Delivery person and delivery requester's device:

[0174] Delivery personnel and delivery requesters access the system via a web browser on their smartphone or computer.

[0175] Use the web form to enter and submit your participation and delivery request information.

[0176] Program processing explanation

[0177] The server first collects participation information from delivery personnel and delivery request information from stores and restaurants, including name, contact information, area of ​​expertise, desired work, available date and time, required delivery content, number of people requested, location, date and time, etc.

[0178] The server stores this data in a database and periodically retrieves it to pass to the generative AI model, which matches delivery staff with delivery requests based on the following example prompt:

[0179] Example prompt sentence:

[0180] Volunteer Name: Taro Yamada

[0181] Skill: Delivery in Tokyo

[0182] Available Time: Saturdays and Sundays

[0183] ---

[0184] Request Task: Pizza Delivery

[0185] Required Volunteers: 5

[0186] Location: Shinjuku Ward

[0187] Date and Time: 2023-12-24 18:00

[0188] Is this a good match? True or False

[0189] The generative AI model analyzes the prompt and generates the optimal matching result by taking into consideration the delivery person's area of ​​expertise, the desired work content, and the request content. Based on the generated matching result, the server notifies both the delivery person and the requester.

[0190] The notification includes specific details of the job, location, date and time, contact information, etc., and is designed to enable quick and efficient communication between the delivery person and the delivery requester. This notification process utilizes SMS APIs and other services.

[0191] Specific examples

[0192] A delivery person (Yamada Taro) enters the information, "Yamada Taro, 090-1234-5678, specializes in deliveries within Tokyo, prefers weekends." The server saves this information in a database and manages it within the system.

[0193] The store enters "Pizza delivery, 5 pax needed, Shinjuku-ku, 2023-12-24 18:00." The server stores this information in the database.

[0194] The server periodically retrieves information about Yamada Taro from the database and passes it along with the delivery request information to the generative AI model. The generative AI model detects that Yamada Taro's area of ​​expertise and desired date and time match the delivery request, and outputs Yamada Taro as a matching result.

[0195] Based on this result, the server sends a notification to Yamada Taro saying, "Please participate in pizza delivery in Shinjuku Ward," and notifies the store that "Yamada Taro will be participating."

[0196] This will enable a fast and efficient delivery service between delivery personnel and delivery requesters, improving the efficiency of delivery operations.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] The user (delivery person) accesses the web form using a smartphone or PC and enters the information they wish to participate in, such as their name, contact information, area of ​​expertise, desired work content, and available dates and times, and clicks the submit button.

[0200] Input: Delivery person registration information

[0201] Output: Save to database

[0202] Step 2:

[0203] The server receives the participation request information sent by the user (delivery person) and saves it in the database. At this time, it converts it into the required data format and stores it appropriately in the database.

[0204] Input: Delivery person registration information

[0205] Output: Participation requests stored in the database

[0206] Step 3:

[0207] Users (stores and restaurants) access a web form using their smartphones or computers and enter delivery request information, including the desired delivery details, number of people, location, date and time, and click the submit button.

[0208] Input: Delivery request information

[0209] Output: Save to database

[0210] Step 4:

[0211] The server receives delivery request information sent by the user (store, etc.) and stores it in a database. At this time, it converts the information into the required data format and stores it appropriately in the database.

[0212] Input: Delivery request information

[0213] Output: Delivery request information stored in the database

[0214] Step 5:

[0215] The server periodically retrieves participation and delivery request information from the database, and at this stage executes a query to obtain the latest information.

[0216] Input: All information in the database

[0217] Output: Latest participation request information and delivery request information

[0218] Step 6:

[0219] The server passes the acquired participation request information and delivery request information to the generative AI model, which analyzes this information and creates a prompt.

[0220] Input: Participation request information and delivery request information

[0221] Output: Prompt sentence to the generative AI model

[0222] Step 7:

[0223] The generative AI model performs optimal matching based on the prompt text and generates matching results, taking into account conditions such as area of ​​expertise, desired work content, date and time, etc.

[0224] Input: prompt statement

[0225] Output: Matching results

[0226] Step 8:

[0227] The server receives the matching results output from the generative AI model and sends a notification based on the results. Specifically, it sends a notification to the delivery person and the store that a match has been made.

[0228] Input: Matching results

[0229] Output: Notification to delivery person and store

[0230] Step 9:

[0231] The user (delivery person and store) receives the notification and confirms the specific work content, location, date and time, etc. The delivery person begins the actual delivery work based on the notification.

[0232] Input: Notification content

[0233] Output: Start of delivery work

[0234] The above processing steps enable efficient matching of delivery personnel with delivery requesters, enabling the provision of fast and accurate delivery services.

[0235] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0236] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Below, we will explain the program processing of this system in natural language.

[0237] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information, stores it in a database, and simultaneously recognizes the user's emotions using an emotion engine.

[0238] The emotion engine analyzes the points that users place particular importance on among the information they enter, and analyzes their emotions and psychological state. For example, it determines their motivation and priorities for volunteer activities. This makes it possible to perform optimal matching while also taking into account the psychological state of those wishing to participate.

[0239] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0240] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[0241] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information. The model also analyzes the applicant's psychological state and priorities, as analyzed by the emotion engine, to generate the optimal matching results. The matching results are calculated taking into account the work content, the applicant's areas of expertise and desires, as well as emotional factors.

[0242] The server then sends notifications to both the potential participants and the volunteer requesters based on the matching results output by the generative AI model. These notifications include the specific task, location, date and time, contact information, and importantly, sentiment analysis results. Upon receiving the notifications, the potential participants and the requesters can communicate with each other and meet at the appropriate time and place to complete the task.

[0243] Specific examples

[0244] A user (Suzuki Ichiro) enters "Suzuki Ichiro, mobile phone number, good at rescue work, preferring weekends" into a web form. The server saves this information in a database and simultaneously starts an emotion engine to analyze the emotional information from Suzuki Ichiro's input, determining his "strong desire to participate in rescue work" and "high priority."

[0245] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[0246] The server periodically retrieves information about Suzuki Ichiro from the database, emotional information, and volunteer request information, and passes it to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities, desired date and time, and emotional information of "high motivation" match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[0247] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro is highly motivated to participate in rescue activities and plans to participate."

[0248] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[0249] The processing flow will be explained below.

[0250] Step 1:

[0251] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[0252] Step 2:

[0253] The server receives the volunteer participation request information entered by the user and stores it in a database. At this time, it activates an emotion engine to collect emotional data from the user's input and their emotions and reactions at the time of sending.

[0254] Step 3:

[0255] The emotion engine analyzes the collected emotion data and extracts information such as the user's current psychological state, motivation for volunteer activities, and priorities. The extracted emotion information is also stored in a database.

[0256] Step 4:

[0257] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[0258] Step 5:

[0259] The server receives the volunteer request information entered by the user and stores it in a database.

[0260] Step 6:

[0261] The server periodically retrieves information on volunteer applicants, emotion information, and volunteer request information from the database. The frequency of retrieval can be adjusted by system settings.

[0262] Step 7:

[0263] The server passes the acquired information to the generative AI model for processing. The generative AI model analyzes the participation request information and volunteer request information to derive the optimal matching results, taking into account the emotional information analyzed by the emotion engine.

[0264] Step 8:

[0265] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, volunteer request information, and emotional information to generate the optimal matching results, which are then returned to the server.

[0266] Step 9:

[0267] The server generates a notification message based on the matching results output by the generative AI model, which includes the specific task, location, date and time, contact information, and important points based on emotional information.

[0268] Step 10:

[0269] The server sends a notification to the volunteer applicant containing details of the matched volunteer work, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer applicant, contact information, and commentary based on the emotion information.

[0270] Step 11:

[0271] Users (those who wish to volunteer and those who request volunteers) communicate with each other based on notifications received from the server, and carry out volunteer activities efficiently at the specified date, time, and location. Notifications based on emotion information build a smoother cooperative system.

[0272] Example 2

[0273] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0274] Conventional volunteer matching systems match participants simply based on their skills and schedules without considering their emotional or psychological state, which can lead to a decline in motivation and satisfaction with volunteer activities.Furthermore, not taking into account emotions and psychological states makes it difficult to optimally allocate personnel, which can reduce the efficiency of volunteer activities.

[0275] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring participation information, means for acquiring volunteer request information, means for analyzing the acquired participation information and volunteer request information and using a generative model to generate optimal matching results, means for notifying based on the generated matching results, means for analyzing the participation information and recognizing the user's emotions, and means for reflecting the emotion recognition results in matching. This enables optimal volunteer matching that takes into account the emotions and psychological state of participants.

[0276] "Participation information" is information provided by individuals who wish to participate in volunteer activities, such as their name, contact information, tasks they are good at, desired work content, and available dates and times.

[0277] "Volunteer request information" is information provided by the party requesting volunteer activities, such as the type of work required of volunteers, the number of people required, the location, and the date and time.

[0278] A "generative model" is a machine learning model or AI model that has the ability to analyze acquired participation request information and volunteer request information and generate optimal matching results.

[0279] "Notification" refers to information sent to prospective participants and volunteer requesters based on the generated matching results, and includes specific work content, location, date and time, contact information, and sentiment analysis results.

[0280] An "emotion engine" is a program or system that has the function of analyzing participation request information and recognizing the emotions and psychological state of the provider.

[0281] "Database" means a digital data storage system for storing participation request information and volunteer request information, and for retrieving and using information as needed.

[0282] The "matching result" is information that indicates the optimal combination of participants and volunteer requesters, generated by analyzing the generative model.

[0283] "Emotion recognition" is the process of analyzing and recognizing the provider's emotions and psychological state based on the participant's participation information.

[0284] This invention is a system that combines a generative AI model and an emotion engine to recognize user emotions while analyzing and matching volunteer applicants with volunteer-requested tasks, thereby achieving optimal volunteer allocation. An embodiment of this system is described in detail below.

[0285] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, their specialties, desired work content, and available dates and times, and clicks the submit button. The server receives this information and stores it in a database. The server then activates an emotion engine, analyzes the entered information, and recognizes the user's emotions.

[0286] For example, if a user enters "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends," the server will store this information in a database and at the same time use an emotion engine to analyze "strong desire to carry out rescue work" and "high priority."

[0287] Next, the user (volunteer requester) accesses the volunteer request registration form and enters information about the required volunteer work. Specifically, the user enters the work content, number of people required, location, date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0288] For example, if a user enters "disaster recovery activities, 10 people needed, Tokyo, weekends," the server stores this information in a database.

[0289] The server periodically retrieves information on volunteer applicants and volunteer requests from the database. This information is passed to the generative AI model, which then analyzes it. During this process, the model also analyzes the psychological state and priorities of the applicants, as analyzed by the emotion engine, to generate optimal matching results.

[0290] For example, the generative AI model detects that "Ichiro Suzuki's specialty rescue activities, desired date and time, and emotional information" match the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs Ichiro Suzuki as the matching result.

[0291] Finally, the server notifies both the prospective participant and the volunteer requester based on the matching results output by the generative AI model, including the specific task, location, date and time, contact information, and importantly, sentiment analysis results.

[0292] For example, a notification saying "Ichiro Suzuki will participate in disaster recovery activities in Tokyo" is sent to those who wish to participate, and a notification saying "Ichiro Suzuki is highly motivated to participate in rescue activities" is sent to the requester.

[0293] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[0294] Examples of prompt statements

[0295] Emotion analysis result for "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends": "High motivation for rescue work"

[0296] Volunteer request information for "Disaster recovery activities, 10 people needed, Tokyo, Saturdays and Sundays" is entered as: "10 people needed for disaster recovery activities in Tokyo, Saturdays and Sundays"

[0297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0298] The flow of this system's program processing

[0299] Subject: Server, Terminal, User

[0300] (Step 1: User enters information and submits)

[0301] A user (a person wishing to participate as a volunteer) accesses the volunteer registration form on the website, enters information such as name, contact details, skills, desired work content, available dates and times, and submits it.

[0302] Specific operation: The user enters "Name: Yamada Taro, Contact: 090-1234-5678, Specialty: Rescue work, Desired work: Rescue work, Available dates and times: Saturdays and Sundays" and clicks the send button.

[0303] Input: User-entered participation information

[0304] Output: The participation request received by the server

[0305] (Step 2: Information storage and analysis request by the server)

[0306] The server stores the received participation request information in a database and simultaneously requests the emotion engine to analyze it.

[0307] Specific operation: The server requests the emotion engine to analyze "strong desire to carry out rescue operations" and "high priority."

[0308] Input: Participation request information received by the server

[0309] Output: Participation preference information stored in the database and analysis request to the emotion engine

[0310] (Step 3: Emotion analysis using the emotion engine)

[0311] The emotion engine analyzes the user's emotions and psychological state from the provided information and returns the results to the server.

[0312] Specific operation: The emotion engine analyzes that "Yamada Taro has a strong desire to participate in rescue activities" and sends the result to the server.

[0313] Input: Participation request information sent from the server

[0314] Output: Emotion analysis results

[0315] (Step 4: User enters volunteer request information and submits)

[0316] The user (volunteer requester) accesses the volunteer request registration form on the website, enters information about the required volunteer work, and submits it.

[0317] Specific operation: The user enters "Work content: disaster recovery activities, required number of people: 10, location: Tokyo, date and time: weekend" and clicks the send button.

[0318] Input: User-entered volunteer request information

[0319] Output: Volunteer request information received by the server

[0320] (Step 5: The server saves the request information)

[0321] The server stores the received volunteer request information in a database.

[0322] Specific operation: The server stores the received volunteer request information in a database.

[0323] Input: Volunteer request information received by the server

[0324] Output: Volunteer request information stored in a database

[0325] (Step 6: The server obtains the information and passes it to the generative AI model)

[0326] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[0327] Specific operation: The server retrieves information from the database and passes it to the generative AI model.

[0328] Input: Participation request information and volunteer request information stored in the database

[0329] Output: Information passed to the generative AI model

[0330] (Step 7: Matching analysis using generative AI model)

[0331] The generative AI model analyzes the information provided and generates optimal matching results, taking into account the results of sentiment analysis.

[0332] Specific operation: The generative AI model compares and analyzes "Yamada Taro's specialty rescue activities, desired date and time, and emotional information" with the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs the matching result with Yamada Taro as a suitable candidate.

[0333] Input: Participation request information, volunteer request information, and emotion analysis results passed to the generative AI model

[0334] Output: Best matching result

[0335] (Step 8: Server creates and sends notification)

[0336] The server notifies both the person wishing to participate and the person requesting the volunteer based on the matching results output by the generative AI model.

[0337] Specific operation: The server sends a notification to those who wish to participate that "Yamada Taro will participate in disaster recovery efforts in Tokyo," and notifies the requester that "Yamada Taro is highly motivated to participate in rescue efforts."

[0338] Input: Matching results output from the generative AI model

[0339] Output: Notifications sent

[0340] The above are the specific processing steps of the program of this system.

[0341] (Application example 2)

[0342] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0343] Current systems make it difficult to carry out fast and efficient volunteer activities during emergencies and disasters. In particular, simply matching volunteers based on the work content and schedule without considering the emotions and motivation of those who wish to volunteer makes it difficult to optimally allocate volunteers, and does not ensure that they arrive at the scene quickly. Therefore, a system is needed that combines efficient transportation of volunteers with optimal matching based on emotions and motivation.

[0344] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring participation desire information, means for acquiring volunteer request information, means for analyzing the acquired participation desire information and volunteer request information and using a generative model to generate optimal matching results, means for issuing notifications based on the generated matching results, and means for issuing pickup and transportation instructions to an autonomously driven vehicle based on the generated matching results and transporting volunteers to their destination via an optimal route. This makes it possible to match optimal volunteers while taking into account the emotions and motivation of those wishing to volunteer, and to transport volunteers to needed locations quickly and efficiently.

[0345] "Participation information" refers to information provided by individuals who wish to participate as volunteers, such as their name, contact information, areas of expertise, desired work content, and available dates and times.

[0346] "Volunteer request information" means information provided by a requester regarding an activity requiring volunteers, such as the type of work required, the number of people required, the location, and the date and time.

[0347] A "generative model" is an artificial intelligence model that uses machine learning algorithms to analyze volunteer applicants and volunteer request information, and generate optimal matching results.

[0348] An "emotion engine" is a software component that analyzes a user's emotional state and motivation based on information provided by the user.

[0349] An "autonomous vehicle" is a vehicle that uses artificial intelligence and sensor technology to operate without a driver.

[0350] "Notification" is an action that conveys information to volunteer applicants, volunteer requesters, and autonomous vehicles based on the generated matching results.

[0351] The "database" is a system that stores information on volunteer applicants and volunteer requests, and quickly retrieves this information when necessary.

