System

Abstract

A system is provided.SOLUTION: A system comprising: means for using an artificial intelligence model to suggest a donation destination of a user; means for managing a donation history of the user; means for predicting a donation effect for the user; and means for using a generative artificial intelligence model to generate a creative material for a donation collector.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Individuals and companies who make donations face the time and effort required to select recipients, manage donation histories, and understand the future impact of their donations. Those seeking donations also face the challenge of finding donors effectively and creating compelling creative materials. Furthermore, there are also challenges in motivating people to continue donating. [Means for solving the problem]

[0005] The present invention provides a system that comprehensively supports users' donation activities. Specifically, these problems can be solved by providing a system that includes a means for using an AI model to suggest donation destinations for users, a means for managing users' donation history, a means for predicting the effectiveness of donations for users, a means for using a generative AI model to generate creative materials for donation solicitors, a means for analyzing voice input to suggest donation destinations for users, and a means for providing donation activities with gamification elements and awarding points when users donate.

[0006] An "artificial intelligence model" is a system that includes a computer program that analyzes a user's interests and data and, based on that, suggests appropriate donation destinations.

[0007] A "donation history" is a dataset containing a record of past donations made by a user.

[0008] "Donation effect" is an evaluation that predicts the impact or results that a user's donation will have.

[0009] "Creative materials" are promotional materials such as catchy slogans and visual content that donors use to effectively encourage donations.

[0010] A "generative artificial intelligence model" is a system that includes an artificial intelligence program that can automatically generate creative materials such as text, images, and audio.

[0011] "Voice input" is a method by which a user sends instructions or questions to a system through speech.

[0012] "Gamification elements" are methods of improving user behavior and motivation using game design elements and techniques.

[0013] "Point awarding" is the process by which users are rewarded with points by the system every time they make a donation.

[0014] A "fundraiser" is an individual or organization that collects donations for a specific purpose. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention provides a comprehensive system for solving various problems in donation activities. The system unifies the management of online and offline donation activities and supports donation activities for both users and donors.

[0037] User donation suggestions

[0038] This system uses an artificial intelligence model to make optimal suggestions when users choose a donation recipient. When a user inputs their interests, the server passes that information to the artificial intelligence model, which then suggests appropriate donation recipients. For example, if a user is interested in environmental protection, the system will suggest relevant nonprofit organizations.

[0039] Donation history management

[0040] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[0041] Predicting the impact of donations

[0042] When a user makes a donation, the system also provides a function to predict the future impact of that donation. When a user inputs the donation amount and the recipient, the server uses an artificial intelligence model based on that information to predict the impact and communicates the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[0043] Creative Material Generation

[0044] The server has the ability to provide donors with creative materials using a generative AI model. When donors start a new campaign and need materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server. This allows donors to easily launch compelling campaigns.

[0045] Voice suggestions

[0046] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text, understands the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[0047] Gamification elements

[0048] The system incorporates gamification elements to make donations sustainable. Users are awarded points every time they donate, and can earn rewards based on those points. This point system makes donations fun and easy to continue.

[0049] Specific examples

[0050] Suppose a user is considering donating to a nonprofit organization but is unsure which one is best. The user accesses a device and speaks, "Please tell me where I can donate to environmental conservation." The device converts this speech into text and sends it to a server. The server passes this information to an artificial intelligence model, which generates several optimal suggestions. The server then returns the results to the device, which then verbally communicates them to the user. The user then selects a donation destination based on these suggestions and makes the donation.

[0051] As described above, the present invention provides a system for efficiently and effectively supporting donation activities for both users and donors.

[0052] The processing flow will be explained below.

[0053] Handling new user registrations

[0054] Step 1:

[0055] The user enters their username, password, and email address on the device and clicks the "Register" button.

[0056] Step 2:

[0057] The terminal generates a registration request including the input information and sends it to the server.

[0058] Step 3:

[0059] The server checks its database to see if the username already exists.

[0060] Step 4:

[0061] If the server determines that the user is new, it saves the user information in the database.

[0062] Step 5:

[0063] The server generates a registration success message and sends it to the terminal.

[0064] Step 6:

[0065] The terminal displays a registration success message to notify the user that registration is complete.

[0066] Processing user donation suggestions

[0067] Step 1:

[0068] The user enters their interests on the device and clicks the "Suggest" button.

[0069] Step 2:

[0070] The terminal generates a proposal request including the interest information and transmits it to the server.

[0071] Step 3:

[0072] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[0073] Step 4:

[0074] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[0075] Step 5:

[0076] The server receives the suggestions and generates a response to send back to the user.

[0077] Step 6:

[0078] The device analyzes the proposal results and displays them to the user.

[0079] Processing donation history verification

[0080] Step 1:

[0081] The user clicks the button to display "Donation History" on the device.

[0082] Step 2:

[0083] The terminal generates a history request including the user ID and sends it to the server.

[0084] Step 3:

[0085] The server connects to the database based on the received user ID and retrieves past donation history.

[0086] Step 4:

[0087] The server formats the donation history and generates a response to send back to the user.

[0088] Step 5:

[0089] The terminal analyzes the received donation history and displays it to the user.

[0090] Processing donation impact forecasts

[0091] Step 1:

[0092] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[0093] Step 2:

[0094] The terminal generates an effect prediction request including the input information and transmits it to the server.

[0095] Step 3:

[0096] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[0097] Step 4:

[0098] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[0099] Step 5:

[0100] The server receives the prediction results and generates a response to send back to the user.

[0101] Step 6:

[0102] The terminal analyzes the received prediction results and displays them to the user.

[0103] Creative material generation process

[0104] Step 1:

[0105] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[0106] Step 2:

[0107] The terminal generates a generation request including the description information and transmits it to the server.

[0108] Step 3:

[0109] The server passes the received description information to the generative artificial intelligence model and requests the generation of creative materials.

[0110] Step 4:

[0111] A generative artificial intelligence model generates creative materials based on input information.

[0112] Step 5:

[0113] The server receives the generated creative material and generates a response to send back to the contributor.

[0114] Step 6:

[0115] The device analyzes the received creative material and displays it to the donor.

[0116] Processing donation suggestions via voice input

[0117] Step 1:

[0118] The user inputs voice information into the terminal to inquire about where to donate.

[0119] Step 2:

[0120] The device converts the speech to text, generates a suggestion request, and sends it to the server.

[0121] Step 3:

[0122] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[0123] Step 4:

[0124] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[0125] Step 5:

[0126] The server receives the proposal results, performs speech synthesis, and generates a response.

[0127] Step 6:

[0128] The terminal plays back the received response to the user by voice.

[0129] Example 1

[0130] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0131] In conventional donation systems, users have difficulty finding appropriate donation recipients and lack the ability to predict the impact of donations. In addition, donors have to create the materials they need to launch effective campaigns, and there are limited ways to increase the sustainability of donation activities. Furthermore, the lack of voice input to suggest donation recipients and the lack of elements that make the donation activity itself enjoyable leads to problems with people not continuing to donate.

[0132] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0133] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the effectiveness of donations for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing voice input to suggest donation destinations for the user, and means for providing donation activities with gamification elements and awarding points when the user makes a donation. This not only allows users to easily find appropriate donation destinations and predict the effectiveness of their donations, but also allows donors to quickly launch effective campaigns. Furthermore, the donation suggestions using voice input and gamification elements make donation activities more enjoyable and sustainable.

[0134] The "artificial intelligence model" is a machine learning algorithm that suggests appropriate donation destinations based on user input information.

[0135] The "donation history management means" is a system that stores and manages the history of donations made by users in the past and provides information to users as needed.

[0136] The "donation effect prediction means" is a system that predicts the future effect of a donation based on the amount donated by the user and the donation recipient.

[0137] A "generative artificial intelligence model" is a machine learning algorithm that automatically generates creative materials (such as text and images) based on a description of a new campaign.

[0138] The "voice input analysis means" is a system that converts information input by voice by the user into text, analyzes it, and suggests appropriate donation destinations.

[0139] "Gamification elements" are elements that introduce point systems and rewards to make users' donation activities fun and easy to continue.

[0140] "Rewards" are rewards or benefits that users can earn based on the points they have been awarded.

[0141] The present invention is a system that supports effective donation activities for both users and donors. The system provides the following main functions:

[0142] User donation suggestions

[0143] When a user selects a donation destination, the system uses an artificial intelligence model to make the most appropriate suggestions. When a user inputs their interests into the device, the device sends the information to a server. The server passes it on to an artificial intelligence model, which then suggests the most appropriate donation destination. The artificial intelligence model used here is a machine learning algorithm built using Python. For example, if a user inputs "Please tell me where I should donate to environmental protection," the system will suggest relevant non-profit organizations.

[0144] Donation history management

[0145] A user's donation history is managed by the server. When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the history information from the database and displays it on the device. A relational database management system such as MySQL is used to manage this database. This allows users to see their past donation activity at a glance.

[0146] Predicting the impact of donations

[0147] When users make a donation, they are also provided with a function to predict the future impact of their donation. After the user enters the donation amount and recipient, the device sends that information to a server. The server uses an artificial intelligence model to predict the impact and returns the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[0148] Creative Material Generation

[0149] When a donor starts a new campaign, the server uses a generative AI model to provide creative materials. When a donor enters a campaign description, the generative AI model automatically creates creative materials such as images and text and sends them to the server. This generative AI model combines natural language processing (NLP) and computer vision (CV) technologies.

