system

Abstract

We provide the system. [Solution] A means of obtaining participant information and storing that information in a database, A means of acquiring disaster relief request information and storing that information in a database, A means of using an artificial intelligence model to analyze participant information and request information and generate the optimal match, A means of sending notifications to matched participants, A means of providing participants and disaster managers with the final schedule and activity details, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a disaster occurs, due to the inappropriate matching of the demand and supply of volunteer activities, the skills of participants are not fully utilized, and appropriate personnel are often not deployed to the required locations. As a result, there arises a problem that the work efficiency decreases and the promptness and effectiveness of support activities are impaired. The purpose of this invention is to solve various problems caused by such inappropriate matching.

Means for Solving the Problems

[0005] This invention provides means for collecting information on volunteer participants and storing that information in a database, and means for collecting disaster relief request information and similarly storing that information in a database. Furthermore, it includes means for analyzing this information and using an artificial intelligence model to generate optimal matching. The matching results are notified to participants, and confirmation of their willingness to participate is accepted, thereby achieving flexible and efficient personnel allocation. Ultimately, the invention constructs a system that promotes effective volunteer activities by providing participants and disaster managers with a finalized schedule and activity details.

[0006] "Participant information" refers to information provided by individuals who wish to volunteer, such as their name, contact information, skills, desired tasks, and available dates and times.

[0007] "Disaster relief request information" refers to data provided by the field in need of assistance during a disaster, including the required skills and number of volunteers, work locations, and activity dates and times.

[0008] "Matching" is the process of comparing the skills and preferences of volunteer participants with the requirements of the disaster relief site to select the most suitable participants.

[0009] An "artificial intelligence model" is a general term for algorithms and data analysis techniques used to find the optimal match between participant information and requested information.

[0010] "Notification" refers to the means by which the system electronically sends participants matching results and future schedules.

[0011] A "database" is an information management system that stores and manages participant information and disaster relief request information, and allows for quick searching and utilization as needed.

[0012] A "schedule" refers to a plan or timetable that includes the date, time, location, and specific tasks of volunteer activities, and is shared with both participants and disaster management personnel. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The present invention provides a series of processes for efficiently matching volunteer participants with disaster relief request information. This system consists of a server, terminals, and users. Specific embodiments of each step are described below.

[0035] First, the user enters their information via their device and sends it to the server. This includes their name, contact information, skills, desired work content, and available dates and times. The server stores the received information in a database and performs data integrity checks as needed.

[0036] Next, disaster relief request information is sent to a server by the administrator of the disaster area using a dedicated terminal. This information includes the required skills, the number of volunteers, the work location, and the date and time of the activity. The server also stores this information in a database and makes it available for real-time updates.

[0037] The server uses an artificial intelligence model to analyze accumulated participant and support information. This model primarily considers participants' skills, available dates and times, and distance constraints to perform optimal matching. For example, if a participant with a certain medical skill is available on weekends and that skill is suitable for the support request, that participant will be selected preferentially.

[0038] Based on this matching result, the server sends a matching notification to the user via the device. The notification includes detailed information about the available activities, which the user can review and choose to "participate" or "not participate." The user's response is sent back to the server, and if confirmed as a participant, a detailed activity schedule is notified to the device.

[0039] Furthermore, the server organizes confirmed volunteer information and provides disaster area managers with a final list and schedule. This allows managers to prepare an appropriate receiving system. This system simplifies pre-activity coordination and enables the rapid and efficient deployment of relief efforts.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user opens the volunteer registration form on their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user enters this information and registers.

[0043] Step 2:

[0044] The terminal sends user input data to the server. The server stores the received data in a database. At the same time, it also checks whether the input content is duplicated and whether the format is correct.

[0045] Step 3:

[0046] The administrator of the disaster area uses a dedicated terminal to input volunteer request information into the server. At this time, they specify details such as the required skills, the number of volunteers, the work location, and the date and time.

[0047] Step 4:

[0048] The server saves the entered request information to a database and updates it by comparing it with existing data. This ensures that the information is kept up-to-date in real time.

[0049] Step 5:

[0050] The server collects participant and request information from the database and begins analysis using an artificial intelligence model. The AI ​​model calculates the best match based on participants' skills, preferred dates and times, and distance constraints.

[0051] Step 6:

[0052] The server sends the matching results obtained through analysis to the terminal. The terminal displays a notification to the user and provides an option to choose whether or not to participate in the activity.

[0053] Step 7:

[0054] The user reviews the notification and chooses either "Participate" or "Do not participate" from the provided options. The user's selection is sent from the device to the server.

[0055] Step 8:

[0056] The server creates a list of users who have responded with "I will participate" and notifies them of the final schedule and details on their devices. Users can then use this information to prepare.

[0057] Step 9:

[0058] The server sends information about confirmed volunteer participants to the disaster area administrator. The administrator uses this information to prepare the necessary receiving arrangements. This supports the smooth start of activities.

[0059] (Example 1)

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

[0061] In disaster relief activities, it is essential to quickly and efficiently match appropriate personnel from a diverse pool of participants to ensure smooth relief operations. However, conventional systems have faced challenges in improving matching accuracy due to the complexity of participant and support request information. Furthermore, the lack of means to verify the consistency of participant information and to flexibly match them with corresponding support requests prevented the maximum effectiveness of relief activities from being realized.

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

[0063] In this invention, the server includes a device for acquiring participant information and storing that information in a database, a device for acquiring disaster relief request information and storing that information in a database, and a device that uses a data processing model to analyze participant information and request information and generate the optimal match. This enables highly accurate matching that takes into account participants' skills, preferences, and geographical factors. Furthermore, by including a device to receive confirmation of participation intentions from participants, the final schedule and activity details can be provided, and the consistency of each participant's information can be verified, enabling the efficient and reliable implementation of support activities.

[0064] A "device for acquiring participant information" refers to a system configuration equipped with functions for collecting necessary data from individuals participating as volunteers.

[0065] A "database storage device" is a system configuration that continuously stores collected information in a structured format, making it available for later processing and retrieval.

[0066] A "device for acquiring disaster relief request information" is a system configuration equipped with functions to specifically gather information on the need for support from disaster-stricken areas and related parties.

[0067] A "device that uses a data processing model" is a system configuration that has algorithms and arithmetic methods for analyzing collected participant information and support request information and automatically generating the optimal match.

[0068] A "device for transmitting information to matched participants" refers to a system configuration equipped with communication means for notifying selected volunteers of the details of the activity and whether or not they can participate.

[0069] A "device that provides the final timetable and activity details" refers to a system configuration that has the function of sharing the decided support activity schedule and implementation details with participants and stakeholders.

[0070] The system for implementing the present invention provides a process for effectively matching participants with disaster relief requests. This system mainly consists of three components: users, terminals, and servers, and is responsible for information collection, storage, analysis, and communication.

[0071] Users enter their information into the terminal using a dedicated application. This information includes their name, contact information, skills, desired work, and available dates and times. The terminal securely collects user information by utilizing a function to send this entered information to a server.

[0072] The server stores the received participant information in a database. During storage, checks are performed to ensure data integrity. Furthermore, disaster relief request information is sent to the server using a similar procedure and stored in the database. This ensures that the necessary skills, activity details, and dates are always up-to-date.

[0073] The server uses a generative AI model to analyze participant information and support request information. This model considers participants' skills, preferences, and geographical conditions to perform optimal matching. For example, if a participant with medical skills has time on weekends, they will be prioritized for disaster requests requiring medical assistance on weekends.

[0074] The matching results are notified to the user via the terminal from the server. The user reviews the notification and chooses whether or not to participate. This response is sent back to the server, and the final schedule and activity details are sent to the user and the disaster manager.

[0075] This system aims to enable support activities to be carried out more quickly and efficiently through an effective matching process using generative AI models.

[0076] An example of a prompt is, "To match disaster relief volunteers, please suggest the best pairings based on the following participant and support request information." This prompt allows the generating AI model to perform the necessary processing and provide highly accurate matching results.

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

[0078] Step 1:

[0079] Users enter their information on a dedicated application. This information includes their name, contact details, skills, desired work, and available dates and times. The terminal prepares this information for transmission to a database and sends the data to the server. The output is transferred to the server as structured user information.

[0080] Step 2:

[0081] The server stores the received user information in the database. The received data undergoes integrity checks to ensure there are no missing entries or formatting errors. For example, it verifies that contact information is in the correct numerical format. The output of this step is that the user information, with its integrity ensured, is securely stored in the database.

[0082] Step 3:

[0083] Managers in disaster areas input disaster relief request information via dedicated terminals. This includes details such as required skills, activity locations, number of volunteers, and activity dates and times, which are then transmitted to the server in real time. The output is the specific relief request data received by the server.

[0084] Step 4:

[0085] The server stores the assistance request information received from the administrator in a database, ensuring that the information is up-to-date. Real-time updates prevent the data from becoming outdated or inconsistent. The output of this step is that the latest disaster assistance request information is stored in the database.

[0086] Step 5:

[0087] The server uses a generative AI model to analyze participant and support information. Based on the input information, the generative AI model performs optimal matching. For example, it determines whether a participant with a certain skill has a matching schedule and support request. The output of this step is a pair of matched participants and support requests.

[0088] Step 6:

[0089] The server sends a notification to the relevant user based on the generated matching results. Through their device, the user receives details of the available activities and chooses whether or not to participate. This choice is then sent back to the server. The output is participation confirmation data based on the user's choice.

[0090] Step 7:

[0091] The server finalizes the detailed schedule of the activities based on confirmed participation. This schedule is notified to users and disaster managers via terminals, enabling efficient execution of the activities. The output is the finalized schedule and implementation plan.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] To implement rapid and efficient relief activities during disasters, it is essential to immediately assign the right personnel from a large pool of volunteers. However, conventional manual matching is time-consuming, and delays in support become a problem in urgent situations. Furthermore, traditional systems have difficulty making optimal assignments based on participants' location information and individual circumstances.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for acquiring participant information and location information and storing that information in a database, means for acquiring disaster relief request information and storing that information in a database, and means for using an artificial intelligence model to analyze participant information and request information and generate optimal assignments. This enables rapid and efficient matching that takes into account participants' skills and geographical conditions.

[0097] "Participant information" refers to data including the name, contact information, skills, and available time slots of registered volunteers.

[0098] "Location information" refers to geographical location information of the participant's current location, including location coordinates obtained through GPS and other location-determining technologies.

[0099] A "database" is a digital data storage area that systematically stores participant information and disaster relief request information, and allows for easy searching and updating.

[0100] "Disaster relief request information" refers to data that includes detailed information such as the skills needed when a disaster occurs, the number of volunteers, the work location, and the date and time of the activity.

[0101] "Assignment" is the process of selecting appropriate volunteers based on participant information and support request information, and assigning them to specific support activities.

[0102] An "artificial intelligence model" is a computational model used to determine the optimal volunteer assignments, taking into account participants' skills, availability, and geographical conditions.

[0103] A "notification" is a message sent to selected volunteers via digital devices such as smartphones, conveying information about volunteer activities.

[0104] A "schedule" is a plan that details the date, time, and location of volunteer activities, and is provided to both participants and support managers.

[0105] The system for implementing this invention effectively acquires participant information and location information and matches it with disaster relief request information to enable rapid volunteer allocation. The specific method by which the system program operates is described below.

[0106] The server receives information entered by participants using smartphones and various digital devices and systematically stores it in a database. This information includes participants' names, contact information, skills, available times, and location. Similarly, support request information entered by disaster area managers is also stored in the database. This includes the required skills, the number of volunteers needed, the work location, and the date and time of the activity.

[0107] The artificial intelligence model analyzes participant information and support request information, and performs optimal matching considering skills, availability, and geographical conditions. Generative AI models such as BERT and GPT are used as examples. By inputting prompts into the AI ​​model, more accurate results can be obtained.

[0108] For example, if a participant possesses a medical qualification and is available to participate in activities on weekends, and these conditions match urgently needed assistance, a notification will be sent to that person inviting them to participate. The notification will be sent via a smartphone app, allowing the user to review the activity details and choose whether or not to participate.

[0109] Examples of prompts for the generative AI model are as follows:

[0110] "A disaster relief request has been registered. Medical skills are needed, and the activity period is weekends. Please select volunteers who can participate."

[0111] This system utilizes cloud servers such as AWS® and Google® Cloud, and uses MySQL® as its database. This configuration minimizes delays in relief efforts and enables effective disaster response.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] Users use smartphones or digital devices to enter their name, contact information, skills, available time, and location. This data is then sent to the server as participant information. The server receives this information and stores it in a database, making it available for subsequent processing.

[0115] Step 2:

[0116] Managers in disaster areas use dedicated terminals to input support request information into a server. This information includes the required skills, the number of volunteers needed, the work location, and the date and time of the activity, and the server stores this information in a database. The stored information is then ready for analysis.

[0117] Step 3:

[0118] The server retrieves participant information and disaster relief request information stored in the database and inputs it into an artificial intelligence model. This model is a generative AI model such as BERT or GPT, and it performs data analysis based on the given prompt sentences. Specifically, it analyzes requirements such as participants' skills, location conditions, and available time to participate, and lists suitable volunteers.