[0352] "Pickup" is the process by which an autonomous vehicle picks up a volunteer from a designated location.

[0353] "Transportation" is the process by which an autonomous vehicle transports volunteers to their designated destinations.

[0354] A "route" is the route chosen by an autonomous vehicle to pick up and transport volunteers to their destination.

[0355] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Furthermore, it also enables efficient transportation of volunteers using autonomous vehicles. A specific embodiment of this system is described below.

[0356] First, a user (a person wishing to volunteer) accesses the volunteer registration form through a smartphone app, enters information such as their name, contact details, tasks they are good at, desired work content, and available dates and times, and clicks the submit button. The submitted information is sent to the server and stored in a database, and at the same time, an emotion engine is activated to analyze the user's emotional state and motivation. The results of this analysis are stored in the database as the user's emotional information.

[0357] Next, those requesting volunteers access the volunteer request registration form via a smartphone app and enter information such as the type of work required, the number of volunteers required, the location, date and time, etc. This information is also sent to the server and stored in the database.

[0358] The server periodically retrieves information on volunteer applicants and volunteer request information from the database and passes it to the generative AI model. The generative AI model analyzes the volunteer applicants' areas of expertise, desired work, available dates and times, and emotional information, and compares them with the volunteer request information to generate the optimal matching results.

[0359] Based on the matching results, the server notifies the volunteers and those requesting volunteers. The notification includes the specific task, location, date, and time, as well as important sentiment analysis results. Based on the matching results, the server also issues pickup and transportation instructions to autonomous vehicles, transporting the volunteers to their destinations via the optimal route.

[0360] For example, a user (a person wishing to participate) enters "I'm good at rescue work, preferring to work on weekends" and submits the request. The server saves this information in a database and uses an emotion engine to analyze "high motivation." Next, the requester enters "disaster recovery work, 10 people needed, Tokyo, weekends" and submits the request, and the server saves this information in its database. The generative AI model performs matching, and if the volunteers wishing to participate match the volunteer request information, a notification is sent. Furthermore, instructions are sent to the autonomous vehicle to "pick up the volunteers and transport them to the specified location."

[0361] (Example of a prompt)

[0362] Please analyze the emotional state of volunteer Suzuki Ichiro based on the following information:

[0363] Name: Suzuki Ichiro

[0364] Contact: 090-1234-5678

[0365] Specialty: Rescue operations

[0366] Desired work: Disaster recovery

[0367] Available dates: Saturdays and Sundays

[0368] Example result:

[0369] (Emotional analysis results)

[0370] Motivation: High

[0371] Priority: High

[0372] This system will enable optimal matching taking into account the emotions and motivation of volunteers, and will enable fast and efficient transportation using self-driving vehicles.

[0373] The hardware used includes smartphones, servers, and autonomous vehicles, and the software uses a smartphone app (Swift / Java), a database (MySQL), a generative AI model (TensorFlow), and an emotion engine (OpenAI GPT-4). This combination enables efficient volunteer activities and rapid response.

[0374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0375] Step 1:

[0376] A user (a prospective volunteer) opens the volunteer registration form using a smartphone app, enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[0377] Input: Volunteer participation request information entered by the user

[0378] Output: Volunteer participation request information sent to the server

[0379] Specific operation: When a user enters the required information into a form on a smartphone app and submits it, the data is sent to a server via the Internet.

[0380] Step 2:

[0381] The server stores the submitted volunteer participation request information in a database, activates the emotion engine, analyzes the user's emotional state and motivation, and stores the analysis results in the database.

[0382] Input: Volunteer participation information

[0383] Output: Emotion analysis results

[0384] Specific operation: The server stores the received data in a database and passes it to the emotion engine, which analyzes it, returns the results to the server, and stores them in the database again.

[0385] Step 3:

[0386] The requester opens the volunteer request registration form using a smartphone app, enters information such as the type of volunteer work required, the number of volunteers required, the location, and the date and time, and clicks the submit button.

[0387] Input: Volunteer request information entered by the requester

[0388] Output: Volunteer request information sent to the server

[0389] Specific operation: When the requester enters the necessary information into the form on the smartphone app and submits it, the data is sent to the server via the Internet.

[0390] Step 4:

[0391] The server stores the submitted volunteer request information in a database.

[0392] Input: Volunteer request information

[0393] Output: Volunteer request information stored in a database

[0394] Specific operation: The server stores the received data in a database.

[0395] Step 5:

[0396] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[0397] Input: Information retrieved from the database (volunteer participation request information, volunteer request information)

[0398] Output: Data passed to the generative AI model

[0399] Specific operation: The server periodically retrieves the necessary information from the database using SQL queries and passes it to the generative AI model.

[0400] Step 6:

[0401] The generative AI model analyzes the areas of expertise, desired work, available dates and times, and emotional information of volunteer applicants, and compares this with volunteer request information to generate the optimal matching results.

[0402] Input: Volunteer participation request information, volunteer request information, emotional information

[0403] Output: Matching results

[0404] Specific operation: The generative AI model runs a machine learning algorithm based on the received data and outputs the optimal matching result.

[0405] Step 7:

[0406] Based on the generated matching results, the server notifies prospective participants and volunteer requesters.

[0407] Input: Matching results

[0408] Output: Notification message

[0409] Specific operation: The server generates a notification message based on the matching results and sends emails and in-app notifications to those who wish to participate and those who request volunteers.

[0410] Step 8:

[0411] Based on the generated matching results, the server instructs the autonomous vehicle to pick up and transport the goods.

[0412] Input: Matching results

[0413] Output: Instruction data for the autonomous vehicle

[0414] Specific operation: The server sends instructions to the autonomous vehicle's control system on which volunteers to pick up, where to pick them up, and where to transport them.

[0415] Step 9:

[0416] The self-driving vehicle will then follow instructions to pick up volunteers and transport them to a designated location.

[0417] Input: Instruction data for the autonomous vehicle

[0418] Output: Transport volunteer to designated location

[0419] Specific operation: The autonomous vehicle calculates the route based on the instruction data, drives to the designated pickup location, picks up the volunteer, and then heads off to the destination.

[0420] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0421] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0422] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0426] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0427] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0428] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0429] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0430] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0431] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0432] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0433] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0434] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0435] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0436] This invention is a system that uses a generative AI model to analyze and match volunteer applicants with volunteer request tasks, and allocates volunteers appropriately. Below, we will explain the program processing of this system in natural language.

[0437] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[0438] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0439] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[0440] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results. Matching results are calculated taking into account the work content and the applicant's areas of expertise and preferences.

[0441] The server then sends notifications to both the person seeking participation and the person requesting the volunteer based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, contact information, etc. Upon receiving the notifications, the person seeking participation and the person requesting the volunteer can communicate with each other and gather at the appropriate time and place to complete the work.

[0442] Specific examples

[0443] A user (Ichiro Suzuki) enters the following information into a web form: "Ichiro Suzuki, mobile phone number, specializes in rescue operations, prefers weekends." The server stores this information in a database and manages it within the system.

[0444] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[0445] The server periodically retrieves information about Suzuki Ichiro from the database and passes it along with volunteer request information to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities and desired date and time match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[0446] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro will be participating."

[0447] This allows cooperation between those who wish to volunteer and those who request volunteers, enabling quick and efficient volunteer activities.

[0448] The processing flow will be explained below.

[0449] Step 1:

[0450] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[0451] Step 2:

[0452] The server receives the volunteer participation request information entered by the user and stores it in a database, which can be accessed only by administrators with limited privileges.

[0453] Step 3:

[0454] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[0455] Step 4:

[0456] The server receives the volunteer request information entered by the user and stores it in a database. As with the participation request information, this information is also accessible only to the administrator.

[0457] Step 5:

[0458] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The frequency of this retrieval can be adjusted by system settings.

[0459] Step 6:

[0460] The server passes the acquired information on volunteer applicants and volunteer request information to the generative AI model, which then converts this information into the data format required for analysis.

[0461] Step 7:

[0462] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results and return them to the server.

[0463] Step 8:

[0464] The server receives the matching results output by the generative AI model and generates notifications to both the prospective participant and the volunteer requester, including the specific task, location, date and time, and contact information for both parties.

[0465] Step 9:

[0466] The server sends a notification to the volunteer requester containing details of the matched volunteer activity, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer, contact information, and the scheduled activity date and time.

[0467] Step 10:

[0468] Users (those wishing to volunteer and those requesting volunteers) communicate with each other based on the notifications received from the server, and efficiently carry out volunteer activities at the designated date, time and place.

[0469] Example 1

[0470] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0471] Conventional volunteer matching systems have had the problem of being unable to properly analyze the information of those who wish to volunteer and those who request volunteers, and to efficiently match them. In particular, there is a demand for a system that can automatically and accurately match the areas of expertise, desired work content, and available dates and times of volunteers with the specific needs of the requester.

[0472] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0473] In this invention, the server includes a means for acquiring participation request information, a means for acquiring volunteer request information, a means for analyzing the acquired participation request information and volunteer request information and using a generation AI model to generate optimal matching results, and a means for notifying based on the generated matching results. This enables efficient and highly accurate matching by appropriately analyzing the areas of expertise, desired work content, and available dates and times of volunteer applicants and volunteer requesters.

[0474] "Participation information" is information such as areas of expertise, desired work content, and available dates and times provided by individuals who wish to participate in volunteer activities.

[0475] "Volunteer request information" is information provided by individuals or organizations in need of volunteer activities, such as the type of work required, the number of people required, the location, and the date and time.

[0476] A "generative AI model" is an artificial intelligence model that uses collected data to analyze and generate optimal matching results.

[0477] "Notification" refers to the act of communicating specific work content, location, date and time, contact information, etc. to those wishing to volunteer and those requesting volunteers based on the generated matching results.

[0478] "Database" refers to an information storage system built on a server for efficiently and safely storing and managing participation request information and volunteer request information.

[0479] A "prompt sentence" is a specific formatted piece of information that is input to a generative AI model for analysis and matching.

[0480] This invention is a system that uses a generative AI model to efficiently match volunteer applicants with those requesting volunteers, and allocates volunteers appropriately.

[0481] System Overview

[0482] This system consists of three main components: a server, a device, and a user. Users (those who wish to participate and those who request) access the website from their own device (PC or smartphone) and enter the necessary information. The server receives this information and stores it in a database. Periodically, the server retrieves the necessary information from the database and inputs it as a prompt sentence into the generative AI model.

[0483] The generative AI model analyzes the input information and generates optimal matching results. Based on the results, the server sends notifications, enabling efficient implementation of volunteer activities.

[0484] Hardware and software used

[0485] Server: Use cloud servers with high-performance data processing capabilities (e.g., Amazon Web Services, Google Cloud Platform).

[0486] Database: A relational database (e.g., MySQL, PostgreSQL) is used to manage data.

[0487] Generative AI models: Use generative AI models built using machine learning frameworks (e.g., TensorFlow, PyTorch).

[0488] Website: Use modern front-end frameworks (e.g. React, Angular) and back-end frameworks (e.g. Node.js, Django) to create web forms and send and receive data.

[0489] Specific operation of the system

[0490] 1. Enter user information

[0491] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[0492] 2. Enter your request information

[0493] Another user (the volunteer requester) accesses a form on the same or another website and opens a volunteer request registration form. The volunteer requester enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0494] 3. Data Processing and Analysis

[0495] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The server then passes this information to the generative AI model as prompts. The generative AI model analyzes the volunteer applicant's areas of expertise, desired work, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results.

[0496] Prompt Sentence Examples

[0497] Information for potential volunteers:

[0498] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[0499] Volunteer Request Information:

[0500] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[0501] 4. Sending notifications

[0502] The server sends notifications to both the volunteer applicant and the volunteer requester based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, and contact information. Upon receiving the notifications, the volunteer applicant and requester will communicate based on the notifications and meet at the designated place and time to complete the work.

[0503] This will enable efficient cooperation between those who wish to volunteer and those who request volunteers, resulting in prompt and effective volunteer activities.

[0504] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0505] Step 1:

[0506] A user (a person wishing to participate as a volunteer) accesses the website and enters information into the volunteer participation registration form.

[0507] Input: Name, contact details, skills, desired work, available dates and times

[0508] What happens: A user visits a web form, fills in the required information, and clicks the submit button.

[0509] Output: The entered information is sent to the server.

[0510] Step 2:

[0511] The server receives the participation request information and stores it in a database.

[0512] Input: Information of the person who wants to participate (name, contact information, skills, desired work, available date and time)

[0513] What it does: The server formats the information it receives and stores it in a database.

[0514] Output: Participation preferences stored in a database

[0515] Step 3:

[0516] A user (volunteer requester) accesses the same or another website and enters information into a volunteer request registration form.

[0517] Input: Volunteer work required, number required, location, date and time

[0518] How it works: A volunteer requester visits a web form, fills in the required information, and clicks submit.

[0519] Output: The requested information is sent to the server.

[0520] Step 4:

[0521] The server receives the requested information and stores it in a database.

[0522] Input: Volunteer request information (task details, number of people required, location, date and time)

[0523] What it does: The server formats the information it receives and stores it in a database.

[0524] Output: Request information stored in the database

[0525] Step 5:

[0526] The server periodically retrieves participation information and request information from the database.

[0527] Input: Participation preferences and request information stored in the database

[0528] How it works: A scheduled task on the server periodically accesses the database to retrieve the necessary information.

[0529] Output: Acquired participation request information and request information

[0530] Step 6:

[0531] The information obtained by the server is used to input prompt sentences into the generative AI model.

[0532] Input: Acquired participation request information and request information

[0533] Example prompt sentence:

[0534] Information for potential volunteers:

[0535] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[0536] Volunteer Request Information:

[0537] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[0538] How it works: The server converts the information it obtains into a prompt sentence and inputs it into the generative AI model.

[0539] Output: The prompt passed to the generative AI model

[0540] Step 7:

[0541] The generative AI model analyzes the prompt and generates the best matching result.

[0542] Input: The prompt passed to the generative AI model

[0543] How it works: The generative AI model analyzes data based on the prompt text and matches the optimal combination of participants and requested information.

[0544] Output: The generated matching results

[0545] Step 8:

[0546] The server receives the matching results output from the generative AI model and notifies them.

[0547] Input: Generated matching results

[0548] How it works: Based on the matching results, the server notifies the participants and volunteer requesters of the tasks, including the location, date, time, and contact information.

[0549] Output: Notifications sent to applicants and requesters

[0550] Step 9:

[0551] Users (those wishing to participate and those making the request) will communicate based on the notification and work at the specified date, time and place.

[0552] Input: Notification sent (task, location, date, time, contact)

[0553] How it works: Users who receive the notification will contact each other and actually volunteer at the specified date, time and place.

[0554] Output: Volunteer activity performed

[0555] (Application example 1)

[0556] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0557] Conventional delivery systems have issues with inefficient matching of delivery personnel with delivery requests, leading to delays and errors in delivery operations. In particular, matching is performed without taking into account the delivery personnel's areas of expertise or desired work content, which often results in unnecessary travel and inappropriate delivery assignments. Therefore, there is a need for a system that can improve the efficiency of delivery operations and efficiently match delivery personnel with delivery requests.

[0558] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0559] In this invention, the server includes a means for acquiring participation desire information, a means for acquiring delivery request information, a means for analyzing the acquired participation desire information and delivery request information and using a generation model to generate an optimal matching result, and a means for notifying based on the generated matching result. This makes it possible to match the optimal delivery person with the delivery request, taking into account the delivery person's area of ​​expertise and the desired work content.

[0560] "Participation information" is information submitted by a delivery person when they wish to participate in a delivery, and includes their name, contact information, area of ​​expertise, desired work content, available dates and times, etc.

[0561] "Delivery request information" refers to information submitted by a restaurant or store when requesting delivery, and includes the required delivery details, number of people requested, location, date and time, etc.

[0562] A "generative model" is an artificial intelligence model that analyzes participation request information and delivery request information and generates optimal matching results based on that information.

[0563] "Notification" is a means of sending communication and instructions to delivery personnel and delivery requesters based on the matching results generated by the generative model.

[0564] "Specialty area" refers to an area in which a delivery person is good at making deliveries, and indicates an area in which deliveries can be made efficiently.

[0565] "Desired work content" refers to the specific work content that a delivery person desires when they apply to participate in a delivery, and what type of delivery work they would like to do.

[0566] "Matching" is the process of comparing participation request information with delivery request information and selecting the best combination.

[0567] The "database" is a system that organizes and stores data such as participation requests and delivery requests, and allows efficient search and retrieval of information as needed.

[0568] The present invention provides a system for efficiently matching delivery personnel with delivery requests in a delivery service, which is implemented by utilizing a server, a terminal of the delivery personnel, and a terminal of the delivery requester.