[0150] Voice suggestions

[0151] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice. This speech recognition uses voice recognition software (e.g., Google Speech-to-Text API).

[0152] Gamification elements

[0153] To make donations sustainable, the system incorporates gamification elements. Users are awarded points every time they donate, and can earn rewards based on those points. The point system is designed to increase user motivation.

[0154] Specific examples

[0155] Here is a specific example of a case where a user is unsure where to donate. The user voice-inputs into the device, "Please tell me where to donate to environmental conservation." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model to suggest the most suitable donation destination and transmits the result to the device. The device then replies with the result by voice to the user, who then chooses a donation destination based on the suggestions and makes the donation.

[0156] Example prompt for a generative AI model:

[0157] The user has indicated that they are interested in "environmental protection." Please suggest the best related donations.

[0158] The present invention provides a system that allows both users and donors to carry out donation activities efficiently and effectively.

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Processing flow for user donation suggestions

[0161] Step 1:

[0162] The user inputs their interests into the terminal.

[0163] Specific operation: The user enters text of an area of ​​interest, such as "environmental protection," into the input form on the device.

[0164] Input: User-entered data (interests)

[0165] Output: Interest data entered into the device

[0166] Step 2:

[0167] The terminal sends the input information to the server.

[0168] Specific operation: The terminal forms user input data and transfers it to the server as an HTTP request.

[0169] Input: User-entered data

[0170] Output: Request data sent to the server

[0171] Step 3:

[0172] The server passes the information to an artificial intelligence model.

[0173] Specific operation: The server analyzes the received data and inputs it as prompts into the artificial intelligence model.

[0174] Input: Request data

[0175] Output: Prompt data

[0176] Step 4:

[0177] An artificial intelligence model generates the suggestions.

[0178] How it works: The AI ​​model generates relevant donation destinations based on the prompt data.

[0179] Input: prompt data

[0180] Output: Donation proposal data

[0181] Step 5:

[0182] The server sends the proposal results to the terminal.

[0183] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[0184] Input: Donation proposal data

[0185] Output: Proposal data sent to the device

[0186] Step 6:

[0187] The terminal displays the suggestion results to the user.

[0188] Specific operation: The terminal displays the received proposal data on the user interface.

[0189] Input: Proposal data

[0190] Output: The suggestions displayed to the user

[0191] Donation history management process flow

[0192] Step 1:

[0193] The server stores the user's donation history in a database.

[0194] Specific operation: The server writes the information of each donation operation to the database.

[0195] Input: Donation data

[0196] Output: Historical data stored in a database

[0197] Step 2:

[0198] The user sends a history check request from the terminal.

[0199] Specific operation: The user generates a request by pressing the "Check History" button on the device.

[0200] Input: User operation data

[0201] Output: Request data sent to the server

[0202] Step 3:

[0203] The server retrieves the history information from the database.

[0204] Specific operation: The server searches and retrieves the corresponding historical data from the database in response to the request.

[0205] Input: Request data

[0206] Output: Retrieved historical data

[0207] Step 4:

[0208] The server transmits the history information to the terminal.

[0209] Specific operation: The server sends the acquired history data to the terminal as an HTTP response.

[0210] Input: Historical data

[0211] Output: Historical data sent to the terminal

[0212] Step 5:

[0213] The terminal displays the history to the user.

[0214] Specific operation: The terminal displays the received history data on the user interface.

[0215] Input: Historical data

[0216] Output: History information displayed to the user

[0217] Donation effect prediction process flow

[0218] Step 1:

[0219] The user enters the donation amount and donation destination into the terminal.

[0220] Specific operation: The user enters the donation amount and donation destination into the donation form.

[0221] Input: Donation amount and donation recipient data

[0222] Output: Donation data entered into the terminal

[0223] Step 2:

[0224] The terminal sends the input information to the server.

[0225] Specific operation: The terminal inputs donation data and transmits it to the server as an HTTP request.

[0226] Input: Donation data

[0227] Output: Request data sent to the server

[0228] Step 3:

[0229] The server uses an artificial intelligence model to predict the effectiveness of donations.

[0230] Specific operation: The server inputs the received data into the AI ​​model and makes a prediction.

[0231] Input: Donation data

[0232] Output: Prediction result data

[0233] Step 4:

[0234] The server sends the prediction results to the device.

[0235] Specific operation: The server sends the generated prediction result data to the terminal as an HTTP response.

[0236] Input: Prediction result data

[0237] Output: Prediction result data sent to the device

[0238] Step 5:

[0239] The terminal displays the predicted effect to the user.

[0240] Specific operation: The terminal displays the received prediction result data on the user interface.

[0241] Input: Prediction result data

[0242] Output: Predicted effect information displayed to the user

[0243] Creative material generation process flow

[0244] Step 1:

[0245] A donor types a new campaign description into a terminal.

[0246] Specific operation: The donor enters a description of the campaign into the input form on the terminal.

[0247] Input: Campaign description data

[0248] Output: Campaign data entered into the terminal

[0249] Step 2:

[0250] The terminal sends the input information to the server.

[0251] Specific operation: The device sends campaign data to the server as an HTTP request.

[0252] Input: Campaign description data

[0253] Output: Request data sent to the server

[0254] Step 3:

[0255] The server generates creative materials using generative AI models.

[0256] Specific operation: The server inputs the received data into a generative AI model to generate creative materials.

[0257] Input: Campaign description data

[0258] Output: Generated creative material data

[0259] Step 4:

[0260] The server transmits the generated material to the terminal.

[0261] Specific operation: The server sends the generated material data to the terminal as an HTTP response.

[0262] Input: Creative material data

[0263] Output: Material data sent to the device

[0264] Step 5:

[0265] The device displays the creative material to the donor.

[0266] Specific operation: The terminal displays the received creative material data on the user interface.

[0267] Input: Creative material data

[0268] Output: Creative material displayed to donors

[0269] Voice suggestion process flow

[0270] Step 1:

[0271] The user speaks to the terminal about where to donate.

[0272] Specific operation: The user speaks into the microphone, saying something like, "Please tell me where to donate to environmental conservation."

[0273] Input: Audio data

[0274] Output: Audio data input to the device

[0275] Step 2:

[0276] The device converts the speech into text and sends it to the server.

[0277] Specific operation: The terminal converts the voice data into text data and transfers it to the server as an HTTP request.

[0278] Input: Audio data

[0279] Output: Text data sent to the server

[0280] Step 3:

[0281] The server analyzes the text and uses an artificial intelligence model to suggest donation destinations.

[0282] Specific operation: The server analyzes the received text data, inputs it into an artificial intelligence model, and generates the optimal donation destination.

[0283] Input: Text data

[0284] Output: Donation proposal data

[0285] Step 4:

[0286] The server sends the proposal results to the terminal.

[0287] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[0288] Input: Donation proposal data

[0289] Output: Proposal data sent to the device

[0290] Step 5:

[0291] The device returns the proposed results to the user by voice.

[0292] Specific operation: The device uses voice synthesis technology to output the received proposal data as a voice response to the user.

[0293] Input: Proposal data

[0294] Output: Spoken suggestions

[0295] Gamification element processing flow

[0296] Step 1:

[0297] A user makes a donation.

[0298] Specific operation: The user enters the donation amount and donation recipient into the donation form on the device and clicks the donate button.

[0299] Input: Donation data

[0300] Output: Donation data sent from the device to the server

[0301] Step 2:

[0302] The server awards points to the user.

[0303] Specific operation: The server receives the donation data, calculates the corresponding points and adds them to the user's account.

[0304] Input: Donation data

[0305] Output: Points added to the account

[0306] Step 3:

[0307] The server calculates rewards based on the points.

[0308] Specific operation: The server checks the user's accumulated points and calculates the reward accordingly.

[0309] Input: Point data

[0310] Output: Reward data

[0311] Step 4:

[0312] The server transmits the reward information to the terminal.

[0313] Specific operation: The server sends the calculated reward data to the terminal as an HTTP response.

[0314] Input: Reward data

[0315] Output: Reward data sent to the device

[0316] Step 5:

[0317] The terminal displays the reward to the user.

[0318] Specific operation: The terminal displays the received reward data on the user interface.

[0319] Input: Reward data

[0320] Output: Reward information displayed to the user

[0321] (Application example 1)

[0322] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0323] In modern donation activities, users have difficulty selecting appropriate donation recipients and there is a lack of ways to predict the impact of donations. Furthermore, donors are burdened with the task of creating attractive campaign materials. Furthermore, there is a lack of gamification elements to make donation activities sustainable.

[0324] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0325] In this invention, the server includes means for using an artificial intelligence model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative artificial intelligence model to generate creative materials for the donor, means for suggesting optimal donation destinations based on the user's purchase history and interests, means for checking the user's donation history using an application, and means for making donations at the same time as purchases and predicting and displaying the effects. This makes it easy for users to select appropriate donation destinations and predict and confirm the effects of donation activities. It also reduces the burden on donors and allows them to develop attractive campaigns, allowing them to continue enjoying donation activities.

[0326] An "artificial intelligence model" is a computer program that analyzes user data and suggests appropriate donation destinations.

[0327] "Donation history" is detailed information about donations made by a user in the past, including donation recipients, donation amounts, donation dates, and the like.

[0328] "Donation impact" is the result that predicts how a user's donation will benefit a particular cause.

[0329] A "generative artificial intelligence model" is a computer program that automatically generates creative materials for contributors.

