system

Abstract

We provide the system. [Solution] A means of registering fundraising information of non-profit organizations and corporate donation policies in a database, A method for analyzing information on non-profit organizations and companies using a generated AI model to identify the optimal matching pair, Based on the matching results, non-profit organizations will be provided with a means to generate proposals, and corporations will be provided with a list of recipient organizations and a story for approval. A means of providing the generated proposal content via the user's display device, 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 method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] Currently, non - profit organizations operated by a small number of people lack funds to expand their activities and have difficulty selecting appropriate donation recipients. On the other hand, it is difficult for companies to convey the messages they want to express through donations, and there is a problem that funds are concentrated only on well - known organizations. It is required to improve such a situation and efficiently promote the cooperation between non - profit organizations and companies.

Means for Solving the Problems

[0005] This invention registers fundraising information from non-profit organizations and donation policies from corporations in a database and analyzes the information from both using a generated AI model. This analysis identifies optimal matching pairs and provides a means for generating proposals for non-profit organizations and donation lists and approval stories for corporations. Furthermore, by providing the generated proposals via a user's display device, it achieves efficient fundraising matching.

[0006] A "non-profit organization" is an organization that operates without the aim of making a profit, and whose primary purpose is to engage in social or charitable activities.

[0007] "Funding information" refers to information about the amount of funds a non-profit organization needs to carry out its activities and how those funds are used.

[0008] A "company" is a legal entity whose purpose is to produce and sell goods or services.

[0009] A "donation policy" is a set of guidelines that outlines the basic principles, such as purpose, recipients, and amount, regarding donations made by a company as part of its social contribution activities.

[0010] A "database" is a collection of information designed to store information for a specific purpose, making it efficiently searchable and usable.

[0011] A "generative AI model" is an artificial intelligence algorithm built to analyze given data and generate results that meet specific objectives.

[0012] A "matching pair" is a combination of a non-profit organization and a company that has been selected to mutually benefit each other.

[0013] A "proposal" is a document that outlines a proposal based on a specific objective, and is used by non-profit organizations when requesting funding from companies.

[0014] The "List of Beneficiaries" is a list of non-profit organizations that a company determines are appropriate for donations it makes.

[0015] The "Approval Story" is a description of the content and significance of a donation used to obtain internal approval within a company when making a donation.

[0016] A "display device" is a device that visually represents digital information and presents it to a user.

Brief Description of the Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the labeled 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 CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0021] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention is a system that enables efficient matching between non-profit organizations and businesses. This system operates by users inputting data through a terminal.

[0039] First, non-profit organizations, as users, use a terminal to input the desired amount of funds, their specific use, and their activities when seeking funding. This registers the non-profit organization's information in the system. Meanwhile, companies, as users, similarly register their information by inputting the purpose of their donation, the message they wish to convey, and their basic donation policy using a terminal.

[0040] After storing this information in a database, the server uses a generative AI model to analyze the information of non-profit organizations and companies. This analysis searches for and identifies the most suitable matching pairs. Based on the identified matching pairs, the server generates a list of candidate companies to propose as funding sources for non-profit organizations, along with detailed proposals. For companies, it generates a list of non-profit organizations to consider donating to, along with a story to help them obtain approval for the donation.

[0041] The generated proposals are provided to each user via their device. This allows non-profit organizations to effectively carry out fundraising activities tailored to the proposed companies. Meanwhile, companies can use the provided information to select recipients and streamline their internal approval processes.

[0042] As a concrete example, if a non-profit organization supporting children needs 1 million yen in funding for a new program, the user enters this information into a terminal, and the server considers this information and matches them with companies interested in local activities. This process allows both the non-profit organization and the company to build a collaborative relationship that aligns with their objectives.

[0043] As a result, the system of the present invention promotes social contribution activities and improves the efficiency of fundraising.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Nonprofit organizations, as users, use a terminal to enter information about their fundraising needs. This includes the desired fundraising amount, the intended use of the funds, and details of their activities. Once the information is entered, the data is sent to the server.

[0047] Step 2:

[0048] Corporate users enter donation-related information through their terminals. This includes the purpose of the donation, the message the company wants to convey, and their donation policy. This information is also sent to the server.

[0049] Step 3:

[0050] The server registers the information received from both users into a database. The registered data is used in the matching process.

[0051] Step 4:

[0052] The server uses a generative AI model to analyze the information in the database. Based on the goals and aspirations of non-profit organizations and businesses, it applies a matching algorithm to find the most suitable combination.

[0053] Step 5:

[0054] Based on the analysis results, the server generates fundraising proposals and lists of potential companies for non-profit organizations, and lists of non-profit organizations as recipients of donations and approval stories for companies.

[0055] Step 6:

[0056] The terminal displays the generated suggestions received from the server to the user. This allows the user to obtain information to consider each step of the process.

[0057] Step 7:

[0058] Users take necessary actions based on the matching results. Nonprofit organizations approach the proposed companies, and companies consider donating to the proposed nonprofit organizations.

[0059] In this way, the system of the present invention enables effective cooperation between non-profit organizations and businesses.

[0060] (Example 1)

[0061] 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."

[0062] The challenge lies in providing a system that can address the difficulties in fundraising due to a lack of efficient matching between non-profit organizations and corporations, as well as the difficulties in effectively distributing donations, thereby facilitating the smooth operation of both parties.

[0063] 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.

[0064] This invention includes a server that receives funding request information and donation policy information from users and registers it in an information processing device; a server that uses an artificial intelligence model generated by the data processing device to analyze the registered information and derive the best match; and a server that generates a proposal document for fundraisers and a list of potential recipients and approval documents for donors based on the matching results. This enables smooth fundraising and donations for non-profit organizations and corporations.

[0065] A "user" is a person or organization, such as a non-profit organization or a company, that intends to use this system to conduct fundraising or donation processes.

[0066] "Fundraising request information" refers to information that includes details such as the amount of money a non-profit organization needs to raise, the purpose of the funds, and the activities it will undertake.

[0067] "Donation policy information" refers to information that includes the purpose of a company's donation, the basic philosophy related to the donation, and the message it wishes to convey.

[0068] An "information processing device" is a device that has the function of registering and managing data received from users and communicating data with other devices.

[0069] An "artificial intelligence model" is a system equipped with algorithms that use machine learning and data analysis techniques to analyze information from non-profit organizations and companies and guide them toward the optimal match.

[0070] "Natural language processing technology" refers to computer science techniques used to analyze text data and understand its meaning and context.

[0071] "Response information" refers to information including feedback provided by users, as well as evaluations and opinions on proposed content.

[0072] This system is designed to facilitate efficient matching between non-profit organizations and businesses. Its main components include servers, terminals, generative AI models, and natural language processing technology. A specific implementation is described below.

[0073] Nonprofit organizations and businesses, as users, access the system through their terminals. Nonprofit users enter information such as the desired amount of funding, the specific use of the funds, and the activities they will undertake. Business users enter information such as the purpose of their donation, the message they wish to convey, and their basic donation policy. This information is formatted by the terminal and sent to the server.

[0074] The server registers the received information in the information processing device and stores it in the database. Based on this registered information, the server uses a generative AI model to perform analysis. The generative AI model uses natural language processing technology to analyze in detail the activities of non-profit organizations and the donation policies of companies, leading to the optimal match.

[0075] The analyzed results are stored on a server, and then proposals based on the best match are generated. Nonprofit organizations are provided with a list of potential corporate funding sources and proposals, while corporate users are provided with a list of potential recipients and the stories necessary for donation approval. These proposals are presented to users via their devices, enabling efficient matching and collaboration between both parties.

[0076] For example, if a non-profit organization that provides educational support for children needs 1 million yen in funding for a new program, they can input this information into a terminal, and the server will analyze the data and match them with companies interested in contributing to the local community.

[0077] An example prompt might be, "Find companies interested in community activities to fund a new educational program." Based on this prompt, the generating AI model optimizes the matching process. This allows the system to provide meaningful matches for both non-profit organizations and companies, supporting the promotion of social contribution activities.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] Users access the system using a terminal and enter the required information. Nonprofit organization users enter the desired amount of funding, the purpose of the funds, and the activities they will be involved in, while corporate users enter the purpose of their donation, a message, and their donation policy. The input at this stage is text data based on a designated input form.

[0081] Step 2:

[0082] The terminal receives information entered by the user and performs data formatting and conversion. This converts the data into a format that is easier for the server to process. This conversion process includes removing unnecessary whitespace and standardizing the format.

[0083] Step 3:

[0084] The terminal sends the formatted data to the server. The server receives the data and registers it in the database. This registration process involves classifying the information and mapping it appropriately to the fields.

[0085] Step 4:

[0086] The server inputs the registered data into the generative AI model. The generative AI model uses prompts to analyze the user's input and performs data calculations to derive the optimal match. Algorithms such as natural language processing are utilized here.

[0087] Step 5:

[0088] The server receives output from the AI ​​model and generates proposals based on the analysis results. For non-profit organizations, it creates a list of potential fundraising companies and proposals; for corporations, it creates a list of potential recipients and approval stories. This generation stage applies a document generation algorithm based on the output of the AI ​​model.

[0089] Step 6:

[0090] The server sends the generated suggestions to the terminal. The terminal receives them and displays them to the user in an appropriate format. This display includes visual emphasis and user interface optimization. Based on this, each user can decide on their next action.

[0091] (Application Example 1)

[0092] 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."

[0093] Traditionally, the matching process between non-profit organizations and corporations has been inefficient, particularly the donation execution stage, which has been cumbersome. Furthermore, mismatches between donor and beneficiary intentions, as well as a lack of communication during the donation approval process, have been significant challenges. This has resulted in delays in fundraising and missed opportunities.

[0094] 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.

[0095] In this invention, the server includes means for registering fundraising information of non-profit organizations and donation policies of companies in a data aggregation device; means for analyzing the information of non-profit organizations and companies using a generated machine learning model to identify the optimal matching pair; and means for providing the generated proposal content via the user's display device and enabling donations to be made using electronic payment functions. This enables optimal donation proposals and immediate execution.

[0096] "Funding information for non-profit organizations" refers to information about the specific amount of funds a non-profit organization needs, how those funds will be used, and the activities it undertakes.

[0097] A "corporate donation policy" refers to information about a company's purpose for making donations, the message it wants to convey, and its basic policies regarding donations.

[0098] A "data collection device" is a device for collecting, systematically storing, and managing information provided by non-profit organizations and companies.

[0099] A "generated machine learning model" is a computer model built on algorithms that analyze information from non-profit organizations and businesses to identify the best matching pairs.

[0100] "User display device" refers to the screen of a digital device that allows users of non-profit organizations and companies to view and confirm matching proposals and results.

[0101] The "electronic payment function" is a function that provides digital payment methods to complete donations online safely and quickly.

[0102] In the system implementing this invention, a server plays a central role. The server runs a program that stores information on non-profit organizations and companies in a data aggregation device, and registers fundraising information and donation policies entered by users.

[0103] The server uses a generated machine learning model to analyze the registered information and identify appropriate matching pairs. This machine learning model incorporates natural language processing techniques, enabling a detailed analysis of the activities of non-profit organizations and the donation policies of corporations. Based on the identified matches, the server further generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations.

[0104] The generated proposals are delivered via the user's device. Users can view this information on their device and take specific actions based on the proposals. The server also has an electronic payment function to help users make donations quickly and securely once a match is made. This payment function uses the Stripe API.

[0105] For example, if a non-profit organization engaged in environmental protection activities needs 2 million yen for a reforestation project, the user enters this information into the terminal, and the server performs optimal matching with a company focused on clean energy and generates an explanation for the donation approval for that company. This allows the company to easily complete the donation through electronic payment within the application.

[0106] Example prompt for a generative AI model: "Please match companies that support environmental protection activities with non-profit organizations that are advancing new reforestation projects."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server receives information from non-profit organizations and corporations and registers it in the data aggregation device. Input from non-profit organizations includes the amount of funding, its use, and activities, while input from corporations includes the purpose of donations, messages, and basic policies. This information is stored in a structured format in the database.

[0110] Step 2:

[0111] The server activates a generated AI model and analyzes the registered information. The input is information on non-profit organizations and companies stored in a database, and the output is a list of optimal matching pairs. Natural language processing techniques are used for data analysis to evaluate the degree of agreement between activities and donation policies.

[0112] Step 3:

[0113] Based on the analysis results, the server generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations. The input is a list of matching pairs obtained in step 2, and the output is a customized document provided to each user. The generated content utilizes an AI model's automated text generation function.