[0569] Overall system overview

[0570] The server acquires participation request information and delivery request information. To collect this information, data entered into a web form from the terminals of the delivery person and the delivery requester is used. The server stores this acquired information in a database and updates the information periodically.

[0571] Hardware and software used

[0572] 1. Server:

[0573] The server is implemented as a web application using Flask.

[0574] The database uses SQLite to store and manage information.

[0575] The generative AI model used is OpenAI's GPT-3.

[0576] 2. Delivery person and delivery requester's device:

[0577] Delivery personnel and delivery requesters access the system via a web browser on their smartphone or computer.

[0578] Use the web form to enter and submit your participation and delivery request information.

[0579] Program processing explanation

[0580] The server first collects participation information from delivery personnel and delivery request information from stores and restaurants, including name, contact information, area of ​​expertise, desired work, available date and time, required delivery content, number of people requested, location, date and time, etc.

[0581] The server stores this data in a database and periodically retrieves it to pass to the generative AI model, which matches delivery staff with delivery requests based on the following example prompt:

[0582] Example prompt sentence:

[0583] Volunteer Name: Taro Yamada

[0584] Skill: Delivery in Tokyo

[0585] Available Time: Saturdays and Sundays

[0586] ---

[0587] Request Task: Pizza Delivery

[0588] Required Volunteers: 5

[0589] Location: Shinjuku Ward

[0590] Date and Time: 2023-12-24 18:00

[0591] Is this a good match? True or False

[0592] The generative AI model analyzes the prompt and generates the optimal matching result by taking into consideration the delivery person's area of ​​expertise, the desired work content, and the request content. Based on the generated matching result, the server notifies both the delivery person and the requester.

[0593] The notification includes specific details of the job, location, date and time, contact information, etc., and is designed to enable quick and efficient communication between the delivery person and the delivery requester. This notification process utilizes SMS APIs and other services.

[0594] Specific examples

[0595] A delivery person (Yamada Taro) enters the information, "Yamada Taro, 090-1234-5678, specializes in deliveries within Tokyo, prefers weekends." The server saves this information in a database and manages it within the system.

[0596] The store enters "Pizza delivery, 5 pax needed, Shinjuku-ku, 2023-12-24 18:00." The server stores this information in the database.

[0597] The server periodically retrieves information about Yamada Taro from the database and passes it along with the delivery request information to the generative AI model. The generative AI model detects that Yamada Taro's area of ​​expertise and desired date and time match the delivery request, and outputs Yamada Taro as a matching result.

[0598] Based on this result, the server sends a notification to Yamada Taro saying, "Please participate in pizza delivery in Shinjuku Ward," and notifies the store that "Yamada Taro will be participating."

[0599] This will enable a fast and efficient delivery service between delivery personnel and delivery requesters, improving the efficiency of delivery operations.

[0600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0601] Step 1:

[0602] The user (delivery person) accesses the web form using a smartphone or PC and enters the information they wish to participate in, such as their name, contact information, area of ​​expertise, desired work content, and available dates and times, and clicks the submit button.

[0603] Input: Delivery person registration information

[0604] Output: Save to database

[0605] Step 2:

[0606] The server receives the participation request information sent by the user (delivery person) and saves it in the database. At this time, it converts it into the required data format and stores it appropriately in the database.

[0607] Input: Delivery person registration information

[0608] Output: Participation requests stored in the database

[0609] Step 3:

[0610] Users (stores and restaurants) access a web form using their smartphones or computers and enter delivery request information, including the desired delivery details, number of people, location, date and time, and click the submit button.

[0611] Input: Delivery request information

[0612] Output: Save to database

[0613] Step 4:

[0614] The server receives delivery request information sent by the user (store, etc.) and stores it in a database. At this time, it converts the information into the required data format and stores it appropriately in the database.

[0615] Input: Delivery request information

[0616] Output: Delivery request information stored in the database

[0617] Step 5:

[0618] The server periodically retrieves participation and delivery request information from the database, and at this stage executes a query to obtain the latest information.

[0619] Input: All information in the database

[0620] Output: Latest participation request information and delivery request information

[0621] Step 6:

[0622] The server passes the acquired participation request information and delivery request information to the generative AI model, which analyzes this information and creates a prompt.

[0623] Input: Participation request information and delivery request information

[0624] Output: Prompt sentence to the generative AI model

[0625] Step 7:

[0626] The generative AI model performs optimal matching based on the prompt text and generates matching results, taking into account conditions such as area of ​​expertise, desired work content, date and time, etc.

[0627] Input: prompt statement

[0628] Output: Matching results

[0629] Step 8:

[0630] The server receives the matching results output from the generative AI model and sends a notification based on the results. Specifically, it sends a notification to the delivery person and the store that a match has been made.

[0631] Input: Matching results

[0632] Output: Notification to delivery person and store

[0633] Step 9:

[0634] The user (delivery person and store) receives the notification and confirms the specific work content, location, date and time, etc. The delivery person begins the actual delivery work based on the notification.

[0635] Input: Notification content

[0636] Output: Start of delivery work

[0637] The above processing steps enable efficient matching of delivery personnel with delivery requesters, enabling the provision of fast and accurate delivery services.

[0638] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0639] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Below, we will explain the program processing of this system in natural language.

[0640] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information, stores it in a database, and simultaneously recognizes the user's emotions using an emotion engine.

[0641] The emotion engine analyzes the points that users place particular importance on among the information they enter, and analyzes their emotions and psychological state. For example, it determines their motivation and priorities for volunteer activities. This makes it possible to perform optimal matching while also taking into account the psychological state of those wishing to participate.

[0642] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0643] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[0644] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information. The model also analyzes the applicant's psychological state and priorities, as analyzed by the emotion engine, to generate the optimal matching results. The matching results are calculated taking into account the work content, the applicant's areas of expertise and desires, as well as emotional factors.

[0645] The server then sends notifications to both the potential participants and the volunteer requesters based on the matching results output by the generative AI model. These notifications include the specific task, location, date and time, contact information, and importantly, sentiment analysis results. Upon receiving the notifications, the potential participants and the requesters can communicate with each other and meet at the appropriate time and place to complete the task.

[0646] Specific examples

[0647] A user (Suzuki Ichiro) enters "Suzuki Ichiro, mobile phone number, good at rescue work, preferring weekends" into a web form. The server saves this information in a database and simultaneously starts an emotion engine to analyze the emotional information from Suzuki Ichiro's input, determining his "strong desire to participate in rescue work" and "high priority."

[0648] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[0649] The server periodically retrieves information about Suzuki Ichiro from the database, emotional information, and volunteer request information, and passes it to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities, desired date and time, and emotional information of "high motivation" match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[0650] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro is highly motivated to participate in rescue activities and plans to participate."

[0651] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[0652] The processing flow will be explained below.

[0653] Step 1:

[0654] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[0655] Step 2:

[0656] The server receives the volunteer participation request information entered by the user and stores it in a database. At this time, it activates an emotion engine to collect emotional data from the user's input and their emotions and reactions at the time of sending.

[0657] Step 3:

[0658] The emotion engine analyzes the collected emotion data and extracts information such as the user's current psychological state, motivation for volunteer activities, and priorities. The extracted emotion information is also stored in a database.

[0659] Step 4:

[0660] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[0661] Step 5:

[0662] The server receives the volunteer request information entered by the user and stores it in a database.

[0663] Step 6:

[0664] The server periodically retrieves information on volunteer applicants, emotion information, and volunteer request information from the database. The frequency of retrieval can be adjusted by system settings.

[0665] Step 7:

[0666] The server passes the acquired information to the generative AI model for processing. The generative AI model analyzes the participation request information and volunteer request information to derive the optimal matching results, taking into account the emotional information analyzed by the emotion engine.

[0667] Step 8:

[0668] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, volunteer request information, and emotional information to generate the optimal matching results, which are then returned to the server.

[0669] Step 9:

[0670] The server generates a notification message based on the matching results output by the generative AI model, which includes the specific task, location, date and time, contact information, and important points based on emotional information.

[0671] Step 10:

[0672] The server sends a notification to the volunteer applicant containing details of the matched volunteer work, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer applicant, contact information, and commentary based on the emotion information.

[0673] Step 11:

[0674] Users (those who wish to volunteer and those who request volunteers) communicate with each other based on notifications received from the server, and carry out volunteer activities efficiently at the specified date, time, and location. Notifications based on emotion information build a smoother cooperative system.

[0675] Example 2

[0676] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0677] Conventional volunteer matching systems match participants simply based on their skills and schedules without considering their emotional or psychological state, which can lead to a decline in motivation and satisfaction with volunteer activities.Furthermore, not taking into account emotions and psychological states makes it difficult to optimally allocate personnel, which can reduce the efficiency of volunteer activities.

[0678] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring participation information, means for acquiring volunteer request information, means for analyzing the acquired participation information and volunteer request information and using a generative model to generate optimal matching results, means for notifying based on the generated matching results, means for analyzing the participation information and recognizing the user's emotions, and means for reflecting the emotion recognition results in matching. This enables optimal volunteer matching that takes into account the emotions and psychological state of participants.

[0679] "Participation information" is information provided by individuals who wish to participate in volunteer activities, such as their name, contact information, tasks they are good at, desired work content, and available dates and times.

[0680] "Volunteer request information" is information provided by the party requesting volunteer activities, such as the type of work required of volunteers, the number of people required, the location, and the date and time.

[0681] A "generative model" is a machine learning model or AI model that has the ability to analyze acquired participation request information and volunteer request information and generate optimal matching results.

[0682] "Notification" refers to information sent to prospective participants and volunteer requesters based on the generated matching results, and includes specific work content, location, date and time, contact information, and sentiment analysis results.

[0683] An "emotion engine" is a program or system that has the function of analyzing participation request information and recognizing the emotions and psychological state of the provider.

[0684] "Database" means a digital data storage system for storing participation request information and volunteer request information, and for retrieving and using information as needed.

[0685] The "matching result" is information that indicates the optimal combination of participants and volunteer requesters, generated by analyzing the generative model.

[0686] "Emotion recognition" is the process of analyzing and recognizing the provider's emotions and psychological state based on the participant's participation information.

[0687] This invention is a system that combines a generative AI model and an emotion engine to recognize user emotions while analyzing and matching volunteer applicants with volunteer-requested tasks, thereby achieving optimal volunteer allocation. An embodiment of this system is described in detail below.

[0688] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, their specialties, desired work content, and available dates and times, and clicks the submit button. The server receives this information and stores it in a database. The server then activates an emotion engine, analyzes the entered information, and recognizes the user's emotions.

[0689] For example, if a user enters "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends," the server will store this information in a database and at the same time use an emotion engine to analyze "strong desire to carry out rescue work" and "high priority."

[0690] Next, the user (volunteer requester) accesses the volunteer request registration form and enters information about the required volunteer work. Specifically, the user enters the work content, number of people required, location, date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0691] For example, if a user enters "disaster recovery activities, 10 people needed, Tokyo, weekends," the server stores this information in a database.

[0692] The server periodically retrieves information on volunteer applicants and volunteer requests from the database. This information is passed to the generative AI model, which then analyzes it. During this process, the model also analyzes the psychological state and priorities of the applicants, as analyzed by the emotion engine, to generate optimal matching results.

[0693] For example, the generative AI model detects that "Ichiro Suzuki's specialty rescue activities, desired date and time, and emotional information" match the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs Ichiro Suzuki as the matching result.

[0694] Finally, the server notifies both the prospective participant and the volunteer requester based on the matching results output by the generative AI model, including the specific task, location, date and time, contact information, and importantly, sentiment analysis results.

[0695] For example, a notification saying "Ichiro Suzuki will participate in disaster recovery activities in Tokyo" is sent to those who wish to participate, and a notification saying "Ichiro Suzuki is highly motivated to participate in rescue activities" is sent to the requester.

[0696] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[0697] Examples of prompt statements

[0698] Emotion analysis result for "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends": "High motivation for rescue work"

[0699] Volunteer request information for "Disaster recovery activities, 10 people needed, Tokyo, Saturdays and Sundays" is entered as: "10 people needed for disaster recovery activities in Tokyo, Saturdays and Sundays"

[0700] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0701] The flow of this system's program processing

[0702] Subject: Server, Terminal, User

[0703] (Step 1: User enters information and submits)

[0704] A user (a person wishing to participate as a volunteer) accesses the volunteer registration form on the website, enters information such as name, contact details, skills, desired work content, available dates and times, and submits it.

[0705] Specific operation: The user enters "Name: Yamada Taro, Contact: 090-1234-5678, Specialty: Rescue work, Desired work: Rescue work, Available dates and times: Saturdays and Sundays" and clicks the send button.

[0706] Input: User-entered participation information

[0707] Output: The participation request received by the server

[0708] (Step 2: Information storage and analysis request by the server)

[0709] The server stores the received participation request information in a database and simultaneously requests the emotion engine to analyze it.

[0710] Specific operation: The server requests the emotion engine to analyze "strong desire to carry out rescue operations" and "high priority."

[0711] Input: Participation request information received by the server

[0712] Output: Participation preference information stored in the database and analysis request to the emotion engine

[0713] (Step 3: Emotion analysis using the emotion engine)

[0714] The emotion engine analyzes the user's emotions and psychological state from the provided information and returns the results to the server.

[0715] Specific operation: The emotion engine analyzes that "Yamada Taro has a strong desire to participate in rescue activities" and sends the result to the server.

[0716] Input: Participation request information sent from the server

[0717] Output: Emotion analysis results

[0718] (Step 4: User enters volunteer request information and submits)

[0719] The user (volunteer requester) accesses the volunteer request registration form on the website, enters information about the required volunteer work, and submits it.

[0720] Specific operation: The user enters "Work content: disaster recovery activities, required number of people: 10, location: Tokyo, date and time: weekend" and clicks the send button.

[0721] Input: User-entered volunteer request information

[0722] Output: Volunteer request information received by the server

[0723] (Step 5: The server saves the request information)

[0724] The server stores the received volunteer request information in a database.

[0725] Specific operation: The server stores the received volunteer request information in a database.

[0726] Input: Volunteer request information received by the server

[0727] Output: Volunteer request information stored in a database

[0728] (Step 6: The server obtains the information and passes it to the generative AI model)

[0729] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[0730] Specific operation: The server retrieves information from the database and passes it to the generative AI model.

[0731] Input: Participation request information and volunteer request information stored in the database

[0732] Output: Information passed to the generative AI model

[0733] (Step 7: Matching analysis using generative AI model)

[0734] The generative AI model analyzes the information provided and generates optimal matching results, taking into account the results of sentiment analysis.

[0735] Specific operation: The generative AI model compares and analyzes "Yamada Taro's specialty rescue activities, desired date and time, and emotional information" with the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs the matching result with Yamada Taro as a suitable candidate.

[0736] Input: Participation request information, volunteer request information, and emotion analysis results passed to the generative AI model

[0737] Output: Best matching result

[0738] (Step 8: Server creates and sends notification)

[0739] The server notifies both the person wishing to participate and the person requesting the volunteer based on the matching results output by the generative AI model.

[0740] Specific operation: The server sends a notification to those who wish to participate that "Yamada Taro will participate in disaster recovery efforts in Tokyo," and notifies the requester that "Yamada Taro is highly motivated to participate in rescue efforts."

[0741] Input: Matching results output from the generative AI model

[0742] Output: Notifications sent

[0743] The above are the specific processing steps of the program of this system.

[0744] (Application example 2)

[0745] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0746] Current systems make it difficult to carry out fast and efficient volunteer activities during emergencies and disasters. In particular, simply matching volunteers based on the work content and schedule without considering the emotions and motivation of those who wish to volunteer makes it difficult to optimally allocate volunteers, and does not ensure that they arrive at the scene quickly. Therefore, a system is needed that combines efficient transportation of volunteers with optimal matching based on emotions and motivation.

[0747] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring participation desire information, means for acquiring volunteer request information, means for analyzing the acquired participation desire information and volunteer request information and using a generative model to generate optimal matching results, means for issuing notifications based on the generated matching results, and means for issuing pickup and transportation instructions to an autonomously driven vehicle based on the generated matching results and transporting volunteers to their destination via an optimal route. This makes it possible to match optimal volunteers while taking into account the emotions and motivation of those wishing to volunteer, and to transport volunteers to needed locations quickly and efficiently.

[0748] "Participation information" refers to information provided by individuals who wish to participate as volunteers, such as their name, contact information, areas of expertise, desired work content, and available dates and times.

[0749] "Volunteer request information" means information provided by a requester regarding an activity requiring volunteers, such as the type of work required, the number of people required, the location, and the date and time.

[0750] A "generative model" is an artificial intelligence model that uses machine learning algorithms to analyze volunteer applicants and volunteer request information, and generate optimal matching results.