[0330] "User purchase history" is detailed information about products purchased by the user in the past, and is data including product names, purchase dates, purchase amounts, and the like.

[0331] "User interests" refers to information about themes or fields in which a user is particularly interested.

[0332] "Means for checking through the application" refers to a means by which users can view their donation history through the software they use.

[0333] The "means for predicting and displaying the effect of donation activities" is a means for calculating how useful a donation will be when a user makes a donation and displaying the result to the user.

[0334] "Gamification elements" are ideas and mechanisms that make donation activities fun, like a game, and easier to continue sustainably.

[0335] The "means for awarding points" is a points system that awards points to users who make donations.

[0336] The present invention is a system for facilitating users' donation activities. This system has various functions for suggesting donation destinations for users, managing donation history, predicting the impact of donations, and providing creative materials to donors.

[0337] System Configuration

[0338] The system mainly consists of the following elements:

[0339] Artificial Intelligence Model

[0340] Generative AI Model

[0341] Database

[0342] server

[0343] User devices (smartphones, tablets, PCs, etc.)

[0344] Program Generation

[0345] First, the system collects interest and purchase history data from users. When users choose a donation destination, an AI model uses this data to suggest the most appropriate donation destination. For example, if a user enters data indicating an interest in "environmental protection," the system will suggest related nonprofit organizations.

[0346] Next, the user's donation history is stored in a database, and when the user requests it, the server retrieves the information and displays it on the terminal, allowing the user to easily check their past donation activity.

[0347] Furthermore, the donation amount and donation recipient information are sent to the server to predict the impact of the user's donation. The server then uses this information to make a prediction using an artificial intelligence model, which then returns the results to the user. For example, if a user donates a specific amount to an environmental protection project, the server predicts and displays the impact that the donation will have.

[0348] Fundraisers can also use generative artificial intelligence models to automatically generate creative materials for their campaigns. Fundraisers enter a description of their campaign, and the system generates materials such as text and images based on that description.

[0349] System action

[0350] The following hardware and software are used for processing in this system:

[0351] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[0352] Software: Artificial intelligence models (e.g., OpenAI API), databases (e.g., MySQL or PostgreSQL), generative AI (e.g., OpenAI GPT-3)

[0353] Specific examples

[0354] The user selects "environmental protection" as a topic of interest and then voice-inputs, "Please tell me where I can donate to environmental protection." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model based on this information to suggest the most appropriate donation destination and returns the result to the device.

[0355] Example prompt sentence:

[0356] "Create a persuasive advertisement for the following campaign: New fundraising campaign for forest restoration."

[0357] In this way, the system can efficiently and effectively support donation activities by suggesting donation destinations, managing donation history, predicting donation effects, and providing creative materials using generative AI models. This system makes donation activities more convenient for both users and donors.

[0358] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0359] Step 1:

[0360] Users input their interest data and purchase history data. The device receives this data and sends it to the server. The input data includes areas of interest (e.g., "environmental protection") and detailed information about purchased products (e.g., "eco-friendly toothbrushes"). The server receives this data and stores it in a database.

[0361] Step 2:

[0362] A user requests donation suggestions. For example, they can say, "Please tell me where to donate to environmental conservation." The device converts this speech into text and sends it to the server. The input is voice data, and the output is text data. The server inputs the text into an artificial intelligence model and generates a list of optimal donation destinations.

[0363] Step 3:

[0364] The server returns a list of donation recipients suggested by the AI ​​model to the device. The user reviews the list and selects a donation recipient. The generated list includes multiple nonprofit organizations and projects. Once the user makes a selection, the selection data is sent to the server.

[0365] Step 4:

[0366] When a user decides to donate, the device sends donation information (donation recipient, donation amount, etc.) to the server. The server records this information in a database and uses an artificial intelligence model to predict the impact of the donation. The input data is the donation recipient and donation amount, and the output data is the predicted impact.

[0367] Step 5:

[0368] The server sends the predicted donation effect to the terminal and displays it to the user, who can see the specific effect of the donation (e.g., "Donating $100 will plant 10 trees").

[0369] Step 6:

[0370] When a donor starts a new campaign, they send a campaign description from their device to the server, which then inputs it into a generative AI model to generate creative materials (text, images, etc.). The input is the campaign description text, and the output is the creative materials.

[0371] Step 7:

[0372] The generated creative materials are sent from the server to the donor's device, where they can be viewed and used, enabling the donor to launch an engaging campaign in a short space of time.

[0373] Step 8:

[0374] When a user wants to check their donation history, they send a request from their device. The server retrieves the user's donation history from the database and sends it to the device. The input is the user ID, and the output is the donation history data.

[0375] Step 9:

[0376] The system provides gamification elements, awarding points each time a user makes a donation. The points based on the user's donation behavior are calculated on the server and recorded in a database. This allows users to have fun while contributing to society through donations.

[0377] As a result, this system can efficiently and effectively support donation activities for both users and donors.

[0378] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0379] This invention provides a comprehensive system that combines an emotion engine to solve various problems in donation activities. This system analyzes users' emotions and, based on this, makes donation suggestions, predicts donation effects, and generates creative materials.

[0380] User donation suggestions

[0381] When a user selects a donation destination, this system uses an artificial intelligence model and an emotion engine to make optimal suggestions. When a user inputs their interests and emotions, the server passes that information to the emotion engine and artificial intelligence model to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and expresses positive emotions, the system will suggest relevant non-profit organizations.

[0382] Donation history management

[0383] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[0384] Predicting the impact of donations

[0385] When a user makes a donation, the system also provides a function to predict the future impact of that donation. The user enters the donation amount, the donation recipient, and their emotion at the time. The server uses this information to predict the impact using an artificial intelligence model and emotion engine, and notifies the user of the results. For example, if the emotion engine detects the user's excited state, the donation may be predicted to be more impactful.

[0386] Creative Material Generation

[0387] The server has the function of providing donors with creative materials using a generative AI model and emotion engine. When a donor starts a new campaign and needs materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server and the donor's emotional information. This allows donors to easily launch compelling campaigns.

[0388] Voice suggestions

[0389] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server uses text analysis and an emotion engine to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[0390] Gamification elements

[0391] The system incorporates gamification elements to make donations sustainable. If positive emotions are detected each time a user makes a donation, more points are awarded. This makes donations fun and easy to continue.

[0392] Specific examples

[0393] Suppose a user is unsure where to donate, but is interested in environmental protection and expresses positive emotions. The user accesses the device and speaks, "Please tell me where to donate to environmental protection." The device converts this speech into text, analyzes the emotion using an emotion engine, and sends it to the server. The server passes this information to an AI model and emotion engine, which suggests several optimal donation destinations. The server then returns the results to the device, which then communicates them to the user via voice. The user chooses a donation destination based on these suggestions and makes a donation.

[0394] As described above, the present invention provides a system that analyzes user emotions to more effectively suggest donations, predict the effects of donations, and generate creative materials, thereby enabling efficient and effective support for donation activities for both users and donors.

[0395] The processing flow will be explained below.

[0396] Handling new user registrations

[0397] Step 1:

[0398] The user enters their username, password, and email address on the device and clicks the "Register" button.

[0399] Step 2:

[0400] The terminal generates a registration request including the input information and sends it to the server.

[0401] Step 3:

[0402] The server checks its database to see if the username already exists.

[0403] Step 4:

[0404] If the server determines that the user is new, it saves the user information in the database.

[0405] Step 5:

[0406] The server generates a registration success message and sends it to the terminal.

[0407] Step 6:

[0408] The terminal displays a registration success message to notify the user that registration is complete.

[0409] Processing user donation suggestions

[0410] Step 1:

[0411] The user enters their interests on the device and clicks the "Suggest" button.

[0412] Step 2:

[0413] The terminal generates a proposal request including the interest information and transmits it to the server.

[0414] Step 3:

[0415] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[0416] Step 4:

[0417] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[0418] Step 5:

[0419] The server receives the suggestions and generates a response to send back to the user.

[0420] Step 6:

[0421] The device analyzes the proposal results and displays them to the user.

[0422] Processing donation history verification

[0423] Step 1:

[0424] The user clicks the button to display "Donation History" on the device.

[0425] Step 2:

[0426] The terminal generates a history request including the user ID and sends it to the server.

[0427] Step 3:

[0428] The server connects to the database based on the received user ID and retrieves past donation history.

[0429] Step 4:

[0430] The server formats the donation history and generates a response to send back to the user.

[0431] Step 5:

[0432] The terminal analyzes the received donation history and displays it to the user.

[0433] Processing donation impact forecasts

[0434] Step 1:

[0435] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[0436] Step 2:

[0437] The terminal generates an effect prediction request including the input information and transmits it to the server.

[0438] Step 3:

[0439] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[0440] Step 4:

[0441] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[0442] Step 5:

[0443] The server receives the prediction results and generates a response to send back to the user.

[0444] Step 6:

[0445] The terminal analyzes the received prediction results and displays them to the user.

[0446] Creative material generation process

[0447] Step 1:

[0448] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[0449] Step 2:

[0450] The terminal generates a generation request including the description information and transmits it to the server.

[0451] Step 3:

[0452] The server passes the received description information to the generative AI model and requests the generation of creative materials.

[0453] Step 4:

[0454] A generative AI model generates creative materials based on input information.

[0455] Step 5:

[0456] The server receives the generated creative material and generates a response to send back to the contributor.

[0457] Step 6:

[0458] The device analyzes the received creative material and displays it to the donor.