[0114] Step 4:

[0115] The terminal presents the generated proposal to the user. The user's terminal has a function to display documents sent from the server, and the user makes a decision by reviewing them. The input is a document generated from the server, and the output is visual information that supports the user's decision-making process.

[0116] Step 5:

[0117] The server facilitates the electronic payment process. Once a corporate user approves a donation, the electronic payment process is initiated via a terminal. Inputs include the corporate user's approval instruction and the donation amount, while output is a confirmation notice certifying the completion of the donation. This payment process utilizes the Stripe API.

[0118] 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.

[0119] This invention is a system for forming effective connections between non-profit organizations and businesses, aiming for even greater accuracy and satisfaction in matching by incorporating emotion recognition technology. This system is equipped with an emotion engine that analyzes emotions based on user input and feedback.

[0120] First, non-profit organizations, as users, enter their desired fundraising amount, purpose, and activities into the terminal. Similarly, companies, as users, enter their donation purpose and desired message into the terminal. This data is then transmitted to the server.

[0121] The server not only registers information collected from non-profit organizations and businesses into a database, but also uses an emotion engine to analyze the emotions contained in the input information. This data includes emotional information estimated from the nuances and tone of the text entered by the user. The data is also stored as emotion analysis data.

[0122] Subsequently, the server uses a generative AI model to analyze the registered information and emotional data in a unified manner. This allows for a deeper understanding of the intentions and desires of non-profit organizations and corporations, and the selection of the most suitable matching pairs. Based on the selected matching pairs, the server generates proposals for non-profit organizations and approval stories for corporations, taking emotional elements into consideration.

[0123] The device displays the generated proposal along with feedback from the emotional engine. This allows non-profit organizations to effectively conduct fundraising activities while confirming emotional alignment with the proposed companies. Companies can quickly make decisions regarding recipient selection based on the received proposals and emotional feedback.

[0124] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs emotionally charged statements emphasizing the importance of the project into a terminal. The server analyzes these statements and matches the organization with companies that have a strong interest in local education and similar emotional orientations. In this way, collaborative relationships that increase the acceptance of proposals become possible.

[0125] Therefore, the system of the present invention utilizes emotion recognition technology to evolve conventional matching and promote effective cooperation between non-profit organizations and businesses.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] Nonprofit organizations, acting as users, input information necessary for fundraising, specific activities, and the emotions behind those activities through their devices. This data is then transmitted to the server.

[0129] Step 2:

[0130] The user company enters the purpose of the donation and the message they wish to convey from their terminal, and also clearly states the emotional intent behind it. This information is then sent to the server.

[0131] Step 3:

[0132] The server registers the information of non-profit organizations and companies it receives into a database, and uses a sentiment engine to analyze the emotional elements in the text and generate sentiment metadata.

[0133] Step 4:

[0134] The server uses registered data along with the generated sentiment metadata to analyze it through a generative AI model. This analysis evaluates the degree of emotional alignment and purpose alignment between non-profit organizations and companies, and determines the most suitable matching pair.

[0135] Step 5:

[0136] Based on the matching results, the server generates proposals for non-profit organizations to companies, and lists of non-profit organizations and approval stories for companies. This generation process reflects the content of sentiment data.

[0137] Step 6:

[0138] The device displays the generated suggestions along with associated emotional feedback to the user. This allows the user to consider their next action based on the emotional data.

[0139] Step 7:

[0140] Users make decisions based on the information displayed and emotional insights. Nonprofit organizations attempt emotional approaches to proposed companies, and companies also consider emotional information when selecting recipients for donations.

[0141] Thus, the system of the present invention utilizes emotion recognition technology to provide a richer matching experience.

[0142] (Example 2)

[0143] 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".

[0144] Achieving effective matching between non-profit organizations and corporations is a challenging task due to differences in their needs and values. Traditional methods often rely on superficial data matching, neglecting deeper factors such as emotions and intentions, resulting in limitations in matching accuracy and satisfaction. To address this problem, a system is needed that takes into account the emotions and values ​​of both non-profit organizations and corporations, enabling more precise matching.

[0145] 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.

[0146] This invention includes a server that records non-profit organization fundraising data and company donation policies, a server that analyzes the non-profit organization and company data using a generated machine learning model and selects the optimal matching pair, and a server that estimates emotional data from the data input using sentiment analysis technology and reflects it in the matching. This enables highly accurate matching that takes emotions and values ​​into consideration.

[0147] A "non-profit organization" is a legal entity or organization that operates for specific social or educational purposes and does not aim to make a profit.

[0148] A "company" is a legal entity that has a specific business purpose and engages in legally recognized profit-making activities.

[0149] "Funding data" refers to information about the amount and use of financial support that non-profit organizations need for their activities.

[0150] A "donation policy" is a set of guidelines outlining the criteria and objectives for a company to provide funds, goods, or other resources to non-profit organizations.

[0151] "Means of recording" refers to the processes and techniques for storing data electronically or on physical media.

[0152] A "machine learning model" is an algorithm or structure that allows a computer to learn patterns from data and perform predictions or classifications according to a specific purpose.

[0153] "Means of analyzing data" refers to the processes and techniques used to classify information based on collected data, identify patterns, and derive useful conclusions.

[0154] "Emotional analysis technology" is a technology that analyzes and understands the emotions and intentions of users from text and conversational data.

[0155] "Emotional data" refers to information about the emotions and values ​​held by non-profit organizations and companies.

[0156] A "terminal device" refers to an electronic device used by users to input information or view outputted information.

[0157] A "user" is an individual or organization that operates the system and provides or receives information according to its purpose.

[0158] "Generated proposals" refer to documents and information containing specific details that the system creates based on its analysis results.

[0159] This system was developed to facilitate effective matching between non-profit organizations and corporations, and it combines emotion recognition technology with generative AI models. The main software used includes a "generative AI model" that supports machine learning algorithms and an "emotion analysis engine" that performs data analysis. The following describes the operation of this system in detail.

[0160] Nonprofit organizations, as users, use terminals to enter their fundraising objectives, desired amount, and detailed activity descriptions. Similarly, corporate users also use terminals to enter their donation policies, expected outcomes, and messages. All of this input data is transmitted to the server.

[0161] The server registers the received information in a database and uses an emotion analysis engine to analyze the emotional elements of the input text. This analysis extracts emotional data such as passion and a sense of social responsibility from expressions like "I want to help children in need." This emotional data forms a crucial foundation for the next steps.

[0162] The server then uses a generative AI model to comprehensively analyze the registration information and sentiment data of non-profit organizations and companies. Based on this analysis, the matching pairs with the best combinations are selected. According to the selection results, the server generates sentiment-inclusive proposals for non-profit organizations and provides approval stories along with a list of recipient organizations for companies.

[0163] These proposals and emotional feedback are displayed via the terminal, allowing both non-profit organizations and companies to confirm their emotional compatibility. The system can generate even more refined proposals by using prompts such as, for example, "How can we attract companies to our children's education support project?"

[0164] Thus, this invention enables non-profit organizations and companies to effectively build cooperative relationships while confirming emotional compatibility.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] Users enter their non-profit organization's fundraising objectives, desired amount, and activities via their device. Corporate users similarly enter their donation objectives and expected message. The entered information is sent from the device to the server. The input here is in text format and includes details of activities and donation policies. This creates the initial dataset.

[0168] Step 2:

[0169] The server registers the received information in a dedicated database. Next, the sentiment analysis engine starts up and analyzes the emotional elements from the registered text. In this process, the nuances of emotion are extracted from the input words and phrases, the linguistic tone is determined, and sentiment data is generated. For example, the expression "urgent funding is needed" is analyzed to produce the emotion of "urgency," which is then stored as sentiment data.

[0170] Step 3:

[0171] The server uses a generative AI model to integrate and analyze information and sentiment data from non-profit organizations and businesses stored in a database. Natural language processing techniques are employed to gain a deep understanding of the needs and intentions of both parties. The analysis outputs a list of the most suitable matching pairs. This list will be used in subsequent implementation phases and to generate proposals.

[0172] Step 4:

[0173] Based on the selected matching pairs, the server generates emotionally charged proposals for non-profit organizations and lists of recipients and approval stories for corporations. In this step, a generative AI model is used to automatically construct documents that evoke emotion and empathy using prompt sentences.

[0174] Step 5:

[0175] The terminal displays the generated proposal and emotional feedback to the user. Nonprofit organization representatives use this information to evaluate the possibility of collaboration with companies, and company representatives review the proposals to approve donations. The displayed information is important for confirming the emotional compatibility between the selected nonprofit organization and the company.

[0176] This process enables systematic and emotionally consistent matching.

[0177] (Application Example 2)

[0178] 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".

[0179] Traditionally, matching non-profit organizations with corporations for fundraising and donations has relied solely on the matching of information, without considering emotional aspects, often resulting in unsatisfactory outcomes for both parties. Furthermore, the lack of real-time visitor sentiment analysis has made it difficult to provide safe and appropriate support.

[0180] 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.

[0181] In this invention, the server includes means for registering fundraising information of non-profit organizations and donation policies of companies in an information storage device; means for analyzing the information of non-profit organizations and companies using a generated artificial intelligence model to identify the optimal pair of responders; and means for generating proposal documents for non-profit organizations and lists of recipients and approval narratives for companies based on the analyzed information. This makes it possible to analyze the emotional state of visitors in real time by utilizing sentiment analysis technology, determine the level of alert, and provide appropriate countermeasures.

[0182] "Funding information" refers to information about the amount of funds a non-profit organization needs and how those funds will be used.

[0183] A "donation policy" is information that outlines a company's policies and intentions regarding the purpose and criteria by which it makes donations.

[0184] An "information storage device" is an electronic device or system used to store data and make it available for retrieval as needed.

[0185] An "artificial intelligence model" is a computer program designed to perform complex calculations based on learned data and to carry out specific tasks.

[0186] A "matching pair" is a pair of a non-profit organization and a company that have been optimally matched based on the objectives and intentions of both parties.

[0187] A "proposal document" is a document created by a non-profit organization to explain the significance of providing funding to a company and to request their cooperation.

[0188] The "List of Donation Recipients" is a list of non-profit organizations that companies are considering as potential recipients of donations.

[0189] An "approval narrative" is a background explanation or story used by a company to facilitate its internal approval process when making a donation.

[0190] "Emotion analysis technology" is a technology that estimates human emotions by analyzing voice, facial expressions, and nuances in documents.

[0191] The "alert level" is a standard used to determine whether a visitor is safe and serves as an indicator for deciding on security measures.

[0192] The system that implements this application employs advanced technology to facilitate effective matching between non-profit organizations and corporations. In this system, non-profit organizations input fundraising information into a terminal, and this data is sent to a server. Similarly, corporations input their donation policies into a terminal and send them to the server.

[0193] The server organizes and registers this data in an information storage device. Next, an artificial intelligence model is used to analyze this data in detail and identify appropriate recipient groups. By also using sentiment analysis technology, the emotional state of visitors is analyzed in real time, and from the obtained data, a document proposing the most suitable donation destination, a list of donation recipients for the company, and an approval narrative are generated.

[0194] Furthermore, the analyzed recommendations are presented visually via the user's display device. This enables non-profit organizations and businesses to make more informed decisions by taking emotional factors into consideration.

[0195] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs information into a terminal that emotionally expresses the importance of the project. The server analyzes this information and matches it with companies that show a high level of interest. At the same time, companies are provided with the necessary narratives to consider donating, supporting smooth decision-making.

[0196] A concrete example of a prompt would be, "Analyze the visitor's emotions from their voice and facial expressions, and generate responses that will help the visitor relax." This allows the generating AI model to analyze the information and provide useful feedback to the user.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The device receives fundraising information and donation policies entered by user non-profit organizations and corporations. The entered information is stored within the device as string data. This allows the user's needs and objectives to be concretely visualized.

[0200] Step 2:

[0201] The server registers data from non-profit organizations and companies transmitted from terminals into an information storage device. The registered data is then converted into an efficient database structure that facilitates later searching and analysis, making it easily accessible.

[0202] Step 3:

[0203] The server applies a generative AI model to the registered non-profit organization and company information to identify appropriate partner pairs. In this process, the AI ​​model analyzes the data, considering the contextual information of each entry, and generates a quantified evaluation score. This helps discover the optimal combination.

[0204] Step 4:

[0205] The server uses sentiment analysis technology to analyze the visitor's emotional state in real time. It takes audio and video data as input, applies a sentiment analysis algorithm, and outputs numerical data representing the emotional state. This data provides information to determine whether the response is appropriate.