[0751] An "emotion engine" is a software component that analyzes a user's emotional state and motivation based on information provided by the user.

[0752] An "autonomous vehicle" is a vehicle that uses artificial intelligence and sensor technology to operate without a driver.

[0753] "Notification" is an action that conveys information to volunteer applicants, volunteer requesters, and autonomous vehicles based on the generated matching results.

[0754] The "database" is a system that stores information on volunteer applicants and volunteer requests, and quickly retrieves this information when necessary.

[0755] "Pickup" is the process by which an autonomous vehicle picks up a volunteer from a designated location.

[0756] "Transportation" is the process by which an autonomous vehicle transports volunteers to their designated destinations.

[0757] A "route" is the route chosen by an autonomous vehicle to pick up and transport volunteers to their destination.

[0758] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Furthermore, it also enables efficient transportation of volunteers using autonomous vehicles. A specific embodiment of this system is described below.

[0759] First, a user (a person wishing to volunteer) accesses the volunteer registration form through a smartphone app, enters information such as their name, contact details, tasks they are good at, desired work content, and available dates and times, and clicks the submit button. The submitted information is sent to the server and stored in a database, and at the same time, an emotion engine is activated to analyze the user's emotional state and motivation. The results of this analysis are stored in the database as the user's emotional information.

[0760] Next, those requesting volunteers access the volunteer request registration form via a smartphone app and enter information such as the type of work required, the number of volunteers required, the location, date and time, etc. This information is also sent to the server and stored in the database.

[0761] The server periodically retrieves information on volunteer applicants and volunteer request information from the database and passes it to the generative AI model. The generative AI model analyzes the volunteer applicants' areas of expertise, desired work, available dates and times, and emotional information, and compares them with the volunteer request information to generate the optimal matching results.

[0762] Based on the matching results, the server notifies the volunteers and those requesting volunteers. The notification includes the specific task, location, date, and time, as well as important sentiment analysis results. Based on the matching results, the server also issues pickup and transportation instructions to autonomous vehicles, transporting the volunteers to their destinations via the optimal route.

[0763] For example, a user (a person wishing to participate) enters "I'm good at rescue work, preferring to work on weekends" and submits the request. The server saves this information in a database and uses an emotion engine to analyze "high motivation." Next, the requester enters "disaster recovery work, 10 people needed, Tokyo, weekends" and submits the request, and the server saves this information in its database. The generative AI model performs matching, and if the volunteers wishing to participate match the volunteer request information, a notification is sent. Furthermore, instructions are sent to the autonomous vehicle to "pick up the volunteers and transport them to the specified location."

[0764] (Example of a prompt)

[0765] Please analyze the emotional state of volunteer Suzuki Ichiro based on the following information:

[0766] Name: Suzuki Ichiro

[0767] Contact: 090-1234-5678

[0768] Specialty: Rescue operations

[0769] Desired work: Disaster recovery

[0770] Available dates: Saturdays and Sundays

[0771] Example result:

[0772] (Emotional analysis results)

[0773] Motivation: High

[0774] Priority: High

[0775] This system will enable optimal matching taking into account the emotions and motivation of volunteers, and will enable fast and efficient transportation using self-driving vehicles.

[0776] The hardware used includes smartphones, servers, and autonomous vehicles, and the software uses a smartphone app (Swift / Java), a database (MySQL), a generative AI model (TensorFlow), and an emotion engine (OpenAI GPT-4). This combination enables efficient volunteer activities and rapid response.

[0777] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0778] Step 1:

[0779] A user (a prospective volunteer) opens the volunteer registration form using a smartphone app, enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[0780] Input: Volunteer participation request information entered by the user

[0781] Output: Volunteer participation request information sent to the server

[0782] Specific operation: When a user enters the required information into a form on a smartphone app and submits it, the data is sent to a server via the Internet.

[0783] Step 2:

[0784] The server stores the submitted volunteer participation request information in a database, activates the emotion engine, analyzes the user's emotional state and motivation, and stores the analysis results in the database.

[0785] Input: Volunteer participation information

[0786] Output: Emotion analysis results

[0787] Specific operation: The server stores the received data in a database and passes it to the emotion engine, which analyzes it, returns the results to the server, and stores them in the database again.

[0788] Step 3:

[0789] The requester opens the volunteer request registration form using a smartphone app, enters information such as the type of volunteer work required, the number of volunteers required, the location, and the date and time, and clicks the submit button.

[0790] Input: Volunteer request information entered by the requester

[0791] Output: Volunteer request information sent to the server

[0792] Specific operation: When the requester enters the necessary information into the form on the smartphone app and submits it, the data is sent to the server via the Internet.

[0793] Step 4:

[0794] The server stores the submitted volunteer request information in a database.

[0795] Input: Volunteer request information

[0796] Output: Volunteer request information stored in a database

[0797] Specific operation: The server stores the received data in a database.

[0798] Step 5:

[0799] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[0800] Input: Information retrieved from the database (volunteer participation request information, volunteer request information)

[0801] Output: Data passed to the generative AI model

[0802] Specific operation: The server periodically retrieves the necessary information from the database using SQL queries and passes it to the generative AI model.

[0803] Step 6:

[0804] The generative AI model analyzes the areas of expertise, desired work, available dates and times, and emotional information of volunteer applicants, and compares this with volunteer request information to generate the optimal matching results.

[0805] Input: Volunteer participation request information, volunteer request information, emotional information

[0806] Output: Matching results

[0807] Specific operation: The generative AI model runs a machine learning algorithm based on the received data and outputs the optimal matching result.

[0808] Step 7:

[0809] Based on the generated matching results, the server notifies prospective participants and volunteer requesters.

[0810] Input: Matching results

[0811] Output: Notification message

[0812] Specific operation: The server generates a notification message based on the matching results and sends emails and in-app notifications to those who wish to participate and those who request volunteers.

[0813] Step 8:

[0814] Based on the generated matching results, the server instructs the autonomous vehicle to pick up and transport the goods.

[0815] Input: Matching results

[0816] Output: Instruction data for the autonomous vehicle

[0817] Specific operation: The server sends instructions to the autonomous vehicle's control system on which volunteers to pick up, where to pick them up, and where to transport them.

[0818] Step 9:

[0819] The self-driving vehicle will then follow instructions to pick up volunteers and transport them to a designated location.

[0820] Input: Instruction data for the autonomous vehicle

[0821] Output: Transport volunteer to designated location

[0822] Specific operation: The autonomous vehicle calculates the route based on the instruction data, drives to the designated pickup location, picks up the volunteer, and then heads off to the destination.

[0823] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0824] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0825] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0826] [Third embodiment]

[0827] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0828] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0829] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0830] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0831] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0832] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0833] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0834] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0835] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0836] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0837] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0838] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0839] This invention is a system that uses a generative AI model to analyze and match volunteer applicants with volunteer request tasks, and allocates volunteers appropriately. Below, we will explain the program processing of this system in natural language.

[0840] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[0841] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0842] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[0843] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results. Matching results are calculated taking into account the work content and the applicant's areas of expertise and preferences.

[0844] The server then sends notifications to both the person seeking participation and the person requesting the volunteer based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, contact information, etc. Upon receiving the notifications, the person seeking participation and the person requesting the volunteer can communicate with each other and gather at the appropriate time and place to complete the work.

[0845] Specific examples

[0846] A user (Ichiro Suzuki) enters the following information into a web form: "Ichiro Suzuki, mobile phone number, specializes in rescue operations, prefers weekends." The server stores this information in a database and manages it within the system.

[0847] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[0848] The server periodically retrieves information about Suzuki Ichiro from the database and passes it along with volunteer request information to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities and desired date and time match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[0849] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro will be participating."

[0850] This allows cooperation between those who wish to volunteer and those who request volunteers, enabling quick and efficient volunteer activities.

[0851] The processing flow will be explained below.

[0852] Step 1:

[0853] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[0854] Step 2:

[0855] The server receives the volunteer participation request information entered by the user and stores it in a database, which can be accessed only by administrators with limited privileges.

[0856] Step 3:

[0857] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[0858] Step 4:

[0859] The server receives the volunteer request information entered by the user and stores it in a database. As with the participation request information, this information is also accessible only to the administrator.

[0860] Step 5:

[0861] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The frequency of this retrieval can be adjusted by system settings.

[0862] Step 6:

[0863] The server passes the acquired information on volunteer applicants and volunteer request information to the generative AI model, which then converts this information into the data format required for analysis.

[0864] Step 7:

[0865] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results and return them to the server.

[0866] Step 8:

[0867] The server receives the matching results output by the generative AI model and generates notifications to both the prospective participant and the volunteer requester, including the specific task, location, date and time, and contact information for both parties.

[0868] Step 9:

[0869] The server sends a notification to the volunteer requester containing details of the matched volunteer activity, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer, contact information, and the scheduled activity date and time.

[0870] Step 10:

[0871] Users (those wishing to volunteer and those requesting volunteers) communicate with each other based on the notifications received from the server, and efficiently carry out volunteer activities at the designated date, time and place.

[0872] Example 1

[0873] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0874] Conventional volunteer matching systems have had the problem of being unable to properly analyze the information of those who wish to volunteer and those who request volunteers, and to efficiently match them. In particular, there is a demand for a system that can automatically and accurately match the areas of expertise, desired work content, and available dates and times of volunteers with the specific needs of the requester.

[0875] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0876] In this invention, the server includes a means for acquiring participation request information, a means for acquiring volunteer request information, a means for analyzing the acquired participation request information and volunteer request information and using a generation AI model to generate optimal matching results, and a means for notifying based on the generated matching results. This enables efficient and highly accurate matching by appropriately analyzing the areas of expertise, desired work content, and available dates and times of volunteer applicants and volunteer requesters.

[0877] "Participation information" is information such as areas of expertise, desired work content, and available dates and times provided by individuals who wish to participate in volunteer activities.

[0878] "Volunteer request information" is information provided by individuals or organizations in need of volunteer activities, such as the type of work required, the number of people required, the location, and the date and time.

[0879] A "generative AI model" is an artificial intelligence model that uses collected data to analyze and generate optimal matching results.

[0880] "Notification" refers to the act of communicating specific work content, location, date and time, contact information, etc. to those wishing to volunteer and those requesting volunteers based on the generated matching results.

[0881] "Database" refers to an information storage system built on a server for efficiently and safely storing and managing participation request information and volunteer request information.

[0882] A "prompt sentence" is a specific formatted piece of information that is input to a generative AI model for analysis and matching.

[0883] This invention is a system that uses a generative AI model to efficiently match volunteer applicants with those requesting volunteers, and allocates volunteers appropriately.

[0884] System Overview

[0885] This system consists of three main components: a server, a device, and a user. Users (those who wish to participate and those who request) access the website from their own device (PC or smartphone) and enter the necessary information. The server receives this information and stores it in a database. Periodically, the server retrieves the necessary information from the database and inputs it as a prompt sentence into the generative AI model.

[0886] The generative AI model analyzes the input information and generates optimal matching results. Based on the results, the server sends notifications, enabling efficient implementation of volunteer activities.

[0887] Hardware and software used

[0888] Server: Use cloud servers with high-performance data processing capabilities (e.g., Amazon Web Services, Google Cloud Platform).

[0889] Database: A relational database (e.g., MySQL, PostgreSQL) is used to manage data.

[0890] Generative AI models: Use generative AI models built using machine learning frameworks (e.g., TensorFlow, PyTorch).

[0891] Website: Use modern front-end frameworks (e.g. React, Angular) and back-end frameworks (e.g. Node.js, Django) to create web forms and send and receive data.

[0892] Specific operation of the system

[0893] 1. Enter user information

[0894] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[0895] 2. Enter your request information

[0896] Another user (the volunteer requester) accesses a form on the same or another website and opens a volunteer request registration form. The volunteer requester enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[0897] 3. Data Processing and Analysis

[0898] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The server then passes this information to the generative AI model as prompts. The generative AI model analyzes the volunteer applicant's areas of expertise, desired work, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results.

[0899] Prompt Sentence Examples

[0900] Information for potential volunteers:

[0901] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[0902] Volunteer Request Information:

[0903] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[0904] 4. Sending notifications

[0905] The server sends notifications to both the volunteer applicant and the volunteer requester based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, and contact information. Upon receiving the notifications, the volunteer applicant and requester will communicate based on the notifications and meet at the designated place and time to complete the work.

[0906] This will enable efficient cooperation between those who wish to volunteer and those who request volunteers, resulting in prompt and effective volunteer activities.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Step 1:

[0909] A user (a person wishing to participate as a volunteer) accesses the website and enters information into the volunteer participation registration form.

[0910] Input: Name, contact details, skills, desired work, available dates and times

[0911] What happens: A user visits a web form, fills in the required information, and clicks the submit button.

[0912] Output: The entered information is sent to the server.

[0913] Step 2:

[0914] The server receives the participation request information and stores it in a database.

[0915] Input: Information of the person who wants to participate (name, contact information, skills, desired work, available date and time)

[0916] What it does: The server formats the information it receives and stores it in a database.

[0917] Output: Participation preferences stored in a database

[0918] Step 3:

[0919] A user (volunteer requester) accesses the same or another website and enters information into a volunteer request registration form.

[0920] Input: Volunteer work required, number required, location, date and time

[0921] How it works: A volunteer requester visits a web form, fills in the required information, and clicks submit.

[0922] Output: The requested information is sent to the server.

[0923] Step 4:

[0924] The server receives the requested information and stores it in a database.

[0925] Input: Volunteer request information (task details, number of people required, location, date and time)

[0926] What it does: The server formats the information it receives and stores it in a database.

[0927] Output: Request information stored in the database

[0928] Step 5:

[0929] The server periodically retrieves participation information and request information from the database.

[0930] Input: Participation preferences and request information stored in the database

[0931] How it works: A scheduled task on the server periodically accesses the database to retrieve the necessary information.

[0932] Output: Acquired participation request information and request information

[0933] Step 6:

[0934] The information obtained by the server is used to input prompt sentences into the generative AI model.

[0935] Input: Acquired participation request information and request information

[0936] Example prompt sentence:

[0937] Information for potential volunteers:

[0938] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[0939] Volunteer Request Information:

[0940] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[0941] How it works: The server converts the information it obtains into a prompt sentence and inputs it into the generative AI model.

[0942] Output: The prompt passed to the generative AI model

[0943] Step 7:

[0944] The generative AI model analyzes the prompt and generates the best matching result.

[0945] Input: The prompt passed to the generative AI model

[0946] How it works: The generative AI model analyzes data based on the prompt text and matches the optimal combination of participants and requested information.

[0947] Output: The generated matching results

[0948] Step 8:

[0949] The server receives the matching results output from the generative AI model and notifies them.

[0950] Input: Generated matching results

[0951] How it works: Based on the matching results, the server notifies the participants and volunteer requesters of the tasks, including the location, date, time, and contact information.

[0952] Output: Notifications sent to applicants and requesters

[0953] Step 9:

[0954] Users (those wishing to participate and those making the request) will communicate based on the notification and work at the specified date, time and place.

[0955] Input: Notification sent (task, location, date, time, contact)

[0956] How it works: Users who receive the notification will contact each other and actually volunteer at the specified date, time and place.

[0957] Output: Volunteer activity performed

[0958] (Application example 1)

[0959] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0960] Conventional delivery systems have issues with inefficient matching of delivery personnel with delivery requests, leading to delays and errors in delivery operations. In particular, matching is performed without taking into account the delivery personnel's areas of expertise or desired work content, which often results in unnecessary travel and inappropriate delivery assignments. Therefore, there is a need for a system that can improve the efficiency of delivery operations and efficiently match delivery personnel with delivery requests.

[0961] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0962] In this invention, the server includes a means for acquiring participation desire information, a means for acquiring delivery request information, a means for analyzing the acquired participation desire information and delivery request information and using a generation model to generate an optimal matching result, and a means for notifying based on the generated matching result. This makes it possible to match the optimal delivery person with the delivery request, taking into account the delivery person's area of ​​expertise and the desired work content.

[0963] "Participation information" is information submitted by a delivery person when they wish to participate in a delivery, and includes their name, contact information, area of ​​expertise, desired work content, available dates and times, etc.

[0964] "Delivery request information" refers to information submitted by a restaurant or store when requesting delivery, and includes the required delivery details, number of people requested, location, date and time, etc.

[0965] A "generative model" is an artificial intelligence model that analyzes participation request information and delivery request information and generates optimal matching results based on that information.

[0966] "Notification" is a means of sending communication and instructions to delivery personnel and delivery requesters based on the matching results generated by the generative model.

[0967] "Specialty area" refers to an area in which a delivery person is good at making deliveries, and indicates an area in which deliveries can be made efficiently.

[0968] "Desired work content" refers to the specific work content that a delivery person desires when they apply to participate in a delivery, and what type of delivery work they would like to do.