[0459] Processing donation suggestions via voice input

[0460] Step 1:

[0461] The user inputs voice information into the terminal to inquire about where to donate.

[0462] Step 2:

[0463] The device converts the speech into text, performs sentiment analysis, generates a proposal request, and sends it to the server.

[0464] Step 3:

[0465] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[0466] Step 4:

[0467] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[0468] Step 5:

[0469] The server receives the proposal results, performs speech synthesis, and generates a response.

[0470] Step 6:

[0471] The terminal plays back the received response to the user by voice.

[0472] Processing donation suggestions using an emotion engine

[0473] Step 1:

[0474] The user inputs their interests and emotions into the terminal, and then inputs or speaks their emotions.

[0475] Step 2:

[0476] The terminal generates a proposal request including interest information and emotion information and transmits it to the server.

[0477] Step 3:

[0478] The server passes the received interest information and emotion information to the artificial intelligence model and emotion engine, and requests suggestions for appropriate donation destinations.

[0479] Step 4:

[0480] An artificial intelligence model and emotion engine analyze the input information and suggest the most suitable donation destination.

[0481] Step 5:

[0482] The server receives the suggestions and generates a response to send back to the user.

[0483] Step 6:

[0484] The device analyzes the proposal results and displays them to the user.

[0485] Processing donation effect prediction using emotion engine

[0486] Step 1:

[0487] The user inputs the donation amount and donation recipient on the terminal, and also inputs their feelings.

[0488] Step 2:

[0489] The terminal generates an effect prediction request including input information and emotion information and transmits it to the server.

[0490] Step 3:

[0491] The server passes the received information to the artificial intelligence model and emotion engine and requests an effect prediction.

[0492] Step 4:

[0493] The artificial intelligence model and emotion engine predict the effects based on the input information and generate the predicted results.

[0494] Step 5:

[0495] The server receives the prediction results and generates a response to send back to the user.

[0496] Step 6:

[0497] The terminal analyzes the received prediction results and displays them to the user.

[0498] Processing creative material generation using emotion engine

[0499] Step 1:

[0500] The donor enters the campaign description and sentiment information on the terminal and clicks the "Generate" button.

[0501] Step 2:

[0502] The terminal generates a generation request including description information and emotion information and transmits it to the server.

[0503] Step 3:

[0504] The server passes the received description and emotion information to the generative AI model and requests the generation of creative materials.

[0505] Step 4:

[0506] A generative AI model generates creative materials based on input information.

[0507] Step 5:

[0508] The server receives the generated creative material and generates a response to send back to the contributor.

[0509] Step 6:

[0510] The device analyzes the received creative material and displays it to the donor.

[0511] Example 2

[0512] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0513] In conventional donation campaigns, it was difficult for users to find the best donation recipients and there was a lack of means to predict the effectiveness of donations. Furthermore, there was a lack of support for donors to generate effective creative materials, which reduced the sustainability and efficiency of donation campaigns. Furthermore, there was a lack of voice input to suggest donation recipients and gamification elements to promote donations.

[0514] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0515] In this invention, the server includes means for analyzing a user's emotions and suggesting donation destinations, means for managing the user's donation history, means for predicting the future effects of a user's donation when the user makes a donation, and means for using a generation engine to generate creative materials for those soliciting donations. This allows users to find the optimal donation destination based on their emotions and interests, and by predicting the future effects of donations, it becomes possible to confirm the effectiveness of donation activities. In addition, donation solicitors can easily generate effective creative materials, thereby increasing the sustainability and efficiency of donation activities.

[0516] A "user" is an individual or organization that uses the system to select a donation recipient and carry out a donation activity.

[0517] "Analyzing emotions" refers to the process of identifying the user's emotional state from their input data and providing appropriate donation destinations and suggestions based on that emotion.

[0518] A "donation recipient" is an organization or group selected by the user to receive the donation.

[0519] "Managing donation history" refers to the process of recording information about donations made by a user in the past and making that information available for viewing as needed.

[0520] "Predicting the future effects of donations" refers to the process of predicting what impact a donation made by a user will have in the future and presenting the results to the user.

[0521] "Creative materials" are content materials such as text and images used by donors when conducting campaigns and promotions.

[0522] "Generative engine" refers to an artificial intelligence model or algorithm that automatically generates creative materials based on input data.

[0523] "Voice input" is a method in which a user gives instructions or asks questions to a system using a voice input device such as a microphone.

[0524] "Gamification" is a system that introduces game elements and point systems to encourage users to donate, thereby increasing user involvement.

[0525] This invention supports users' donation activities through a system that combines an emotion engine and an artificial intelligence model. The system has three main components: a server, a terminal, and a user. The role of each component is explained below.

[0526] Initial Setup

[0527] The system's terminals are equipped with interfaces that support voice and text input. Voice input uses a microphone and compatible software (e.g., Google Speech-to-Text API), while text input uses a keyboard or touchscreen. The server incorporates an emotion engine (e.g., IBM Watson Tone Analyzer) and an artificial intelligence model (e.g., GPT-4).

[0528] User donation suggestions

[0529] The user accesses the donation suggestion function via their device and types or speaks, for example, "Please tell me where I should donate to environmental conservation." The device converts the voice data into text and analyzes it with an emotion engine. After analysis, the emotion data and text data are sent to the server.

[0530] The server analyzes the user's emotions using an emotion engine and inputs a prompt to the AI ​​model. For example, "Please suggest donation destinations for positive users who are interested in environmental protection." The AI ​​model generates a list of relevant donation destinations based on the prompt.

[0531] The generated donation list is sent from the server to the terminal and displayed or audibly notified to the user, allowing the user to find the most suitable donation destination based on their feelings and interests.

[0532] Donation history management

[0533] The donation history made by the user is stored in a database on the server (e.g., MySQL). The user sends a request from the terminal, and the server retrieves the donation history from the database and displays it on the terminal. This allows the user to understand their past donation activity at a glance.

[0534] Predicting the impact of donations

[0535] The user inputs the donation amount and donation recipient, as well as their emotions at the time. The device sends the information to the server, which uses an emotion engine and an artificial intelligence model to predict the impact of the donation. The prediction results are sent to the device and displayed to the user, allowing them to see the future impact of their donation.

[0536] Creative Material Generation

[0537] The donor inputs the campaign description and emotion information. The device sends this to the server, which then uses a generation engine (e.g., DALL-E) and emotion engine to generate creative materials. The generated materials are sent to the device, and the donor can use them to develop their campaign.

[0538] Voice suggestions

[0539] When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server understands the user's intention and suggests the most appropriate donation destination. The device then conveys the results to the user via voice.

[0540] Gamification elements

[0541] The system incorporates gamification elements to make donations more enjoyable and sustainable. When a user makes a donation and positive emotions are analyzed, points are awarded. Points are managed on the server and displayed on the device.

[0542] Specific examples

[0543] When a user voice-inputs "Please tell me where to donate to environmental conservation," the device converts the speech to text using the Google Speech-to-Text API and then performs sentiment analysis using IBM Watson Tone Analyzer. The analysis results are sent to the server, which then inputs the prompt into a GPT-4 model to generate a list of donations. The list is then sent to the device and notified to the user via voice. This series of processes allows the user to find appropriate donation destinations for environmental conservation.

[0544] As described above, the system of the present invention supports optimal donation activities based on the user's emotions and interests. By utilizing generative AI models and prompts, the efficiency and effectiveness of donation activities can be significantly improved.

[0545] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0546] Step 1:

[0547] The user accesses the donation suggestion function. The user either inputs text or voice into the device's input interface, saying, "Please tell me where I can donate to environmental conservation." In the case of voice input, the device collects the voice and converts it into text. This converts the voice data into text data.

[0548] Input: User text or voice input

[0549] Output: Text data

[0550] Step 2:

[0551] The text data collected by the device is sent to a server for sentiment analysis. The server receives the text data and passes it to an emotion engine (e.g., IBM Watson Tone Analyzer) for sentiment analysis. Here, the user's emotional state is analyzed, and positive emotions, for example, are detected. The results of this analysis are also saved as data.

[0552] Input: Text data

[0553] Output: Emotion analysis results

[0554] Step 3:

[0555] The server combines the sentiment analysis results with the text data to input a prompt into an AI model (e.g., GPT-4). The prompt takes the form of "Please suggest donation destinations for positive users who are interested in environmental protection." The generative AI model then uses this prompt and the data to suggest appropriate donation destinations.

[0556] Input: Sentiment analysis results and text data

[0557] Output: Donation list

[0558] Step 4:

[0559] The server sends the generated list of donation recipients to the device. The device displays the list of donation recipients received from the server to the user. If voice input is used, the device synthesizes voice and tells the user the results by voice. This allows the user to find the most suitable donation recipient.

[0560] Input: Donation list

[0561] Output: Display or audio notification

[0562] Step 5:

[0563] The user selects a donation recipient and makes a donation. The device sends the donation information to the server. The server saves the donation history in a database and manages new history data. This data is saved so that the user can refer to it later.

[0564] Input: Donation information

[0565] Output: Database update

[0566] Step 6:

[0567] When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the user's donation history from the database and sends it to the device. The device then displays the received history data to the user.

[0568] Input: History confirmation request

[0569] Output: Donation history data

[0570] Step 7:

[0571] When a donor starts a new campaign, they input a campaign description and emotional information. The device sends this information to the server, which then uses a generation engine (e.g., DALL-E) and an emotional engine to generate creative materials. The generated materials are sent to the device, where the donor receives and uses them.