[0119] Step 4:

[0120] Based on the matching results generated in Step 3, the server sends activity notifications to participants. These notifications are sent via a smartphone app and displayed on the participants' devices. Users can receive the notification and choose whether or not to participate.

[0121] Step 5:

[0122] When a user chooses to participate in an activity, their response is sent from their device to the server. The server receives this response, confirms them as a participant, and saves the final schedule and activity details to the database. This information is then sent to the support administrator so that the necessary preparations for their acceptance can be made.

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

[0124] This invention integrates an emotion engine into a system for collecting information on volunteer participants and performing optimal matching, enabling a more accurate understanding of participants' will and motivation compared to conventional systems. This allows for efficient matching that considers not only participants' skills and preferences but also their emotional readiness. The specific process is described below.

[0125] When a user opens the volunteer registration form on their device, they enter their name, contact information, skills, desired tasks, and available dates and times. Information is also collected from the user's text and tone of voice to analyze their emotions.

[0126] The terminal sends user input data to the server, which stores the information in a database. During this process, an emotion engine is used to analyze the user's emotional state. The emotion engine evaluates positive / negative tendencies, excitement levels, and calmness based on text input and the user's voice tone.

[0127] Managers in disaster areas use terminals to input volunteer request information and send it to a server. The server stores this information in a database and updates it in real time.

[0128] The server analyzes participant and support information using an artificial intelligence model. This model considers the participant's skills, preferences, geographical location, and evaluation results from an emotion engine to perform optimal matching. For example, even if a participant meets the skill requirements, if they are emotionally negative, another participant may be deemed more suitable.

[0129] Based on the matching results, the server sends a notification to the user's device, providing details. After reviewing the notification, the user chooses to "participate" or "not participate." This choice may be influenced by the results of a sentiment evaluation, allowing for careful consideration.

[0130] Ultimately, the server notifies users of the confirmed volunteer schedules and activity details on their devices, prompting them to prepare. Confirmed information is also sent to disaster area managers, allowing them to prepare the necessary receiving arrangements. This system, by taking into account the psychological preparation of participants, supports more effective and harmonious activities.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The user accesses the volunteer registration form through their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user fills in this information and prepares to submit it.

[0134] Step 2:

[0135] The terminal sends data entered by the user to the server. The server receives the information and stores it in a database. During saving, it also checks the format and checks for duplicate data.

[0136] Step 3:

[0137] The server activates an emotion engine and analyzes the user's emotions from the text data and tone of voice they input. This analysis evaluates the user's current mental state, for example, whether it is positive or negative.

[0138] Step 4:

[0139] Managers in disaster areas input volunteer request information for specific activities via terminals and send it to a server. This request information includes required skills, the number of volunteers needed, the work location, and the date and time.

[0140] Step 5:

[0141] The server stores the disaster relief request information it receives in a database and prepares to perform optimal matching by combining it with participant information.

[0142] Step 6:

[0143] The server uses an artificial intelligence model to analyze participant information and support request information. The model considers participants' skills, preferences, geographical location, and emotional state to select the most suitable participant. For example, participants in a positive emotional state may be prioritized.

[0144] Step 7:

[0145] The server sends a notification to the user via their device based on the matching results. The notification will include available roles and schedules, and the user will be asked to confirm their willingness to participate.

[0146] Step 8:

[0147] The user reviews the notification and selects "Participate" or "Do not participate." The selection is sent from the device to the server and recorded in the database.

[0148] Step 9:

[0149] The server compiles information on volunteers who have expressed their willingness to participate and notifies them of the final schedule and activity details on their devices. It also provides a list of confirmed participants to disaster area managers, enabling them to coordinate the necessary acceptance arrangements.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] Traditional volunteer matching systems have struggled to adequately reflect changes in participants' will and motivation, making it difficult to achieve optimal matching. Furthermore, because matching does not take into account participants' emotional states, there is a possibility that the efficiency and effectiveness of activities will decrease.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes means for acquiring participant information and storing that information in a storage medium, means for acquiring disaster relief request information and storing that information in a storage medium, and means for analyzing participant information and request information and using an artificial intelligence model to generate the optimal match. This makes it possible to achieve optimal volunteer matching that also takes into account the emotional state of the participants, and thereby realize efficient and effective activities.

[0155] A "participant" is an individual or group that has registered with the intention to participate in volunteer activities.

[0156] "Information" refers to data such as the participant's name, contact information, skills, desired activities, available dates and times, and emotional state.

[0157] A "storage medium" is a data storage system used to store and manage digital information.

[0158] "Disaster relief request information" refers to data provided by the administrators of disaster-stricken areas regarding the types and conditions of assistance requested.

[0159] An "artificial intelligence model" is an algorithm that uses machine learning or other AI technologies to perform analysis and inference based on data and propose the optimal fit.

[0160] "Matching" is the process of combining participant information with disaster relief needs information to pair the most suitable participants with the appropriate relief activities.

[0161] "Emotional state" is an assessment that represents emotional tendencies and changes, analyzed from participants' text and tone of voice.

[0162] "Notification" refers to a means of communication sent from the system to participants or related parties, including matching results and activity instructions.

[0163] As an embodiment of this invention, the volunteer matching system has the function of efficiently acquiring, storing, and analyzing participant information and disaster relief request information, and providing the optimal match between participants and relief activities. Participants and disaster area managers access the system using their respective terminals. The terminals collect information such as the user's name, contact information, skills, desired activities, and available dates and times, and transmit it to the server. Data for sentiment analysis from the user's voice tone and input text is also collected simultaneously.

[0164] The server stores the received information on a storage medium and uses sentiment analysis technology to evaluate the user's emotional state. This sentiment analysis combines natural language processing and speech analysis techniques to determine positive / negative tendencies and emotional intensity based on both text and speech. For example, if a user inputs, "I'm interested in tree planting. I can participate on weekends," and speaks in a calm tone, the system will interpret this as a positive expression of intent.

[0165] The administrator also uses a terminal to input the required volunteer skills and requirements and sends this information to the server. The server analyzes the participant and request information stored on the storage medium using a generative AI model. This AI model considers the input skills, preferences, geographical conditions, emotional state, etc., and proposes the best match. As an example of the AI ​​analysis, it may determine that a person with a low level of excitement is suitable for participating in tree-planting activities.

[0166] The matching results are notified from the server to the user's device, allowing the user to receive the notification and confirm their willingness to participate in the activity. This process enables efficient and appropriate coordination of volunteer activities that take into account the feelings and wishes of the participants.

[0167] An example of a prompt for the generating AI model would be: "The user has entered specific skills and interests related to the activity. Based on this text and voice tone data, please use the emotion engine to evaluate the user's emotions and match them with their skills and preferences." This allows the AI ​​model to be utilized to achieve accurate participant matching.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] Users open a volunteer registration form on their device and enter their name, contact information, skills, desired activities, and available dates and times. The device's microphone also records the user's voice tone, collecting sentiment analysis data along with the text input. The entered data is compiled by a form management system and sent to the server in JSON format.

[0171] Step 2:

[0172] The server saves the received data to a storage medium. The recorded data is then stored in the appropriate table in the database as participant information. This process involves analyzing the received data and inserting each item into the database.

[0173] Step 3:

[0174] The server uses an emotion analysis engine to analyze the user's text input and voice tone. It calculates a text emotion score from the input data through natural language processing and evaluates the emotional state of the voice through speech analysis. These are integrated to quantify the participant's emotional state on a scale from positive to negative. The analysis results are stored in a database.

[0175] Step 4:

[0176] The disaster area administrator uses a terminal to input the necessary volunteer skills and requirements and sends them to the server. The data entered by the administrator is received by the server and stored on a storage medium. Here too, the data is analyzed on the server side and stored as request information in a specific table in the database.

[0177] Step 5:

[0178] The server passes already stored participant information and disaster relief request information to an artificial intelligence model for analysis. The generative AI model verifies each participant's skills, preferences, geographical location, and emotional state to select the most suitable participant. In this process, the AI ​​uses an algorithm to evaluate each item and calculates a matching score. The output is the result of the optimal matching.

[0179] Step 6:

[0180] The server sends a notification to the device of the relevant participant based on the matching results. Specifically, a pop-up notification or email notification will appear on the device, and the user will be presented with details about the participation.

[0181] Step 7:

[0182] The user reviews the notification and provides feedback to the system from their device regarding whether or not they want to participate. The feedback is completed by selecting an item and choosing "Participate" or "Do not participate," and the information is then sent back to the server.

[0183] Step 8:

[0184] The server notifies users and disaster administrators of the finalized volunteer schedules and activity details. The schedule information is automatically registered in the user's calendar application, and a list of necessary items to bring and activity details are provided, along with notifications to encourage preparation.

[0185] (Application Example 2)

[0186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0187] In volunteer and worker matching, the process often relies solely on simple skills and preferences, without considering complex factors including participants' emotional states. This results in an inability to assign tasks optimally to participants based on their motivation and readiness. Consequently, efficient and proactive matching is not achieved, potentially impacting the success of the activity.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0189] In this invention, the server includes means for acquiring participant information and storing it in a data set, means for acquiring support request information and storing it in a data set, and means for integrating an emotion analysis engine and analyzing the participant's emotional state. This makes it possible to assign the optimal task by comprehensively considering the participant's skills, desires, and emotional state.

[0190] "Means for acquiring participant information and storing it in a data set" refers to a function for collecting volunteer and worker names, contact information, skills, desired working hours, and other relevant information, and securely storing them as a data set in a format that can be used for subsequent processing.

[0191] "Means for acquiring support request information and storing it in a data set" refers to a function that collects information about the support and tasks required, maintains it as a consistent data set, and uses it for real-time updates and subsequent analysis.

[0192] "A means of integrating an emotion analysis engine to analyze participants' emotional states" refers to a technology that uses data obtained from text and audio to evaluate participants' emotional states as indicators such as positive / negative tendencies, excitement levels, and calmness, and utilizes the results as part of the analysis.

[0193] "Optimal task assignment" is the process of selecting and assigning the most suitable tasks and roles to each participant in a way that maximizes efficiency and motivation, based on their skills, preferences, and emotional state.

[0194] To implement this invention, a system is constructed for efficiently managing information on volunteers and workers and for optimally assigning them to tasks. The system includes a server that receives input from participants and performs analysis using an emotion analysis engine and a machine learning model, as well as terminals for use by participants and administrators.

[0195] Users input personal information, desired working conditions, skills, or current emotional state using their smartphones or tablets, and send this information from their devices to the server. On the device, the input voice or text data is analyzed by an emotion analysis engine to evaluate the emotional state. This analysis uses the Text Analytics API from Microsoft® Azure® as the emotion analysis engine. The server then stores the collected data in a data set and, based on the analysis results, uses a generative AI model to assign the most suitable tasks to participants. Frameworks such as Scikit-learn are used as machine learning models. The results generated by the server are sent to the device as a notification, and the user can choose to "participate" or "not participate" in the assigned tasks.

[0196] As a concrete example, if a worker voice-inputs "I'm a little tired today" into a terminal, the system analyzes the message, recognizes the emotional state of "fatigue," and assigns them a less demanding task that suits them, rather than a normally strenuous one. Another possible prompt for the generative AI model is: "I would like to participate in volunteer activities, but I'm dissatisfied with recent teamwork, so I would like a less demanding role."

[0197] This system configuration allows for optimal matching that takes into account participants' emotions and motivations, enabling effective management of volunteer activities and operations at logistics centers.

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The user uses a device to enter their information (name, contact information, skills, desired working hours, and current emotional state, etc.). The entered information is captured by the device as text or audio data. The entered data is necessary to accurately represent the user's profile and is ready to be sent to the server.

[0201] Step 2:

[0202] The terminal sends text and voice data entered by the user to the server. During this process, the data is structured and transmitted according to a standard protocol. The server receives this information and stores it in a data set for further detailed analysis.

[0203] Step 3:

[0204] The server processes the received audio and text data using an emotion analysis engine. Specifically, it uses the Microsoft Azure Text Analytics API to evaluate attributes such as positive or negative emotional states, excitement levels, and calmness. The output is numerical data indicating the emotional state, which serves as a basis for subsequent decision-making.

[0205] Step 4:

[0206] The server uses a generative AI model to assign tasks optimally based on sentiment analysis results and other participant information. Input data includes emotional states, technical skills, and desired work conditions, while output is recommended tasks and their detailed information. Machine learning frameworks such as Scikit-learn are utilized in this process.

[0207] Step 5:

[0208] The terminal receives output from the server (optimal task assignment results) and provides feedback to the user by sending a notification. The user checks the notification on the terminal and chooses whether to "participate" or "not participate" in the assigned task. This choice is sent from the terminal to the server and stored as data for decision-making.

[0209] Step 6:

[0210] The server finalizes the task execution plan based on the user's final selection and resends a notification to the terminal containing the schedule and work details. This notification allows the user to prepare for the activity and begin the actual work.