[0969] "Matching" is the process of comparing participation request information with delivery request information and selecting the best combination.

[0970] The "database" is a system that organizes and stores data such as participation requests and delivery requests, and allows efficient search and retrieval of information as needed.

[0971] The present invention provides a system for efficiently matching delivery personnel with delivery requests in a delivery service, which is implemented by utilizing a server, a terminal of the delivery personnel, and a terminal of the delivery requester.

[0972] Overall system overview

[0973] The server acquires participation request information and delivery request information. To collect this information, data entered into a web form from the terminals of the delivery person and the delivery requester is used. The server stores this acquired information in a database and updates the information periodically.

[0974] Hardware and software used

[0975] 1. Server:

[0976] The server is implemented as a web application using Flask.

[0977] The database uses SQLite to store and manage information.

[0978] The generative AI model used is OpenAI's GPT-3.

[0979] 2. Delivery person and delivery requester's device:

[0980] Delivery personnel and delivery requesters access the system via a web browser on their smartphone or computer.

[0981] Use the web form to enter and submit your participation and delivery request information.

[0982] Program processing explanation

[0983] The server first collects participation information from delivery personnel and delivery request information from stores and restaurants, including name, contact information, area of ​​expertise, desired work, available date and time, required delivery content, number of people requested, location, date and time, etc.

[0984] The server stores this data in a database and periodically retrieves it to pass to the generative AI model, which matches delivery staff with delivery requests based on the following example prompt:

[0985] Example prompt sentence:

[0986] Volunteer Name: Taro Yamada

[0987] Skill: Delivery in Tokyo

[0988] Available Time: Saturdays and Sundays

[0989] ---

[0990] Request Task: Pizza Delivery

[0991] Required Volunteers: 5

[0992] Location: Shinjuku Ward

[0993] Date and Time: 2023-12-24 18:00

[0994] Is this a good match? True or False

[0995] The generative AI model analyzes the prompt and generates the optimal matching result by taking into consideration the delivery person's area of ​​expertise, the desired work content, and the request content. Based on the generated matching result, the server notifies both the delivery person and the requester.

[0996] The notification includes specific details of the job, location, date and time, contact information, etc., and is designed to enable quick and efficient communication between the delivery person and the delivery requester. This notification process utilizes SMS APIs and other services.

[0997] Specific examples

[0998] A delivery person (Yamada Taro) enters the information, "Yamada Taro, 090-1234-5678, specializes in deliveries within Tokyo, prefers weekends." The server saves this information in a database and manages it within the system.

[0999] The store enters "Pizza delivery, 5 pax needed, Shinjuku-ku, 2023-12-24 18:00." The server stores this information in the database.

[1000] The server periodically retrieves information about Yamada Taro from the database and passes it along with the delivery request information to the generative AI model. The generative AI model detects that Yamada Taro's area of ​​expertise and desired date and time match the delivery request, and outputs Yamada Taro as a matching result.

[1001] Based on this result, the server sends a notification to Yamada Taro saying, "Please participate in pizza delivery in Shinjuku Ward," and notifies the store that "Yamada Taro will be participating."

[1002] This will enable a fast and efficient delivery service between delivery personnel and delivery requesters, improving the efficiency of delivery operations.

[1003] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1004] Step 1:

[1005] The user (delivery person) accesses the web form using a smartphone or PC and enters the information they wish to participate in, such as their name, contact information, area of ​​expertise, desired work content, and available dates and times, and clicks the submit button.

[1006] Input: Delivery person registration information

[1007] Output: Save to database

[1008] Step 2:

[1009] The server receives the participation request information sent by the user (delivery person) and saves it in the database. At this time, it converts it into the required data format and stores it appropriately in the database.

[1010] Input: Delivery person registration information

[1011] Output: Participation requests stored in the database

[1012] Step 3:

[1013] Users (stores and restaurants) access a web form using their smartphones or computers and enter delivery request information, including the desired delivery details, number of people, location, date and time, and click the submit button.

[1014] Input: Delivery request information

[1015] Output: Save to database

[1016] Step 4:

[1017] The server receives delivery request information sent by the user (store, etc.) and stores it in a database. At this time, it converts the information into the required data format and stores it appropriately in the database.

[1018] Input: Delivery request information

[1019] Output: Delivery request information stored in the database

[1020] Step 5:

[1021] The server periodically retrieves participation and delivery request information from the database, and at this stage executes a query to obtain the latest information.

[1022] Input: All information in the database

[1023] Output: Latest participation request information and delivery request information

[1024] Step 6:

[1025] The server passes the acquired participation request information and delivery request information to the generative AI model, which analyzes this information and creates a prompt.

[1026] Input: Participation request information and delivery request information

[1027] Output: Prompt sentence to the generative AI model

[1028] Step 7:

[1029] The generative AI model performs optimal matching based on the prompt text and generates matching results, taking into account conditions such as area of ​​expertise, desired work content, date and time, etc.

[1030] Input: prompt statement

[1031] Output: Matching results

[1032] Step 8:

[1033] The server receives the matching results output from the generative AI model and sends a notification based on the results. Specifically, it sends a notification to the delivery person and the store that a match has been made.

[1034] Input: Matching results

[1035] Output: Notification to delivery person and store

[1036] Step 9:

[1037] The user (delivery person and store) receives the notification and confirms the specific work content, location, date and time, etc. The delivery person begins the actual delivery work based on the notification.

[1038] Input: Notification content

[1039] Output: Start of delivery work

[1040] The above processing steps enable efficient matching of delivery personnel with delivery requesters, enabling the provision of fast and accurate delivery services.

[1041] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1042] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Below, we will explain the program processing of this system in natural language.

[1043] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information, stores it in a database, and simultaneously recognizes the user's emotions using an emotion engine.

[1044] The emotion engine analyzes the points that users place particular importance on among the information they enter, and analyzes their emotions and psychological state. For example, it determines their motivation and priorities for volunteer activities. This makes it possible to perform optimal matching while also taking into account the psychological state of those wishing to participate.

[1045] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[1046] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[1047] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information. The model also analyzes the applicant's psychological state and priorities, as analyzed by the emotion engine, to generate the optimal matching results. The matching results are calculated taking into account the work content, the applicant's areas of expertise and desires, as well as emotional factors.

[1048] The server then sends notifications to both the potential participants and the volunteer requesters based on the matching results output by the generative AI model. These notifications include the specific task, location, date and time, contact information, and importantly, sentiment analysis results. Upon receiving the notifications, the potential participants and the requesters can communicate with each other and meet at the appropriate time and place to complete the task.

[1049] Specific examples

[1050] A user (Suzuki Ichiro) enters "Suzuki Ichiro, mobile phone number, good at rescue work, preferring weekends" into a web form. The server saves this information in a database and simultaneously starts an emotion engine to analyze the emotional information from Suzuki Ichiro's input, determining his "strong desire to participate in rescue work" and "high priority."

[1051] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[1052] The server periodically retrieves information about Suzuki Ichiro from the database, emotional information, and volunteer request information, and passes it to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities, desired date and time, and emotional information of "high motivation" match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[1053] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro is highly motivated to participate in rescue activities and plans to participate."

[1054] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[1055] The processing flow will be explained below.

[1056] Step 1:

[1057] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[1058] Step 2:

[1059] The server receives the volunteer participation request information entered by the user and stores it in a database. At this time, it activates an emotion engine to collect emotional data from the user's input and their emotions and reactions at the time of sending.

[1060] Step 3:

[1061] The emotion engine analyzes the collected emotion data and extracts information such as the user's current psychological state, motivation for volunteer activities, and priorities. The extracted emotion information is also stored in a database.

[1062] Step 4:

[1063] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[1064] Step 5:

[1065] The server receives the volunteer request information entered by the user and stores it in a database.

[1066] Step 6:

[1067] The server periodically retrieves information on volunteer applicants, emotion information, and volunteer request information from the database. The frequency of retrieval can be adjusted by system settings.

[1068] Step 7:

[1069] The server passes the acquired information to the generative AI model for processing. The generative AI model analyzes the participation request information and volunteer request information to derive the optimal matching results, taking into account the emotional information analyzed by the emotion engine.

[1070] Step 8:

[1071] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, volunteer request information, and emotional information to generate the optimal matching results, which are then returned to the server.

[1072] Step 9:

[1073] The server generates a notification message based on the matching results output by the generative AI model, which includes the specific task, location, date and time, contact information, and important points based on emotional information.

[1074] Step 10:

[1075] The server sends a notification to the volunteer applicant containing details of the matched volunteer work, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer applicant, contact information, and commentary based on the emotion information.

[1076] Step 11:

[1077] Users (those who wish to volunteer and those who request volunteers) communicate with each other based on notifications received from the server, and carry out volunteer activities efficiently at the specified date, time, and location. Notifications based on emotion information build a smoother cooperative system.

[1078] Example 2

[1079] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1080] Conventional volunteer matching systems match participants simply based on their skills and schedules without considering their emotional or psychological state, which can lead to a decline in motivation and satisfaction with volunteer activities.Furthermore, not taking into account emotions and psychological states makes it difficult to optimally allocate personnel, which can reduce the efficiency of volunteer activities.

[1081] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring participation information, means for acquiring volunteer request information, means for analyzing the acquired participation information and volunteer request information and using a generative model to generate optimal matching results, means for notifying based on the generated matching results, means for analyzing the participation information and recognizing the user's emotions, and means for reflecting the emotion recognition results in matching. This enables optimal volunteer matching that takes into account the emotions and psychological state of participants.

[1082] "Participation information" is information provided by individuals who wish to participate in volunteer activities, such as their name, contact information, tasks they are good at, desired work content, and available dates and times.

[1083] "Volunteer request information" is information provided by the party requesting volunteer activities, such as the type of work required of volunteers, the number of people required, the location, and the date and time.

[1084] A "generative model" is a machine learning model or AI model that has the ability to analyze acquired participation request information and volunteer request information and generate optimal matching results.

[1085] "Notification" refers to information sent to prospective participants and volunteer requesters based on the generated matching results, and includes specific work content, location, date and time, contact information, and sentiment analysis results.

[1086] An "emotion engine" is a program or system that has the function of analyzing participation request information and recognizing the emotions and psychological state of the provider.

[1087] "Database" means a digital data storage system for storing participation request information and volunteer request information, and for retrieving and using information as needed.

[1088] The "matching result" is information that indicates the optimal combination of participants and volunteer requesters, generated by analyzing the generative model.

[1089] "Emotion recognition" is the process of analyzing and recognizing the provider's emotions and psychological state based on the participant's participation information.

[1090] This invention is a system that combines a generative AI model and an emotion engine to recognize user emotions while analyzing and matching volunteer applicants with volunteer-requested tasks, thereby achieving optimal volunteer allocation. An embodiment of this system is described in detail below.

[1091] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, their specialties, desired work content, and available dates and times, and clicks the submit button. The server receives this information and stores it in a database. The server then activates an emotion engine, analyzes the entered information, and recognizes the user's emotions.

[1092] For example, if a user enters "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends," the server will store this information in a database and at the same time use an emotion engine to analyze "strong desire to carry out rescue work" and "high priority."

[1093] Next, the user (volunteer requester) accesses the volunteer request registration form and enters information about the required volunteer work. Specifically, the user enters the work content, number of people required, location, date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[1094] For example, if a user enters "disaster recovery activities, 10 people needed, Tokyo, weekends," the server stores this information in a database.

[1095] The server periodically retrieves information on volunteer applicants and volunteer requests from the database. This information is passed to the generative AI model, which then analyzes it. During this process, the model also analyzes the psychological state and priorities of the applicants, as analyzed by the emotion engine, to generate optimal matching results.

[1096] For example, the generative AI model detects that "Ichiro Suzuki's specialty rescue activities, desired date and time, and emotional information" match the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs Ichiro Suzuki as the matching result.

[1097] Finally, the server notifies both the prospective participant and the volunteer requester based on the matching results output by the generative AI model, including the specific task, location, date and time, contact information, and importantly, sentiment analysis results.

[1098] For example, a notification saying "Ichiro Suzuki will participate in disaster recovery activities in Tokyo" is sent to those who wish to participate, and a notification saying "Ichiro Suzuki is highly motivated to participate in rescue activities" is sent to the requester.

[1099] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[1100] Examples of prompt statements

[1101] Emotion analysis result for "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends": "High motivation for rescue work"

[1102] Volunteer request information for "Disaster recovery activities, 10 people needed, Tokyo, Saturdays and Sundays" is entered as: "10 people needed for disaster recovery activities in Tokyo, Saturdays and Sundays"

[1103] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1104] The flow of this system's program processing

[1105] Subject: Server, Terminal, User

[1106] (Step 1: User enters information and submits)

[1107] A user (a person wishing to participate as a volunteer) accesses the volunteer registration form on the website, enters information such as name, contact details, skills, desired work content, available dates and times, and submits it.

[1108] Specific operation: The user enters "Name: Yamada Taro, Contact: 090-1234-5678, Specialty: Rescue work, Desired work: Rescue work, Available dates and times: Saturdays and Sundays" and clicks the send button.

[1109] Input: User-entered participation information

[1110] Output: The participation request received by the server

[1111] (Step 2: Information storage and analysis request by the server)

[1112] The server stores the received participation request information in a database and simultaneously requests the emotion engine to analyze it.

[1113] Specific operation: The server requests the emotion engine to analyze "strong desire to carry out rescue operations" and "high priority."

[1114] Input: Participation request information received by the server

[1115] Output: Participation preference information stored in the database and analysis request to the emotion engine

[1116] (Step 3: Emotion analysis using the emotion engine)

[1117] The emotion engine analyzes the user's emotions and psychological state from the provided information and returns the results to the server.

[1118] Specific operation: The emotion engine analyzes that "Yamada Taro has a strong desire to participate in rescue activities" and sends the result to the server.

[1119] Input: Participation request information sent from the server

[1120] Output: Emotion analysis results

[1121] (Step 4: User enters volunteer request information and submits)

[1122] The user (volunteer requester) accesses the volunteer request registration form on the website, enters information about the required volunteer work, and submits it.

[1123] Specific operation: The user enters "Work content: disaster recovery activities, required number of people: 10, location: Tokyo, date and time: weekend" and clicks the send button.

[1124] Input: User-entered volunteer request information

[1125] Output: Volunteer request information received by the server

[1126] (Step 5: The server saves the request information)

[1127] The server stores the received volunteer request information in a database.

[1128] Specific operation: The server stores the received volunteer request information in a database.

[1129] Input: Volunteer request information received by the server

[1130] Output: Volunteer request information stored in a database

[1131] (Step 6: The server obtains the information and passes it to the generative AI model)

[1132] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[1133] Specific operation: The server retrieves information from the database and passes it to the generative AI model.

[1134] Input: Participation request information and volunteer request information stored in the database

[1135] Output: Information passed to the generative AI model

[1136] (Step 7: Matching analysis using generative AI model)

[1137] The generative AI model analyzes the information provided and generates optimal matching results, taking into account the results of sentiment analysis.

[1138] Specific operation: The generative AI model compares and analyzes "Yamada Taro's specialty rescue activities, desired date and time, and emotional information" with the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs the matching result with Yamada Taro as a suitable candidate.

[1139] Input: Participation request information, volunteer request information, and emotion analysis results passed to the generative AI model

[1140] Output: Best matching result

[1141] (Step 8: Server creates and sends notification)

[1142] The server notifies both the person wishing to participate and the person requesting the volunteer based on the matching results output by the generative AI model.

[1143] Specific operation: The server sends a notification to those who wish to participate that "Yamada Taro will participate in disaster recovery efforts in Tokyo," and notifies the requester that "Yamada Taro is highly motivated to participate in rescue efforts."

[1144] Input: Matching results output from the generative AI model

[1145] Output: Notifications sent

[1146] The above are the specific processing steps of the program of this system.

[1147] (Application example 2)

[1148] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1149] Current systems make it difficult to carry out fast and efficient volunteer activities during emergencies and disasters. In particular, simply matching volunteers based on the work content and schedule without considering the emotions and motivation of those who wish to volunteer makes it difficult to optimally allocate volunteers, and does not ensure that they arrive at the scene quickly. Therefore, a system is needed that combines efficient transportation of volunteers with optimal matching based on emotions and motivation.

[1150] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring participation desire information, means for acquiring volunteer request information, means for analyzing the acquired participation desire information and volunteer request information and using a generative model to generate optimal matching results, means for issuing notifications based on the generated matching results, and means for issuing pickup and transportation instructions to an autonomously driven vehicle based on the generated matching results and transporting volunteers to their destination via an optimal route. This makes it possible to match optimal volunteers while taking into account the emotions and motivation of those wishing to volunteer, and to transport volunteers to needed locations quickly and efficiently.