[0572] Input: Campaign description and sentiment information

[0573] Output: Creative materials

[0574] Step 8:

[0575] To encourage donations, the system incorporates gamification elements. When a user makes a donation and positive emotions are analyzed, the system awards points. The point information is managed on the server and displayed on the device.

[0576] Input: Donation information and sentiment analysis results

[0577] Output: Display of points awarded and point information

[0578] (Application example 2)

[0579] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0580] Conventional donation support systems make suggestions and predictions without considering the user's emotions, which means they are unable to fully attract the user's attention. Furthermore, in the advertising field, personalization is lacking, preventing optimal ad display tailored to the user's emotions. Furthermore, generating ads in real time is difficult, which can sometimes detract from the user experience. To solve these issues, a comprehensive system that combines emotion analysis and generative AI models is needed.

[0581] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0582] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing the user's emotions using an emotion analysis engine and personalizing the suggested information, and means for generating advertisements to be displayed on the smart device in real time, thereby enabling optimal donation destination suggestions based on the user's emotions, personalized advertisement display, and real-time advertisement generation.

[0583] An "artificial intelligence model" is a computer program used to suggest optimal donation destinations through analysis of user data.

[0584] "Donation history" is data that records and manages detailed information about donations made by a user in the past.

[0585] "Donation effect prediction" is a function that predicts the future social impact of a donation based on a user's donation behavior.

[0586] A "generative AI model" is an artificial intelligence algorithm used to automatically generate advertising or creative materials.

[0587] An "emotion analysis engine" is a system that analyzes a user's emotional state from their facial expressions and voice, and makes appropriate suggestions based on that data.

[0588] "Personalization" refers to optimizing information and services to suit the individual interests and feelings of each user.

[0589] "Real-time" refers to the process of acquiring data, analyzing it, and providing the results being carried out instantly.

[0590] "Smart devices" are portable electronic devices with advanced computing capabilities, such as smartphones and smart glasses.

[0591] "Advertising" means information intended to promote a product or service.

[0592] MODE FOR CARRYING OUT THE INVENTION

[0593] This invention is a system that combines an emotion engine and a generative AI model to support donation activities and personalize advertisements based on user emotions. This system interacts with users through smart devices such as smartphones and smart glasses.

[0594] Hardware and software used

[0595] Hardware:

[0596] Smartphone

[0597] Smart Glasses

[0598] server

[0599] Audio input device

[0600] software:

[0601] Emotion Analysis Engine (EmotionEngine)

[0602] Ad generation AI model (AdGenerator)

[0603] User Data Management System

[0604] System processing explanation

[0605] 1. Acquiring emotion data:

[0606] When a user uses a smart device to consider where to donate, the device collects emotional data in real time through facial recognition and voice analysis. For example, the camera in smart glasses can read the user's facial expressions and analyze them with an emotion analysis engine.

[0607] 2. Use of sentiment analysis results:

[0608] The acquired emotional data is sent to a server and analyzed by an emotion analysis engine (EmotionEngine). Based on the results of this analysis, the most appropriate donation recipients and advertisements are selected.

[0609] 3. Suggested donations:

[0610] The server uses an artificial intelligence model to combine the analysis results with the user's past donation history to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and has positive feelings, relevant non-profit organizations will be suggested.

[0611] 4. Ad generation and display:

[0612] Based on the results of the sentiment analysis, an ad generation AI model (AdGenerator) generates ads in real time and displays them on smart devices. For example, if a user is excited, an ad for a new gadget will be displayed on the HUD of smart glasses.

[0613] 5. Analysis of voice input:

[0614] The system also supports voice input, so when a user voices their preference for a donation destination, the device converts the voice into text, performs sentiment analysis, and sends it to the server. The server then uses text analysis and an emotion engine to understand the user's intent and suggests the most appropriate donation destination.

[0615] Specific examples

[0616] The user puts on the smart glasses and speaks, "Please tell me where I should donate to environmental conservation." This voice data is picked up through the smart glasses' microphone and analyzed by the sentiment analysis engine. If the user's sentiment is confirmed to be positive, the server suggests relevant nonprofit organizations. The generative AI model then generates appropriate creative materials, and this information is displayed on the smart glasses' HUD.

[0617] Example prompt sentence:

[0618] "The user's current emotion is excitement. Create an ad for a new electronic gadget that builds on this emotion. The target users are men in their 20s who are interested in the latest technology."

[0619] The above is a detailed description of the embodiment of the present invention, which enables suggestions of donation destinations based on the user's emotions and generation of personalized real-time advertisements.

[0620] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0621] Step 1:

[0622] The device acquires the user's emotional data. The device captures the user's facial expressions and voice using a camera and microphone through a smart device (for example, smart glasses or a smartphone). The input is facial expression data and voice data, and the output is input data to the emotion analysis engine. Specifically, the device takes a picture of the user's face and acquires the image data.

[0623] Step 2:

[0624] The device sends the acquired emotional data to an emotion analysis engine, which analyzes the data and identifies the user's emotional state. The input is facial expression data and voice data, and the output is emotional state information. Specifically, the emotion analysis engine identifies the user's current emotion (e.g., positive, negative, excited, etc.) from the facial expression data.

[0625] Step 3:

[0626] The server generates optimal donation destinations and advertisements based on the results of the sentiment analysis. It uses an AI model to make optimal suggestions based on the sentiment analysis results and the user's past donation history. The input is emotional state information and donation history, and the output is donation destination suggestions or advertising content. Specifically, the AI ​​model selects nonprofit organizations and advertisements that are appropriate for the emotional state.

[0627] Step 4:

[0628] The server passes the generated advertising content to a generative AI model, which generates creative materials (e.g., text, images) based on the prompt. The input is the advertising content and the prompt, and the output is the generated creative materials. Specifically, the generative AI model generates advertising copy and images based on the specified prompt.

[0629] Step 5:

[0630] The server sends the generated creative materials to the device. The device receives them and displays them to the user. The input is the generated creative materials, and the output is the content displayed to the user. Specifically, the device displays advertisements on the HUD of smart glasses or on the screen of a smartphone.

[0631] Step 6:

[0632] The user confirms the displayed content and takes adaptive action (e.g., making a donation or clicking on an advertisement). The input is the displayed advertisement and donation proposal, and the output is the user's behavioral data. Specifically, the user confirms the donation selection and completes the donation procedure on their smartphone.

[0633] As described above, through the specific processing performed at each step, optimal donation destination suggestions and personalized advertisement displays based on the user's emotions are realized.

[0634] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0635] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0636] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0637] [Second embodiment]

[0638] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0639] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0640] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0641] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0642] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0643] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0644] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0645] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0646] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0647] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0648] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0649] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0650] The present invention provides a comprehensive system for solving various problems in donation activities. The system unifies the management of online and offline donation activities and supports donation activities for both users and donors.

[0651] User donation suggestions

[0652] This system uses an artificial intelligence model to make optimal suggestions when users choose a donation recipient. When a user inputs their interests, the server passes that information to the artificial intelligence model, which then suggests appropriate donation recipients. For example, if a user is interested in environmental protection, the system will suggest relevant nonprofit organizations.

[0653] Donation history management

[0654] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[0655] Predicting the impact of donations

[0656] When a user makes a donation, the system also provides a function to predict the future impact of that donation. When a user inputs the donation amount and the recipient, the server uses an artificial intelligence model based on that information to predict the impact and communicates the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[0657] Creative Material Generation

[0658] The server has the ability to provide donors with creative materials using a generative AI model. When donors start a new campaign and need materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server. This allows donors to easily launch compelling campaigns.

[0659] Voice suggestions

[0660] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text, understands the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[0661] Gamification elements

[0662] The system incorporates gamification elements to make donations sustainable. Users are awarded points every time they donate, and can earn rewards based on those points. This point system makes donations fun and easy to continue.

[0663] Specific examples

[0664] Suppose a user is considering donating to a nonprofit organization but is unsure which one is best. The user accesses a device and speaks, "Please tell me where I can donate to environmental conservation." The device converts this speech into text and sends it to a server. The server passes this information to an artificial intelligence model, which generates several optimal suggestions. The server then returns the results to the device, which then verbally communicates them to the user. The user then selects a donation destination based on these suggestions and makes the donation.

[0665] As described above, the present invention provides a system for efficiently and effectively supporting donation activities for both users and donors.

[0666] The processing flow will be explained below.

[0667] Handling new user registrations

[0668] Step 1:

[0669] The user enters their username, password, and email address on the device and clicks the "Register" button.

[0670] Step 2:

[0671] The terminal generates a registration request including the input information and sends it to the server.

[0672] Step 3:

[0673] The server checks its database to see if the username already exists.

[0674] Step 4:

[0675] If the server determines that the user is new, it saves the user information in the database.

[0676] Step 5:

[0677] The server generates a registration success message and sends it to the terminal.

[0678] Step 6:

[0679] The terminal displays a registration success message to notify the user that registration is complete.

[0680] Processing user donation suggestions

[0681] Step 1:

[0682] The user enters their interests on the device and clicks the "Suggest" button.

[0683] Step 2:

[0684] The terminal generates a proposal request including the interest information and transmits it to the server.

[0685] Step 3:

[0686] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[0687] Step 4:

[0688] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[0689] Step 5:

[0690] The server receives the suggestions and generates a response to send back to the user.