[0206] Step 5:

[0207] The server generates proposal documents for non-profit organizations and lists of recipients and approval narratives for corporations based on the analyzed information. This step utilizes automated text generation technology with a generative AI model. The final output is documented in a user-friendly format.

[0208] Step 6:

[0209] The terminal visually displays the generated proposals and analysis results to the user. The displayed information serves as supplementary material for the user's decision-making and helps in evaluating each proposal.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] [Second Embodiment]

[0214] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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".

[0226] This invention is a system that enables efficient matching between non-profit organizations and businesses. This system operates by users inputting data through a terminal.

[0227] First, non-profit organizations, as users, use a terminal to input the desired amount of funds, their specific use, and their activities when seeking funding. This registers the non-profit organization's information in the system. Meanwhile, companies, as users, similarly register their information by inputting the purpose of their donation, the message they wish to convey, and their basic donation policy using a terminal.

[0228] After storing this information in a database, the server uses a generative AI model to analyze the information of non-profit organizations and companies. This analysis searches for and identifies the most suitable matching pairs. Based on the identified matching pairs, the server generates a list of candidate companies to propose as funding sources for non-profit organizations, along with detailed proposals. For companies, it generates a list of non-profit organizations to consider donating to, along with a story to help them obtain approval for the donation.

[0229] The generated proposals are provided to each user via their device. This allows non-profit organizations to effectively carry out fundraising activities tailored to the proposed companies. Meanwhile, companies can use the provided information to select recipients and streamline their internal approval processes.

[0230] As a concrete example, if a non-profit organization supporting children needs 1 million yen in funding for a new program, the user enters this information into a terminal, and the server considers this information and matches them with companies interested in local activities. This process allows both the non-profit organization and the company to build a collaborative relationship that aligns with their objectives.

[0231] As a result, the system of the present invention promotes social contribution activities and improves the efficiency of fundraising.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] Nonprofit organizations, as users, use a terminal to enter information about their fundraising needs. This includes the desired fundraising amount, the intended use of the funds, and details of their activities. Once the information is entered, the data is sent to the server.

[0235] Step 2:

[0236] Corporate users enter donation-related information through their terminals. This includes the purpose of the donation, the message the company wants to convey, and their donation policy. This information is also sent to the server.

[0237] Step 3:

[0238] The server registers the information received from both users into a database. The registered data is used in the matching process.

[0239] Step 4:

[0240] The server uses a generative AI model to analyze the information in the database. Based on the goals and aspirations of non-profit organizations and businesses, it applies a matching algorithm to find the most suitable combination.

[0241] Step 5:

[0242] Based on the analysis results, the server generates fundraising proposals and lists of potential companies for non-profit organizations, and lists of non-profit organizations as recipients of donations and approval stories for companies.

[0243] Step 6:

[0244] The terminal displays the generated suggestions received from the server to the user. This allows the user to obtain information to consider each step of the process.

[0245] Step 7:

[0246] Users take necessary actions based on the matching results. Nonprofit organizations approach the proposed companies, and companies consider donating to the proposed nonprofit organizations.

[0247] In this way, the system of the present invention enables effective cooperation between non-profit organizations and businesses.

[0248] (Example 1)

[0249] 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."

[0250] The challenge lies in providing a system that can address the difficulties in fundraising due to a lack of efficient matching between non-profit organizations and corporations, as well as the difficulties in effectively distributing donations, thereby facilitating the smooth operation of both parties.

[0251] 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.

[0252] This invention includes a server that receives funding request information and donation policy information from users and registers it in an information processing device; a server that uses an artificial intelligence model generated by the data processing device to analyze the registered information and derive the best match; and a server that generates a proposal document for fundraisers and a list of potential recipients and approval documents for donors based on the matching results. This enables smooth fundraising and donations for non-profit organizations and corporations.

[0253] A "user" is a person or organization, such as a non-profit organization or a company, that intends to use this system to conduct fundraising or donation processes.

[0254] "Fundraising request information" refers to information that includes details such as the amount of money a non-profit organization needs to raise, the purpose of the funds, and the activities it will undertake.

[0255] "Donation policy information" refers to information that includes the purpose of a company's donation, the basic philosophy related to the donation, and the message it wishes to convey.

[0256] An "information processing device" is a device that has the function of registering and managing data received from users and communicating data with other devices.

[0257] An "artificial intelligence model" is a system equipped with algorithms that use machine learning and data analysis techniques to analyze information from non-profit organizations and companies and guide them toward the optimal match.

[0258] "Natural language processing technology" refers to computer science techniques used to analyze text data and understand its meaning and context.

[0259] "Response information" refers to information including feedback provided by users, as well as evaluations and opinions on proposed content.

[0260] This system is designed to facilitate efficient matching between non-profit organizations and businesses. Its main components include servers, terminals, generative AI models, and natural language processing technology. A specific implementation is described below.

[0261] Nonprofit organizations and businesses, as users, access the system through their terminals. Nonprofit users enter information such as the desired amount of funding, the specific use of the funds, and the activities they will undertake. Business users enter information such as the purpose of their donation, the message they wish to convey, and their basic donation policy. This information is formatted by the terminal and sent to the server.

[0262] The server registers the received information in the information processing device and stores it in the database. Based on this registered information, the server uses a generative AI model to perform analysis. The generative AI model uses natural language processing technology to analyze in detail the activities of non-profit organizations and the donation policies of companies, leading to the optimal match.

[0263] The analyzed results are stored on a server, and then proposals based on the best match are generated. Nonprofit organizations are provided with a list of potential corporate funding sources and proposals, while corporate users are provided with a list of potential recipients and the stories necessary for donation approval. These proposals are presented to users via their devices, enabling efficient matching and collaboration between both parties.

[0264] For example, if a non-profit organization that provides educational support for children needs 1 million yen in funding for a new program, they can input this information into a terminal, and the server will analyze the data and match them with companies interested in contributing to the local community.

[0265] An example prompt might be, "Find companies interested in community activities to fund a new educational program." Based on this prompt, the generating AI model optimizes the matching process. This allows the system to provide meaningful matches for both non-profit organizations and companies, supporting the promotion of social contribution activities.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] Users access the system using a terminal and enter the required information. Nonprofit organization users enter the desired amount of funding, the purpose of the funds, and the activities they will be involved in, while corporate users enter the purpose of their donation, a message, and their donation policy. The input at this stage is text data based on a designated input form.

[0269] Step 2:

[0270] The terminal receives information entered by the user and performs data formatting and conversion. This converts the data into a format that is easier for the server to process. This conversion process includes removing unnecessary whitespace and standardizing the format.

[0271] Step 3:

[0272] The terminal sends the formatted data to the server. The server receives the data and registers it in the database. This registration process involves classifying the information and mapping it appropriately to the fields.

[0273] Step 4:

[0274] The server inputs the registered data into the generative AI model. The generative AI model uses prompts to analyze the user's input and performs data calculations to derive the optimal match. Algorithms such as natural language processing are utilized here.

[0275] Step 5:

[0276] The server receives output from the AI ​​model and generates proposals based on the analysis results. For non-profit organizations, it creates a list of potential fundraising companies and proposals; for corporations, it creates a list of potential recipients and approval stories. This generation stage applies a document generation algorithm based on the output of the AI ​​model.

[0277] Step 6:

[0278] The server sends the generated suggestions to the terminal. The terminal receives them and displays them to the user in an appropriate format. This display includes visual emphasis and user interface optimization. Based on this, each user can decide on their next action.

[0279] (Application Example 1)

[0280] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0281] Traditionally, the matching process between non-profit organizations and corporations has been inefficient, particularly the donation execution stage, which has been cumbersome. Furthermore, mismatches between donor and beneficiary intentions, as well as a lack of communication during the donation approval process, have been significant challenges. This has resulted in delays in fundraising and missed opportunities.

[0282] 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.

[0283] In this invention, the server includes means for registering the fundraising information of non-profit organizations and the donation policies of enterprises in a data integration device, means for analyzing the information of non-profit organizations and enterprises using the generated machine learning model to identify optimal matching pairs, and means for providing the generated proposed content via the user's display device and enabling donations by utilizing an electronic payment function. As a result, optimal donation proposals and immediate execution become possible.

[0284] The "fundraising information of non-profit organizations" refers to information regarding the specific amounts and uses for which non-profit organizations need funds, as well as information about their activities.

[0285] The "donation policies of enterprises" refers to information indicating the purposes when enterprises make donations, the messages they want to convey, and the basic policies regarding donations.

[0286] The "data integration device" is a device for collecting the information provided by non-profit organizations and enterprises and storing and managing it systematically.

[0287] The "generated machine learning model" is a computer model constructed based on an algorithm for analyzing the information of non-profit organizations and enterprises to identify optimal matching pairs.

[0288] The "user's display device" refers to the screen of a digital device through which users of non-profit organizations and enterprises can view and confirm the proposed content and results of matching.

[0289] The "electronic payment function" is a function that provides digital payment means for securely and quickly completing the execution of donations online.

[0290] In the system for implementing this invention, the server plays a central role. The server runs a program for storing the information of non-profit organizations and enterprises in a data integration device, and the fundraising information and donation policies input by the user are registered.

[0291] The server uses a generated machine learning model to analyze the registered information and identify appropriate matching pairs. This machine learning model incorporates natural language processing techniques, enabling a detailed analysis of the activities of non-profit organizations and the donation policies of corporations. Based on the identified matches, the server further generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations.

[0292] The generated proposals are delivered via the user's device. Users can view this information on their device and take specific actions based on the proposals. The server also has an electronic payment function to help users make donations quickly and securely once a match is made. This payment function uses the Stripe API.

[0293] For example, if a non-profit organization engaged in environmental protection activities needs 2 million yen for a reforestation project, the user enters this information into the terminal, and the server performs optimal matching with a company focused on clean energy and generates an explanation for the donation approval for that company. This allows the company to easily complete the donation through electronic payment within the application.

[0294] Example prompt for a generative AI model: "Please match companies that support environmental protection activities with non-profit organizations that are advancing new reforestation projects."

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The server receives information from non-profit organizations and corporations and registers it in the data aggregation device. Input from non-profit organizations includes the amount of funding, its use, and activities, while input from corporations includes the purpose of donations, messages, and basic policies. This information is stored in a structured format in the database.

[0298] Step 2:

[0299] The server activates a generated AI model and analyzes the registered information. The input is information on non-profit organizations and companies stored in a database, and the output is a list of optimal matching pairs. Natural language processing techniques are used for data analysis to evaluate the degree of agreement between activities and donation policies.

[0300] Step 3:

[0301] Based on the analysis results, the server generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations. The input is a list of matching pairs obtained in step 2, and the output is a customized document provided to each user. The generated content utilizes an AI model's automated text generation function.

[0302] Step 4:

[0303] The terminal presents the generated proposal to the user. The user's terminal has a function to display documents sent from the server, and the user makes a decision by reviewing them. The input is a document generated from the server, and the output is visual information that supports the user's decision-making process.

[0304] Step 5:

[0305] The server facilitates the electronic payment process. Once a corporate user approves a donation, the electronic payment process is initiated via a terminal. Inputs include the corporate user's approval instruction and the donation amount, while output is a confirmation notice certifying the completion of the donation. This payment process utilizes the Stripe API.

[0306] 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.

[0307] The present invention is a system that forms an effective connection between non-profit organizations and enterprises, aiming for more accurate and satisfactory matching by incorporating emotion recognition technology. This system includes an emotion engine that analyzes emotions based on user input and feedback.

[0308] First, the non-profit organization, which is the user, inputs the desired amount and purpose of fundraising, as well as the details of its activities, into the terminal. Also, the enterprise, which is the user, inputs the purpose of donation and the desired message into the terminal. As a result, the necessary data is transmitted to the server.

[0309] The server not only registers the information collected from non-profit organizations and enterprises in the database but also analyzes the emotions in the input information using the emotion engine. This data includes emotion information estimated from the nuances and tones of the text input by the users. The data is also saved as emotion analysis data.

[0310] After that, the server uses the generated AI model to analyze the registered information and emotion data together. This enables a deeper understanding of the intentions and hopes of non-profit organizations and enterprises, and selects the most suitable matching pairs. Based on the selected matching pairs, the server generates a proposal letter for the non-profit organization and an approval story for the enterprise while taking emotional elements into consideration.

[0311] The terminal displays the generated proposal content along with feedback from the emotion engine to the user. This allows the non-profit organization to effectively carry out fundraising activities while confirming the emotional compatibility with the proposed enterprise. The enterprise can quickly make a decision on the selection of the donation recipient based on the received proposal letter and emotional feedback.