[1151] "Participation information" refers to information provided by individuals who wish to participate as volunteers, such as their name, contact information, areas of expertise, desired work content, and available dates and times.

[1152] "Volunteer request information" means information provided by a requester regarding an activity requiring volunteers, such as the type of work required, the number of people required, the location, and the date and time.

[1153] A "generative model" is an artificial intelligence model that uses machine learning algorithms to analyze volunteer applicants and volunteer request information, and generate optimal matching results.

[1154] An "emotion engine" is a software component that analyzes a user's emotional state and motivation based on information provided by the user.

[1155] An "autonomous vehicle" is a vehicle that uses artificial intelligence and sensor technology to operate without a driver.

[1156] "Notification" is an action that conveys information to volunteer applicants, volunteer requesters, and autonomous vehicles based on the generated matching results.

[1157] The "database" is a system that stores information on volunteer applicants and volunteer requests, and quickly retrieves this information when necessary.

[1158] "Pickup" is the process by which an autonomous vehicle picks up a volunteer from a designated location.

[1159] "Transportation" is the process by which an autonomous vehicle transports volunteers to their designated destinations.

[1160] A "route" is the route chosen by an autonomous vehicle to pick up and transport volunteers to their destination.

[1161] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Furthermore, it also enables efficient transportation of volunteers using autonomous vehicles. A specific embodiment of this system is described below.

[1162] First, a user (a person wishing to volunteer) accesses the volunteer registration form through a smartphone app, enters information such as their name, contact details, tasks they are good at, desired work content, and available dates and times, and clicks the submit button. The submitted information is sent to the server and stored in a database, and at the same time, an emotion engine is activated to analyze the user's emotional state and motivation. The results of this analysis are stored in the database as the user's emotional information.

[1163] Next, those requesting volunteers access the volunteer request registration form via a smartphone app and enter information such as the type of work required, the number of volunteers required, the location, date and time, etc. This information is also sent to the server and stored in the database.

[1164] The server periodically retrieves information on volunteer applicants and volunteer request information from the database and passes it to the generative AI model. The generative AI model analyzes the volunteer applicants' areas of expertise, desired work, available dates and times, and emotional information, and compares them with the volunteer request information to generate the optimal matching results.

[1165] Based on the matching results, the server notifies the volunteers and those requesting volunteers. The notification includes the specific task, location, date, and time, as well as important sentiment analysis results. Based on the matching results, the server also issues pickup and transportation instructions to autonomous vehicles, transporting the volunteers to their destinations via the optimal route.

[1166] For example, a user (a person wishing to participate) enters "I'm good at rescue work, preferring to work on weekends" and submits the request. The server saves this information in a database and uses an emotion engine to analyze "high motivation." Next, the requester enters "disaster recovery work, 10 people needed, Tokyo, weekends" and submits the request, and the server saves this information in its database. The generative AI model performs matching, and if the volunteers wishing to participate match the volunteer request information, a notification is sent. Furthermore, instructions are sent to the autonomous vehicle to "pick up the volunteers and transport them to the specified location."

[1167] (Example of a prompt)

[1168] Please analyze the emotional state of volunteer Suzuki Ichiro based on the following information:

[1169] Name: Suzuki Ichiro

[1170] Contact: 090-1234-5678

[1171] Specialty: Rescue operations

[1172] Desired work: Disaster recovery

[1173] Available dates: Saturdays and Sundays

[1174] Example result:

[1175] (Emotional analysis results)

[1176] Motivation: High

[1177] Priority: High

[1178] This system will enable optimal matching taking into account the emotions and motivation of volunteers, and will enable fast and efficient transportation using self-driving vehicles.

[1179] The hardware used includes smartphones, servers, and autonomous vehicles, and the software uses a smartphone app (Swift / Java), a database (MySQL), a generative AI model (TensorFlow), and an emotion engine (OpenAI GPT-4). This combination enables efficient volunteer activities and rapid response.

[1180] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1181] Step 1:

[1182] A user (a prospective volunteer) opens the volunteer registration form using a smartphone app, enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[1183] Input: Volunteer participation request information entered by the user

[1184] Output: Volunteer participation request information sent to the server

[1185] Specific operation: When a user enters the required information into a form on a smartphone app and submits it, the data is sent to a server via the Internet.

[1186] Step 2:

[1187] The server stores the submitted volunteer participation request information in a database, activates the emotion engine, analyzes the user's emotional state and motivation, and stores the analysis results in the database.

[1188] Input: Volunteer participation information

[1189] Output: Emotion analysis results

[1190] Specific operation: The server stores the received data in a database and passes it to the emotion engine, which analyzes it, returns the results to the server, and stores them in the database again.

[1191] Step 3:

[1192] The requester opens the volunteer request registration form using a smartphone app, enters information such as the type of volunteer work required, the number of volunteers required, the location, and the date and time, and clicks the submit button.

[1193] Input: Volunteer request information entered by the requester

[1194] Output: Volunteer request information sent to the server

[1195] Specific operation: When the requester enters the necessary information into the form on the smartphone app and submits it, the data is sent to the server via the Internet.

[1196] Step 4:

[1197] The server stores the submitted volunteer request information in a database.

[1198] Input: Volunteer request information

[1199] Output: Volunteer request information stored in a database

[1200] Specific operation: The server stores the received data in a database.

[1201] Step 5:

[1202] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[1203] Input: Information retrieved from the database (volunteer participation request information, volunteer request information)

[1204] Output: Data passed to the generative AI model

[1205] Specific operation: The server periodically retrieves the necessary information from the database using SQL queries and passes it to the generative AI model.

[1206] Step 6:

[1207] The generative AI model analyzes the areas of expertise, desired work, available dates and times, and emotional information of volunteer applicants, and compares this with volunteer request information to generate the optimal matching results.

[1208] Input: Volunteer participation request information, volunteer request information, emotional information

[1209] Output: Matching results

[1210] Specific operation: The generative AI model runs a machine learning algorithm based on the received data and outputs the optimal matching result.

[1211] Step 7:

[1212] Based on the generated matching results, the server notifies prospective participants and volunteer requesters.

[1213] Input: Matching results

[1214] Output: Notification message

[1215] Specific operation: The server generates a notification message based on the matching results and sends emails and in-app notifications to those who wish to participate and those who request volunteers.

[1216] Step 8:

[1217] Based on the generated matching results, the server instructs the autonomous vehicle to pick up and transport the goods.

[1218] Input: Matching results

[1219] Output: Instruction data for the autonomous vehicle

[1220] Specific operation: The server sends instructions to the autonomous vehicle's control system on which volunteers to pick up, where to pick them up, and where to transport them.

[1221] Step 9:

[1222] The self-driving vehicle will then follow instructions to pick up volunteers and transport them to a designated location.

[1223] Input: Instruction data for the autonomous vehicle

[1224] Output: Transport volunteer to designated location

[1225] Specific operation: The autonomous vehicle calculates the route based on the instruction data, drives to the designated pickup location, picks up the volunteer, and then heads off to the destination.

[1226] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1227] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1228] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1229] [Fourth embodiment]

[1230] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1231] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1232] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1233] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1234] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1235] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1236] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1237] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1238] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1239] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1240] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1241] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1242] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1243] This invention is a system that uses a generative AI model to analyze and match volunteer applicants with volunteer request tasks, and allocates volunteers appropriately. Below, we will explain the program processing of this system in natural language.

[1244] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[1245] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[1246] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[1247] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results. Matching results are calculated taking into account the work content and the applicant's areas of expertise and preferences.

[1248] The server then sends notifications to both the person seeking participation and the person requesting the volunteer based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, contact information, etc. Upon receiving the notifications, the person seeking participation and the person requesting the volunteer can communicate with each other and gather at the appropriate time and place to complete the work.

[1249] Specific examples

[1250] A user (Ichiro Suzuki) enters the following information into a web form: "Ichiro Suzuki, mobile phone number, specializes in rescue operations, prefers weekends." The server stores this information in a database and manages it within the system.

[1251] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[1252] The server periodically retrieves information about Suzuki Ichiro from the database and passes it along with volunteer request information to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities and desired date and time match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[1253] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro will be participating."

[1254] This allows cooperation between those who wish to volunteer and those who request volunteers, enabling quick and efficient volunteer activities.

[1255] The processing flow will be explained below.

[1256] Step 1:

[1257] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[1258] Step 2:

[1259] The server receives the volunteer participation request information entered by the user and stores it in a database, which can be accessed only by administrators with limited privileges.

[1260] Step 3:

[1261] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[1262] Step 4:

[1263] The server receives the volunteer request information entered by the user and stores it in a database. As with the participation request information, this information is also accessible only to the administrator.

[1264] Step 5:

[1265] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The frequency of this retrieval can be adjusted by system settings.

[1266] Step 6:

[1267] The server passes the acquired information on volunteer applicants and volunteer request information to the generative AI model, which then converts this information into the data format required for analysis.

[1268] Step 7:

[1269] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results and return them to the server.

[1270] Step 8:

[1271] The server receives the matching results output by the generative AI model and generates notifications to both the prospective participant and the volunteer requester, including the specific task, location, date and time, and contact information for both parties.

[1272] Step 9:

[1273] The server sends a notification to the volunteer requester containing details of the matched volunteer activity, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer, contact information, and the scheduled activity date and time.

[1274] Step 10:

[1275] Users (those wishing to volunteer and those requesting volunteers) communicate with each other based on the notifications received from the server, and efficiently carry out volunteer activities at the designated date, time and place.

[1276] Example 1

[1277] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1278] Conventional volunteer matching systems have had the problem of being unable to properly analyze the information of those who wish to volunteer and those who request volunteers, and to efficiently match them. In particular, there is a demand for a system that can automatically and accurately match the areas of expertise, desired work content, and available dates and times of volunteers with the specific needs of the requester.

[1279] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1280] In this invention, the server includes a means for acquiring participation request information, a means for acquiring volunteer request information, a means for analyzing the acquired participation request information and volunteer request information and using a generation AI model to generate optimal matching results, and a means for notifying based on the generated matching results. This enables efficient and highly accurate matching by appropriately analyzing the areas of expertise, desired work content, and available dates and times of volunteer applicants and volunteer requesters.

[1281] "Participation information" is information such as areas of expertise, desired work content, and available dates and times provided by individuals who wish to participate in volunteer activities.

[1282] "Volunteer request information" is information provided by individuals or organizations in need of volunteer activities, such as the type of work required, the number of people required, the location, and the date and time.

[1283] A "generative AI model" is an artificial intelligence model that uses collected data to analyze and generate optimal matching results.

[1284] "Notification" refers to the act of communicating specific work content, location, date and time, contact information, etc. to those wishing to volunteer and those requesting volunteers based on the generated matching results.

[1285] "Database" refers to an information storage system built on a server for efficiently and safely storing and managing participation request information and volunteer request information.

[1286] A "prompt sentence" is a specific formatted piece of information that is input to a generative AI model for analysis and matching.

[1287] This invention is a system that uses a generative AI model to efficiently match volunteer applicants with those requesting volunteers, and allocates volunteers appropriately.

[1288] System Overview

[1289] This system consists of three main components: a server, a device, and a user. Users (those who wish to participate and those who request) access the website from their own device (PC or smartphone) and enter the necessary information. The server receives this information and stores it in a database. Periodically, the server retrieves the necessary information from the database and inputs it as a prompt sentence into the generative AI model.

[1290] The generative AI model analyzes the input information and generates optimal matching results. Based on the results, the server sends notifications, enabling efficient implementation of volunteer activities.

[1291] Hardware and software used

[1292] Server: Use cloud servers with high-performance data processing capabilities (e.g., Amazon Web Services, Google Cloud Platform).

[1293] Database: A relational database (e.g., MySQL, PostgreSQL) is used to manage data.

[1294] Generative AI models: Use generative AI models built using machine learning frameworks (e.g., TensorFlow, PyTorch).

[1295] Website: Use modern front-end frameworks (e.g. React, Angular) and back-end frameworks (e.g. Node.js, Django) to create web forms and send and receive data.

[1296] Specific operation of the system

[1297] 1. Enter user information

[1298] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information and stores it in a database.

[1299] 2. Enter your request information

[1300] Another user (the volunteer requester) accesses a form on the same or another website and opens a volunteer request registration form. The volunteer requester enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[1301] 3. Data Processing and Analysis

[1302] The server periodically retrieves information on volunteer applicants and volunteer request information from the database. The server then passes this information to the generative AI model as prompts. The generative AI model analyzes the volunteer applicant's areas of expertise, desired work, available dates and times, and the work content, number of people requested, location, and date and time in the volunteer request information, to generate the optimal matching results.

[1303] Prompt Sentence Examples

[1304] Information for potential volunteers:

[1305] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[1306] Volunteer Request Information:

[1307] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[1308] 4. Sending notifications

[1309] The server sends notifications to both the volunteer applicant and the volunteer requester based on the matching results output by the generative AI model. The notifications include specific work content, location, date and time, and contact information. Upon receiving the notifications, the volunteer applicant and requester will communicate based on the notifications and meet at the designated place and time to complete the work.

[1310] This will enable efficient cooperation between those who wish to volunteer and those who request volunteers, resulting in prompt and effective volunteer activities.

[1311] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1312] Step 1:

[1313] A user (a person wishing to participate as a volunteer) accesses the website and enters information into the volunteer participation registration form.

[1314] Input: Name, contact details, skills, desired work, available dates and times

[1315] What happens: A user visits a web form, fills in the required information, and clicks the submit button.

[1316] Output: The entered information is sent to the server.

[1317] Step 2:

[1318] The server receives the participation request information and stores it in a database.

[1319] Input: Information of the person who wants to participate (name, contact information, skills, desired work, available date and time)

[1320] What it does: The server formats the information it receives and stores it in a database.

[1321] Output: Participation preferences stored in a database

[1322] Step 3:

[1323] A user (volunteer requester) accesses the same or another website and enters information into a volunteer request registration form.

[1324] Input: Volunteer work required, number required, location, date and time

[1325] How it works: A volunteer requester visits a web form, fills in the required information, and clicks submit.

[1326] Output: The requested information is sent to the server.

[1327] Step 4:

[1328] The server receives the requested information and stores it in a database.

[1329] Input: Volunteer request information (task details, number of people required, location, date and time)

[1330] What it does: The server formats the information it receives and stores it in a database.

[1331] Output: Request information stored in the database

[1332] Step 5:

[1333] The server periodically retrieves participation information and request information from the database.

[1334] Input: Participation preferences and request information stored in the database

[1335] How it works: A scheduled task on the server periodically accesses the database to retrieve the necessary information.

[1336] Output: Acquired participation request information and request information

[1337] Step 6:

[1338] The information obtained by the server is used to input prompt sentences into the generative AI model.

[1339] Input: Acquired participation request information and request information

[1340] Example prompt sentence:

[1341] Information for potential volunteers:

[1342] Name: Yamada Taro, Contact: 090-xxxx-xxxx, Specialty: Rescue operations, Preferred date and time: Weekend

[1343] Volunteer Request Information:

[1344] Work: Disaster recovery activities, Number of people required: 5, Location: Osaka Prefecture, Date and time: Weekend

[1345] How it works: The server converts the information it obtains into a prompt sentence and inputs it into the generative AI model.

[1346] Output: The prompt passed to the generative AI model

[1347] Step 7:

[1348] The generative AI model analyzes the prompt and generates the best matching result.

[1349] Input: The prompt passed to the generative AI model

[1350] How it works: The generative AI model analyzes data based on the prompt text and matches the optimal combination of participants and requested information.

[1351] Output: The generated matching results

[1352] Step 8:

[1353] The server receives the matching results output from the generative AI model and notifies them.

[1354] Input: Generated matching results

[1355] How it works: Based on the matching results, the server notifies the participants and volunteer requesters of the tasks, including the location, date, time, and contact information.

[1356] Output: Notifications sent to applicants and requesters

[1357] Step 9:

[1358] Users (those wishing to participate and those making the request) will communicate based on the notification and work at the specified date, time and place.

[1359] Input: Notification sent (task, location, date, time, contact)

[1360] How it works: Users who receive the notification will contact each other and actually volunteer at the specified date, time and place.

[1361] Output: Volunteer activity performed

[1362] (Application example 1)

[1363] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1364] Conventional delivery systems have issues with inefficient matching of delivery personnel with delivery requests, leading to delays and errors in delivery operations. In particular, matching is performed without taking into account the delivery personnel's areas of expertise or desired work content, which often results in unnecessary travel and inappropriate delivery assignments. Therefore, there is a need for a system that can improve the efficiency of delivery operations and efficiently match delivery personnel with delivery requests.