[0691] Step 6:

[0692] The device analyzes the proposal results and displays them to the user.

[0693] Processing donation history verification

[0694] Step 1:

[0695] The user clicks the button to display "Donation History" on the device.

[0696] Step 2:

[0697] The terminal generates a history request including the user ID and sends it to the server.

[0698] Step 3:

[0699] The server connects to the database based on the received user ID and retrieves past donation history.

[0700] Step 4:

[0701] The server formats the donation history and generates a response to send back to the user.

[0702] Step 5:

[0703] The terminal analyzes the received donation history and displays it to the user.

[0704] Processing donation impact forecasts

[0705] Step 1:

[0706] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[0707] Step 2:

[0708] The terminal generates an effect prediction request including the input information and transmits it to the server.

[0709] Step 3:

[0710] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[0711] Step 4:

[0712] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[0713] Step 5:

[0714] The server receives the prediction results and generates a response to send back to the user.

[0715] Step 6:

[0716] The terminal analyzes the received prediction results and displays them to the user.

[0717] Creative material generation process

[0718] Step 1:

[0719] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[0720] Step 2:

[0721] The terminal generates a generation request including the description information and transmits it to the server.

[0722] Step 3:

[0723] The server passes the received description information to the generative artificial intelligence model and requests the generation of creative materials.

[0724] Step 4:

[0725] A generative artificial intelligence model generates creative materials based on input information.

[0726] Step 5:

[0727] The server receives the generated creative material and generates a response to send back to the contributor.

[0728] Step 6:

[0729] The device analyzes the received creative material and displays it to the donor.

[0730] Processing donation suggestions via voice input

[0731] Step 1:

[0732] The user inputs voice information into the terminal to inquire about where to donate.

[0733] Step 2:

[0734] The device converts the speech to text, generates a suggestion request, and sends it to the server.

[0735] Step 3:

[0736] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[0737] Step 4:

[0738] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[0739] Step 5:

[0740] The server receives the proposal results, performs speech synthesis, and generates a response.

[0741] Step 6:

[0742] The terminal plays back the received response to the user by voice.

[0743] Example 1

[0744] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0745] In conventional donation systems, users have difficulty finding appropriate donation recipients and lack the ability to predict the impact of donations. In addition, donors have to create the materials they need to launch effective campaigns, and there are limited ways to increase the sustainability of donation activities. Furthermore, the lack of voice input to suggest donation recipients and the lack of elements that make the donation activity itself enjoyable leads to problems with people not continuing to donate.

[0746] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0747] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the effectiveness of donations for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing voice input to suggest donation destinations for the user, and means for providing donation activities with gamification elements and awarding points when the user makes a donation. This not only allows users to easily find appropriate donation destinations and predict the effectiveness of their donations, but also allows donors to quickly launch effective campaigns. Furthermore, the donation suggestions using voice input and gamification elements make donation activities more enjoyable and sustainable.

[0748] The "artificial intelligence model" is a machine learning algorithm that suggests appropriate donation destinations based on user input information.

[0749] The "donation history management means" is a system that stores and manages the history of donations made by users in the past and provides information to users as needed.

[0750] The "donation effect prediction means" is a system that predicts the future effect of a donation based on the amount donated by the user and the donation recipient.

[0751] A "generative artificial intelligence model" is a machine learning algorithm that automatically generates creative materials (such as text and images) based on a description of a new campaign.

[0752] The "voice input analysis means" is a system that converts information input by voice by the user into text, analyzes it, and suggests appropriate donation destinations.

[0753] "Gamification elements" are elements that introduce point systems and rewards to make users' donation activities fun and easy to continue.

[0754] "Rewards" are rewards or benefits that users can earn based on the points they have been awarded.

[0755] The present invention is a system that supports effective donation activities for both users and donors. The system provides the following main functions:

[0756] User donation suggestions

[0757] When a user selects a donation destination, the system uses an artificial intelligence model to make the most appropriate suggestions. When a user inputs their interests into the device, the device sends the information to a server. The server passes it on to an artificial intelligence model, which then suggests the most appropriate donation destination. The artificial intelligence model used here is a machine learning algorithm built using Python. For example, if a user inputs "Please tell me where I should donate to environmental protection," the system will suggest relevant non-profit organizations.

[0758] Donation history management

[0759] A user's donation history is managed by the server. When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the history information from the database and displays it on the device. A relational database management system such as MySQL is used to manage this database. This allows users to see their past donation activity at a glance.

[0760] Predicting the impact of donations

[0761] When users make a donation, they are also provided with a function to predict the future impact of their donation. After the user enters the donation amount and recipient, the device sends that information to a server. The server uses an artificial intelligence model to predict the impact and returns the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[0762] Creative Material Generation

[0763] When a donor starts a new campaign, the server uses a generative AI model to provide creative materials. When a donor enters a campaign description, the generative AI model automatically creates creative materials such as images and text and sends them to the server. This generative AI model combines natural language processing (NLP) and computer vision (CV) technologies.

[0764] Voice suggestions

[0765] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice. This speech recognition uses voice recognition software (e.g., Google Speech-to-Text API).

[0766] Gamification elements

[0767] To make donations sustainable, the system incorporates gamification elements. Users are awarded points every time they donate, and can earn rewards based on those points. The point system is designed to increase user motivation.

[0768] Specific examples

[0769] Here is a specific example of a case where a user is unsure where to donate. The user voice-inputs into the device, "Please tell me where to donate to environmental conservation." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model to suggest the most suitable donation destination and transmits the result to the device. The device then replies with the result by voice to the user, who then chooses a donation destination based on the suggestions and makes the donation.

[0770] Example prompt for a generative AI model:

[0771] The user has indicated that they are interested in "environmental protection." Please suggest the best related donations.

[0772] The present invention provides a system that allows both users and donors to carry out donation activities efficiently and effectively.

[0773] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0774] Processing flow for user donation suggestions

[0775] Step 1:

[0776] The user inputs their interests into the terminal.

[0777] Specific operation: The user enters text of an area of ​​interest, such as "environmental protection," into the input form on the device.

[0778] Input: User-entered data (interests)

[0779] Output: Interest data entered into the device

[0780] Step 2:

[0781] The terminal sends the input information to the server.

[0782] Specific operation: The terminal forms user input data and transfers it to the server as an HTTP request.

[0783] Input: User-entered data

[0784] Output: Request data sent to the server

[0785] Step 3:

[0786] The server passes the information to an artificial intelligence model.

[0787] Specific operation: The server analyzes the received data and inputs it as prompts into the artificial intelligence model.

[0788] Input: Request data

[0789] Output: Prompt data

[0790] Step 4:

[0791] An artificial intelligence model generates the suggestions.

[0792] How it works: The AI ​​model generates relevant donation destinations based on the prompt data.

[0793] Input: prompt data

[0794] Output: Donation proposal data

[0795] Step 5:

[0796] The server sends the proposal results to the terminal.

[0797] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[0798] Input: Donation proposal data

[0799] Output: Proposal data sent to the device

[0800] Step 6:

[0801] The terminal displays the suggestion results to the user.

[0802] Specific operation: The terminal displays the received proposal data on the user interface.

[0803] Input: Proposal data

[0804] Output: The suggestions displayed to the user

[0805] Donation history management process flow

[0806] Step 1:

[0807] The server stores the user's donation history in a database.

[0808] Specific operation: The server writes the information of each donation operation to the database.

[0809] Input: Donation data

[0810] Output: Historical data stored in a database

[0811] Step 2:

[0812] The user sends a history check request from the terminal.

[0813] Specific operation: The user generates a request by pressing the "Check History" button on the device.

[0814] Input: User operation data

[0815] Output: Request data sent to the server

[0816] Step 3:

[0817] The server retrieves the history information from the database.

[0818] Specific operation: The server searches and retrieves the corresponding historical data from the database in response to the request.

[0819] Input: Request data

[0820] Output: Retrieved historical data

[0821] Step 4:

[0822] The server transmits the history information to the terminal.

[0823] Specific operation: The server sends the acquired history data to the terminal as an HTTP response.

[0824] Input: Historical data

[0825] Output: Historical data sent to the terminal

[0826] Step 5:

[0827] The terminal displays the history to the user.

[0828] Specific operation: The terminal displays the received history data on the user interface.

[0829] Input: Historical data

[0830] Output: History information displayed to the user

[0831] Donation effect prediction process flow

[0832] Step 1:

[0833] The user enters the donation amount and donation destination into the terminal.

[0834] Specific operation: The user enters the donation amount and donation destination into the donation form.

[0835] Input: Donation amount and donation recipient data

[0836] Output: Donation data entered into the terminal

[0837] Step 2:

[0838] The terminal sends the input information to the server.

[0839] Specific operation: The terminal inputs donation data and transmits it to the server as an HTTP request.

[0840] Input: Donation data

[0841] Output: Request data sent to the server

[0842] Step 3:

[0843] The server uses an artificial intelligence model to predict the effectiveness of donations.

[0844] Specific operation: The server inputs the received data into the AI ​​model and makes a prediction.

[0845] Input: Donation data

[0846] Output: Prediction result data

[0847] Step 4:

[0848] The server sends the prediction results to the device.

[0849] Specific operation: The server sends the generated prediction result data to the terminal as an HTTP response.

[0850] Input: Prediction result data

[0851] Output: Prediction result data sent to the device

[0852] Step 5:

[0853] The terminal displays the predicted effect to the user.

[0854] Specific operation: The terminal displays the received prediction result data on the user interface.