[0211] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0212] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0213] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0217] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0218] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0219] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0220] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0221] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0222] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0223] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0225] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0226] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0227] The present invention provides a series of processes for efficiently matching volunteer participants with disaster relief request information. This system consists of a server, terminals, and users. Specific embodiments of each step are described below.

[0228] First, the user enters their information via their device and sends it to the server. This includes their name, contact information, skills, desired work content, and available dates and times. The server stores the received information in a database and performs data integrity checks as needed.

[0229] Next, disaster relief request information is sent to a server by the administrator of the disaster area using a dedicated terminal. This information includes the required skills, the number of volunteers, the work location, and the date and time of the activity. The server also stores this information in a database and makes it available for real-time updates.

[0230] The server uses an artificial intelligence model to analyze accumulated participant and support information. This model primarily considers participants' skills, available dates and times, and distance constraints to perform optimal matching. For example, if a participant with a certain medical skill is available on weekends and that skill is suitable for the support request, that participant will be selected preferentially.

[0231] Based on this matching result, the server sends a matching notification to the user via the device. The notification includes detailed information about the available activities, which the user can review and choose to "participate" or "not participate." The user's response is sent back to the server, and if confirmed as a participant, a detailed activity schedule is notified to the device.

[0232] Furthermore, the server organizes confirmed volunteer information and provides disaster area managers with a final list and schedule. This allows managers to prepare an appropriate receiving system. This system simplifies pre-activity coordination and enables the rapid and efficient deployment of relief efforts.

[0233] The following describes the processing flow.

[0234] Step 1:

[0235] The user opens the volunteer registration form on their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user enters this information and registers.

[0236] Step 2:

[0237] The terminal sends user input data to the server. The server stores the received data in a database. At the same time, it also checks whether the input content is duplicated and whether the format is correct.

[0238] Step 3:

[0239] The administrator of the disaster area uses a dedicated terminal to input volunteer request information into the server. At this time, they specify details such as the required skills, the number of volunteers, the work location, and the date and time.

[0240] Step 4:

[0241] The server saves the entered request information to a database and updates it by comparing it with existing data. This ensures that the information is kept up-to-date in real time.

[0242] Step 5:

[0243] The server collects participant and request information from the database and begins analysis using an artificial intelligence model. The AI ​​model calculates the best match based on participants' skills, preferred dates and times, and distance constraints.

[0244] Step 6:

[0245] The server sends the matching results obtained through analysis to the terminal. The terminal displays a notification to the user and provides an option to choose whether or not to participate in the activity.

[0246] Step 7:

[0247] The user reviews the notification and chooses either "Participate" or "Do not participate" from the provided options. The user's selection is sent from the device to the server.

[0248] Step 8:

[0249] The server creates a list of users who have responded with "I will participate" and notifies them of the final schedule and details on their devices. Users can then use this information to prepare.

[0250] Step 9:

[0251] The server sends information about confirmed volunteer participants to the disaster area administrator. The administrator uses this information to prepare the necessary receiving arrangements. This supports the smooth start of activities.

[0252] (Example 1)

[0253] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0254] In disaster relief activities, it is essential to quickly and efficiently match appropriate personnel from a diverse pool of participants to ensure smooth relief operations. However, conventional systems have faced challenges in improving matching accuracy due to the complexity of participant and support request information. Furthermore, the lack of means to verify the consistency of participant information and to flexibly match them with corresponding support requests prevented the maximum effectiveness of relief activities from being realized.

[0255] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0256] In this invention, the server includes a device for acquiring participant information and storing that information in a database, a device for acquiring disaster relief request information and storing that information in a database, and a device that uses a data processing model to analyze participant information and request information and generate the optimal match. This enables highly accurate matching that takes into account participants' skills, preferences, and geographical factors. Furthermore, by including a device to receive confirmation of participation intentions from participants, the final schedule and activity details can be provided, and the consistency of each participant's information can be verified, enabling the efficient and reliable implementation of support activities.

[0257] A "device for acquiring participant information" refers to a system configuration equipped with functions for collecting necessary data from individuals participating as volunteers.

[0258] A "database storage device" is a system configuration that continuously stores collected information in a structured format, making it available for later processing and retrieval.

[0259] A "device for acquiring disaster relief request information" is a system configuration equipped with functions to specifically gather information on the need for support from disaster-stricken areas and related parties.

[0260] A "device that uses a data processing model" is a system configuration that has algorithms and arithmetic methods for analyzing collected participant information and support request information and automatically generating the optimal match.

[0261] A "device for transmitting information to matched participants" refers to a system configuration equipped with communication means for notifying selected volunteers of the details of the activity and whether or not they can participate.

[0262] A "device that provides the final timetable and activity details" refers to a system configuration that has the function of sharing the decided support activity schedule and implementation details with participants and stakeholders.

[0263] The system for implementing the present invention provides a process for effectively matching participants with disaster relief requests. This system mainly consists of three components: users, terminals, and servers, and is responsible for information collection, storage, analysis, and communication.

[0264] Users enter their information into the terminal using a dedicated application. This information includes their name, contact information, skills, desired work, and available dates and times. The terminal securely collects user information by utilizing a function to send this entered information to a server.

[0265] The server stores the received participant information in a database. During storage, checks are performed to ensure data integrity. Furthermore, disaster relief request information is sent to the server using a similar procedure and stored in the database. This ensures that the necessary skills, activity details, and dates are always up-to-date.

[0266] The server uses a generative AI model to analyze participant information and support request information. This model considers participants' skills, preferences, and geographical conditions to perform optimal matching. For example, if a participant with medical skills has time on weekends, they will be prioritized for disaster requests requiring medical assistance on weekends.

[0267] The matching results are notified to the user via the terminal from the server. The user reviews the notification and chooses whether or not to participate. This response is sent back to the server, and the final schedule and activity details are sent to the user and the disaster manager.

[0268] This system aims to enable support activities to be carried out more quickly and efficiently through an effective matching process using generative AI models.

[0269] An example of a prompt is, "To match disaster relief volunteers, please suggest the best pairings based on the following participant and support request information." This prompt allows the generating AI model to perform the necessary processing and provide highly accurate matching results.

[0270] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0271] Step 1:

[0272] Users enter their information on a dedicated application. This information includes their name, contact details, skills, desired work, and available dates and times. The terminal prepares this information for transmission to a database and sends the data to the server. The output is transferred to the server as structured user information.

[0273] Step 2:

[0274] The server stores the received user information in the database. The received data undergoes integrity checks to ensure there are no missing entries or formatting errors. For example, it verifies that contact information is in the correct numerical format. The output of this step is that the user information, with its integrity ensured, is securely stored in the database.

[0275] Step 3:

[0276] Managers in disaster areas input disaster relief request information via dedicated terminals. This includes details such as required skills, activity locations, number of volunteers, and activity dates and times, which are then transmitted to the server in real time. The output is the specific relief request data received by the server.

[0277] Step 4:

[0278] The server stores the support request information received from the administrator in the database and ensures that the information is up-to-date. Through real-time updates, it prevents the data from becoming outdated or inconsistent. The output of this step is that the disaster support request information in the latest state is stored in the database.

[0279] Step 5:

[0280] The server uses a generative AI model to analyze the participant information and support information. Based on the input information, the generative AI model performs an optimal matching. As a specific example, it determines whether the schedule of a participant with a certain skill matches the support request. The output of this step is the pair of matched participants and support requests.

[0281] Step 6:

[0282] Based on the generated matching results, the server sends a notification to the corresponding user. Through the terminal, the user receives the details of the activities that can be participated in and selects whether to participate. This selection is sent back to the server again. The output is the participation confirmation data based on the user's selection.

[0283] Step 7:

[0284] Based on the confirmed willingness to participate, the server determines the detailed schedule of the activity. Through the terminal, this schedule is notified to the user and the disaster administrator, enabling the efficient execution of the activity. The output is the determined schedule and implementation plan.

[0285] (Application Example 1)

[0286] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0287] To implement rapid and efficient relief activities during disasters, it is essential to immediately assign the right personnel from a large pool of volunteers. However, conventional manual matching is time-consuming, and delays in support become a problem in urgent situations. Furthermore, traditional systems have difficulty making optimal assignments based on participants' location information and individual circumstances.

[0288] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0289] In this invention, the server includes means for acquiring participant information and location information and storing that information in a database, means for acquiring disaster relief request information and storing that information in a database, and means for using an artificial intelligence model to analyze participant information and request information and generate optimal assignments. This enables rapid and efficient matching that takes into account participants' skills and geographical conditions.

[0290] "Participant information" refers to data including the name, contact information, skills, and available time slots of registered volunteers.

[0291] "Location information" refers to geographical location information of the participant's current location, including location coordinates obtained through GPS and other location-determining technologies.

[0292] A "database" is a digital data storage area that systematically stores participant information and disaster relief request information, and allows for easy searching and updating.

[0293] "Disaster relief request information" refers to data that includes detailed information such as the skills needed when a disaster occurs, the number of volunteers, the work location, and the date and time of the activity.

[0294] "Assignment" is the process of selecting appropriate volunteers based on participant information and support request information, and assigning them to specific support activities.

[0295] An "artificial intelligence model" is a computational model used to determine the optimal volunteer assignments, taking into account participants' skills, availability, and geographical conditions.

[0296] A "notification" is a message sent to selected volunteers via digital devices such as smartphones, conveying information about volunteer activities.

[0297] A "schedule" is a plan that details the date, time, and location of volunteer activities, and is provided to both participants and support managers.

[0298] The system for implementing this invention effectively acquires participant information and location information and matches it with disaster relief request information to enable rapid volunteer allocation. The specific method by which the system program operates is described below.

[0299] The server receives information entered by participants using smartphones and various digital devices and systematically stores it in a database. This information includes participants' names, contact information, skills, available times, and location. Similarly, support request information entered by disaster area managers is also stored in the database. This includes the required skills, the number of volunteers needed, the work location, and the date and time of the activity.

[0300] The artificial intelligence model analyzes participant information and support request information, and performs optimal matching considering skills, availability, and geographical conditions. Generative AI models such as BERT and GPT are used as examples. By inputting prompts into the AI ​​model, more accurate results can be obtained.

[0301] As a specific example, if there is a person with a medical qualification among the participants and they are available on weekends, and if their conditions match the support information urgently required, a notice of activity participation will be sent to that person. The notice is sent through a smartphone app, and the user can check the details of the activity and choose whether to participate.

[0302] Examples of prompts for the generative AI model are as follows.

[0303] "Disaster support request information has been registered. Medical skills are required, and the activity period is on weekends. Please select eligible volunteers."

[0304] This system uses cloud servers such as AWS and Google Cloud, and MySQL is used for the database. With such a configuration, delays in support activities can be minimized, enabling effective disaster response.

[0305] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0306] Step 1:

[0307] The user uses a smartphone or digital terminal to input their name, contact information, skills, available time, and location information. As a result, the data input as participant information is sent to the server. The server receives this information and saves it in the database to make it available for subsequent processing.

[0308] Step 2:

[0309] The administrator of the disaster area uses a dedicated terminal to input support request information into the server. This information includes the required skills, the number of volunteers needed, the work location, and the activity date and time, and the server saves this in the database. The saved information is ready for analysis.

[0310] Step 3:

[0311] The server retrieves participant information and disaster relief request information stored in the database and inputs it into an artificial intelligence model. This model is a generative AI model such as BERT or GPT, and it performs data analysis based on the given prompt sentences. Specifically, it analyzes requirements such as participants' skills, location conditions, and available time to participate, and lists suitable volunteers.

[0312] Step 4:

[0313] Based on the matching results generated in Step 3, the server sends activity notifications to participants. These notifications are sent via a smartphone app and displayed on the participants' devices. Users can receive the notification and choose whether or not to participate.

[0314] Step 5:

[0315] When a user chooses to participate in an activity, their response is sent from their device to the server. The server receives this response, confirms them as a participant, and saves the final schedule and activity details to the database. This information is then sent to the support administrator so that the necessary preparations for their acceptance can be made.

[0316] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0317] This invention integrates an emotion engine into a system for collecting information on volunteer participants and performing optimal matching, enabling a more accurate understanding of participants' will and motivation compared to conventional systems. This allows for efficient matching that considers not only participants' skills and preferences but also their emotional readiness. The specific process is described below.

[0318] When a user opens the volunteer registration form on their device, they enter their name, contact information, skills, desired tasks, and available dates and times. Information is also collected from the user's text and tone of voice to analyze their emotions.

[0319] The terminal sends user input data to the server, which stores the information in a database. During this process, an emotion engine is used to analyze the user's emotional state. The emotion engine evaluates positive / negative tendencies, excitement levels, and calmness based on text input and the user's voice tone.

[0320] Managers in disaster areas use terminals to input volunteer request information and send it to a server. The server stores this information in a database and updates it in real time.

[0321] The server analyzes participant and support information using an artificial intelligence model. This model considers the participant's skills, preferences, geographical location, and evaluation results from an emotion engine to perform optimal matching. For example, even if a participant meets the skill requirements, if they are emotionally negative, another participant may be deemed more suitable.