[1365] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1366] In this invention, the server includes a means for acquiring participation desire information, a means for acquiring delivery request information, a means for analyzing the acquired participation desire information and delivery request information and using a generation model to generate an optimal matching result, and a means for notifying based on the generated matching result. This makes it possible to match the optimal delivery person with the delivery request, taking into account the delivery person's area of ​​expertise and the desired work content.

[1367] "Participation information" is information submitted by a delivery person when they wish to participate in a delivery, and includes their name, contact information, area of ​​expertise, desired work content, available dates and times, etc.

[1368] "Delivery request information" refers to information submitted by a restaurant or store when requesting delivery, and includes the required delivery details, number of people requested, location, date and time, etc.

[1369] A "generative model" is an artificial intelligence model that analyzes participation request information and delivery request information and generates optimal matching results based on that information.

[1370] "Notification" is a means of sending communication and instructions to delivery personnel and delivery requesters based on the matching results generated by the generative model.

[1371] "Specialty area" refers to an area in which a delivery person is good at making deliveries, and indicates an area in which deliveries can be made efficiently.

[1372] "Desired work content" refers to the specific work content that a delivery person desires when they apply to participate in a delivery, and what type of delivery work they would like to do.

[1373] "Matching" is the process of comparing participation request information with delivery request information and selecting the best combination.

[1374] The "database" is a system that organizes and stores data such as participation requests and delivery requests, and allows efficient search and retrieval of information as needed.

[1375] The present invention provides a system for efficiently matching delivery personnel with delivery requests in a delivery service, which is implemented by utilizing a server, a terminal of the delivery personnel, and a terminal of the delivery requester.

[1376] Overall system overview

[1377] The server acquires participation request information and delivery request information. To collect this information, data entered into a web form from the terminals of the delivery person and the delivery requester is used. The server stores this acquired information in a database and updates the information periodically.

[1378] Hardware and software used

[1379] 1. Server:

[1380] The server is implemented as a web application using Flask.

[1381] The database uses SQLite to store and manage information.

[1382] The generative AI model used is OpenAI's GPT-3.

[1383] 2. Delivery person and delivery requester's device:

[1384] Delivery personnel and delivery requesters access the system via a web browser on their smartphone or computer.

[1385] Use the web form to enter and submit your participation and delivery request information.

[1386] Program processing explanation

[1387] The server first collects participation information from delivery personnel and delivery request information from stores and restaurants, including name, contact information, area of ​​expertise, desired work, available date and time, required delivery content, number of people requested, location, date and time, etc.

[1388] The server stores this data in a database and periodically retrieves it to pass to the generative AI model, which matches delivery staff with delivery requests based on the following example prompt:

[1389] Example prompt sentence:

[1390] Volunteer Name: Taro Yamada

[1391] Skill: Delivery in Tokyo

[1392] Available Time: Saturdays and Sundays

[1393] ---

[1394] Request Task: Pizza Delivery

[1395] Required Volunteers: 5

[1396] Location: Shinjuku Ward

[1397] Date and Time: 2023-12-24 18:00

[1398] Is this a good match? True or False

[1399] The generative AI model analyzes the prompt and generates the optimal matching result by taking into consideration the delivery person's area of ​​expertise, the desired work content, and the request content. Based on the generated matching result, the server notifies both the delivery person and the requester.

[1400] The notification includes specific details of the job, location, date and time, contact information, etc., and is designed to enable quick and efficient communication between the delivery person and the delivery requester. This notification process utilizes SMS APIs and other services.

[1401] Specific examples

[1402] A delivery person (Yamada Taro) enters the information, "Yamada Taro, 090-1234-5678, specializes in deliveries within Tokyo, prefers weekends." The server saves this information in a database and manages it within the system.

[1403] The store enters "Pizza delivery, 5 pax needed, Shinjuku-ku, 2023-12-24 18:00." The server stores this information in the database.

[1404] The server periodically retrieves information about Yamada Taro from the database and passes it along with the delivery request information to the generative AI model. The generative AI model detects that Yamada Taro's area of ​​expertise and desired date and time match the delivery request, and outputs Yamada Taro as a matching result.

[1405] Based on this result, the server sends a notification to Yamada Taro saying, "Please participate in pizza delivery in Shinjuku Ward," and notifies the store that "Yamada Taro will be participating."

[1406] This will enable a fast and efficient delivery service between delivery personnel and delivery requesters, improving the efficiency of delivery operations.

[1407] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1408] Step 1:

[1409] The user (delivery person) accesses the web form using a smartphone or PC and enters the information they wish to participate in, such as their name, contact information, area of ​​expertise, desired work content, and available dates and times, and clicks the submit button.

[1410] Input: Delivery person registration information

[1411] Output: Save to database

[1412] Step 2:

[1413] The server receives the participation request information sent by the user (delivery person) and saves it in the database. At this time, it converts it into the required data format and stores it appropriately in the database.

[1414] Input: Delivery person registration information

[1415] Output: Participation requests stored in the database

[1416] Step 3:

[1417] Users (stores and restaurants) access a web form using their smartphones or computers and enter delivery request information, including the desired delivery details, number of people, location, date and time, and click the submit button.

[1418] Input: Delivery request information

[1419] Output: Save to database

[1420] Step 4:

[1421] The server receives delivery request information sent by the user (store, etc.) and stores it in a database. At this time, it converts the information into the required data format and stores it appropriately in the database.

[1422] Input: Delivery request information

[1423] Output: Delivery request information stored in the database

[1424] Step 5:

[1425] The server periodically retrieves participation and delivery request information from the database, and at this stage executes a query to obtain the latest information.

[1426] Input: All information in the database

[1427] Output: Latest participation request information and delivery request information

[1428] Step 6:

[1429] The server passes the acquired participation request information and delivery request information to the generative AI model, which analyzes this information and creates a prompt.

[1430] Input: Participation request information and delivery request information

[1431] Output: Prompt sentence to the generative AI model

[1432] Step 7:

[1433] The generative AI model performs optimal matching based on the prompt text and generates matching results, taking into account conditions such as area of ​​expertise, desired work content, date and time, etc.

[1434] Input: prompt statement

[1435] Output: Matching results

[1436] Step 8:

[1437] The server receives the matching results output from the generative AI model and sends a notification based on the results. Specifically, it sends a notification to the delivery person and the store that a match has been made.

[1438] Input: Matching results

[1439] Output: Notification to delivery person and store

[1440] Step 9:

[1441] The user (delivery person and store) receives the notification and confirms the specific work content, location, date and time, etc. The delivery person begins the actual delivery work based on the notification.

[1442] Input: Notification content

[1443] Output: Start of delivery work

[1444] The above processing steps enable efficient matching of delivery personnel with delivery requesters, enabling the provision of fast and accurate delivery services.

[1445] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1446] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Below, we will explain the program processing of this system in natural language.

[1447] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, skills, desired work content, and available dates and times, and clicks the submit button. The server receives the submitted information, stores it in a database, and simultaneously recognizes the user's emotions using an emotion engine.

[1448] The emotion engine analyzes the points that users place particular importance on among the information they enter, and analyzes their emotions and psychological state. For example, it determines their motivation and priorities for volunteer activities. This makes it possible to perform optimal matching while also taking into account the psychological state of those wishing to participate.

[1449] Next, the user (volunteer requester) accesses another website or a different form on the same website and opens the volunteer request registration form. The user enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[1450] In this system, the server periodically retrieves information on volunteer applicants and volunteer requests from the database, and passes this information to the generative AI model.

[1451] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, and available dates and times, as well as the work content, number of people requested, location, and date and time in the volunteer request information. The model also analyzes the applicant's psychological state and priorities, as analyzed by the emotion engine, to generate the optimal matching results. The matching results are calculated taking into account the work content, the applicant's areas of expertise and desires, as well as emotional factors.

[1452] The server then sends notifications to both the potential participants and the volunteer requesters based on the matching results output by the generative AI model. These notifications include the specific task, location, date and time, contact information, and importantly, sentiment analysis results. Upon receiving the notifications, the potential participants and the requesters can communicate with each other and meet at the appropriate time and place to complete the task.

[1453] Specific examples

[1454] A user (Suzuki Ichiro) enters "Suzuki Ichiro, mobile phone number, good at rescue work, preferring weekends" into a web form. The server saves this information in a database and simultaneously starts an emotion engine to analyze the emotional information from Suzuki Ichiro's input, determining his "strong desire to participate in rescue work" and "high priority."

[1455] A user (volunteer requester) enters the following information into a web form: "Disaster recovery activities, 10 volunteers needed, Tokyo, weekends." The server stores this information in a database.

[1456] The server periodically retrieves information about Suzuki Ichiro from the database, emotional information, and volunteer request information, and passes it to the generative AI model. The generative AI model detects that Suzuki Ichiro's specialty rescue activities, desired date and time, and emotional information of "high motivation" match the volunteer request information, and outputs Suzuki Ichiro as a matching result.

[1457] Based on this result, the server sends a notification to Suzuki Ichiro saying, "Please participate in disaster recovery activities in Tokyo," and notifies the requester that "Suzuki Ichiro is highly motivated to participate in rescue activities and plans to participate."

[1458] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[1459] The processing flow will be explained below.

[1460] Step 1:

[1461] A user (a person wishing to volunteer) accesses a website and opens a volunteer registration form. The user enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[1462] Step 2:

[1463] The server receives the volunteer participation request information entered by the user and stores it in a database. At this time, it activates an emotion engine to collect emotional data from the user's input and their emotions and reactions at the time of sending.

[1464] Step 3:

[1465] The emotion engine analyzes the collected emotion data and extracts information such as the user's current psychological state, motivation for volunteer activities, and priorities. The extracted emotion information is also stored in a database.

[1466] Step 4:

[1467] The user (volunteer requester) accesses the volunteer request registration form, either on the same website or a different form, enters information such as the type of volunteer work required, the number of volunteers required, the location, the date and time, and clicks the submit button.

[1468] Step 5:

[1469] The server receives the volunteer request information entered by the user and stores it in a database.

[1470] Step 6:

[1471] The server periodically retrieves information on volunteer applicants, emotion information, and volunteer request information from the database. The frequency of retrieval can be adjusted by system settings.

[1472] Step 7:

[1473] The server passes the acquired information to the generative AI model for processing. The generative AI model analyzes the participation request information and volunteer request information to derive the optimal matching results, taking into account the emotional information analyzed by the emotion engine.

[1474] Step 8:

[1475] The generative AI model analyzes the volunteer applicant's areas of expertise, desired work content, available dates and times, volunteer request information, and emotional information to generate the optimal matching results, which are then returned to the server.

[1476] Step 9:

[1477] The server generates a notification message based on the matching results output by the generative AI model, which includes the specific task, location, date and time, contact information, and important points based on emotional information.

[1478] Step 10:

[1479] The server sends a notification to the volunteer applicant containing details of the matched volunteer work, location, date and time, and the requester's contact information, and also sends a notification to the volunteer requester containing details of the matched volunteer applicant, contact information, and commentary based on the emotion information.

[1480] Step 11:

[1481] Users (those who wish to volunteer and those who request volunteers) communicate with each other based on notifications received from the server, and carry out volunteer activities efficiently at the specified date, time, and location. Notifications based on emotion information build a smoother cooperative system.

[1482] Example 2

[1483] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1484] Conventional volunteer matching systems match participants simply based on their skills and schedules without considering their emotional or psychological state, which can lead to a decline in motivation and satisfaction with volunteer activities.Furthermore, not taking into account emotions and psychological states makes it difficult to optimally allocate personnel, which can reduce the efficiency of volunteer activities.

[1485] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring participation information, means for acquiring volunteer request information, means for analyzing the acquired participation information and volunteer request information and using a generative model to generate optimal matching results, means for notifying based on the generated matching results, means for analyzing the participation information and recognizing the user's emotions, and means for reflecting the emotion recognition results in matching. This enables optimal volunteer matching that takes into account the emotions and psychological state of participants.

[1486] "Participation information" is information provided by individuals who wish to participate in volunteer activities, such as their name, contact information, tasks they are good at, desired work content, and available dates and times.

[1487] "Volunteer request information" is information provided by the party requesting volunteer activities, such as the type of work required of volunteers, the number of people required, the location, and the date and time.

[1488] A "generative model" is a machine learning model or AI model that has the ability to analyze acquired participation request information and volunteer request information and generate optimal matching results.

[1489] "Notification" refers to information sent to prospective participants and volunteer requesters based on the generated matching results, and includes specific work content, location, date and time, contact information, and sentiment analysis results.

[1490] An "emotion engine" is a program or system that has the function of analyzing participation request information and recognizing the emotions and psychological state of the provider.

[1491] "Database" means a digital data storage system for storing participation request information and volunteer request information, and for retrieving and using information as needed.

[1492] The "matching result" is information that indicates the optimal combination of participants and volunteer requesters, generated by analyzing the generative model.

[1493] "Emotion recognition" is the process of analyzing and recognizing the provider's emotions and psychological state based on the participant's participation information.

[1494] This invention is a system that combines a generative AI model and an emotion engine to recognize user emotions while analyzing and matching volunteer applicants with volunteer-requested tasks, thereby achieving optimal volunteer allocation. An embodiment of this system is described in detail below.

[1495] First, a user (a person wishing to volunteer) accesses the website and opens the volunteer registration form. The user enters information such as their name, contact details, their specialties, desired work content, and available dates and times, and clicks the submit button. The server receives this information and stores it in a database. The server then activates an emotion engine, analyzes the entered information, and recognizes the user's emotions.

[1496] For example, if a user enters "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends," the server will store this information in a database and at the same time use an emotion engine to analyze "strong desire to carry out rescue work" and "high priority."

[1497] Next, the user (volunteer requester) accesses the volunteer request registration form and enters information about the required volunteer work. Specifically, the user enters the work content, number of people required, location, date and time, etc., and clicks the submit button. The server also receives this information and stores it in the database.

[1498] For example, if a user enters "disaster recovery activities, 10 people needed, Tokyo, weekends," the server stores this information in a database.

[1499] The server periodically retrieves information on volunteer applicants and volunteer requests from the database. This information is passed to the generative AI model, which then analyzes it. During this process, the model also analyzes the psychological state and priorities of the applicants, as analyzed by the emotion engine, to generate optimal matching results.

[1500] For example, the generative AI model detects that "Ichiro Suzuki's specialty rescue activities, desired date and time, and emotional information" match the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs Ichiro Suzuki as the matching result.

[1501] Finally, the server notifies both the prospective participant and the volunteer requester based on the matching results output by the generative AI model, including the specific task, location, date and time, contact information, and importantly, sentiment analysis results.

[1502] For example, a notification saying "Ichiro Suzuki will participate in disaster recovery activities in Tokyo" is sent to those who wish to participate, and a notification saying "Ichiro Suzuki is highly motivated to participate in rescue activities" is sent to the requester.

[1503] This will allow for optimal placement and efficient volunteer activities, taking into consideration the feelings of those wishing to volunteer.

[1504] Examples of prompt statements

[1505] Emotion analysis result for "Suzuki Ichiro, mobile number 123-4567, good at rescue work, preferring weekends": "High motivation for rescue work"

[1506] Volunteer request information for "Disaster recovery activities, 10 people needed, Tokyo, Saturdays and Sundays" is entered as: "10 people needed for disaster recovery activities in Tokyo, Saturdays and Sundays"

[1507] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1508] The flow of this system's program processing

[1509] Subject: Server, Terminal, User

[1510] (Step 1: User enters information and submits)

[1511] A user (a person wishing to participate as a volunteer) accesses the volunteer registration form on the website, enters information such as name, contact details, skills, desired work content, available dates and times, and submits it.

[1512] Specific operation: The user enters "Name: Yamada Taro, Contact: 090-1234-5678, Specialty: Rescue work, Desired work: Rescue work, Available dates and times: Saturdays and Sundays" and clicks the send button.

[1513] Input: User-entered participation information

[1514] Output: The participation request received by the server

[1515] (Step 2: Information storage and analysis request by the server)

[1516] The server stores the received participation request information in a database and simultaneously requests the emotion engine to analyze it.

[1517] Specific operation: The server requests the emotion engine to analyze "strong desire to carry out rescue operations" and "high priority."

[1518] Input: Participation request information received by the server

[1519] Output: Participation preference information stored in the database and analysis request to the emotion engine

[1520] (Step 3: Emotion analysis using the emotion engine)

[1521] The emotion engine analyzes the user's emotions and psychological state from the provided information and returns the results to the server.

[1522] Specific operation: The emotion engine analyzes that "Yamada Taro has a strong desire to participate in rescue activities" and sends the result to the server.

[1523] Input: Participation request information sent from the server

[1524] Output: Emotion analysis results

[1525] (Step 4: User enters volunteer request information and submits)

[1526] The user (volunteer requester) accesses the volunteer request registration form on the website, enters information about the required volunteer work, and submits it.