[0855] Input: Prediction result data

[0856] Output: Predicted effect information displayed to the user

[0857] Creative material generation process flow

[0858] Step 1:

[0859] A donor types a new campaign description into a terminal.

[0860] Specific operation: The donor enters a description of the campaign into the input form on the terminal.

[0861] Input: Campaign description data

[0862] Output: Campaign data entered into the terminal

[0863] Step 2:

[0864] The terminal sends the input information to the server.

[0865] Specific operation: The device sends campaign data to the server as an HTTP request.

[0866] Input: Campaign description data

[0867] Output: Request data sent to the server

[0868] Step 3:

[0869] The server generates creative materials using generative AI models.

[0870] Specific operation: The server inputs the received data into a generative AI model to generate creative materials.

[0871] Input: Campaign description data

[0872] Output: Generated creative material data

[0873] Step 4:

[0874] The server transmits the generated material to the terminal.

[0875] Specific operation: The server sends the generated material data to the terminal as an HTTP response.

[0876] Input: Creative material data

[0877] Output: Material data sent to the device

[0878] Step 5:

[0879] The device displays the creative material to the donor.

[0880] Specific operation: The terminal displays the received creative material data on the user interface.

[0881] Input: Creative material data

[0882] Output: Creative material displayed to donors

[0883] Voice suggestion process flow

[0884] Step 1:

[0885] The user speaks to the terminal about where to donate.

[0886] Specific operation: The user speaks into the microphone, saying something like, "Please tell me where to donate to environmental conservation."

[0887] Input: Audio data

[0888] Output: Audio data input to the device

[0889] Step 2:

[0890] The device converts the speech into text and sends it to the server.

[0891] Specific operation: The terminal converts the voice data into text data and transfers it to the server as an HTTP request.

[0892] Input: Audio data

[0893] Output: Text data sent to the server

[0894] Step 3:

[0895] The server analyzes the text and uses an artificial intelligence model to suggest donation destinations.

[0896] Specific operation: The server analyzes the received text data, inputs it into an artificial intelligence model, and generates the optimal donation destination.

[0897] Input: Text data

[0898] Output: Donation proposal data

[0899] Step 4:

[0900] The server sends the proposal results to the terminal.

[0901] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[0902] Input: Donation proposal data

[0903] Output: Proposal data sent to the device

[0904] Step 5:

[0905] The device returns the proposed results to the user by voice.

[0906] Specific operation: The device uses voice synthesis technology to output the received proposal data as a voice response to the user.

[0907] Input: Proposal data

[0908] Output: Spoken suggestions

[0909] Gamification element processing flow

[0910] Step 1:

[0911] A user makes a donation.

[0912] Specific operation: The user enters the donation amount and donation recipient into the donation form on the device and clicks the donate button.

[0913] Input: Donation data

[0914] Output: Donation data sent from the device to the server

[0915] Step 2:

[0916] The server awards points to the user.

[0917] Specific operation: The server receives the donation data, calculates the corresponding points and adds them to the user's account.

[0918] Input: Donation data

[0919] Output: Points added to the account

[0920] Step 3:

[0921] The server calculates rewards based on the points.

[0922] Specific operation: The server checks the user's accumulated points and calculates the reward accordingly.

[0923] Input: Point data

[0924] Output: Reward data

[0925] Step 4:

[0926] The server transmits the reward information to the terminal.

[0927] Specific operation: The server sends the calculated reward data to the terminal as an HTTP response.

[0928] Input: Reward data

[0929] Output: Reward data sent to the device

[0930] Step 5:

[0931] The terminal displays the reward to the user.

[0932] Specific operation: The terminal displays the received reward data on the user interface.

[0933] Input: Reward data

[0934] Output: Reward information displayed to the user

[0935] (Application example 1)

[0936] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0937] In modern donation activities, users have difficulty selecting appropriate donation recipients and there is a lack of ways to predict the impact of donations. Furthermore, donors are burdened with the task of creating attractive campaign materials. Furthermore, there is a lack of gamification elements to make donation activities sustainable.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0939] In this invention, the server includes means for using an artificial intelligence model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative artificial intelligence model to generate creative materials for the donor, means for suggesting optimal donation destinations based on the user's purchase history and interests, means for checking the user's donation history using an application, and means for making donations at the same time as purchases and predicting and displaying the effects. This makes it easy for users to select appropriate donation destinations and predict and confirm the effects of donation activities. It also reduces the burden on donors and allows them to develop attractive campaigns, allowing them to continue enjoying donation activities.

[0940] An "artificial intelligence model" is a computer program that analyzes user data and suggests appropriate donation destinations.

[0941] "Donation history" is detailed information about donations made by a user in the past, including donation recipients, donation amounts, donation dates, and the like.

[0942] "Donation impact" is the result that predicts how a user's donation will benefit a particular cause.

[0943] A "generative artificial intelligence model" is a computer program that automatically generates creative materials for contributors.

[0944] "User purchase history" is detailed information about products purchased by the user in the past, and is data including product names, purchase dates, purchase amounts, and the like.

[0945] "User interests" refers to information about themes or fields in which a user is particularly interested.

[0946] "Means for checking through the application" refers to a means by which users can view their donation history through the software they use.

[0947] The "means for predicting and displaying the effect of donation activities" is a means for calculating how useful a donation will be when a user makes a donation and displaying the result to the user.

[0948] "Gamification elements" are ideas and mechanisms that make donation activities fun, like a game, and easier to continue sustainably.

[0949] The "means for awarding points" is a points system that awards points to users who make donations.

[0950] The present invention is a system for facilitating users' donation activities. This system has various functions for suggesting donation destinations for users, managing donation history, predicting the impact of donations, and providing creative materials to donors.

[0951] System Configuration

[0952] The system mainly consists of the following elements:

[0953] Artificial Intelligence Model

[0954] Generative AI Model

[0955] Database

[0956] server

[0957] User devices (smartphones, tablets, PCs, etc.)

[0958] Program Generation

[0959] First, the system collects interest and purchase history data from users. When users choose a donation destination, an AI model uses this data to suggest the most appropriate donation destination. For example, if a user enters data indicating an interest in "environmental protection," the system will suggest related nonprofit organizations.

[0960] Next, the user's donation history is stored in a database, and when the user requests it, the server retrieves the information and displays it on the terminal, allowing the user to easily check their past donation activity.

[0961] Furthermore, the donation amount and donation recipient information are sent to the server to predict the impact of the user's donation. The server then uses this information to make a prediction using an artificial intelligence model, which then returns the results to the user. For example, if a user donates a specific amount to an environmental protection project, the server predicts and displays the impact that the donation will have.

[0962] Fundraisers can also use generative artificial intelligence models to automatically generate creative materials for their campaigns. Fundraisers enter a description of their campaign, and the system generates materials such as text and images based on that description.

[0963] System action

[0964] The following hardware and software are used for processing in this system:

[0965] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[0966] Software: Artificial intelligence models (e.g., OpenAI API), databases (e.g., MySQL or PostgreSQL), generative AI (e.g., OpenAI GPT-3)

[0967] Specific examples

[0968] The user selects "environmental protection" as a topic of interest and then voice-inputs, "Please tell me where I can donate to environmental protection." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model based on this information to suggest the most appropriate donation destination and returns the result to the device.

[0969] Example prompt sentence:

[0970] "Create a persuasive advertisement for the following campaign: New fundraising campaign for forest restoration."

[0971] In this way, the system can efficiently and effectively support donation activities by suggesting donation destinations, managing donation history, predicting donation effects, and providing creative materials using generative AI models. This system makes donation activities more convenient for both users and donors.

[0972] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0973] Step 1:

[0974] Users input their interest data and purchase history data. The device receives this data and sends it to the server. The input data includes areas of interest (e.g., "environmental protection") and detailed information about purchased products (e.g., "eco-friendly toothbrushes"). The server receives this data and stores it in a database.

[0975] Step 2:

[0976] A user requests donation suggestions. For example, they can say, "Please tell me where to donate to environmental conservation." The device converts this speech into text and sends it to the server. The input is voice data, and the output is text data. The server inputs the text into an artificial intelligence model and generates a list of optimal donation destinations.

[0977] Step 3:

[0978] The server returns a list of donation recipients suggested by the AI ​​model to the device. The user reviews the list and selects a donation recipient. The generated list includes multiple nonprofit organizations and projects. Once the user makes a selection, the selection data is sent to the server.

[0979] Step 4:

[0980] When a user decides to donate, the device sends donation information (donation recipient, donation amount, etc.) to the server. The server records this information in a database and uses an artificial intelligence model to predict the impact of the donation. The input data is the donation recipient and donation amount, and the output data is the predicted impact.

[0981] Step 5:

[0982] The server sends the predicted donation effect to the terminal and displays it to the user, who can see the specific effect of the donation (e.g., "Donating $100 will plant 10 trees").

[0983] Step 6:

[0984] When a donor starts a new campaign, they send a campaign description from their device to the server, which then inputs it into a generative AI model to generate creative materials (text, images, etc.). The input is the campaign description text, and the output is the creative materials.

[0985] Step 7:

[0986] The generated creative materials are sent from the server to the donor's device, where they can be viewed and used, enabling the donor to launch an engaging campaign in a short space of time.

[0987] Step 8:

[0988] When a user wants to check their donation history, they send a request from their device. The server retrieves the user's donation history from the database and sends it to the device. The input is the user ID, and the output is the donation history data.