[0322] Based on the matching results, the server sends a notification to the user's device, providing details. After reviewing the notification, the user chooses to "participate" or "not participate." This choice may be influenced by the results of a sentiment evaluation, allowing for careful consideration.

[0323] Ultimately, the server notifies users of the confirmed volunteer schedules and activity details on their devices, prompting them to prepare. Confirmed information is also sent to disaster area managers, allowing them to prepare the necessary receiving arrangements. This system, by taking into account the psychological preparation of participants, supports more effective and harmonious activities.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The user accesses the volunteer registration form through their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user fills in this information and prepares to submit it.

[0327] Step 2:

[0328] The terminal sends data entered by the user to the server. The server receives the information and stores it in a database. During saving, it also checks the format and checks for duplicate data.

[0329] Step 3:

[0330] The server activates an emotion engine and analyzes the user's emotions from the text data and tone of voice they input. This analysis evaluates the user's current mental state, for example, whether it is positive or negative.

[0331] Step 4:

[0332] Managers in disaster areas input volunteer request information for specific activities via terminals and send it to a server. This request information includes required skills, the number of volunteers needed, the work location, and the date and time.

[0333] Step 5:

[0334] The server stores the disaster relief request information it receives in a database and prepares to perform optimal matching by combining it with participant information.

[0335] Step 6:

[0336] The server uses an artificial intelligence model to analyze participant information and support request information. The model considers participants' skills, preferences, geographical location, and emotional state to select the most suitable participant. For example, participants in a positive emotional state may be prioritized.

[0337] Step 7:

[0338] The server sends a notification to the user via their device based on the matching results. The notification will include available roles and schedules, and the user will be asked to confirm their willingness to participate.

[0339] Step 8:

[0340] The user reviews the notification and selects "Participate" or "Do not participate." The selection is sent from the device to the server and recorded in the database.

[0341] Step 9:

[0342] The server compiles information on volunteers who have expressed their willingness to participate and notifies them of the final schedule and activity details on their devices. It also provides a list of confirmed participants to disaster area managers, enabling them to coordinate the necessary acceptance arrangements.

[0343] (Example 2)

[0344] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0345] Traditional volunteer matching systems have struggled to adequately reflect changes in participants' will and motivation, making it difficult to achieve optimal matching. Furthermore, because matching does not take into account participants' emotional states, there is a possibility that the efficiency and effectiveness of activities will decrease.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes means for acquiring participant information and storing that information in a storage medium, means for acquiring disaster relief request information and storing that information in a storage medium, and means for analyzing participant information and request information and using an artificial intelligence model to generate the optimal match. This makes it possible to achieve optimal volunteer matching that also takes into account the emotional state of the participants, and thereby realize efficient and effective activities.

[0348] A "participant" is an individual or group that has registered with the intention to participate in volunteer activities.

[0349] "Information" refers to data such as the participant's name, contact information, skills, desired activities, available dates and times, and emotional state.

[0350] A "storage medium" is a data storage system used to store and manage digital information.

[0351] "Disaster relief request information" refers to data provided by the administrators of disaster-stricken areas regarding the types and conditions of assistance requested.

[0352] An "artificial intelligence model" is an algorithm that uses machine learning or other AI technologies to perform analysis and inference based on data and propose the optimal fit.

[0353] "Matching" is the process of combining participant information with disaster relief needs information to pair the most suitable participants with the appropriate relief activities.

[0354] "Emotional state" is an assessment that represents emotional tendencies and changes, analyzed from participants' text and tone of voice.

[0355] "Notification" refers to a means of communication sent from the system to participants or related parties, including matching results and activity instructions.

[0356] As an embodiment of this invention, the volunteer matching system has the function of efficiently acquiring, storing, and analyzing participant information and disaster relief request information, and providing the optimal match between participants and relief activities. Participants and disaster area managers access the system using their respective terminals. The terminals collect information such as the user's name, contact information, skills, desired activities, and available dates and times, and transmit it to the server. Data for sentiment analysis from the user's voice tone and input text is also collected simultaneously.

[0357] The server stores the received information on a storage medium and uses sentiment analysis technology to evaluate the user's emotional state. This sentiment analysis combines natural language processing and speech analysis techniques to determine positive / negative tendencies and emotional intensity based on both text and speech. For example, if a user inputs, "I'm interested in tree planting. I can participate on weekends," and speaks in a calm tone, the system will interpret this as a positive expression of intent.

[0358] The administrator also uses a terminal to input the required volunteer skills and requirements and sends this information to the server. The server analyzes the participant and request information stored on the storage medium using a generative AI model. This AI model considers the input skills, preferences, geographical conditions, emotional state, etc., and proposes the best match. As an example of the AI ​​analysis, it may determine that a person with a low level of excitement is suitable for participating in tree-planting activities.

[0359] The matching results are notified from the server to the user's device, allowing the user to receive the notification and confirm their willingness to participate in the activity. This process enables efficient and appropriate coordination of volunteer activities that take into account the feelings and wishes of the participants.

[0360] An example of a prompt for the generating AI model would be: "The user has entered specific skills and interests related to the activity. Based on this text and voice tone data, please use the emotion engine to evaluate the user's emotions and match them with their skills and preferences." This allows the AI ​​model to be utilized to achieve accurate participant matching.

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] Users open a volunteer registration form on their device and enter their name, contact information, skills, desired activities, and available dates and times. The device's microphone also records the user's voice tone, collecting sentiment analysis data along with the text input. The entered data is compiled by a form management system and sent to the server in JSON format.

[0364] Step 2:

[0365] The server saves the received data to a storage medium. The recorded data is then stored in the appropriate table in the database as participant information. This process involves analyzing the received data and inserting each item into the database.

[0366] Step 3:

[0367] The server uses an emotion analysis engine to analyze the user's text input and voice tone. It calculates a text emotion score from the input data through natural language processing and evaluates the emotional state of the voice through speech analysis. These are integrated to quantify the participant's emotional state on a scale from positive to negative. The analysis results are stored in a database.

[0368] Step 4:

[0369] The disaster area administrator uses a terminal to input the necessary volunteer skills and requirements and sends them to the server. The data entered by the administrator is received by the server and stored on a storage medium. Here too, the data is analyzed on the server side and stored as request information in a specific table in the database.

[0370] Step 5:

[0371] The server passes already stored participant information and disaster relief request information to an artificial intelligence model for analysis. The generative AI model verifies each participant's skills, preferences, geographical location, and emotional state to select the most suitable participant. In this process, the AI ​​uses an algorithm to evaluate each item and calculates a matching score. The output is the result of the optimal matching.

[0372] Step 6:

[0373] The server sends a notification to the device of the relevant participant based on the matching results. Specifically, a pop-up notification or email notification will appear on the device, and the user will be presented with details about the participation.

[0374] Step 7:

[0375] The user reviews the notification and provides feedback to the system from their device regarding whether or not they want to participate. The feedback is completed by selecting an item and choosing "Participate" or "Do not participate," and the information is then sent back to the server.

[0376] Step 8:

[0377] The server notifies users and disaster administrators of the finalized volunteer schedules and activity details. The schedule information is automatically registered in the user's calendar application, and a list of necessary items to bring and activity details are provided, along with notifications to encourage preparation.

[0378] (Application Example 2)

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

[0380] In volunteer and worker matching, the process often relies solely on simple skills and preferences, without considering complex factors including participants' emotional states. This results in an inability to assign tasks optimally to participants based on their motivation and readiness. Consequently, efficient and proactive matching is not achieved, potentially impacting the success of the activity.

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

[0382] In this invention, the server includes means for acquiring participant information and storing it in a data set, means for acquiring support request information and storing it in a data set, and means for integrating an emotion analysis engine and analyzing the participant's emotional state. This makes it possible to assign the optimal task by comprehensively considering the participant's skills, desires, and emotional state.

[0383] "Means for acquiring participant information and storing it in a data set" refers to a function for collecting volunteer and worker names, contact information, skills, desired working hours, and other relevant information, and securely storing them as a data set in a format that can be used for subsequent processing.

[0384] "Means for acquiring support request information and storing it in a data set" refers to a function that collects information about the support and tasks required, maintains it as a consistent data set, and uses it for real-time updates and subsequent analysis.

[0385] "A means of integrating an emotion analysis engine to analyze participants' emotional states" refers to a technology that uses data obtained from text and audio to evaluate participants' emotional states as indicators such as positive / negative tendencies, excitement levels, and calmness, and utilizes the results as part of the analysis.

[0386] "Optimal task assignment" is the process of selecting and assigning the most suitable tasks and roles to each participant in a way that maximizes efficiency and motivation, based on their skills, preferences, and emotional state.

[0387] To implement this invention, a system is constructed for efficiently managing information on volunteers and workers and for optimally assigning them to tasks. The system includes a server that receives input from participants and performs analysis using an emotion analysis engine and a machine learning model, as well as terminals for use by participants and administrators.

[0388] Users input personal information, desired working conditions, skills, or current emotional state using their smartphones or tablets, and send this information from their devices to the server. On the device, the input voice or text data is analyzed by an emotion analysis engine to evaluate the emotional state. This analysis uses the Microsoft Azure Text Analytics API as the emotion analysis engine. The server then stores the collected data in a data set and, based on the analysis results, uses a generative AI model to assign the most suitable tasks to participants. Frameworks such as Scikit-learn are used as machine learning models. The results generated by the server are sent to the device as a notification, and the user can choose to "participate" or "not participate" in the assigned tasks.

[0389] As a concrete example, if a worker voice-inputs "I'm a little tired today" into a terminal, the system analyzes the message, recognizes the emotional state of "fatigue," and assigns them a less demanding task that suits them, rather than a normally strenuous one. Another possible prompt for the generative AI model is: "I would like to participate in volunteer activities, but I'm dissatisfied with recent teamwork, so I would like a less demanding role."

[0390] This system configuration allows for optimal matching that takes into account participants' emotions and motivations, enabling effective management of volunteer activities and operations at logistics centers.

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The user uses a device to enter their information (name, contact information, skills, desired working hours, and current emotional state, etc.). The entered information is captured by the device as text or audio data. The entered data is necessary to accurately represent the user's profile and is ready to be sent to the server.

[0394] Step 2:

[0395] The terminal sends text and voice data entered by the user to the server. During this process, the data is structured and transmitted according to a standard protocol. The server receives this information and stores it in a data set for further detailed analysis.

[0396] Step 3:

[0397] The server processes the received audio and text data using an emotion analysis engine. Specifically, it uses the Microsoft Azure Text Analytics API to evaluate attributes such as positive or negative emotional states, excitement levels, and calmness. The output is numerical data indicating the emotional state, which serves as a basis for subsequent decision-making.

[0398] Step 4:

[0399] The server uses a generative AI model to assign tasks optimally based on sentiment analysis results and other participant information. Input data includes emotional states, technical skills, and desired work conditions, while output is recommended tasks and their detailed information. Machine learning frameworks such as Scikit-learn are utilized in this process.

[0400] Step 5:

[0401] The terminal receives output from the server (optimal task assignment results) and provides feedback to the user by sending a notification. The user checks the notification on the terminal and chooses whether to "participate" or "not participate" in the assigned task. This choice is sent from the terminal to the server and stored as data for decision-making.

[0402] Step 6:

[0403] The server finalizes the task execution plan based on the user's final selection and resends a notification to the terminal containing the schedule and work details. This notification allows the user to prepare for the activity and begin the actual work.

[0404] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0405] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0407] [Third Embodiment]

[0408] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0409] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0410] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0411] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0412] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0414] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0415] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0416] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0417] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0418] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0419] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0420] The present invention provides a series of processes for efficiently matching volunteer participants with disaster relief request information. This system consists of a server, terminals, and users. Specific embodiments of each step are described below.

[0421] First, the user enters their information via their device and sends it to the server. This includes their name, contact information, skills, desired work content, and available dates and times. The server stores the received information in a database and performs data integrity checks as needed.

[0422] Next, disaster relief request information is sent to a server by the administrator of the disaster area using a dedicated terminal. This information includes the required skills, the number of volunteers, the work location, and the date and time of the activity. The server also stores this information in a database and makes it available for real-time updates.

[0423] The server uses an artificial intelligence model to analyze accumulated participant and support information. This model primarily considers participants' skills, available dates and times, and distance constraints to perform optimal matching. For example, if a participant with a certain medical skill is available on weekends and that skill is suitable for the support request, that participant will be selected preferentially.

[0424] Based on this matching result, the server sends a matching notification to the user via the device. The notification includes detailed information about the available activities, which the user can review and choose to "participate" or "not participate." The user's response is sent back to the server, and if confirmed as a participant, a detailed activity schedule is notified to the device.

[0425] Furthermore, the server organizes confirmed volunteer information and provides disaster area managers with a final list and schedule. This allows managers to prepare an appropriate receiving system. This system simplifies pre-activity coordination and enables the rapid and efficient deployment of relief efforts.

[0426] The following describes the processing flow.