[0312] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs emotionally charged statements emphasizing the importance of the project into a terminal. The server analyzes these statements and matches the organization with companies that have a strong interest in local education and similar emotional orientations. In this way, collaborative relationships that increase the acceptance of proposals become possible.

[0313] Therefore, the system of the present invention utilizes emotion recognition technology to evolve conventional matching and promote effective cooperation between non-profit organizations and businesses.

[0314] The following describes the processing flow.

[0315] Step 1:

[0316] Nonprofit organizations, acting as users, input information necessary for fundraising, specific activities, and the emotions behind those activities through their devices. This data is then transmitted to the server.

[0317] Step 2:

[0318] The user company enters the purpose of the donation and the message they wish to convey from their terminal, and also clearly states the emotional intent behind it. This information is then sent to the server.

[0319] Step 3:

[0320] The server registers the information of non-profit organizations and companies it receives into a database, and uses a sentiment engine to analyze the emotional elements in the text and generate sentiment metadata.

[0321] Step 4:

[0322] The server uses registered data along with the generated sentiment metadata to analyze it through a generative AI model. This analysis evaluates the degree of emotional alignment and purpose alignment between non-profit organizations and companies, and determines the most suitable matching pair.

[0323] Step 5:

[0324] Based on the matching results, the server generates proposals for non-profit organizations to companies, and lists of non-profit organizations and approval stories for companies. This generation process reflects the content of sentiment data.

[0325] Step 6:

[0326] The device displays the generated suggestions and associated emotional feedback to the user. This allows the user to consider their next action based on the emotional data.

[0327] Step 7:

[0328] Users make decisions based on the information displayed and emotional insights. Nonprofit organizations attempt emotional approaches to proposed companies, and companies also consider emotional information when selecting recipients for donations.

[0329] Thus, the system of the present invention utilizes emotion recognition technology to provide a richer matching experience.

[0330] (Example 2)

[0331] 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".

[0332] Achieving effective matching between non-profit organizations and corporations is a challenging task due to differences in their needs and values. Traditional methods often rely on superficial data matching, neglecting deeper factors such as emotions and intentions, resulting in limitations in matching accuracy and satisfaction. To address this problem, a system is needed that takes into account the emotions and values ​​of both non-profit organizations and corporations, enabling more precise matching.

[0333] 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.

[0334] This invention includes a server that records non-profit organization fundraising data and company donation policies, a server that analyzes the non-profit organization and company data using a generated machine learning model and selects the optimal matching pair, and a server that estimates emotional data from the data input using sentiment analysis technology and reflects it in the matching. This enables highly accurate matching that takes emotions and values ​​into consideration.

[0335] A "non-profit organization" is a legal entity or organization that operates for specific social or educational purposes and does not aim to make a profit.

[0336] A "company" is a legal entity that has a specific business purpose and engages in legally recognized profit-making activities.

[0337] "Funding data" refers to information about the amount and use of financial support that non-profit organizations need for their activities.

[0338] A "donation policy" is a set of guidelines outlining the criteria and objectives for a company to provide funds, goods, or other resources to non-profit organizations.

[0339] "Means of recording" refers to the processes and techniques for storing data electronically or on physical media.

[0340] A "machine learning model" is an algorithm or structure that allows a computer to learn patterns from data and perform predictions or classifications according to a specific purpose.

[0341] "Means of analyzing data" refers to the processes and techniques used to classify information based on collected data, identify patterns, and derive useful conclusions.

[0342] "Emotional analysis technology" is a technology that analyzes and understands the emotions and intentions of users from text and conversational data.

[0343] "Emotional data" refers to information about the emotions and values ​​held by non-profit organizations and companies.

[0344] A "terminal device" refers to an electronic device used by users to input information or view outputted information.

[0345] A "user" is an individual or organization that operates the system and provides or receives information according to its purpose.

[0346] "Generated proposals" refer to documents and information containing specific details that the system creates based on its analysis results.

[0347] This system was developed to facilitate effective matching between non-profit organizations and corporations, and it combines emotion recognition technology with generative AI models. The main software used includes a "generative AI model" that supports machine learning algorithms and an "emotion analysis engine" that performs data analysis. The following describes the operation of this system in detail.

[0348] Nonprofit organizations, as users, use terminals to enter their fundraising objectives, desired amount, and detailed activity descriptions. Similarly, corporate users also use terminals to enter their donation policies, expected outcomes, and messages. All of this input data is transmitted to the server.

[0349] The server registers the received information in a database and uses an emotion analysis engine to analyze the emotional elements of the input text. This analysis extracts emotional data such as passion and a sense of social responsibility from expressions like "I want to help children in need." This emotional data forms a crucial foundation for the next steps.

[0350] The server then uses a generative AI model to comprehensively analyze the registration information and sentiment data of non-profit organizations and companies. Based on this analysis, the matching pairs with the best combinations are selected. According to the selection results, the server generates sentiment-inclusive proposals for non-profit organizations and provides approval stories along with a list of recipient organizations for companies.

[0351] These proposals and emotional feedback are displayed via the terminal, allowing both non-profit organizations and companies to confirm their emotional compatibility. The system can generate even more refined proposals by using prompts such as, for example, "How can we attract companies to our children's education support project?"

[0352] Thus, this invention enables non-profit organizations and companies to effectively build cooperative relationships while confirming emotional compatibility.

[0353] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0354] Step 1:

[0355] Users enter their non-profit organization's fundraising objectives, desired amount, and activities via their device. Corporate users similarly enter their donation objectives and expected message. The entered information is sent from the device to the server. The input here is in text format and includes details of activities and donation policies. This creates the initial dataset.

[0356] Step 2:

[0357] The server registers the received information in a dedicated database. Next, the sentiment analysis engine starts up and analyzes the emotional elements from the registered text. In this process, the nuances of emotion are extracted from the input words and phrases, the linguistic tone is determined, and sentiment data is generated. For example, the expression "urgent funding is needed" is analyzed to produce the emotion of "urgency," which is then stored as sentiment data.

[0358] Step 3:

[0359] The server uses a generative AI model to integrate and analyze information and sentiment data from non-profit organizations and businesses stored in a database. Natural language processing techniques are employed to gain a deep understanding of the needs and intentions of both parties. The analysis outputs a list of the most suitable matching pairs. This list will be used in subsequent implementation phases and to generate proposals.

[0360] Step 4:

[0361] Based on the selected matching pairs, the server generates emotionally charged proposals for non-profit organizations and lists of recipients and approval stories for corporations. In this step, a generative AI model is used to automatically construct documents that evoke emotion and empathy using prompt sentences.

[0362] Step 5:

[0363] The terminal displays the generated proposal and emotional feedback to the user. Nonprofit organization representatives use this information to evaluate the possibility of collaboration with companies, and company representatives review the proposals to approve donations. The displayed information is important for confirming the emotional compatibility between the selected nonprofit organization and the company.

[0364] This process enables systematic and emotionally consistent matching.

[0365] (Application Example 2)

[0366] 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."

[0367] Traditionally, matching non-profit organizations with corporations for fundraising and donations has relied solely on the matching of information, without considering emotional aspects, often resulting in unsatisfactory outcomes for both parties. Furthermore, the lack of real-time visitor sentiment analysis has made it difficult to provide safe and appropriate support.

[0368] 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.

[0369] In this invention, the server includes means for registering fundraising information of non-profit organizations and donation policies of companies in an information storage device; means for analyzing the information of non-profit organizations and companies using a generated artificial intelligence model to identify the optimal pair of responders; and means for generating proposal documents for non-profit organizations and lists of recipients and approval narratives for companies based on the analyzed information. This makes it possible to analyze the emotional state of visitors in real time by utilizing sentiment analysis technology, determine the level of alert, and provide appropriate countermeasures.

[0370] "Funding information" refers to information about the amount of funds a non-profit organization needs and how those funds will be used.

[0371] A "donation policy" is information that outlines a company's policies and intentions regarding the purpose and criteria by which it makes donations.

[0372] An "information storage device" is an electronic device or system used to store data and make it available for retrieval as needed.

[0373] An "artificial intelligence model" is a computer program designed to perform complex calculations based on learned data and to carry out specific tasks.

[0374] A "matching pair" is a pair of a non-profit organization and a company that have been optimally matched based on the objectives and intentions of both parties.

[0375] A "proposal document" is a document created by a non-profit organization to explain the significance of providing funding to a company and to request their cooperation.

[0376] The "List of Donation Recipients" is a list of non-profit organizations that companies are considering as potential recipients of donations.

[0377] An "approval narrative" is a background explanation or story used by a company to facilitate its internal approval process when making a donation.

[0378] "Emotion analysis technology" is a technology that estimates human emotions by analyzing voice, facial expressions, and nuances in documents.

[0379] The "alert level" is a standard used to determine whether a visitor is safe and serves as an indicator for deciding on security measures.

[0380] The system that implements this application employs advanced technology to facilitate effective matching between non-profit organizations and corporations. In this system, non-profit organizations input fundraising information into a terminal, and this data is sent to a server. Similarly, corporations input their donation policies into a terminal and send them to the server.

[0381] The server organizes and registers this data in an information storage device. Next, an artificial intelligence model is used to analyze this data in detail and identify appropriate recipient groups. By also using sentiment analysis technology, the emotional state of visitors is analyzed in real time, and from the obtained data, a document proposing the most suitable donation destination, a list of donation recipients for the company, and an approval narrative are generated.

[0382] Furthermore, the analyzed recommendations are presented visually via the user's display device. This enables non-profit organizations and businesses to make more informed decisions by taking emotional factors into consideration.

[0383] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs information into a terminal that emotionally expresses the importance of the project. The server analyzes this information and matches it with companies that show a high level of interest. At the same time, companies are provided with the necessary narratives to consider donating, supporting smooth decision-making.

[0384] A concrete example of a prompt would be, "Analyze the visitor's emotions from their voice and facial expressions, and generate responses that will help the visitor relax." This allows the generating AI model to analyze the information and provide useful feedback to the user.

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The device receives fundraising information and donation policies entered by user non-profit organizations and corporations. The entered information is stored within the device as string data. This allows the user's needs and objectives to be concretely visualized.

[0388] Step 2:

[0389] The server registers data from non-profit organizations and companies transmitted from terminals into an information storage device. The registered data is then converted into an efficient database structure that facilitates later searching and analysis, making it easily accessible.

[0390] Step 3:

[0391] The server applies a generative AI model to the registered non-profit organization and company information to identify appropriate partner pairs. In this process, the AI ​​model analyzes the data, considering the contextual information of each entry, and generates a quantified evaluation score. This helps discover the optimal combination.

[0392] Step 4:

[0393] The server uses sentiment analysis technology to analyze the visitor's emotional state in real time. It takes audio and video data as input, applies a sentiment analysis algorithm, and outputs numerical data representing the emotional state. This data provides information to determine whether the response is appropriate.

[0394] Step 5:

[0395] The server generates proposal documents for non-profit organizations and lists of recipients and approval narratives for corporations based on the analyzed information. This step utilizes automated text generation technology with a generative AI model. The final output is documented in a user-friendly format.

[0396] Step 6:

[0397] The terminal visually displays the generated proposals and analysis results to the user. The displayed information serves as supplementary material for the user's decision-making and helps in evaluating each proposal.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] [Third Embodiment]

[0402] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0403] 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.

[0404] 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).

[0405] 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.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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".

[0414] This invention is a system that enables efficient matching between non-profit organizations and businesses. This system operates by users inputting data through a terminal.

[0415] First, non-profit organizations, as users, use a terminal to input the desired amount of funds, their specific use, and their activities when seeking funding. This registers the non-profit organization's information in the system. Meanwhile, companies, as users, similarly register their information by inputting the purpose of their donation, the message they wish to convey, and their basic donation policy using a terminal.

[0416] After storing this information in a database, the server uses a generative AI model to analyze the information of non-profit organizations and companies. This analysis searches for and identifies the most suitable matching pairs. Based on the identified matching pairs, the server generates a list of candidate companies to propose as funding sources for non-profit organizations, along with detailed proposals. For companies, it generates a list of non-profit organizations to consider donating to, along with a story to help them obtain approval for the donation.

[0417] The generated proposals are provided to each user via their device. This allows non-profit organizations to effectively carry out fundraising activities tailored to the proposed companies. Meanwhile, companies can use the provided information to select recipients and streamline their internal approval processes.

[0418] As a concrete example, if a non-profit organization supporting children needs 1 million yen in funding for a new program, the user enters this information into a terminal, and the server considers this information and matches them with companies interested in local activities. This process allows both the non-profit organization and the company to build a collaborative relationship that aligns with their objectives.

[0419] As a result, the system of the present invention promotes social contribution activities and improves the efficiency of fundraising.