[1527] Specific operation: The user enters "Work content: disaster recovery activities, required number of people: 10, location: Tokyo, date and time: weekend" and clicks the send button.

[1528] Input: User-entered volunteer request information

[1529] Output: Volunteer request information received by the server

[1530] (Step 5: The server saves the request information)

[1531] The server stores the received volunteer request information in a database.

[1532] Specific operation: The server stores the received volunteer request information in a database.

[1533] Input: Volunteer request information received by the server

[1534] Output: Volunteer request information stored in a database

[1535] (Step 6: The server obtains the information and passes it to the generative AI model)

[1536] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[1537] Specific operation: The server retrieves information from the database and passes it to the generative AI model.

[1538] Input: Participation request information and volunteer request information stored in the database

[1539] Output: Information passed to the generative AI model

[1540] (Step 7: Matching analysis using generative AI model)

[1541] The generative AI model analyzes the information provided and generates optimal matching results, taking into account the results of sentiment analysis.

[1542] Specific operation: The generative AI model compares and analyzes "Yamada Taro's specialty rescue activities, desired date and time, and emotional information" with the request information of "disaster recovery activities, required number of people: 10, Tokyo, weekends," and outputs the matching result with Yamada Taro as a suitable candidate.

[1543] Input: Participation request information, volunteer request information, and emotion analysis results passed to the generative AI model

[1544] Output: Best matching result

[1545] (Step 8: Server creates and sends notification)

[1546] The server notifies both the person wishing to participate and the person requesting the volunteer based on the matching results output by the generative AI model.

[1547] Specific operation: The server sends a notification to those who wish to participate that "Yamada Taro will participate in disaster recovery efforts in Tokyo," and notifies the requester that "Yamada Taro is highly motivated to participate in rescue efforts."

[1548] Input: Matching results output from the generative AI model

[1549] Output: Notifications sent

[1550] The above are the specific processing steps of the program of this system.

[1551] (Application example 2)

[1552] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1553] Current systems make it difficult to carry out fast and efficient volunteer activities during emergencies and disasters. In particular, simply matching volunteers based on the work content and schedule without considering the emotions and motivation of those who wish to volunteer makes it difficult to optimally allocate volunteers, and does not ensure that they arrive at the scene quickly. Therefore, a system is needed that combines efficient transportation of volunteers with optimal matching based on emotions and motivation.

[1554] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring participation desire information, means for acquiring volunteer request information, means for analyzing the acquired participation desire information and volunteer request information and using a generative model to generate optimal matching results, means for issuing notifications based on the generated matching results, and means for issuing pickup and transportation instructions to an autonomously driven vehicle based on the generated matching results and transporting volunteers to their destination via an optimal route. This makes it possible to match optimal volunteers while taking into account the emotions and motivation of those wishing to volunteer, and to transport volunteers to needed locations quickly and efficiently.

[1555] "Participation information" refers to information provided by individuals who wish to participate as volunteers, such as their name, contact information, areas of expertise, desired work content, and available dates and times.

[1556] "Volunteer request information" means information provided by a requester regarding an activity requiring volunteers, such as the type of work required, the number of people required, the location, and the date and time.

[1557] A "generative model" is an artificial intelligence model that uses machine learning algorithms to analyze volunteer applicants and volunteer request information, and generate optimal matching results.

[1558] An "emotion engine" is a software component that analyzes a user's emotional state and motivation based on information provided by the user.

[1559] An "autonomous vehicle" is a vehicle that uses artificial intelligence and sensor technology to operate without a driver.

[1560] "Notification" is an action that conveys information to volunteer applicants, volunteer requesters, and autonomous vehicles based on the generated matching results.

[1561] The "database" is a system that stores information on volunteer applicants and volunteer requests, and quickly retrieves this information when necessary.

[1562] "Pickup" is the process by which an autonomous vehicle picks up a volunteer from a designated location.

[1563] "Transportation" is the process by which an autonomous vehicle transports volunteers to their designated destinations.

[1564] A "route" is the route chosen by an autonomous vehicle to pick up and transport volunteers to their destination.

[1565] This invention is a system that combines a generative AI model and an emotion engine to analyze and match volunteer applicants with volunteer request tasks while recognizing user emotions, thereby optimally allocating volunteers. Furthermore, it also enables efficient transportation of volunteers using autonomous vehicles. A specific embodiment of this system is described below.

[1566] First, a user (a person wishing to volunteer) accesses the volunteer registration form through a smartphone app, enters information such as their name, contact details, tasks they are good at, desired work content, and available dates and times, and clicks the submit button. The submitted information is sent to the server and stored in a database, and at the same time, an emotion engine is activated to analyze the user's emotional state and motivation. The results of this analysis are stored in the database as the user's emotional information.

[1567] Next, those requesting volunteers access the volunteer request registration form via a smartphone app and enter information such as the type of work required, the number of volunteers required, the location, date and time, etc. This information is also sent to the server and stored in the database.

[1568] The server periodically retrieves information on volunteer applicants and volunteer request information from the database and passes it to the generative AI model. The generative AI model analyzes the volunteer applicants' areas of expertise, desired work, available dates and times, and emotional information, and compares them with the volunteer request information to generate the optimal matching results.

[1569] Based on the matching results, the server notifies the volunteers and those requesting volunteers. The notification includes the specific task, location, date, and time, as well as important sentiment analysis results. Based on the matching results, the server also issues pickup and transportation instructions to autonomous vehicles, transporting the volunteers to their destinations via the optimal route.

[1570] For example, a user (a person wishing to participate) enters "I'm good at rescue work, preferring to work on weekends" and submits the request. The server saves this information in a database and uses an emotion engine to analyze "high motivation." Next, the requester enters "disaster recovery work, 10 people needed, Tokyo, weekends" and submits the request, and the server saves this information in its database. The generative AI model performs matching, and if the volunteers wishing to participate match the volunteer request information, a notification is sent. Furthermore, instructions are sent to the autonomous vehicle to "pick up the volunteers and transport them to the specified location."

[1571] (Example of a prompt)

[1572] Please analyze the emotional state of volunteer Suzuki Ichiro based on the following information:

[1573] Name: Suzuki Ichiro

[1574] Contact: 090-1234-5678

[1575] Specialty: Rescue operations

[1576] Desired work: Disaster recovery

[1577] Available dates: Saturdays and Sundays

[1578] Example result:

[1579] (Emotional analysis results)

[1580] Motivation: High

[1581] Priority: High

[1582] This system will enable optimal matching taking into account the emotions and motivation of volunteers, and will enable fast and efficient transportation using self-driving vehicles.

[1583] The hardware used includes smartphones, servers, and autonomous vehicles, and the software uses a smartphone app (Swift / Java), a database (MySQL), a generative AI model (TensorFlow), and an emotion engine (OpenAI GPT-4). This combination enables efficient volunteer activities and rapid response.

[1584] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1585] Step 1:

[1586] A user (a prospective volunteer) opens the volunteer registration form using a smartphone app, enters information such as their name, contact details, skills, desired work, and available dates and times, and clicks the submit button.

[1587] Input: Volunteer participation request information entered by the user

[1588] Output: Volunteer participation request information sent to the server

[1589] Specific operation: When a user enters the required information into a form on a smartphone app and submits it, the data is sent to a server via the Internet.

[1590] Step 2:

[1591] The server stores the submitted volunteer participation request information in a database, activates the emotion engine, analyzes the user's emotional state and motivation, and stores the analysis results in the database.

[1592] Input: Volunteer participation information

[1593] Output: Emotion analysis results

[1594] Specific operation: The server stores the received data in a database and passes it to the emotion engine, which analyzes it, returns the results to the server, and stores them in the database again.

[1595] Step 3:

[1596] The requester opens the volunteer request registration form using a smartphone app, enters information such as the type of volunteer work required, the number of volunteers required, the location, and the date and time, and clicks the submit button.

[1597] Input: Volunteer request information entered by the requester

[1598] Output: Volunteer request information sent to the server

[1599] Specific operation: When the requester enters the necessary information into the form on the smartphone app and submits it, the data is sent to the server via the Internet.

[1600] Step 4:

[1601] The server stores the submitted volunteer request information in a database.

[1602] Input: Volunteer request information

[1603] Output: Volunteer request information stored in a database

[1604] Specific operation: The server stores the received data in a database.

[1605] Step 5:

[1606] The server periodically retrieves volunteer participation request information and volunteer participation request information from the database and passes it to the generative AI model.

[1607] Input: Information retrieved from the database (volunteer participation request information, volunteer request information)

[1608] Output: Data passed to the generative AI model

[1609] Specific operation: The server periodically retrieves the necessary information from the database using SQL queries and passes it to the generative AI model.

[1610] Step 6:

[1611] The generative AI model analyzes the areas of expertise, desired work, available dates and times, and emotional information of volunteer applicants, and compares this with volunteer request information to generate the optimal matching results.

[1612] Input: Volunteer participation request information, volunteer request information, emotional information

[1613] Output: Matching results

[1614] Specific operation: The generative AI model runs a machine learning algorithm based on the received data and outputs the optimal matching result.

[1615] Step 7:

[1616] Based on the generated matching results, the server notifies prospective participants and volunteer requesters.

[1617] Input: Matching results

[1618] Output: Notification message

[1619] Specific operation: The server generates a notification message based on the matching results and sends emails and in-app notifications to those who wish to participate and those who request volunteers.

[1620] Step 8:

[1621] Based on the generated matching results, the server instructs the autonomous vehicle to pick up and transport the goods.

[1622] Input: Matching results

[1623] Output: Instruction data for the autonomous vehicle

[1624] Specific operation: The server sends instructions to the autonomous vehicle's control system on which volunteers to pick up, where to pick them up, and where to transport them.

[1625] Step 9:

[1626] The self-driving vehicle will then follow instructions to pick up volunteers and transport them to a designated location.

[1627] Input: Instruction data for the autonomous vehicle

[1628] Output: Transport volunteer to designated location

[1629] Specific operation: The autonomous vehicle calculates the route based on the instruction data, drives to the designated pickup location, picks up the volunteer, and then heads off to the destination.

[1630] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1631] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1632] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1633] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1634] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1635] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1636] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1637] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1638] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1639] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1640] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1641] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1642] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1643] 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.

[1644] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1645] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1646] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1647] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1648] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1649] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1650] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1651] The following is further disclosed regarding the above embodiment.

[1652] (Claim 1)

[1653] A means for obtaining participation preference information;

[1654] a means for obtaining volunteer request information;

[1655] A means for analyzing the acquired participation request information and volunteer request information and using a generative model to generate optimal matching results;

[1656] means for providing a notification based on the generated matching result;

[1657] A system including:

[1658] (Claim 2)

[1659] A means of obtaining information on the areas of expertise and desired work of participants;

[1660] A means for acquiring the content of the volunteer request work and the number of people required;

[1661] A means for analyzing the acquired participation request information and volunteer request information and using a generative model to perform matching based on areas of expertise and desired work content;

[1662] A means for notifying prospective participants and volunteer requesters based on the generated matching results;

[1663] 10. The system of claim 1, comprising:

[1664] (Claim 3)

[1665] a means for storing information about prospective volunteers in a database;

[1666] a means for storing volunteer request information in a database;

[1667] A means to periodically retrieve information from the database and pass it to the generative model;

[1668] 10. The system of claim 1, comprising:

[1669] "Example 1"

[1670] (Claim 1)

[1671] A means for obtaining participation preference information;

[1672] a means for obtaining volunteer request information;

[1673] A means for using a generative AI model to analyze the acquired participation request information and volunteer request information and generate optimal matching results;

[1674] means for providing a notification based on the generated matching result;

[1675] A system including:

[1676] (Claim 2)

[1677] A means of obtaining information on the areas of expertise and desired work of participants;

[1678] A means for acquiring the content of the volunteer request work and the number of people required;

[1679] A means for using a generative AI model to analyze the acquired participation request information and volunteer request information and perform matching based on areas of expertise and desired work content;

[1680] A means for notifying prospective participants and volunteer requesters based on the generated matching results;

[1681] 10. The system of claim 1, comprising:

[1682] (Claim 3)

[1683] a means for storing information about prospective volunteers in a database;

[1684] a means for storing volunteer request information in a database;

[1685] A means to periodically retrieve information from the database and pass it to the generative AI model;

[1686] a means for processing input to the generative AI model as a prompt sentence;

[1687] 10. The system of claim 1, comprising:

[1688] "Application Example 1"

[1689] (Claim 1)

[1690] A means for obtaining participation preference information;

[1691] A means for obtaining delivery request information;

[1692] A means for analyzing the acquired participation request information and delivery request information and using a generative model to generate optimal matching results;

[1693] means for providing a notification based on the generated matching result;

[1694] A system including:

[1695] (Claim 2)

[1696] A means for acquiring the specialty areas and desired work contents of the participants;

[1697] A means for acquiring the content of the delivery request and the number of people requested;

[1698] A means for analyzing the acquired participation request information and delivery request information and using a generative model to perform matching based on the area of ​​expertise and the desired work content;

[1699] A means for notifying the participant and the delivery requester based on the generated matching result;

[1700] 10. The system of claim 1, comprising:

[1701] (Claim 3)

[1702] a means for storing information of prospective participants in a database;

[1703] means for storing delivery request information in a database;

[1704] A means to periodically retrieve information from the database and pass it to the generative model;

[1705] 10. The system of claim 1, comprising:

[1706] "Example 2: Combining Emotion Engines"

[1707] (Claim 1)

[1708] A means for obtaining participation preference information;

[1709] a means for obtaining volunteer request information;

[1710] A means for analyzing the acquired participation request information and volunteer request information and using a generative model to generate optimal matching results;

[1711] means for providing a notification based on the generated matching result;

[1712] A means for analyzing participation preference information and recognizing user emotions;

[1713] A means for reflecting emotion recognition results in matching;

[1714] A system including:

[1715] (Claim 2)

[1716] A means of obtaining information on the areas of expertise and desired work of participants;

[1717] A means for acquiring the content of the volunteer request work and the number of people required;

[1718] A means for analyzing the acquired participation request information and volunteer request information and using a generative model to perform matching based on areas of expertise and desired work content;

[1719] A means for notifying prospective participants and volunteer requesters based on the generated matching results;

[1720] means for analyzing emotional components based on participation preference information;

[1721] 10. The system of claim 1, comprising:

[1722] (Claim 3)

[1723] a means for storing information about prospective volunteers in a database;

[1724] a means for storing volunteer request information in a database;

[1725] A means to periodically retrieve information from the database and pass it to the generative model;

[1726] means for performing emotion recognition analysis based on information obtained from the database;

[1727] 10. The system of claim 1, comprising:

[1728] "Application example 2 when combining emotion engines"

[1729] (Claim 1)

[1730] A means for obtaining participation preference information;

[1731] a means for obtaining volunteer request information;

[1732] A means for analyzing the acquired participation request information and volunteer request information and using a generative model to generate optimal matching results;

[1733] means for providing a notification based on the generated matching result;

[1734] Based on the generated matching results, a method is provided to instruct an autonomous vehicle to pick up and transport the volunteers to their destination via the optimal route.

[1735] A system including:

[1736] (Claim 2)

[1737] A means of obtaining information on the areas of expertise and desired work of participants;

[1738] A means for acquiring the content of the volunteer request work and the number of people required;

[1739] A means for analyzing the acquired participation request information and volunteer request information and using a generative model to perform matching based on areas of expertise and desired work content;

[1740] A means for notifying prospective participants and volunteer requesters based on the generated matching results, and for issuing instructions to the autonomous vehicle;

[1741] 10. The system of claim 1, comprising:

[1742] (Claim 3)

[1743] a means for storing information about prospective volunteers in a database;

[1744] a means for storing volunteer request information in a database;

[1745] A means to periodically retrieve information from the database and pass it to the generative model;

[1746] A means for instructing an autonomous vehicle based on the generated matching results to efficiently pick up and transport volunteers; and

[1747] 10. The system of claim 1, comprising: [Explanation of symbols]

[1748] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for obtaining participation preference information; a means for obtaining volunteer request information; A means for analyzing the acquired participation request information and volunteer request information and using a generative model to generate optimal matching results; means for providing a notification based on the generated matching result; A system including:

2. A means of obtaining information on the areas of expertise and desired work of participants; A means for acquiring the content of the volunteer request work and the number of people required; A means for analyzing the acquired participation request information and volunteer request information and using a generative model to perform matching based on areas of expertise and desired work content; A means for notifying prospective participants and volunteer requesters based on the generated matching results; The system of claim 1 , comprising:

3. a means for storing information about prospective volunteers in a database; a means for storing volunteer request information in a database; A means to periodically retrieve information from the database and pass it to the generative model; The system of claim 1 , comprising:

Images