[0427] Step 1:

[0428] The user opens the volunteer registration form on their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user enters this information and registers.

[0429] Step 2:

[0430] The terminal sends user input data to the server. The server stores the received data in a database. At the same time, it also checks whether the input content is duplicated and whether the format is correct.

[0431] Step 3:

[0432] The administrator of the disaster area uses a dedicated terminal to input volunteer request information into the server. At this time, they specify details such as the required skills, the number of volunteers, the work location, and the date and time.

[0433] Step 4:

[0434] The server saves the entered request information to a database and updates it by comparing it with existing data. This ensures that the information is kept up-to-date in real time.

[0435] Step 5:

[0436] The server collects participant and request information from the database and begins analysis using an artificial intelligence model. The AI ​​model calculates the best match based on participants' skills, preferred dates and times, and distance constraints.

[0437] Step 6:

[0438] The server sends the matching results obtained through analysis to the terminal. The terminal displays a notification to the user and provides an option to choose whether or not to participate in the activity.

[0439] Step 7:

[0440] The user reviews the notification and chooses either "Participate" or "Do not participate" from the provided options. The user's selection is sent from the device to the server.

[0441] Step 8:

[0442] The server creates a list of users who have responded with "I will participate" and notifies them of the final schedule and details on their devices. Users can then use this information to prepare.

[0443] Step 9:

[0444] The server sends information about confirmed volunteer participants to the disaster area administrator. The administrator uses this information to prepare the necessary receiving arrangements. This supports the smooth start of activities.

[0445] (Example 1)

[0446] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0447] In disaster relief activities, it is essential to quickly and efficiently match appropriate personnel from a diverse pool of participants to ensure smooth relief operations. However, conventional systems have faced challenges in improving matching accuracy due to the complexity of participant and support request information. Furthermore, the lack of means to verify the consistency of participant information and to flexibly match them with corresponding support requests prevented the maximum effectiveness of relief activities from being realized.

[0448] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0449] In this invention, the server includes a device for acquiring participant information and storing that information in a database, a device for acquiring disaster relief request information and storing that information in a database, and a device that uses a data processing model to analyze participant information and request information and generate the optimal match. This enables highly accurate matching that takes into account participants' skills, preferences, and geographical factors. Furthermore, by including a device to receive confirmation of participation intentions from participants, the final schedule and activity details can be provided, and the consistency of each participant's information can be verified, enabling the efficient and reliable implementation of support activities.

[0450] A "device for acquiring participant information" refers to a system configuration equipped with functions for collecting necessary data from individuals participating as volunteers.

[0451] A "database storage device" is a system configuration that continuously stores collected information in a structured format, making it available for later processing and retrieval.

[0452] A "device for acquiring disaster relief request information" is a system configuration equipped with functions to specifically gather information on the need for support from disaster-stricken areas and related parties.

[0453] A "device that uses a data processing model" is a system configuration that has algorithms and arithmetic methods for analyzing collected participant information and support request information and automatically generating the optimal match.

[0454] A "device for transmitting information to matched participants" refers to a system configuration equipped with communication means for notifying selected volunteers of the details of the activity and whether or not they can participate.

[0455] A "device that provides the final timetable and activity details" refers to a system configuration that has the function of sharing the decided support activity schedule and implementation details with participants and stakeholders.

[0456] The system for implementing the present invention provides a process for effectively matching participants with disaster relief requests. This system mainly consists of three components: users, terminals, and servers, and is responsible for information collection, storage, analysis, and communication.

[0457] Users enter their information into the terminal using a dedicated application. This information includes their name, contact information, skills, desired work, and available dates and times. The terminal securely collects user information by utilizing a function to send this entered information to a server.

[0458] The server stores the received participant information in a database. During storage, checks are performed to ensure data integrity. Furthermore, disaster relief request information is sent to the server using a similar procedure and stored in the database. This ensures that the necessary skills, activity details, and dates are always up-to-date.

[0459] The server uses a generative AI model to analyze participant information and support request information. This model considers participants' skills, preferences, and geographical conditions to perform optimal matching. For example, if a participant with medical skills has time on weekends, they will be prioritized for disaster requests requiring medical assistance on weekends.

[0460] The matching results are notified to the user via the terminal from the server. The user reviews the notification and chooses whether or not to participate. This response is sent back to the server, and the final schedule and activity details are sent to the user and the disaster manager.

[0461] This system aims to enable support activities to be carried out more quickly and efficiently through an effective matching process using generative AI models.

[0462] An example of a prompt is, "To match disaster relief volunteers, please suggest the best pairings based on the following participant and support request information." This prompt allows the generating AI model to perform the necessary processing and provide highly accurate matching results.

[0463] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0464] Step 1:

[0465] Users enter their information on a dedicated application. This information includes their name, contact details, skills, desired work, and available dates and times. The terminal prepares this information for transmission to a database and sends the data to the server. The output is transferred to the server as structured user information.

[0466] Step 2:

[0467] The server stores the received user information in the database. The received data undergoes integrity checks to ensure there are no missing entries or formatting errors. For example, it verifies that contact information is in the correct numerical format. The output of this step is that the user information, with its integrity ensured, is securely stored in the database.

[0468] Step 3:

[0469] Managers in disaster areas input disaster relief request information via dedicated terminals. This includes details such as required skills, activity locations, number of volunteers, and activity dates and times, which are then transmitted to the server in real time. The output is the specific relief request data received by the server.

[0470] Step 4:

[0471] The server stores the assistance request information received from the administrator in a database, ensuring that the information is up-to-date. Real-time updates prevent the data from becoming outdated or inconsistent. The output of this step is that the latest disaster assistance request information is stored in the database.

[0472] Step 5:

[0473] The server uses a generative AI model to analyze participant and support information. Based on the input information, the generative AI model performs optimal matching. For example, it determines whether a participant with a certain skill has a matching schedule and support request. The output of this step is a pair of matched participants and support requests.

[0474] Step 6:

[0475] The server sends a notification to the relevant user based on the generated matching results. Through their device, the user receives details of the available activities and chooses whether or not to participate. This choice is then sent back to the server. The output is participation confirmation data based on the user's choice.

[0476] Step 7:

[0477] The server finalizes the detailed schedule of the activities based on confirmed participation. This schedule is notified to users and disaster managers via terminals, enabling efficient execution of the activities. The output is the finalized schedule and implementation plan.

[0478] (Application Example 1)

[0479] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0480] To implement rapid and efficient relief activities during disasters, it is essential to immediately assign the right personnel from a large pool of volunteers. However, conventional manual matching is time-consuming, and delays in support become a problem in urgent situations. Furthermore, traditional systems have difficulty making optimal assignments based on participants' location information and individual circumstances.

[0481] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0482] In this invention, the server includes means for acquiring participant information and location information and storing that information in a database, means for acquiring disaster relief request information and storing that information in a database, and means for using an artificial intelligence model to analyze participant information and request information and generate optimal assignments. This enables rapid and efficient matching that takes into account participants' skills and geographical conditions.

[0483] "Participant information" refers to data including the name, contact information, skills, and available time slots of registered volunteers.

[0484] "Location information" refers to geographical location information of the participant's current location, including location coordinates obtained through GPS and other location-determining technologies.

[0485] A "database" is a digital data storage area that systematically stores participant information and disaster relief request information, and allows for easy searching and updating.

[0486] "Disaster relief request information" refers to data that includes detailed information such as the skills needed when a disaster occurs, the number of volunteers, the work location, and the date and time of the activity.

[0487] "Assignment" is the process of selecting appropriate volunteers based on participant information and support request information, and assigning them to specific support activities.

[0488] An "artificial intelligence model" is a computational model used to determine the optimal volunteer assignments, taking into account participants' skills, availability, and geographical conditions.

[0489] A "notification" is a message sent to selected volunteers via digital devices such as smartphones, conveying information about volunteer activities.

[0490] A "schedule" is a plan that details the date, time, and location of volunteer activities, and is provided to both participants and support managers.

[0491] The system for implementing this invention effectively acquires participant information and location information and matches it with disaster relief request information to enable rapid volunteer allocation. The specific method by which the system program operates is described below.

[0492] The server receives information entered by participants using smartphones and various digital devices and systematically stores it in a database. This information includes participants' names, contact information, skills, available times, and location. Similarly, support request information entered by disaster area managers is also stored in the database. This includes the required skills, the number of volunteers needed, the work location, and the date and time of the activity.

[0493] The artificial intelligence model analyzes participant information and support request information, and performs optimal matching considering skills, availability, and geographical conditions. Generative AI models such as BERT and GPT are used as examples. By inputting prompts into the AI ​​model, more accurate results can be obtained.

[0494] For example, if a participant possesses a medical qualification and is available to participate in activities on weekends, and these conditions match urgently needed assistance, a notification will be sent to that person inviting them to participate. The notification will be sent via a smartphone app, allowing the user to review the activity details and choose whether or not to participate.

[0495] Examples of prompts for the generative AI model are as follows:

[0496] "A disaster relief request has been registered. Medical skills are needed, and the activity period is weekends. Please select volunteers who can participate."

[0497] This system utilizes cloud servers such as AWS and Google Cloud, and uses MySQL as its database. This configuration minimizes delays in relief efforts and enables effective disaster response.

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] Users use smartphones or digital devices to enter their name, contact information, skills, available time, and location. This data is then sent to the server as participant information. The server receives this information and stores it in a database, making it available for subsequent processing.

[0501] Step 2:

[0502] Managers in disaster areas use dedicated terminals to input support request information into a server. This information includes the required skills, the number of volunteers needed, the work location, and the date and time of the activity, and the server stores this information in a database. The stored information is then ready for analysis.

[0503] Step 3:

[0504] The server retrieves participant information and disaster relief request information stored in the database and inputs it into an artificial intelligence model. This model is a generative AI model such as BERT or GPT, and it performs data analysis based on the given prompt sentences. Specifically, it analyzes requirements such as participants' skills, location conditions, and available time to participate, and lists suitable volunteers.

[0505] Step 4:

[0506] Based on the matching results generated in Step 3, the server sends activity notifications to participants. These notifications are sent via a smartphone app and displayed on the participants' devices. Users can receive the notification and choose whether or not to participate.

[0507] Step 5:

[0508] When a user chooses to participate in an activity, their response is sent from their device to the server. The server receives this response, confirms them as a participant, and saves the final schedule and activity details to the database. This information is then sent to the support administrator so that the necessary preparations for their acceptance can be made.

[0509] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0510] This invention integrates an emotion engine into a system for collecting information on volunteer participants and performing optimal matching, enabling a more accurate understanding of participants' will and motivation compared to conventional systems. This allows for efficient matching that considers not only participants' skills and preferences but also their emotional readiness. The specific process is described below.

[0511] When a user opens the volunteer registration form on their device, they enter their name, contact information, skills, desired tasks, and available dates and times. Information is also collected from the user's text and tone of voice to analyze their emotions.

[0512] The terminal sends user input data to the server, which stores the information in a database. During this process, an emotion engine is used to analyze the user's emotional state. The emotion engine evaluates positive / negative tendencies, excitement levels, and calmness based on text input and the user's voice tone.

[0513] Managers in disaster areas use terminals to input volunteer request information and send it to a server. The server stores this information in a database and updates it in real time.

[0514] The server analyzes participant and support information using an artificial intelligence model. This model considers the participant's skills, preferences, geographical location, and evaluation results from an emotion engine to perform optimal matching. For example, even if a participant meets the skill requirements, if they are emotionally negative, another participant may be deemed more suitable.

[0515] Based on the matching results, the server sends a notification to the user's device, providing details. After reviewing the notification, the user chooses to "participate" or "not participate." This choice may be influenced by the results of a sentiment evaluation, allowing for careful consideration.

[0516] Ultimately, the server notifies users of the confirmed volunteer schedules and activity details on their devices, prompting them to prepare. Confirmed information is also sent to disaster area managers, allowing them to prepare the necessary receiving arrangements. This system, by taking into account the psychological preparation of participants, supports more effective and harmonious activities.

[0517] The following describes the processing flow.

[0518] Step 1:

[0519] The user accesses the volunteer registration form through their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user fills in this information and prepares to submit it.

[0520] Step 2:

[0521] The terminal sends data entered by the user to the server. The server receives the information and stores it in a database. During saving, it also checks the format and checks for duplicate data.

[0522] Step 3:

[0523] The server activates an emotion engine and analyzes the user's emotions from the text data and tone of voice they input. This analysis evaluates the user's current mental state, for example, whether it is positive or negative.

[0524] Step 4:

[0525] Managers in disaster areas input volunteer request information for specific activities via terminals and send it to a server. This request information includes required skills, the number of volunteers needed, the work location, and the date and time.

[0526] Step 5:

[0527] The server stores the disaster relief request information it receives in a database and prepares to perform optimal matching by combining it with participant information.

[0528] Step 6:

[0529] The server uses an artificial intelligence model to analyze participant information and support request information. The model considers participants' skills, preferences, geographical location, and emotional state to select the most suitable participant. For example, participants in a positive emotional state may be prioritized.