[0420] The following describes the processing flow.

[0421] Step 1:

[0422] Nonprofit organizations, as users, use a terminal to enter information about their fundraising needs. This includes the desired fundraising amount, the intended use of the funds, and details of their activities. Once the information is entered, the data is sent to the server.

[0423] Step 2:

[0424] Corporate users enter donation-related information through their terminals. This includes the purpose of the donation, the message the company wants to convey, and their donation policy. This information is also sent to the server.

[0425] Step 3:

[0426] The server registers the information received from both users into a database. The registered data is used in the matching process.

[0427] Step 4:

[0428] The server uses a generative AI model to analyze the information in the database. Based on the goals and aspirations of non-profit organizations and businesses, it applies a matching algorithm to find the most suitable combination.

[0429] Step 5:

[0430] Based on the analysis results, the server generates fundraising proposals and lists of potential companies for non-profit organizations, and lists of non-profit organizations as recipients of donations and approval stories for companies.

[0431] Step 6:

[0432] The terminal displays the generated suggestions received from the server to the user. This allows the user to obtain information to consider each step of the process.

[0433] Step 7:

[0434] Users take necessary actions based on the matching results. Nonprofit organizations approach the proposed companies, and companies consider donating to the proposed nonprofit organizations.

[0435] In this way, the system of the present invention enables effective cooperation between non-profit organizations and businesses.

[0436] (Example 1)

[0437] 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."

[0438] The challenge lies in providing a system that can address the difficulties in fundraising due to a lack of efficient matching between non-profit organizations and corporations, as well as the difficulties in effectively distributing donations, thereby facilitating the smooth operation of both parties.

[0439] 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.

[0440] This invention includes a server that receives funding request information and donation policy information from users and registers it in an information processing device; a server that uses an artificial intelligence model generated by the data processing device to analyze the registered information and derive the best match; and a server that generates a proposal document for fundraisers and a list of potential recipients and approval documents for donors based on the matching results. This enables smooth fundraising and donations for non-profit organizations and corporations.

[0441] A "user" is a person or organization, such as a non-profit organization or a company, that intends to use this system to conduct fundraising or donation processes.

[0442] "Fundraising request information" refers to information that includes details such as the amount of money a non-profit organization needs to raise, the purpose of the funds, and the activities it will undertake.

[0443] "Donation policy information" refers to information that includes the purpose of a company's donation, the basic philosophy related to the donation, and the message it wishes to convey.

[0444] An "information processing device" is a device that has the function of registering and managing data received from users and communicating data with other devices.

[0445] An "artificial intelligence model" is a system equipped with algorithms that use machine learning and data analysis techniques to analyze information from non-profit organizations and companies and guide them toward the optimal match.

[0446] "Natural language processing technology" refers to computer science techniques used to analyze text data and understand its meaning and context.

[0447] "Response information" refers to information including feedback provided by users, as well as evaluations and opinions on proposed content.

[0448] This system is designed to facilitate efficient matching between non-profit organizations and businesses. Its main components include servers, terminals, generative AI models, and natural language processing technology. A specific implementation is described below.

[0449] Nonprofit organizations and businesses, as users, access the system through their terminals. Nonprofit users enter information such as the desired amount of funding, the specific use of the funds, and the activities they will undertake. Business users enter information such as the purpose of their donation, the message they wish to convey, and their basic donation policy. This information is formatted by the terminal and sent to the server.

[0450] The server registers the received information in the information processing device and stores it in the database. Based on this registered information, the server uses a generative AI model to perform analysis. The generative AI model uses natural language processing technology to analyze in detail the activities of non-profit organizations and the donation policies of companies, leading to the optimal match.

[0451] The analyzed results are stored on a server, and then proposals based on the best match are generated. Nonprofit organizations are provided with a list of potential corporate funding sources and proposals, while corporate users are provided with a list of potential recipients and the stories necessary for donation approval. These proposals are presented to users via their devices, enabling efficient matching and collaboration between both parties.

[0452] For example, if a non-profit organization that provides educational support for children needs 1 million yen in funding for a new program, they can input this information into a terminal, and the server will analyze the data and match them with companies interested in contributing to the local community.

[0453] An example prompt might be, "Find companies interested in community activities to fund a new educational program." Based on this prompt, the generating AI model optimizes the matching process. This allows the system to provide meaningful matches for both non-profit organizations and companies, supporting the promotion of social contribution activities.

[0454] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0455] Step 1:

[0456] Users access the system using a terminal and enter the required information. Nonprofit organization users enter the desired amount of funding, the purpose of the funds, and the activities they will be involved in, while corporate users enter the purpose of their donation, a message, and their donation policy. The input at this stage is text data based on a designated input form.

[0457] Step 2:

[0458] The terminal receives information entered by the user and performs data formatting and conversion. This converts the data into a format that is easier for the server to process. This conversion process includes removing unnecessary whitespace and standardizing the format.

[0459] Step 3:

[0460] The terminal sends the formatted data to the server. The server receives the data and registers it in the database. This registration process involves classifying the information and mapping it appropriately to the fields.

[0461] Step 4:

[0462] The server inputs the registered data into the generative AI model. The generative AI model uses prompts to analyze the user's input and performs data calculations to derive the optimal match. Algorithms such as natural language processing are utilized here.

[0463] Step 5:

[0464] The server receives output from the AI ​​model and generates proposals based on the analysis results. For non-profit organizations, it creates a list of potential fundraising companies and proposals; for corporations, it creates a list of potential recipients and approval stories. This generation stage applies a document generation algorithm based on the output of the AI ​​model.

[0465] Step 6:

[0466] The server sends the generated suggestions to the terminal. The terminal receives them and displays them to the user in an appropriate format. This display includes visual emphasis and user interface optimization. Based on this, each user can decide on their next action.

[0467] (Application Example 1)

[0468] 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."

[0469] Traditionally, the matching process between non-profit organizations and corporations has been inefficient, particularly the donation execution stage, which has been cumbersome. Furthermore, mismatches between donor and beneficiary intentions, as well as a lack of communication during the donation approval process, have been significant challenges. This has resulted in delays in fundraising and missed opportunities.

[0470] 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.

[0471] In this invention, the server includes means for registering fundraising information of non-profit organizations and donation policies of companies in a data aggregation device; means for analyzing the information of non-profit organizations and companies using a generated machine learning model to identify the optimal matching pair; and means for providing the generated proposal content via the user's display device and enabling donations to be made using electronic payment functions. This enables optimal donation proposals and immediate execution.

[0472] "Funding information for non-profit organizations" refers to information about the specific amount of funds a non-profit organization needs, how those funds will be used, and the activities it undertakes.

[0473] A "corporate donation policy" refers to information about a company's purpose for making donations, the message it wants to convey, and its basic policies regarding donations.

[0474] A "data collection device" is a device for collecting, systematically storing, and managing information provided by non-profit organizations and companies.

[0475] A "generated machine learning model" is a computer model built on algorithms that analyze information from non-profit organizations and businesses to identify the best matching pairs.

[0476] "User display device" refers to the screen of a digital device that allows users of non-profit organizations and companies to view and confirm matching proposals and results.

[0477] The "electronic payment function" is a function that provides digital payment methods to complete donations online safely and quickly.

[0478] In the system implementing this invention, a server plays a central role. The server runs a program that stores information on non-profit organizations and companies in a data aggregation device, and registers fundraising information and donation policies entered by users.

[0479] The server uses a generated machine learning model to analyze the registered information and identify appropriate matching pairs. This machine learning model incorporates natural language processing techniques, enabling a detailed analysis of the activities of non-profit organizations and the donation policies of corporations. Based on the identified matches, the server further generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations.

[0480] The generated proposals are delivered via the user's device. Users can view this information on their device and take specific actions based on the proposals. The server also has an electronic payment function to help users make donations quickly and securely once a match is made. This payment function uses the Stripe API.

[0481] For example, if a non-profit organization engaged in environmental protection activities needs 2 million yen for a reforestation project, the user enters this information into the terminal, and the server performs optimal matching with a company focused on clean energy and generates an explanation for the donation approval for that company. This allows the company to easily complete the donation through electronic payment within the application.

[0482] Example prompt for a generative AI model: "Please match companies that support environmental protection activities with non-profit organizations that are advancing new reforestation projects."

[0483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0484] Step 1:

[0485] The server receives information from non-profit organizations and corporations and registers it in the data aggregation device. Input from non-profit organizations includes the amount of funding, its use, and activities, while input from corporations includes the purpose of donations, messages, and basic policies. This information is stored in a structured format in the database.

[0486] Step 2:

[0487] The server activates a generated AI model and analyzes the registered information. The input is information on non-profit organizations and companies stored in a database, and the output is a list of optimal matching pairs. Natural language processing techniques are used for data analysis to evaluate the degree of agreement between activities and donation policies.

[0488] Step 3:

[0489] Based on the analysis results, the server generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations. The input is a list of matching pairs obtained in step 2, and the output is a customized document provided to each user. The generated content utilizes an AI model's automated text generation function.

[0490] Step 4:

[0491] The terminal presents the generated proposal to the user. The user's terminal has a function to display documents sent from the server, and the user makes a decision by reviewing them. The input is a document generated from the server, and the output is visual information that supports the user's decision-making process.

[0492] Step 5:

[0493] The server facilitates the electronic payment process. Once a corporate user approves a donation, the electronic payment process is initiated via a terminal. Inputs include the corporate user's approval instruction and the donation amount, while output is a confirmation notice certifying the completion of the donation. This payment process utilizes the Stripe API.

[0494] 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.

[0495] This invention is a system for forming effective connections between non-profit organizations and businesses, aiming for even greater accuracy and satisfaction in matching by incorporating emotion recognition technology. This system is equipped with an emotion engine that analyzes emotions based on user input and feedback.

[0496] First, non-profit organizations, as users, enter their desired fundraising amount, purpose, and activities into the terminal. Similarly, companies, as users, enter their donation purpose and desired message into the terminal. This data is then transmitted to the server.

[0497] The server not only registers information collected from non-profit organizations and businesses into a database, but also uses an emotion engine to analyze the emotions contained in the input information. This data includes emotional information estimated from the nuances and tone of the text entered by the user. The data is also stored as emotion analysis data.

[0498] Subsequently, the server uses a generative AI model to analyze the registered information and emotional data in a unified manner. This allows for a deeper understanding of the intentions and desires of non-profit organizations and corporations, and the selection of the most suitable matching pairs. Based on the selected matching pairs, the server generates proposals for non-profit organizations and approval stories for corporations, taking emotional elements into consideration.

[0499] The device displays the generated proposal along with feedback from the emotional engine. This allows non-profit organizations to effectively conduct fundraising activities while confirming emotional alignment with the proposed companies. Companies can quickly make decisions regarding recipient selection based on the received proposals and emotional feedback.

[0500] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs emotionally charged statements emphasizing the importance of the project into a terminal. The server analyzes these statements and matches the organization with companies that have a strong interest in local education and similar emotional orientations. In this way, collaborative relationships that increase the acceptance of proposals become possible.

[0501] Therefore, the system of the present invention utilizes emotion recognition technology to evolve conventional matching and promote effective cooperation between non-profit organizations and businesses.

[0502] The following describes the processing flow.

[0503] Step 1:

[0504] Nonprofit organizations, acting as users, input information necessary for fundraising, specific activities, and the emotions behind those activities through their devices. This data is then transmitted to the server.

[0505] Step 2:

[0506] The user company enters the purpose of the donation and the message they wish to convey from their terminal, and also clearly states the emotional intent behind it. This information is then sent to the server.

[0507] Step 3:

[0508] The server registers the information of non-profit organizations and companies it receives into a database, and uses a sentiment engine to analyze the emotional elements in the text and generate sentiment metadata.

[0509] Step 4:

[0510] The server uses registered data along with the generated sentiment metadata to analyze it through a generative AI model. This analysis evaluates the degree of emotional alignment and purpose alignment between non-profit organizations and companies, and determines the most suitable matching pair.

[0511] Step 5:

[0512] Based on the matching results, the server generates proposals for non-profit organizations to companies, and lists of non-profit organizations and approval stories for companies. This generation process reflects the content of sentiment data.

[0513] Step 6:

[0514] The device displays the generated suggestions and associated emotional feedback to the user. This allows the user to consider their next action based on the emotional data.

[0515] Step 7:

[0516] Users make decisions based on the information displayed and emotional insights. Nonprofit organizations attempt emotional approaches to proposed companies, and companies also consider emotional information when selecting recipients for donations.

[0517] Thus, the system of the present invention utilizes emotion recognition technology to provide a richer matching experience.