[0530] Step 7:

[0531] The server sends a notification to the user via their device based on the matching results. The notification will include available roles and schedules, and the user will be asked to confirm their willingness to participate.

[0532] Step 8:

[0533] The user reviews the notification and selects "Participate" or "Do not participate." The selection is sent from the device to the server and recorded in the database.

[0534] Step 9:

[0535] The server compiles information on volunteers who have expressed their willingness to participate and notifies them of the final schedule and activity details on their devices. It also provides a list of confirmed participants to disaster area managers, enabling them to coordinate the necessary acceptance arrangements.

[0536] (Example 2)

[0537] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0538] Traditional volunteer matching systems have struggled to adequately reflect changes in participants' will and motivation, making it difficult to achieve optimal matching. Furthermore, because matching does not take into account participants' emotional states, there is a possibility that the efficiency and effectiveness of activities will decrease.

[0539] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0540] In this invention, the server includes means for acquiring participant information and storing that information in a storage medium, means for acquiring disaster relief request information and storing that information in a storage medium, and means for analyzing participant information and request information and using an artificial intelligence model to generate the optimal match. This makes it possible to achieve optimal volunteer matching that also takes into account the emotional state of the participants, and thereby realize efficient and effective activities.

[0541] A "participant" is an individual or group that has registered with the intention to participate in volunteer activities.

[0542] "Information" refers to data such as the participant's name, contact information, skills, desired activities, available dates and times, and emotional state.

[0543] A "storage medium" is a data storage system used to store and manage digital information.

[0544] "Disaster relief request information" refers to data provided by the administrators of disaster-stricken areas regarding the types and conditions of assistance requested.

[0545] An "artificial intelligence model" is an algorithm that uses machine learning or other AI technologies to perform analysis and inference based on data and propose the optimal fit.

[0546] "Matching" is the process of combining participant information with disaster relief needs information to pair the most suitable participants with the appropriate relief activities.

[0547] "Emotional state" is an assessment that represents emotional tendencies and changes, analyzed from participants' text and tone of voice.

[0548] "Notification" refers to a means of communication sent from the system to participants or related parties, including matching results and activity instructions.

[0549] As an embodiment of this invention, the volunteer matching system has the function of efficiently acquiring, storing, and analyzing participant information and disaster relief request information, and providing the optimal match between participants and relief activities. Participants and disaster area managers access the system using their respective terminals. The terminals collect information such as the user's name, contact information, skills, desired activities, and available dates and times, and transmit it to the server. Data for sentiment analysis from the user's voice tone and input text is also collected simultaneously.

[0550] The server stores the received information on a storage medium and uses sentiment analysis technology to evaluate the user's emotional state. This sentiment analysis combines natural language processing and speech analysis techniques to determine positive / negative tendencies and emotional intensity based on both text and speech. For example, if a user inputs, "I'm interested in tree planting. I can participate on weekends," and speaks in a calm tone, the system will interpret this as a positive expression of intent.

[0551] The administrator also uses a terminal to input the required volunteer skills and requirements and sends this information to the server. The server analyzes the participant and request information stored on the storage medium using a generative AI model. This AI model considers the input skills, preferences, geographical conditions, emotional state, etc., and proposes the best match. As an example of the AI ​​analysis, it may determine that a person with a low level of excitement is suitable for participating in tree-planting activities.

[0552] The matching results are notified from the server to the user's device, allowing the user to receive the notification and confirm their willingness to participate in the activity. This process enables efficient and appropriate coordination of volunteer activities that take into account the feelings and wishes of the participants.

[0553] An example of a prompt for the generating AI model would be: "The user has entered specific skills and interests related to the activity. Based on this text and voice tone data, please use the emotion engine to evaluate the user's emotions and match them with their skills and preferences." This allows the AI ​​model to be utilized to achieve accurate participant matching.

[0554] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0555] Step 1:

[0556] Users open a volunteer registration form on their device and enter their name, contact information, skills, desired activities, and available dates and times. The device's microphone also records the user's voice tone, collecting sentiment analysis data along with the text input. The entered data is compiled by a form management system and sent to the server in JSON format.

[0557] Step 2:

[0558] The server saves the received data to a storage medium. The recorded data is then stored in the appropriate table in the database as participant information. This process involves analyzing the received data and inserting each item into the database.

[0559] Step 3:

[0560] The server uses an emotion analysis engine to analyze the user's text input and voice tone. It calculates a text emotion score from the input data through natural language processing and evaluates the emotional state of the voice through speech analysis. These are integrated to quantify the participant's emotional state on a scale from positive to negative. The analysis results are stored in a database.

[0561] Step 4:

[0562] The disaster area administrator uses a terminal to input the necessary volunteer skills and requirements and sends them to the server. The data entered by the administrator is received by the server and stored on a storage medium. Here too, the data is analyzed on the server side and stored as request information in a specific table in the database.

[0563] Step 5:

[0564] The server passes already stored participant information and disaster relief request information to an artificial intelligence model for analysis. The generative AI model verifies each participant's skills, preferences, geographical location, and emotional state to select the most suitable participant. In this process, the AI ​​uses an algorithm to evaluate each item and calculates a matching score. The output is the result of the optimal matching.

[0565] Step 6:

[0566] The server sends a notification to the device of the relevant participant based on the matching results. Specifically, a pop-up notification or email notification will appear on the device, and the user will be presented with details about the participation.

[0567] Step 7:

[0568] The user reviews the notification and provides feedback to the system from their device regarding whether or not they want to participate. The feedback is completed by selecting an item and choosing "Participate" or "Do not participate," and the information is then sent back to the server.

[0569] Step 8:

[0570] The server notifies users and disaster administrators of the finalized volunteer schedules and activity details. The schedule information is automatically registered in the user's calendar application, and a list of necessary items to bring and activity details are provided, along with notifications to encourage preparation.

[0571] (Application Example 2)

[0572] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0573] In volunteer and worker matching, the process often relies solely on simple skills and preferences, without considering complex factors including participants' emotional states. This results in an inability to assign tasks optimally to participants based on their motivation and readiness. Consequently, efficient and proactive matching is not achieved, potentially impacting the success of the activity.

[0574] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0575] In this invention, the server includes means for acquiring participant information and storing it in a data set, means for acquiring support request information and storing it in a data set, and means for integrating an emotion analysis engine and analyzing the participant's emotional state. This makes it possible to assign the optimal task by comprehensively considering the participant's skills, desires, and emotional state.

[0576] "Means for acquiring participant information and storing it in a data set" refers to a function for collecting volunteer and worker names, contact information, skills, desired working hours, and other relevant information, and securely storing them as a data set in a format that can be used for subsequent processing.

[0577] "Means for acquiring support request information and storing it in a data set" refers to a function that collects information about the support and tasks required, maintains it as a consistent data set, and uses it for real-time updates and subsequent analysis.

[0578] "A means of integrating an emotion analysis engine to analyze participants' emotional states" refers to a technology that uses data obtained from text and audio to evaluate participants' emotional states as indicators such as positive / negative tendencies, excitement levels, and calmness, and utilizes the results as part of the analysis.

[0579] "Optimal task assignment" is the process of selecting and assigning the most suitable tasks and roles to each participant in a way that maximizes efficiency and motivation, based on their skills, preferences, and emotional state.

[0580] To implement this invention, a system is constructed for efficiently managing information on volunteers and workers and for optimally assigning them to tasks. The system includes a server that receives input from participants and performs analysis using an emotion analysis engine and a machine learning model, as well as terminals for use by participants and administrators.

[0581] Users input personal information, desired working conditions, skills, or current emotional state using their smartphones or tablets, and send this information from their devices to the server. On the device, the input voice or text data is analyzed by an emotion analysis engine to evaluate the emotional state. This analysis uses the Microsoft Azure Text Analytics API as the emotion analysis engine. The server then stores the collected data in a data set and, based on the analysis results, uses a generative AI model to assign the most suitable tasks to participants. Frameworks such as Scikit-learn are used as machine learning models. The results generated by the server are sent to the device as a notification, and the user can choose to "participate" or "not participate" in the assigned tasks.

[0582] As a concrete example, if a worker voice-inputs "I'm a little tired today" into a terminal, the system analyzes the message, recognizes the emotional state of "fatigue," and assigns them a less demanding task that suits them, rather than a normally strenuous one. Another possible prompt for the generative AI model is: "I would like to participate in volunteer activities, but I'm dissatisfied with recent teamwork, so I would like a less demanding role."

[0583] This system configuration allows for optimal matching that takes into account participants' emotions and motivations, enabling effective management of volunteer activities and operations at logistics centers.

[0584] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0585] Step 1:

[0586] The user uses a device to enter their information (name, contact information, skills, desired working hours, and current emotional state, etc.). The entered information is captured by the device as text or audio data. The entered data is necessary to accurately represent the user's profile and is ready to be sent to the server.

[0587] Step 2:

[0588] The terminal sends text and voice data entered by the user to the server. During this process, the data is structured and transmitted according to a standard protocol. The server receives this information and stores it in a data set for further detailed analysis.

[0589] Step 3:

[0590] The server processes the received audio and text data using an emotion analysis engine. Specifically, it uses the Microsoft Azure Text Analytics API to evaluate attributes such as positive or negative emotional states, excitement levels, and calmness. The output is numerical data indicating the emotional state, which serves as a basis for subsequent decision-making.

[0591] Step 4:

[0592] The server uses a generative AI model to assign tasks optimally based on sentiment analysis results and other participant information. Input data includes emotional states, technical skills, and desired work conditions, while output is recommended tasks and their detailed information. Machine learning frameworks such as Scikit-learn are utilized in this process.

[0593] Step 5:

[0594] The terminal receives output from the server (optimal task assignment results) and provides feedback to the user by sending a notification. The user checks the notification on the terminal and chooses whether to "participate" or "not participate" in the assigned task. This choice is sent from the terminal to the server and stored as data for decision-making.

[0595] Step 6:

[0596] The server finalizes the task execution plan based on the user's final selection and resends a notification to the terminal containing the schedule and work details. This notification allows the user to prepare for the activity and begin the actual work.

[0597] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0598] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0599] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0600] [Fourth Embodiment]

[0601] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0602] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0603] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0604] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0605] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0606] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0607] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0608] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0609] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0610] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0611] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0612] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0613] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0614] The present invention provides a series of processes for efficiently matching volunteer participants with disaster relief request information. This system consists of a server, terminals, and users. Specific embodiments of each step are described below.

[0615] First, the user enters their information via their device and sends it to the server. This includes their name, contact information, skills, desired work content, and available dates and times. The server stores the received information in a database and performs data integrity checks as needed.

[0616] Next, disaster relief request information is sent to a server by the administrator of the disaster area using a dedicated terminal. This information includes the required skills, the number of volunteers, the work location, and the date and time of the activity. The server also stores this information in a database and makes it available for real-time updates.

[0617] The server uses an artificial intelligence model to analyze accumulated participant and support information. This model primarily considers participants' skills, available dates and times, and distance constraints to perform optimal matching. For example, if a participant with a certain medical skill is available on weekends and that skill is suitable for the support request, that participant will be selected preferentially.

[0618] Based on this matching result, the server sends a matching notification to the user via the device. The notification includes detailed information about the available activities, which the user can review and choose to "participate" or "not participate." The user's response is sent back to the server, and if confirmed as a participant, a detailed activity schedule is notified to the device.

[0619] Furthermore, the server organizes confirmed volunteer information and provides disaster area managers with a final list and schedule. This allows managers to prepare an appropriate receiving system. This system simplifies pre-activity coordination and enables the rapid and efficient deployment of relief efforts.

[0620] The following describes the processing flow.

[0621] Step 1:

[0622] The user opens the volunteer registration form on their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user enters this information and registers.

[0623] Step 2:

[0624] The terminal sends user input data to the server. The server stores the received data in a database. At the same time, it also checks whether the input content is duplicated and whether the format is correct.

[0625] Step 3:

[0626] The administrator of the disaster area uses a dedicated terminal to input volunteer request information into the server. At this time, they specify details such as the required skills, the number of volunteers, the work location, and the date and time.

[0627] Step 4:

[0628] The server saves the entered request information to a database and updates it by comparing it with existing data. This ensures that the information is kept up-to-date in real time.

[0629] Step 5:

[0630] The server collects participant and request information from the database and begins analysis using an artificial intelligence model. The AI ​​model calculates the best match based on participants' skills, preferred dates and times, and distance constraints.

[0631] Step 6:

[0632] The server sends the matching results obtained through analysis to the terminal. The terminal displays a notification to the user and provides an option to choose whether or not to participate in the activity.

[0633] Step 7:

[0634] The user reviews the notification and chooses either "Participate" or "Do not participate" from the provided options. The user's selection is sent from the device to the server.

[0635] Step 8:

[0636] The server creates a list of users who have responded with "I will participate" and notifies them of the final schedule and details on their devices. Users can then use this information to prepare.

[0637] Step 9:

[0638] The server sends information about confirmed volunteer participants to the disaster area administrator. The administrator uses this information to prepare the necessary receiving arrangements. This supports the smooth start of activities.

[0639] (Example 1)

[0640] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0641] In disaster relief activities, it is essential to quickly and efficiently match appropriate personnel from a diverse pool of participants to ensure smooth relief operations. However, conventional systems have faced challenges in improving matching accuracy due to the complexity of participant and support request information. Furthermore, the lack of means to verify the consistency of participant information and to flexibly match them with corresponding support requests prevented the maximum effectiveness of relief activities from being realized.

[0642] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0643] In this invention, the server includes a device for acquiring participant information and storing that information in a database, a device for acquiring disaster relief request information and storing that information in a database, and a device that uses a data processing model to analyze participant information and request information and generate the optimal match. This enables highly accurate matching that takes into account participants' skills, preferences, and geographical factors. Furthermore, by including a device to receive confirmation of participation intentions from participants, the final schedule and activity details can be provided, and the consistency of each participant's information can be verified, enabling the efficient and reliable implementation of support activities.

[0644] A "device for acquiring participant information" refers to a system configuration equipped with functions for collecting necessary data from individuals participating as volunteers.

[0645] A "database storage device" is a system configuration that continuously stores collected information in a structured format, making it available for later processing and retrieval.

[0646] A "device for acquiring disaster relief request information" is a system configuration equipped with functions to specifically gather information on the need for support from disaster-stricken areas and related parties.

[0647] A "device that uses a data processing model" is a system configuration that has algorithms and arithmetic methods for analyzing collected participant information and support request information and automatically generating the optimal match.

[0648] A "device for transmitting information to matched participants" refers to a system configuration equipped with communication means for notifying selected volunteers of the details of the activity and whether or not they can participate.

[0649] A "device that provides the final timetable and activity details" refers to a system configuration that has the function of sharing the decided support activity schedule and implementation details with participants and stakeholders.

[0650] The system for implementing the present invention provides a process for effectively matching participants with disaster relief requests. This system mainly consists of three components: users, terminals, and servers, and is responsible for information collection, storage, analysis, and communication.

[0651] Users enter their information into the terminal using a dedicated application. This information includes their name, contact information, skills, desired work, and available dates and times. The terminal securely collects user information by utilizing a function to send this entered information to a server.

[0652] The server stores the received participant information in a database. During storage, checks are performed to ensure data integrity. Furthermore, disaster relief request information is sent to the server using a similar procedure and stored in the database. This ensures that the necessary skills, activity details, and dates are always up-to-date.

[0653] The server uses a generative AI model to analyze participant information and support request information. This model considers participants' skills, preferences, and geographical conditions to perform optimal matching. For example, if a participant with medical skills has time on weekends, they will be prioritized for disaster requests requiring medical assistance on weekends.

[0654] The matching results are notified to the user via the terminal from the server. The user reviews the notification and chooses whether or not to participate. This response is sent back to the server, and the final schedule and activity details are sent to the user and the disaster manager.

[0655] This system aims to enable support activities to be carried out more quickly and efficiently through an effective matching process using generative AI models.

[0656] An example of a prompt is, "To match disaster relief volunteers, please suggest the best pairings based on the following participant and support request information." This prompt allows the generating AI model to perform the necessary processing and provide highly accurate matching results.

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] Users enter their information on a dedicated application. This information includes their name, contact details, skills, desired work, and available dates and times. The terminal prepares this information for transmission to a database and sends the data to the server. The output is transferred to the server as structured user information.

[0660] Step 2:

[0661] The server stores the received user information in the database. The received data undergoes integrity checks to ensure there are no missing entries or formatting errors. For example, it verifies that contact information is in the correct numerical format. The output of this step is that the user information, with its integrity ensured, is securely stored in the database.

[0662] Step 3:

[0663] Managers in disaster areas input disaster relief request information via dedicated terminals. This includes details such as required skills, activity locations, number of volunteers, and activity dates and times, which are then transmitted to the server in real time. The output is the specific relief request data received by the server.

[0664] Step 4:

[0665] The server stores the assistance request information received from the administrator in a database, ensuring that the information is up-to-date. Real-time updates prevent the data from becoming outdated or inconsistent. The output of this step is that the latest disaster assistance request information is stored in the database.

[0666] Step 5:

[0667] The server uses a generative AI model to analyze participant and support information. Based on the input information, the generative AI model performs optimal matching. For example, it determines whether a participant with a certain skill has a matching schedule and support request. The output of this step is a pair of matched participants and support requests.

[0668] Step 6:

[0669] The server sends a notification to the relevant user based on the generated matching results. Through their device, the user receives details of the available activities and chooses whether or not to participate. This choice is then sent back to the server. The output is participation confirmation data based on the user's choice.

[0670] Step 7:

[0671] The server finalizes the detailed schedule of the activities based on confirmed participation. This schedule is notified to users and disaster managers via terminals, enabling efficient execution of the activities. The output is the finalized schedule and implementation plan.

[0672] (Application Example 1)

[0673] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] To implement rapid and efficient relief activities during disasters, it is essential to immediately assign the right personnel from a large pool of volunteers. However, conventional manual matching is time-consuming, and delays in support become a problem in urgent situations. Furthermore, traditional systems have difficulty making optimal assignments based on participants' location information and individual circumstances.

[0675] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0676] In this invention, the server includes means for acquiring participant information and location information and storing that information in a database, means for acquiring disaster relief request information and storing that information in a database, and means for using an artificial intelligence model to analyze participant information and request information and generate optimal assignments. This enables rapid and efficient matching that takes into account participants' skills and geographical conditions.

[0677] "Participant information" refers to data including the name, contact information, skills, and available time slots of registered volunteers.

[0678] "Location information" refers to geographical location information of the participant's current location, including location coordinates obtained through GPS and other location-determining technologies.

[0679] A "database" is a digital data storage area that systematically stores participant information and disaster relief request information, and allows for easy searching and updating.

[0680] "Disaster relief request information" refers to data that includes detailed information such as the skills needed when a disaster occurs, the number of volunteers, the work location, and the date and time of the activity.

[0681] "Assignment" is the process of selecting appropriate volunteers based on participant information and support request information, and assigning them to specific support activities.

[0682] An "artificial intelligence model" is a computational model used to determine the optimal volunteer assignments, taking into account participants' skills, availability, and geographical conditions.

[0683] A "notification" is a message sent to selected volunteers via digital devices such as smartphones, conveying information about volunteer activities.

[0684] A "schedule" is a plan that details the date, time, and location of volunteer activities, and is provided to both participants and support managers.

[0685] The system for implementing this invention effectively acquires participant information and location information and matches it with disaster relief request information to enable rapid volunteer allocation. The specific method by which the system program operates is described below.

[0686] The server receives information entered by participants using smartphones and various digital devices and systematically stores it in a database. This information includes participants' names, contact information, skills, available times, and location. Similarly, support request information entered by disaster area managers is also stored in the database. This includes the required skills, the number of volunteers needed, the work location, and the date and time of the activity.

[0687] The artificial intelligence model analyzes participant information and support request information, and performs optimal matching considering skills, availability, and geographical conditions. Generative AI models such as BERT and GPT are used as examples. By inputting prompts into the AI ​​model, more accurate results can be obtained.

[0688] For example, if a participant possesses a medical qualification and is available to participate in activities on weekends, and these conditions match urgently needed assistance, a notification will be sent to that person inviting them to participate. The notification will be sent via a smartphone app, allowing the user to review the activity details and choose whether or not to participate.

[0689] Examples of prompts for the generative AI model are as follows:

[0690] "A disaster relief request has been registered. Medical skills are needed, and the activity period is weekends. Please select volunteers who can participate."

[0691] This system utilizes cloud servers such as AWS and Google Cloud, and uses MySQL as its database. This configuration minimizes delays in relief efforts and enables effective disaster response.

[0692] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0693] Step 1:

[0694] Users use smartphones or digital devices to enter their name, contact information, skills, available time, and location. This data is then sent to the server as participant information. The server receives this information and stores it in a database, making it available for subsequent processing.

[0695] Step 2:

[0696] Managers in disaster areas use dedicated terminals to input support request information into a server. This information includes the required skills, the number of volunteers needed, the work location, and the date and time of the activity, and the server stores this information in a database. The stored information is then ready for analysis.

[0697] Step 3:

[0698] The server retrieves participant information and disaster relief request information stored in the database and inputs it into an artificial intelligence model. This model is a generative AI model such as BERT or GPT, and it performs data analysis based on the given prompt sentences. Specifically, it analyzes requirements such as participants' skills, location conditions, and available time to participate, and lists suitable volunteers.

[0699] Step 4:

[0700] Based on the matching results generated in Step 3, the server sends activity notifications to participants. These notifications are sent via a smartphone app and displayed on the participants' devices. Users can receive the notification and choose whether or not to participate.

[0701] Step 5:

[0702] When a user chooses to participate in an activity, their response is sent from their device to the server. The server receives this response, confirms them as a participant, and saves the final schedule and activity details to the database. This information is then sent to the support administrator so that the necessary preparations for their acceptance can be made.

[0703] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0704] This invention integrates an emotion engine into a system for collecting information on volunteer participants and performing optimal matching, enabling a more accurate understanding of participants' will and motivation compared to conventional systems. This allows for efficient matching that considers not only participants' skills and preferences but also their emotional readiness. The specific process is described below.

[0705] When a user opens the volunteer registration form on their device, they enter their name, contact information, skills, desired tasks, and available dates and times. Information is also collected from the user's text and tone of voice to analyze their emotions.

[0706] The terminal sends user input data to the server, which stores the information in a database. During this process, an emotion engine is used to analyze the user's emotional state. The emotion engine evaluates positive / negative tendencies, excitement levels, and calmness based on text input and the user's voice tone.

[0707] Managers in disaster areas use terminals to input volunteer request information and send it to a server. The server stores this information in a database and updates it in real time.

[0708] The server analyzes participant and support information using an artificial intelligence model. This model considers the participant's skills, preferences, geographical location, and evaluation results from an emotion engine to perform optimal matching. For example, even if a participant meets the skill requirements, if they are emotionally negative, another participant may be deemed more suitable.

[0709] Based on the matching results, the server sends a notification to the user's device, providing details. After reviewing the notification, the user chooses to "participate" or "not participate." This choice may be influenced by the results of a sentiment evaluation, allowing for careful consideration.

[0710] Ultimately, the server notifies users of the confirmed volunteer schedules and activity details on their devices, prompting them to prepare. Confirmed information is also sent to disaster area managers, allowing them to prepare the necessary receiving arrangements. This system, by taking into account the psychological preparation of participants, supports more effective and harmonious activities.

[0711] The following describes the processing flow.

[0712] Step 1:

[0713] The user accesses the volunteer registration form through their device. The form includes fields for name, contact information, skills, desired tasks, and available dates and times. The user fills in this information and prepares to submit it.

[0714] Step 2:

[0715] The terminal sends data entered by the user to the server. The server receives the information and stores it in a database. During saving, it also checks the format and checks for duplicate data.

[0716] Step 3:

[0717] The server activates an emotion engine and analyzes the user's emotions from the text data and tone of voice they input. This analysis evaluates the user's current mental state, for example, whether it is positive or negative.

[0718] Step 4:

[0719] Managers in disaster areas input volunteer request information for specific activities via terminals and send it to a server. This request information includes required skills, the number of volunteers needed, the work location, and the date and time.

[0720] Step 5:

[0721] The server stores the disaster relief request information it receives in a database and prepares to perform optimal matching by combining it with participant information.

[0722] Step 6:

[0723] The server uses an artificial intelligence model to analyze participant information and support request information. The model considers participants' skills, preferences, geographical location, and emotional state to select the most suitable participant. For example, participants in a positive emotional state may be prioritized.

[0724] Step 7:

[0725] The server sends a notification to the user via their device based on the matching results. The notification will include available roles and schedules, and the user will be asked to confirm their willingness to participate.

[0726] Step 8:

[0727] The user reviews the notification and selects "Participate" or "Do not participate." The selection is sent from the device to the server and recorded in the database.

[0728] Step 9:

[0729] The server compiles information on volunteers who have expressed their willingness to participate and notifies them of the final schedule and activity details on their devices. It also provides a list of confirmed participants to disaster area managers, enabling them to coordinate the necessary acceptance arrangements.

[0730] (Example 2)

[0731] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0732] Traditional volunteer matching systems have struggled to adequately reflect changes in participants' will and motivation, making it difficult to achieve optimal matching. Furthermore, because matching does not take into account participants' emotional states, there is a possibility that the efficiency and effectiveness of activities will decrease.

[0733] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0734] In this invention, the server includes means for acquiring participant information and storing that information in a storage medium, means for acquiring disaster relief request information and storing that information in a storage medium, and means for analyzing participant information and request information and using an artificial intelligence model to generate the optimal match. This makes it possible to achieve optimal volunteer matching that also takes into account the emotional state of the participants, and thereby realize efficient and effective activities.

[0735] A "participant" is an individual or group that has registered with the intention to participate in volunteer activities.