[0518] (Example 2)

[0519] 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."

[0520] Achieving effective matching between non-profit organizations and corporations is a challenging task due to differences in their needs and values. Traditional methods often rely on superficial data matching, neglecting deeper factors such as emotions and intentions, resulting in limitations in matching accuracy and satisfaction. To address this problem, a system is needed that takes into account the emotions and values ​​of both non-profit organizations and corporations, enabling more precise matching.

[0521] 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.

[0522] This invention includes a server that records non-profit organization fundraising data and company donation policies, a server that analyzes the non-profit organization and company data using a generated machine learning model and selects the optimal matching pair, and a server that estimates emotional data from the data input using sentiment analysis technology and reflects it in the matching. This enables highly accurate matching that takes emotions and values ​​into consideration.

[0523] A "non-profit organization" is a legal entity or organization that operates for specific social or educational purposes and does not aim to make a profit.

[0524] A "company" is a legal entity that has a specific business purpose and engages in legally recognized profit-making activities.

[0525] "Funding data" refers to information about the amount and use of financial support that non-profit organizations need for their activities.

[0526] A "donation policy" is a set of guidelines outlining the criteria and objectives for a company to provide funds, goods, or other resources to non-profit organizations.

[0527] "Means of recording" refers to the processes and techniques for storing data electronically or on physical media.

[0528] A "machine learning model" is an algorithm or structure that allows a computer to learn patterns from data and perform predictions or classifications according to a specific purpose.

[0529] "Means of analyzing data" refers to the processes and techniques used to classify information based on collected data, identify patterns, and derive useful conclusions.

[0530] "Emotional analysis technology" is a technology that analyzes and understands the emotions and intentions of users from text and conversational data.

[0531] "Emotional data" refers to information about the emotions and values ​​held by non-profit organizations and companies.

[0532] A "terminal device" refers to an electronic device used by users to input information or view outputted information.

[0533] A "user" is an individual or organization that operates the system and provides or receives information according to its purpose.

[0534] "Generated proposals" refer to documents and information containing specific details that the system creates based on its analysis results.

[0535] This system was developed to facilitate effective matching between non-profit organizations and corporations, and it combines emotion recognition technology with generative AI models. The main software used includes a "generative AI model" that supports machine learning algorithms and an "emotion analysis engine" that performs data analysis. The following describes the operation of this system in detail.

[0536] Nonprofit organizations, as users, use terminals to enter their fundraising objectives, desired amount, and detailed activity descriptions. Similarly, corporate users also use terminals to enter their donation policies, expected outcomes, and messages. All of this input data is transmitted to the server.

[0537] The server registers the received information in a database and uses an emotion analysis engine to analyze the emotional elements of the input text. This analysis extracts emotional data such as passion and a sense of social responsibility from expressions like "I want to help children in need." This emotional data forms a crucial foundation for the next steps.

[0538] The server then uses a generative AI model to comprehensively analyze the registration information and sentiment data of non-profit organizations and companies. Based on this analysis, the matching pairs with the best combinations are selected. According to the selection results, the server generates sentiment-inclusive proposals for non-profit organizations and provides approval stories along with a list of recipient organizations for companies.

[0539] These proposals and emotional feedback are displayed via the terminal, allowing both non-profit organizations and companies to confirm their emotional compatibility. The system can generate even more refined proposals by using prompts such as, for example, "How can we attract companies to our children's education support project?"

[0540] Thus, this invention enables non-profit organizations and companies to effectively build cooperative relationships while confirming emotional compatibility.

[0541] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0542] Step 1:

[0543] Users enter their non-profit organization's fundraising objectives, desired amount, and activities via their device. Corporate users similarly enter their donation objectives and expected message. The entered information is sent from the device to the server. The input here is in text format and includes details of activities and donation policies. This creates the initial dataset.

[0544] Step 2:

[0545] The server registers the received information in a dedicated database. Next, the sentiment analysis engine starts up and analyzes the emotional elements from the registered text. In this process, the nuances of emotion are extracted from the input words and phrases, the linguistic tone is determined, and sentiment data is generated. For example, the expression "urgent funding is needed" is analyzed to produce the emotion of "urgency," which is then stored as sentiment data.

[0546] Step 3:

[0547] The server uses a generative AI model to integrate and analyze information and sentiment data from non-profit organizations and businesses stored in a database. Natural language processing techniques are employed to gain a deep understanding of the needs and intentions of both parties. The analysis outputs a list of the most suitable matching pairs. This list will be used in subsequent implementation phases and to generate proposals.

[0548] Step 4:

[0549] Based on the selected matching pairs, the server generates emotionally charged proposals for non-profit organizations and lists of recipients and approval stories for corporations. In this step, a generative AI model is used to automatically construct documents that evoke emotion and empathy using prompt sentences.

[0550] Step 5:

[0551] The terminal displays the generated proposal and emotional feedback to the user. Nonprofit organization representatives use this information to evaluate the possibility of collaboration with companies, and company representatives review the proposals to approve donations. The displayed information is important for confirming the emotional compatibility between the selected nonprofit organization and the company.

[0552] This process enables systematic and emotionally consistent matching.

[0553] (Application Example 2)

[0554] 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."

[0555] Traditionally, matching non-profit organizations with corporations for fundraising and donations has relied solely on the matching of information, without considering emotional aspects, often resulting in unsatisfactory outcomes for both parties. Furthermore, the lack of real-time visitor sentiment analysis has made it difficult to provide safe and appropriate support.

[0556] 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.

[0557] In this invention, the server includes means for registering fundraising information of non-profit organizations and donation policies of companies in an information storage device; means for analyzing the information of non-profit organizations and companies using a generated artificial intelligence model to identify the optimal pair of responders; and means for generating proposal documents for non-profit organizations and lists of recipients and approval narratives for companies based on the analyzed information. This makes it possible to analyze the emotional state of visitors in real time by utilizing sentiment analysis technology, determine the level of alert, and provide appropriate countermeasures.

[0558] "Funding information" refers to information about the amount of funds a non-profit organization needs and how those funds will be used.

[0559] A "donation policy" is information that outlines a company's policies and intentions regarding the purpose and criteria by which it makes donations.

[0560] An "information storage device" is an electronic device or system used to store data and make it available for retrieval as needed.

[0561] An "artificial intelligence model" is a computer program designed to perform complex calculations based on learned data and to carry out specific tasks.

[0562] A "matching pair" is a pair of a non-profit organization and a company that have been optimally matched based on the objectives and intentions of both parties.

[0563] A "proposal document" is a document created by a non-profit organization to explain the significance of providing funding to a company and to request their cooperation.

[0564] The "List of Donation Recipients" is a list of non-profit organizations that companies are considering as potential recipients of donations.

[0565] An "approval narrative" is a background explanation or story used by a company to facilitate its internal approval process when making a donation.

[0566] "Emotion analysis technology" is a technology that estimates human emotions by analyzing voice, facial expressions, and nuances in documents.

[0567] The "alert level" is a standard used to determine whether a visitor is safe and serves as an indicator for deciding on security measures.

[0568] The system that implements this application employs advanced technology to facilitate effective matching between non-profit organizations and corporations. In this system, non-profit organizations input fundraising information into a terminal, and this data is sent to a server. Similarly, corporations input their donation policies into a terminal and send them to the server.

[0569] The server organizes and registers this data in an information storage device. Next, an artificial intelligence model is used to analyze this data in detail and identify appropriate recipient groups. By also using sentiment analysis technology, the emotional state of visitors is analyzed in real time, and from the obtained data, a document proposing the most suitable donation destination, a list of donation recipients for the company, and an approval narrative are generated.

[0570] Furthermore, the analyzed recommendations are presented visually via the user's display device. This enables non-profit organizations and businesses to make more informed decisions by taking emotional factors into consideration.

[0571] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs information into a terminal that emotionally expresses the importance of the project. The server analyzes this information and matches it with companies that show a high level of interest. At the same time, companies are provided with the necessary narratives to consider donating, supporting smooth decision-making.

[0572] A concrete example of a prompt would be, "Analyze the visitor's emotions from their voice and facial expressions, and generate responses that will help the visitor relax." This allows the generating AI model to analyze the information and provide useful feedback to the user.

[0573] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0574] Step 1:

[0575] The device receives fundraising information and donation policies entered by user non-profit organizations and corporations. The entered information is stored within the device as string data. This allows the user's needs and objectives to be concretely visualized.

[0576] Step 2:

[0577] The server registers data from non-profit organizations and companies transmitted from terminals into an information storage device. The registered data is then converted into an efficient database structure that facilitates later searching and analysis, making it easily accessible.

[0578] Step 3:

[0579] The server applies a generative AI model to the registered non-profit organization and company information to identify appropriate partner pairs. In this process, the AI ​​model analyzes the data, considering the contextual information of each entry, and generates a quantified evaluation score. This helps discover the optimal combination.

[0580] Step 4:

[0581] The server uses sentiment analysis technology to analyze the visitor's emotional state in real time. It takes audio and video data as input, applies a sentiment analysis algorithm, and outputs numerical data representing the emotional state. This data provides information to determine whether the response is appropriate.

[0582] Step 5:

[0583] The server generates proposal documents for non-profit organizations and lists of recipients and approval narratives for corporations based on the analyzed information. This step utilizes automated text generation technology with a generative AI model. The final output is documented in a user-friendly format.

[0584] Step 6:

[0585] The terminal visually displays the generated proposals and analysis results to the user. The displayed information serves as supplementary material for the user's decision-making and helps in evaluating each proposal.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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".

[0603] This invention is a system that enables efficient matching between non-profit organizations and businesses. This system operates by users inputting data through a terminal.

[0604] First, non-profit organizations, as users, use a terminal to input the desired amount of funds, their specific use, and their activities when seeking funding. This registers the non-profit organization's information in the system. Meanwhile, companies, as users, similarly register their information by inputting the purpose of their donation, the message they wish to convey, and their basic donation policy using a terminal.

[0605] After storing this information in a database, the server uses a generative AI model to analyze the information of non-profit organizations and companies. This analysis searches for and identifies the most suitable matching pairs. Based on the identified matching pairs, the server generates a list of candidate companies to propose as funding sources for non-profit organizations, along with detailed proposals. For companies, it generates a list of non-profit organizations to consider donating to, along with a story to help them obtain approval for the donation.

[0606] The generated proposals are provided to each user via their device. This allows non-profit organizations to effectively carry out fundraising activities tailored to the proposed companies. Meanwhile, companies can use the provided information to select recipients and streamline their internal approval processes.

[0607] As a concrete example, if a non-profit organization supporting children needs 1 million yen in funding for a new program, the user enters this information into a terminal, and the server considers this information and matches them with companies interested in local activities. This process allows both the non-profit organization and the company to build a collaborative relationship that aligns with their objectives.

[0608] As a result, the system of the present invention promotes social contribution activities and improves the efficiency of fundraising.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] Nonprofit organizations, as users, use a terminal to enter information about their fundraising needs. This includes the desired fundraising amount, the intended use of the funds, and details of their activities. Once the information is entered, the data is sent to the server.

[0612] Step 2:

[0613] Corporate users enter donation-related information through their terminals. This includes the purpose of the donation, the message the company wants to convey, and their donation policy. This information is also sent to the server.

[0614] Step 3:

[0615] The server registers the information received from both users into a database. The registered data is used in the matching process.

[0616] Step 4:

[0617] The server uses a generative AI model to analyze the information in the database. Based on the goals and aspirations of non-profit organizations and businesses, it applies a matching algorithm to find the most suitable combination.

[0618] Step 5:

[0619] Based on the analysis results, the server generates fundraising proposals and lists of potential companies for non-profit organizations, and lists of non-profit organizations as recipients of donations and approval stories for companies.

[0620] Step 6:

[0621] The terminal displays the generated suggestions received from the server to the user. This allows the user to obtain information to consider each step of the process.

[0622] Step 7:

[0623] Users take necessary actions based on the matching results. Nonprofit organizations approach the proposed companies, and companies consider donating to the proposed nonprofit organizations.

[0624] In this way, the system of the present invention enables effective cooperation between non-profit organizations and businesses.

[0625] (Example 1)

[0626] 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".

[0627] The challenge lies in providing a system that can address the difficulties in fundraising due to a lack of efficient matching between non-profit organizations and corporations, as well as the difficulties in effectively distributing donations, thereby facilitating the smooth operation of both parties.

[0628] 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.

[0629] This invention includes a server that receives funding request information and donation policy information from users and registers it in an information processing device; a server that uses an artificial intelligence model generated by the data processing device to analyze the registered information and derive the best match; and a server that generates a proposal document for fundraisers and a list of potential recipients and approval documents for donors based on the matching results. This enables smooth fundraising and donations for non-profit organizations and corporations.

[0630] A "user" is a person or organization, such as a non-profit organization or a company, that intends to use this system to conduct fundraising or donation processes.

[0631] "Fundraising request information" refers to information that includes details such as the amount of money a non-profit organization needs to raise, the purpose of the funds, and the activities it will undertake.

[0632] "Donation policy information" refers to information that includes the purpose of a company's donation, the basic philosophy related to the donation, and the message it wishes to convey.

[0633] An "information processing device" is a device that has the function of registering and managing data received from users and communicating data with other devices.

[0634] An "artificial intelligence model" is a system equipped with algorithms that use machine learning and data analysis techniques to analyze information from non-profit organizations and companies and guide them toward the optimal match.

[0635] "Natural language processing technology" refers to computer science techniques used to analyze text data and understand its meaning and context.

[0636] "Response information" refers to information including feedback provided by users, as well as evaluations and opinions on proposed content.

[0637] This system is designed to facilitate efficient matching between non-profit organizations and businesses. Its main components include servers, terminals, generative AI models, and natural language processing technology. A specific implementation is described below.

[0638] Nonprofit organizations and businesses, as users, access the system through their terminals. Nonprofit users enter information such as the desired amount of funding, the specific use of the funds, and the activities they will undertake. Business users enter information such as the purpose of their donation, the message they wish to convey, and their basic donation policy. This information is formatted by the terminal and sent to the server.

[0639] The server registers the received information in the information processing device and stores it in the database. Based on this registered information, the server uses a generative AI model to perform analysis. The generative AI model uses natural language processing technology to analyze in detail the activities of non-profit organizations and the donation policies of companies, leading to the optimal match.

[0640] The analyzed results are stored on a server, and then proposals based on the best match are generated. Nonprofit organizations are provided with a list of potential corporate funding sources and proposals, while corporate users are provided with a list of potential recipients and the stories necessary for donation approval. These proposals are presented to users via their devices, enabling efficient matching and collaboration between both parties.

[0641] For example, if a non-profit organization that provides educational support for children needs 1 million yen in funding for a new program, they can input this information into a terminal, and the server will analyze the data and match them with companies interested in contributing to the local community.

[0642] An example prompt might be, "Find companies interested in community activities to fund a new educational program." Based on this prompt, the generating AI model optimizes the matching process. This allows the system to provide meaningful matches for both non-profit organizations and companies, supporting the promotion of social contribution activities.

[0643] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0644] Step 1:

[0645] Users access the system using a terminal and enter the required information. Nonprofit organization users enter the desired amount of funding, the purpose of the funds, and the activities they will be involved in, while corporate users enter the purpose of their donation, a message, and their donation policy. The input at this stage is text data based on a designated input form.

[0646] Step 2:

[0647] The terminal receives information entered by the user and performs data formatting and conversion. This converts the data into a format that is easier for the server to process. This conversion process includes removing unnecessary whitespace and standardizing the format.

[0648] Step 3:

[0649] The terminal sends the formatted data to the server. The server receives the data and registers it in the database. This registration process involves classifying the information and mapping it appropriately to the fields.

[0650] Step 4:

[0651] The server inputs the registered data into the generative AI model. The generative AI model uses prompts to analyze the user's input and performs data calculations to derive the optimal match. Algorithms such as natural language processing are utilized here.

[0652] Step 5:

[0653] The server receives output from the AI ​​model and generates proposals based on the analysis results. For non-profit organizations, it creates a list of potential fundraising companies and proposals; for corporations, it creates a list of potential recipients and approval stories. This generation stage applies a document generation algorithm based on the output of the AI ​​model.

[0654] Step 6:

[0655] The server sends the generated suggestions to the terminal. The terminal receives them and displays them to the user in an appropriate format. This display includes visual emphasis and user interface optimization. Based on this, each user can decide on their next action.

[0656] (Application Example 1)

[0657] 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".

[0658] Traditionally, the matching process between non-profit organizations and corporations has been inefficient, particularly the donation execution stage, which has been cumbersome. Furthermore, mismatches between donor and beneficiary intentions, as well as a lack of communication during the donation approval process, have been significant challenges. This has resulted in delays in fundraising and missed opportunities.

[0659] 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.

[0660] In this invention, the server includes means for registering fundraising information of non-profit organizations and donation policies of companies in a data aggregation device; means for analyzing the information of non-profit organizations and companies using a generated machine learning model to identify the optimal matching pair; and means for providing the generated proposal content via the user's display device and enabling donations to be made using electronic payment functions. This enables optimal donation proposals and immediate execution.

[0661] "Funding information for non-profit organizations" refers to information about the specific amount of funds a non-profit organization needs, how those funds will be used, and the activities it undertakes.

[0662] A "corporate donation policy" refers to information about a company's purpose for making donations, the message it wants to convey, and its basic policies regarding donations.

[0663] A "data collection device" is a device for collecting, systematically storing, and managing information provided by non-profit organizations and companies.

[0664] A "generated machine learning model" is a computer model built on algorithms that analyze information from non-profit organizations and businesses to identify the best matching pairs.

[0665] "User display device" refers to the screen of a digital device that allows users of non-profit organizations and companies to view and confirm matching proposals and results.

[0666] The "electronic payment function" is a function that provides digital payment methods to complete donations online safely and quickly.

[0667] In the system implementing this invention, a server plays a central role. The server runs a program that stores information on non-profit organizations and companies in a data aggregation device, and registers fundraising information and donation policies entered by users.

[0668] The server uses a generated machine learning model to analyze the registered information and identify appropriate matching pairs. This machine learning model incorporates natural language processing techniques, enabling a detailed analysis of the activities of non-profit organizations and the donation policies of corporations. Based on the identified matches, the server further generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations.

[0669] The generated proposals are delivered via the user's device. Users can view this information on their device and take specific actions based on the proposals. The server also has an electronic payment function to help users make donations quickly and securely once a match is made. This payment function uses the Stripe API.

[0670] For example, if a non-profit organization engaged in environmental protection activities needs 2 million yen for a reforestation project, the user enters this information into the terminal, and the server performs optimal matching with a company focused on clean energy and generates an explanation for the donation approval for that company. This allows the company to easily complete the donation through electronic payment within the application.

[0671] Example prompt for a generative AI model: "Please match companies that support environmental protection activities with non-profit organizations that are advancing new reforestation projects."

[0672] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0673] Step 1:

[0674] The server receives information from non-profit organizations and corporations and registers it in the data aggregation device. Input from non-profit organizations includes the amount of funding, its use, and activities, while input from corporations includes the purpose of donations, messages, and basic policies. This information is stored in a structured format in the database.

[0675] Step 2:

[0676] The server activates a generated AI model and analyzes the registered information. The input is information on non-profit organizations and companies stored in a database, and the output is a list of optimal matching pairs. Natural language processing techniques are used for data analysis to evaluate the degree of agreement between activities and donation policies.

[0677] Step 3:

[0678] Based on the analysis results, the server generates proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations. The input is a list of matching pairs obtained in step 2, and the output is a customized document provided to each user. The generated content utilizes an AI model's automated text generation function.

[0679] Step 4:

[0680] The terminal presents the generated proposal to the user. The user's terminal has a function to display documents sent from the server, and the user makes a decision by reviewing them. The input is a document generated from the server, and the output is visual information that supports the user's decision-making process.

[0681] Step 5:

[0682] The server facilitates the electronic payment process. Once a corporate user approves a donation, the electronic payment process is initiated via a terminal. Inputs include the corporate user's approval instruction and the donation amount, while output is a confirmation notice certifying the completion of the donation. This payment process utilizes the Stripe API.

[0683] 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.

[0684] This invention is a system for forming effective connections between non-profit organizations and businesses, aiming for even greater accuracy and satisfaction in matching by incorporating emotion recognition technology. This system is equipped with an emotion engine that analyzes emotions based on user input and feedback.

[0685] First, non-profit organizations, as users, enter their desired fundraising amount, purpose, and activities into the terminal. Similarly, companies, as users, enter their donation purpose and desired message into the terminal. This data is then transmitted to the server.

[0686] The server not only registers information collected from non-profit organizations and businesses into a database, but also uses an emotion engine to analyze the emotions contained in the input information. This data includes emotional information estimated from the nuances and tone of the text entered by the user. The data is also stored as emotion analysis data.

[0687] Subsequently, the server uses a generative AI model to analyze the registered information and emotional data in a unified manner. This allows for a deeper understanding of the intentions and desires of non-profit organizations and corporations, and the selection of the most suitable matching pairs. Based on the selected matching pairs, the server generates proposals for non-profit organizations and approval stories for corporations, taking emotional elements into consideration.

[0688] The device displays the generated proposal along with feedback from the emotional engine. This allows non-profit organizations to effectively conduct fundraising activities while confirming emotional alignment with the proposed companies. Companies can quickly make decisions regarding recipient selection based on the received proposals and emotional feedback.

[0689] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs emotionally charged statements emphasizing the importance of the project into a terminal. The server analyzes these statements and matches the organization with companies that have a strong interest in local education and similar emotional orientations. In this way, collaborative relationships that increase the acceptance of proposals become possible.

[0690] Therefore, the system of the present invention utilizes emotion recognition technology to evolve conventional matching and promote effective cooperation between non-profit organizations and businesses.

[0691] The following describes the processing flow.

[0692] Step 1:

[0693] Nonprofit organizations, acting as users, input information necessary for fundraising, specific activities, and the emotions behind those activities through their devices. This data is then transmitted to the server.

[0694] Step 2:

[0695] The user company enters the purpose of the donation and the message they wish to convey from their terminal, and also clearly states the emotional intent behind it. This information is then sent to the server.

[0696] Step 3:

[0697] The server registers the information of non-profit organizations and companies it receives into a database, and uses a sentiment engine to analyze the emotional elements in the text and generate sentiment metadata.

[0698] Step 4:

[0699] The server uses registered data along with the generated sentiment metadata to analyze it through a generative AI model. This analysis evaluates the degree of emotional alignment and purpose alignment between non-profit organizations and companies, and determines the most suitable matching pair.

[0700] Step 5:

[0701] Based on the matching results, the server generates proposals for non-profit organizations to companies, and lists of non-profit organizations and approval stories for companies. This generation process reflects the content of sentiment data.

[0702] Step 6:

[0703] The device displays the generated suggestions and associated emotional feedback to the user. This allows the user to consider their next action based on the emotional data.

[0704] Step 7:

[0705] Users make decisions based on the information displayed and emotional insights. Nonprofit organizations attempt emotional approaches to proposed companies, and companies also consider emotional information when selecting recipients for donations.

[0706] Thus, the system of the present invention utilizes emotion recognition technology to provide a richer matching experience.

[0707] (Example 2)

[0708] 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".

[0709] Achieving effective matching between non-profit organizations and corporations is a challenging task due to differences in their needs and values. Traditional methods often rely on superficial data matching, neglecting deeper factors such as emotions and intentions, resulting in limitations in matching accuracy and satisfaction. To address this problem, a system is needed that takes into account the emotions and values ​​of both non-profit organizations and corporations, enabling more precise matching.

[0710] 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.

[0711] This invention includes a server that records non-profit organization fundraising data and company donation policies, a server that analyzes the non-profit organization and company data using a generated machine learning model and selects the optimal matching pair, and a server that estimates emotional data from the data input using sentiment analysis technology and reflects it in the matching. This enables highly accurate matching that takes emotions and values ​​into consideration.

[0712] A "non-profit organization" is a legal entity or organization that operates for specific social or educational purposes and does not aim to make a profit.

[0713] A "company" is a legal entity that has a specific business purpose and engages in legally recognized profit-making activities.

[0714] "Funding data" refers to information about the amount and use of financial support that non-profit organizations need for their activities.

[0715] A "donation policy" is a set of guidelines outlining the criteria and objectives for a company to provide funds, goods, or other resources to non-profit organizations.

[0716] "Means of recording" refers to the processes and techniques for storing data electronically or on physical media.

[0717] A "machine learning model" is an algorithm or structure that allows a computer to learn patterns from data and perform predictions or classifications according to a specific purpose.

[0718] "Means of analyzing data" refers to the processes and techniques used to classify information based on collected data, identify patterns, and derive useful conclusions.

[0719] "Emotional analysis technology" is a technology that analyzes and understands the emotions and intentions of users from text and conversational data.

[0720] "Emotional data" refers to information about the emotions and values ​​held by non-profit organizations and companies.