[0736] "Information" refers to data such as the participant's name, contact information, skills, desired activities, available dates and times, and emotional state.

[0737] A "storage medium" is a data storage system used to store and manage digital information.

[0738] "Disaster relief request information" refers to data provided by the administrators of disaster-stricken areas regarding the types and conditions of assistance requested.

[0739] An "artificial intelligence model" is an algorithm that uses machine learning or other AI technologies to perform analysis and inference based on data and propose the optimal fit.

[0740] "Matching" is the process of combining participant information with disaster relief needs information to pair the most suitable participants with the appropriate relief activities.

[0741] "Emotional state" is an assessment that represents emotional tendencies and changes, analyzed from participants' text and tone of voice.

[0742] "Notification" refers to a means of communication sent from the system to participants or related parties, including matching results and activity instructions.

[0743] As an embodiment of this invention, the volunteer matching system has the function of efficiently acquiring, storing, and analyzing participant information and disaster relief request information, and providing the optimal match between participants and relief activities. Participants and disaster area managers access the system using their respective terminals. The terminals collect information such as the user's name, contact information, skills, desired activities, and available dates and times, and transmit it to the server. Data for sentiment analysis from the user's voice tone and input text is also collected simultaneously.

[0744] The server stores the received information on a storage medium and uses sentiment analysis technology to evaluate the user's emotional state. This sentiment analysis combines natural language processing and speech analysis techniques to determine positive / negative tendencies and emotional intensity based on both text and speech. For example, if a user inputs, "I'm interested in tree planting. I can participate on weekends," and speaks in a calm tone, the system will interpret this as a positive expression of intent.

[0745] The administrator also uses a terminal to input the required volunteer skills and requirements and sends this information to the server. The server analyzes the participant and request information stored on the storage medium using a generative AI model. This AI model considers the input skills, preferences, geographical conditions, emotional state, etc., and proposes the best match. As an example of the AI ​​analysis, it may determine that a person with a low level of excitement is suitable for participating in tree-planting activities.

[0746] The matching results are notified from the server to the user's device, allowing the user to receive the notification and confirm their willingness to participate in the activity. This process enables efficient and appropriate coordination of volunteer activities that take into account the feelings and wishes of the participants.

[0747] An example of a prompt for the generating AI model would be: "The user has entered specific skills and interests related to the activity. Based on this text and voice tone data, please use the emotion engine to evaluate the user's emotions and match them with their skills and preferences." This allows the AI ​​model to be utilized to achieve accurate participant matching.

[0748] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0749] Step 1:

[0750] Users open a volunteer registration form on their device and enter their name, contact information, skills, desired activities, and available dates and times. The device's microphone also records the user's voice tone, collecting sentiment analysis data along with the text input. The entered data is compiled by a form management system and sent to the server in JSON format.

[0751] Step 2:

[0752] The server saves the received data to a storage medium. The recorded data is then stored in the appropriate table in the database as participant information. This process involves analyzing the received data and inserting each item into the database.

[0753] Step 3:

[0754] The server uses an emotion analysis engine to analyze the user's text input and voice tone. It calculates a text emotion score from the input data through natural language processing and evaluates the emotional state of the voice through speech analysis. These are integrated to quantify the participant's emotional state on a scale from positive to negative. The analysis results are stored in a database.

[0755] Step 4:

[0756] The disaster area administrator uses a terminal to input the necessary volunteer skills and requirements and sends them to the server. The data entered by the administrator is received by the server and stored on a storage medium. Here too, the data is analyzed on the server side and stored as request information in a specific table in the database.

[0757] Step 5:

[0758] The server passes already stored participant information and disaster relief request information to an artificial intelligence model for analysis. The generative AI model verifies each participant's skills, preferences, geographical location, and emotional state to select the most suitable participant. In this process, the AI ​​uses an algorithm to evaluate each item and calculates a matching score. The output is the result of the optimal matching.

[0759] Step 6:

[0760] The server sends a notification to the device of the relevant participant based on the matching results. Specifically, a pop-up notification or email notification will appear on the device, and the user will be presented with details about the participation.

[0761] Step 7:

[0762] The user reviews the notification and provides feedback to the system from their device regarding whether or not they want to participate. The feedback is completed by selecting an item and choosing "Participate" or "Do not participate," and the information is then sent back to the server.

[0763] Step 8:

[0764] The server notifies users and disaster administrators of the finalized volunteer schedules and activity details. The schedule information is automatically registered in the user's calendar application, and a list of necessary items to bring and activity details are provided, along with notifications to encourage preparation.

[0765] (Application Example 2)

[0766] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0767] In volunteer and worker matching, the process often relies solely on simple skills and preferences, without considering complex factors including participants' emotional states. This results in an inability to assign tasks optimally to participants based on their motivation and readiness. Consequently, efficient and proactive matching is not achieved, potentially impacting the success of the activity.

[0768] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0769] In this invention, the server includes means for acquiring participant information and storing it in a data set, means for acquiring support request information and storing it in a data set, and means for integrating an emotion analysis engine and analyzing the participant's emotional state. This makes it possible to assign the optimal task by comprehensively considering the participant's skills, desires, and emotional state.

[0770] "Means for acquiring participant information and storing it in a data set" refers to a function for collecting volunteer and worker names, contact information, skills, desired working hours, and other relevant information, and securely storing them as a data set in a format that can be used for subsequent processing.

[0771] "Means for acquiring support request information and storing it in a data set" refers to a function that collects information about the support and tasks required, maintains it as a consistent data set, and uses it for real-time updates and subsequent analysis.

[0772] "A means of integrating an emotion analysis engine to analyze participants' emotional states" refers to a technology that uses data obtained from text and audio to evaluate participants' emotional states as indicators such as positive / negative tendencies, excitement levels, and calmness, and utilizes the results as part of the analysis.

[0773] "Optimal task assignment" is the process of selecting and assigning the most suitable tasks and roles to each participant in a way that maximizes efficiency and motivation, based on their skills, preferences, and emotional state.

[0774] To implement this invention, a system is constructed for efficiently managing information on volunteers and workers and for optimally assigning them to tasks. The system includes a server that receives input from participants and performs analysis using an emotion analysis engine and a machine learning model, as well as terminals for use by participants and administrators.

[0775] Users input personal information, desired working conditions, skills, or current emotional state using their smartphones or tablets, and send this information from their devices to the server. On the device, the input voice or text data is analyzed by an emotion analysis engine to evaluate the emotional state. This analysis uses the Microsoft Azure Text Analytics API as the emotion analysis engine. The server then stores the collected data in a data set and, based on the analysis results, uses a generative AI model to assign the most suitable tasks to participants. Frameworks such as Scikit-learn are used as machine learning models. The results generated by the server are sent to the device as a notification, and the user can choose to "participate" or "not participate" in the assigned tasks.

[0776] As a concrete example, if a worker voice-inputs "I'm a little tired today" into a terminal, the system analyzes the message, recognizes the emotional state of "fatigue," and assigns them a less demanding task that suits them, rather than a normally strenuous one. Another possible prompt for the generative AI model is: "I would like to participate in volunteer activities, but I'm dissatisfied with recent teamwork, so I would like a less demanding role."

[0777] This system configuration allows for optimal matching that takes into account participants' emotions and motivations, enabling effective management of volunteer activities and operations at logistics centers.

[0778] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0779] Step 1:

[0780] The user uses a device to enter their information (name, contact information, skills, desired working hours, and current emotional state, etc.). The entered information is captured by the device as text or audio data. The entered data is necessary to accurately represent the user's profile and is ready to be sent to the server.

[0781] Step 2:

[0782] The terminal sends text and voice data entered by the user to the server. During this process, the data is structured and transmitted according to a standard protocol. The server receives this information and stores it in a data set for further detailed analysis.

[0783] Step 3:

[0784] The server processes the received audio and text data using an emotion analysis engine. Specifically, it uses the Microsoft Azure Text Analytics API to evaluate attributes such as positive or negative emotional states, excitement levels, and calmness. The output is numerical data indicating the emotional state, which serves as a basis for subsequent decision-making.

[0785] Step 4:

[0786] The server uses a generative AI model to assign tasks optimally based on sentiment analysis results and other participant information. Input data includes emotional states, technical skills, and desired work conditions, while output is recommended tasks and their detailed information. Machine learning frameworks such as Scikit-learn are utilized in this process.

[0787] Step 5:

[0788] The terminal receives output from the server (optimal task assignment results) and provides feedback to the user by sending a notification. The user checks the notification on the terminal and chooses whether to "participate" or "not participate" in the assigned task. This choice is sent from the terminal to the server and stored as data for decision-making.

[0789] Step 6:

[0790] The server finalizes the task execution plan based on the user's final selection and resends a notification to the terminal containing the schedule and work details. This notification allows the user to prepare for the activity and begin the actual work.

[0791] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0792] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0793] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0794] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0795] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0796] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0797] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0798] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0799] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0800] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0801] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0802] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0803] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0804] 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.

[0805] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0806] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0807] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0808] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0809] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0810] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0811] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0812] The following is further disclosed regarding the embodiments described above.

[0813] (Claim 1)

[0814] A means of obtaining participant information and storing that information in a database,

[0815] A means of acquiring disaster relief request information and storing that information in a database,

[0816] A means of using an artificial intelligence model to analyze participant information and request information and generate the optimal match,

[0817] A means of sending notifications to matched participants,

[0818] A means of providing participants and disaster managers with the final schedule and activity details,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, further comprising means for receiving confirmation of participation intent from participants.

[0822] (Claim 3)

[0823] The system according to claim 1, wherein the artificial intelligence model is configured to perform matching taking into account the skills, preferences, and geographical conditions of the participants.

[0824] "Example 1"

[0825] (Claim 1)

[0826] A device that acquires participant information and stores that information in a database,

[0827] A device that acquires disaster relief request information and stores that information in a database,

[0828] A device that uses a data processing model to analyze participant information and request information and generate the optimal match,

[0829] A device that transmits information to matched participants,

[0830] A device that provides participants and disaster managers with the final schedule and activity details,

[0831] A device to verify the integrity of participant information,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, further comprising a device for receiving confirmation of the participant's intention to participate.

[0835] (Claim 3)

[0836] The system according to claim 1, wherein the data processing model has a configuration that performs matching considering the skills, preferences and geographical factors of the participants.

[0837] "Application Example 1"

[0838] (Claim 1)

[0839] A means of acquiring participant information and location information and storing that information in a database,

[0840] A means of acquiring disaster relief request information and storing that information in a database,

[0841] A means of using an artificial intelligence model to analyze participant information and request information and generate the optimal assignment,

[0842] A means of sending activity notifications to assigned participants,

[0843] A means of providing participants and support managers with the final schedule and activity details,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, further comprising means for receiving responses from participants indicating their participation in the activity.

[0847] (Claim 3)

[0848] The system according to claim 1, wherein the artificial intelligence model is configured to make assignments taking into account the skills, availability, and geographical constraints of the participants.

[0849] "Example 2 of combining an emotion engine"

[0850] (Claim 1)

[0851] A means of obtaining participant information and saving that information to a storage medium,

[0852] A means of acquiring disaster relief request information and saving that information to a storage medium,

[0853] A means of using an artificial intelligence model to analyze participant information and request information and generate the optimal fit,

[0854] A means of sending notifications to matched participants,

[0855] A means of providing participants and disaster managers with the final schedule and activity details,

[0856] A means of using emotion analysis technology to analyze the emotional state of participants and taking the results into consideration to make the best fit,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for receiving confirmation of participation intent from participants.

[0860] (Claim 3)

[0861] The system according to claim 1, wherein the artificial intelligence model is configured to make a fit that takes into account the participant's skills, preferences, geographical conditions and emotional state.

[0862] "Application example 2 when combining with an emotional engine"

[0863] (Claim 1)

[0864] A means of obtaining participant information and storing that information in a data set,

[0865] A means for acquiring support request information and storing that information in a data set,

[0866] A means of using a machine learning model to analyze participant information and request information and generate the optimal response,

[0867] A means of integrating an emotion analysis engine to analyze the emotional state of participants,

[0868] A means of assigning the optimal task based on the analysis results,

[0869] A means of sending notifications to matched participants,

[0870] A means of providing participants and administrators with the final schedule and work details,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, further comprising means for receiving confirmation of participation intent from participants.

[0874] (Claim 3)

[0875] The system according to claim 1, wherein the machine learning model is configured to perform optimal matching by considering the participant's skills, preferences, geographical conditions, and evaluation by an emotion analysis engine. [Explanation of symbols]

[0876] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining participant information and storing that information in a database, A means of acquiring disaster relief request information and storing that information in a database, A means of using an artificial intelligence model to analyze participant information and request information and generate the optimal match, A means of sending notifications to matched participants, A means of providing participants and disaster managers with the final schedule and activity details, A system that includes this.

2. The system according to claim 1, further comprising means for receiving confirmation of participation intent from participants.

3. The system according to claim 1, wherein the artificial intelligence model is configured to perform matching considering the skills, preferences, and geographical conditions of the participants.

Images