[0721] A "terminal device" refers to an electronic device used by users to input information or view outputted information.

[0722] A "user" is an individual or organization that operates the system and provides or receives information according to its purpose.

[0723] "Generated proposals" refer to documents and information containing specific details that the system creates based on its analysis results.

[0724] This system was developed to facilitate effective matching between non-profit organizations and corporations, and it combines emotion recognition technology with generative AI models. The main software used includes a "generative AI model" that supports machine learning algorithms and an "emotion analysis engine" that performs data analysis. The following describes the operation of this system in detail.

[0725] Nonprofit organizations, as users, use terminals to enter their fundraising objectives, desired amount, and detailed activity descriptions. Similarly, corporate users also use terminals to enter their donation policies, expected outcomes, and messages. All of this input data is transmitted to the server.

[0726] The server registers the received information in a database and uses an emotion analysis engine to analyze the emotional elements of the input text. This analysis extracts emotional data such as passion and a sense of social responsibility from expressions like "I want to help children in need." This emotional data forms a crucial foundation for the next steps.

[0727] The server then uses a generative AI model to comprehensively analyze the registration information and sentiment data of non-profit organizations and companies. Based on this analysis, the matching pairs with the best combinations are selected. According to the selection results, the server generates sentiment-inclusive proposals for non-profit organizations and provides approval stories along with a list of recipient organizations for companies.

[0728] These proposals and emotional feedback are displayed via the terminal, allowing both non-profit organizations and companies to confirm their emotional compatibility. The system can generate even more refined proposals by using prompts such as, for example, "How can we attract companies to our children's education support project?"

[0729] Thus, this invention enables non-profit organizations and companies to effectively build cooperative relationships while confirming emotional compatibility.

[0730] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0731] Step 1:

[0732] Users enter their non-profit organization's fundraising objectives, desired amount, and activities via their device. Corporate users similarly enter their donation objectives and expected message. The entered information is sent from the device to the server. The input here is in text format and includes details of activities and donation policies. This creates the initial dataset.

[0733] Step 2:

[0734] The server registers the received information in a dedicated database. Next, the sentiment analysis engine starts up and analyzes the emotional elements from the registered text. In this process, the nuances of emotion are extracted from the input words and phrases, the linguistic tone is determined, and sentiment data is generated. For example, the expression "urgent funding is needed" is analyzed to produce the emotion of "urgency," which is then stored as sentiment data.

[0735] Step 3:

[0736] The server uses a generative AI model to integrate and analyze information and sentiment data from non-profit organizations and businesses stored in a database. Natural language processing techniques are employed to gain a deep understanding of the needs and intentions of both parties. The analysis outputs a list of the most suitable matching pairs. This list will be used in subsequent implementation phases and to generate proposals.

[0737] Step 4:

[0738] Based on the selected matching pairs, the server generates emotionally charged proposals for non-profit organizations and lists of recipients and approval stories for corporations. In this step, a generative AI model is used to automatically construct documents that evoke emotion and empathy using prompt sentences.

[0739] Step 5:

[0740] The terminal displays the generated proposal and emotional feedback to the user. Nonprofit organization representatives use this information to evaluate the possibility of collaboration with companies, and company representatives review the proposals to approve donations. The displayed information is important for confirming the emotional compatibility between the selected nonprofit organization and the company.

[0741] This process enables systematic and emotionally consistent matching.

[0742] (Application Example 2)

[0743] 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".

[0744] Traditionally, matching non-profit organizations with corporations for fundraising and donations has relied solely on the matching of information, without considering emotional aspects, often resulting in unsatisfactory outcomes for both parties. Furthermore, the lack of real-time visitor sentiment analysis has made it difficult to provide safe and appropriate support.

[0745] 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.

[0746] In this invention, the server includes means for registering fundraising information of non-profit organizations and donation policies of companies in an information storage device; means for analyzing the information of non-profit organizations and companies using a generated artificial intelligence model to identify the optimal pair of responders; and means for generating proposal documents for non-profit organizations and lists of recipients and approval narratives for companies based on the analyzed information. This makes it possible to analyze the emotional state of visitors in real time by utilizing sentiment analysis technology, determine the level of alert, and provide appropriate countermeasures.

[0747] "Funding information" refers to information about the amount of funds a non-profit organization needs and how those funds will be used.

[0748] A "donation policy" is information that outlines a company's policies and intentions regarding the purpose and criteria by which it makes donations.

[0749] An "information storage device" is an electronic device or system used to store data and make it available for retrieval as needed.

[0750] An "artificial intelligence model" is a computer program designed to perform complex calculations based on learned data and to carry out specific tasks.

[0751] A "matching pair" is a pair of a non-profit organization and a company that have been optimally matched based on the objectives and intentions of both parties.

[0752] A "proposal document" is a document created by a non-profit organization to explain the significance of providing funding to a company and to request their cooperation.

[0753] The "List of Donation Recipients" is a list of non-profit organizations that companies are considering as potential recipients of donations.

[0754] An "approval narrative" is a background explanation or story used by a company to facilitate its internal approval process when making a donation.

[0755] "Emotion analysis technology" is a technology that estimates human emotions by analyzing voice, facial expressions, and nuances in documents.

[0756] The "alert level" is a standard used to determine whether a visitor is safe and serves as an indicator for deciding on security measures.

[0757] The system that implements this application employs advanced technology to facilitate effective matching between non-profit organizations and corporations. In this system, non-profit organizations input fundraising information into a terminal, and this data is sent to a server. Similarly, corporations input their donation policies into a terminal and send them to the server.

[0758] The server organizes and registers this data in an information storage device. Next, an artificial intelligence model is used to analyze this data in detail and identify appropriate recipient groups. By also using sentiment analysis technology, the emotional state of visitors is analyzed in real time, and from the obtained data, a document proposing the most suitable donation destination, a list of donation recipients for the company, and an approval narrative are generated.

[0759] Furthermore, the analyzed recommendations are presented visually via the user's display device. This enables non-profit organizations and businesses to make more informed decisions by taking emotional factors into consideration.

[0760] As a concrete example, suppose a non-profit organization is seeking funding for a project to support children's education. This organization inputs information into a terminal that emotionally expresses the importance of the project. The server analyzes this information and matches it with companies that show a high level of interest. At the same time, companies are provided with the necessary narratives to consider donating, supporting smooth decision-making.

[0761] A concrete example of a prompt would be, "Analyze the visitor's emotions from their voice and facial expressions, and generate responses that will help the visitor relax." This allows the generating AI model to analyze the information and provide useful feedback to the user.

[0762] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0763] Step 1:

[0764] The device receives fundraising information and donation policies entered by user non-profit organizations and corporations. The entered information is stored within the device as string data. This allows the user's needs and objectives to be concretely visualized.

[0765] Step 2:

[0766] The server registers data from non-profit organizations and companies transmitted from terminals into an information storage device. The registered data is then converted into an efficient database structure that facilitates later searching and analysis, making it easily accessible.

[0767] Step 3:

[0768] The server applies a generative AI model to the registered non-profit organization and company information to identify appropriate partner pairs. In this process, the AI ​​model analyzes the data, considering the contextual information of each entry, and generates a quantified evaluation score. This helps discover the optimal combination.

[0769] Step 4:

[0770] The server uses sentiment analysis technology to analyze the visitor's emotional state in real time. It takes audio and video data as input, applies a sentiment analysis algorithm, and outputs numerical data representing the emotional state. This data provides information to determine whether the response is appropriate.

[0771] Step 5:

[0772] The server generates proposal documents for non-profit organizations and lists of recipients and approval narratives for corporations based on the analyzed information. This step utilizes automated text generation technology with a generative AI model. The final output is documented in a user-friendly format.

[0773] Step 6:

[0774] The terminal visually displays the generated proposals and analysis results to the user. The displayed information serves as supplementary material for the user's decision-making and helps in evaluating each proposal.

[0775] 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.

[0776] 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.

[0777] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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."

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] The following is further disclosed regarding the embodiments described above.

[0797] (Claim 1)

[0798] A means of registering fundraising information of non-profit organizations and corporate donation policies in a database,

[0799] A method for analyzing information on non-profit organizations and companies using a generated AI model to identify the optimal matching pair,

[0800] Based on the matching results, non-profit organizations will be provided with a means to generate proposals, and corporations will be provided with a list of recipient organizations and a story for approval.

[0801] A means of providing the generated proposal content via the user's display device,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, which uses natural language processing technology when analyzing the activities of non-profit organizations and corporate messages in the matching process.

[0805] (Claim 3)

[0806] The system according to claim 1, which stores user feedback information in a database and contributes to improving matching accuracy in subsequent matches.

[0807] "Example 1"

[0808] (Claim 1)

[0809] A means for receiving information on fundraising requests and donation policies from users and registering them in an information processing device,

[0810] A means of analyzing registered information and deriving the optimal match using an artificial intelligence model generated by a data processing device,

[0811] Based on the matching results, a means is provided to generate proposal documents for fundraising seekers and a list of potential recipients and approval documents for donors.

[0812] A means of notifying the user of the proposal generated through the provided device,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, which utilizes natural language processing technology when analyzing the summary of an organization's activities and the intentions of donors in data matching processing.

[0816] (Claim 3)

[0817] The system according to claim 1, which records user response information in an information processing device and contributes to improving matching accuracy in subsequent instances.

[0818] "Application Example 1"

[0819] (Claim 1)

[0820] A means of registering fundraising information of non-profit organizations and corporate donation policies in a data collection device,

[0821] A method for analyzing information on non-profit organizations and companies using a generated machine learning model to identify the optimal matching pair,

[0822] Based on the matching results, a means is provided to generate proposal documents for non-profit organizations and donation recipient lists and approval explanations for corporations.

[0823] A means of providing the generated proposal content via the user's display device and enabling donations to be made using electronic payment functions,

[0824] A system that includes this.

[0825] (Claim 2)

[0826] The system according to claim 1, which uses natural language processing technology to analyze the activities of non-profit organizations and the messages of companies in the matching process, and proposes payment methods based on the analyzed data.

[0827] (Claim 3)

[0828] The system according to claim 1, which stores user feedback information in a data collection device and contributes to improving matching accuracy and the efficiency of electronic payment processing in subsequent transactions.

[0829] "Example 2 of combining an emotion engine"

[0830] (Claim 1)

[0831] A means of recording non-profit organization fundraising data and a company's donation policy,

[0832] A method for analyzing data from non-profit organizations and companies using a generated machine learning model and selecting the optimal matching pair,

[0833] A means of using emotion analysis technology to estimate emotion data from data input and reflect it in matching,

[0834] A method for generating proposals containing emotional elements for non-profit organizations and generating approval stories containing emotional feedback for companies,

[0835] A means of presenting the generated proposal to the user via a terminal device,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, which includes using natural language processing technology to analyze the details of a non-profit organization's activities and a company's message.

[0839] (Claim 3)

[0840] The system according to claim 1, which includes accumulating user feedback information in a database and utilizing it to improve matching accuracy in the future.

[0841] "Application example 2 when combining with an emotional engine"

[0842] (Claim 1)

[0843] A means for registering fundraising information of non-profit organizations and donation policies of companies in an information storage device,

[0844] A method for analyzing information on non-profit organizations and companies using a generated artificial intelligence model to identify the optimal response team,

[0845] Based on the analyzed information, non-profit organizations will be provided with a means to generate proposal documents, and corporations will be provided with a list of recipients and a narrative for approval.

[0846] The generated suggestions are provided via the user's display device, and the system also uses emotion analysis technology to analyze the visitor's emotional state in real time, providing a warning level and countermeasures based on the analysis results.

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, which uses natural language processing technology to analyze the activities of non-profit organizations and the messages of companies in the matching process, and further uses sentiment recognition technology to improve the accuracy of the analysis.

[0850] (Claim 3)

[0851] The system according to claim 1, which stores user feedback and sentiment analysis results in an information storage device, thereby contributing to improved matching accuracy and optimized visitor handling in the future. [Explanation of Symbols]

[0852] 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 registering fundraising information of non-profit organizations and corporate donation policies in a database, A method for analyzing information on non-profit organizations and companies using a generated AI model to identify the optimal matching pair, Based on the matching results, non-profit organizations will be provided with a means to generate proposals, and corporations will be provided with a list of recipient organizations and a story for approval. A means of providing the generated proposal content via the user's display device, A system that includes this.

2. The system according to claim 1, which uses natural language processing technology when analyzing the activities of non-profit organizations and corporate messages in the matching process.

3. The system according to claim 1, which stores user feedback information in a database and contributes to improving matching accuracy in subsequent matches.

Images