[0989] Step 9:

[0990] The system provides gamification elements, awarding points each time a user makes a donation. The points based on the user's donation behavior are calculated on the server and recorded in a database. This allows users to have fun while contributing to society through donations.

[0991] As a result, this system can efficiently and effectively support donation activities for both users and donors.

[0992] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0993] This invention provides a comprehensive system that combines an emotion engine to solve various problems in donation activities. This system analyzes users' emotions and, based on this, makes donation suggestions, predicts donation effects, and generates creative materials.

[0994] User donation suggestions

[0995] When a user selects a donation destination, this system uses an artificial intelligence model and an emotion engine to make optimal suggestions. When a user inputs their interests and emotions, the server passes that information to the emotion engine and artificial intelligence model to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and expresses positive emotions, the system will suggest relevant non-profit organizations.

[0996] Donation history management

[0997] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[0998] Predicting the impact of donations

[0999] When a user makes a donation, the system also provides a function to predict the future impact of that donation. The user enters the donation amount, the donation recipient, and their emotion at the time. The server uses this information to predict the impact using an artificial intelligence model and emotion engine, and notifies the user of the results. For example, if the emotion engine detects the user's excited state, the donation may be predicted to be more impactful.

[1000] Creative Material Generation

[1001] The server has the function of providing donors with creative materials using a generative AI model and emotion engine. When a donor starts a new campaign and needs materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server and the donor's emotional information. This allows donors to easily launch compelling campaigns.

[1002] Voice suggestions

[1003] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server uses text analysis and an emotion engine to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[1004] Gamification elements

[1005] The system incorporates gamification elements to make donations sustainable. If positive emotions are detected each time a user makes a donation, more points are awarded. This makes donations fun and easy to continue.

[1006] Specific examples

[1007] Suppose a user is unsure where to donate, but is interested in environmental protection and expresses positive emotions. The user accesses the device and speaks, "Please tell me where to donate to environmental protection." The device converts this speech into text, analyzes the emotion using an emotion engine, and sends it to the server. The server passes this information to an AI model and emotion engine, which suggests several optimal donation destinations. The server then returns the results to the device, which then communicates them to the user via voice. The user chooses a donation destination based on these suggestions and makes a donation.

[1008] As described above, the present invention provides a system that analyzes user emotions to more effectively suggest donations, predict the effects of donations, and generate creative materials, thereby enabling efficient and effective support for donation activities for both users and donors.

[1009] The processing flow will be explained below.

[1010] Handling new user registrations

[1011] Step 1:

[1012] The user enters their username, password, and email address on the device and clicks the "Register" button.

[1013] Step 2:

[1014] The terminal generates a registration request including the input information and sends it to the server.

[1015] Step 3:

[1016] The server checks its database to see if the username already exists.

[1017] Step 4:

[1018] If the server determines that the user is new, it saves the user information in the database.

[1019] Step 5:

[1020] The server generates a registration success message and sends it to the terminal.

[1021] Step 6:

[1022] The terminal displays a registration success message to notify the user that registration is complete.

[1023] Processing user donation suggestions

[1024] Step 1:

[1025] The user enters their interests on the device and clicks the "Suggest" button.

[1026] Step 2:

[1027] The terminal generates a proposal request including the interest information and transmits it to the server.

[1028] Step 3:

[1029] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1030] Step 4:

[1031] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[1032] Step 5:

[1033] The server receives the suggestions and generates a response to send back to the user.

[1034] Step 6:

[1035] The device analyzes the proposal results and displays them to the user.

[1036] Processing donation history verification

[1037] Step 1:

[1038] The user clicks the button to display "Donation History" on the device.

[1039] Step 2:

[1040] The terminal generates a history request including the user ID and sends it to the server.

[1041] Step 3:

[1042] The server connects to the database based on the received user ID and retrieves past donation history.

[1043] Step 4:

[1044] The server formats the donation history and generates a response to send back to the user.

[1045] Step 5:

[1046] The terminal analyzes the received donation history and displays it to the user.

[1047] Processing donation impact forecasts

[1048] Step 1:

[1049] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[1050] Step 2:

[1051] The terminal generates an effect prediction request including the input information and transmits it to the server.

[1052] Step 3:

[1053] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[1054] Step 4:

[1055] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[1056] Step 5:

[1057] The server receives the prediction results and generates a response to send back to the user.

[1058] Step 6:

[1059] The terminal analyzes the received prediction results and displays them to the user.

[1060] Creative material generation process

[1061] Step 1:

[1062] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[1063] Step 2:

[1064] The terminal generates a generation request including the description information and transmits it to the server.

[1065] Step 3:

[1066] The server passes the received description information to the generative AI model and requests the generation of creative materials.

[1067] Step 4:

[1068] A generative AI model generates creative materials based on input information.

[1069] Step 5:

[1070] The server receives the generated creative material and generates a response to send back to the contributor.

[1071] Step 6:

[1072] The device analyzes the received creative material and displays it to the donor.

[1073] Processing donation suggestions via voice input

[1074] Step 1:

[1075] The user inputs voice information into the terminal to inquire about where to donate.

[1076] Step 2:

[1077] The device converts the speech into text, performs sentiment analysis, generates a proposal request, and sends it to the server.

[1078] Step 3:

[1079] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1080] Step 4:

[1081] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[1082] Step 5:

[1083] The server receives the proposal results, performs speech synthesis, and generates a response.

[1084] Step 6:

[1085] The terminal plays back the received response to the user by voice.

[1086] Processing donation suggestions using an emotion engine

[1087] Step 1:

[1088] The user inputs their interests and emotions into the terminal, and then inputs or speaks their emotions.

[1089] Step 2:

[1090] The terminal generates a proposal request including interest information and emotion information and transmits it to the server.

[1091] Step 3:

[1092] The server passes the received interest information and emotion information to the artificial intelligence model and emotion engine, and requests suggestions for appropriate donation destinations.

[1093] Step 4:

[1094] An artificial intelligence model and emotion engine analyze the input information and suggest the most suitable donation destination.

[1095] Step 5:

[1096] The server receives the suggestions and generates a response to send back to the user.

[1097] Step 6:

[1098] The device analyzes the proposal results and displays them to the user.

[1099] Processing donation effect prediction using emotion engine

[1100] Step 1:

[1101] The user inputs the donation amount and donation recipient on the terminal, and also inputs their feelings.

[1102] Step 2:

[1103] The terminal generates an effect prediction request including input information and emotion information and transmits it to the server.

[1104] Step 3:

[1105] The server passes the received information to the artificial intelligence model and emotion engine and requests an effect prediction.

[1106] Step 4:

[1107] The artificial intelligence model and emotion engine predict the effects based on the input information and generate the predicted results.

[1108] Step 5:

[1109] The server receives the prediction results and generates a response to send back to the user.

[1110] Step 6:

[1111] The terminal analyzes the received prediction results and displays them to the user.

[1112] Processing creative material generation using emotion engine

[1113] Step 1:

[1114] The donor enters the campaign description and sentiment information on the terminal and clicks the "Generate" button.

[1115] Step 2:

[1116] The terminal generates a generation request including description information and emotion information and transmits it to the server.

[1117] Step 3:

[1118] The server passes the received description and emotion information to the generative AI model and requests the generation of creative materials.

[1119] Step 4:

[1120] A generative AI model generates creative materials based on input information.

[1121] Step 5:

[1122] The server receives the generated creative material and generates a response to send back to the contributor.

[1123] Step 6:

[1124] The device analyzes the received creative material and displays it to the donor.

[1125] Example 2

[1126] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1127] In conventional donation campaigns, it was difficult for users to find the best donation recipients and there was a lack of means to predict the effectiveness of donations. Furthermore, there was a lack of support for donors to generate effective creative materials, which reduced the sustainability and efficiency of donation campaigns. Furthermore, there was a lack of voice input to suggest donation recipients and gamification elements to promote donations.

[1128] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1129] In this invention, the server includes means for analyzing a user's emotions and suggesting donation destinations, means for managing the user's donation history, means for predicting the future effects of a user's donation when the user makes a donation, and means for using a generation engine to generate creative materials for those soliciting donations. This allows users to find the optimal donation destination based on their emotions and interests, and by predicting the future effects of donations, it becomes possible to confirm the effectiveness of donation activities. In addition, donation solicitors can easily generate effective creative materials, thereby increasing the sustainability and efficiency of donation activities.

[1130] A "user" is an individual or organization that uses the system to select a donation recipient and carry out a donation activity.

[1131] "Analyzing emotions" refers to the process of identifying the user's emotional state from their input data and providing appropriate donation destinations and suggestions based on that emotion.

[1132] A "donation recipient" is an organization or group selected by the user to receive the donation.

[1133] "Managing donation history" refers to the process of recording information about donations made by a user in the past and making that information available for viewing as needed.

[1134] "Predicting the future effects of donations" refers to the process of predicting what impact a donation made by a user will have in the future and presenting the results to the user.

[1135] "Creative materials" are content materials such as text and images used by donors when conducting campaigns and promotions.

[1136] "Generative engine" refers to an artificial intelligence model or algorithm that automatically generates creative materials based on input data.

[1137] "Voice input" is a method in which a user gives instructions or asks questions to a system using a voice input device such as a microphone.

[1138] "Gamification" is a system that introduces game elements and point systems to encourage users to donate, thereby increasing user involvement.

[1139] This invention supports users' donation activities through a system that combines an emotion engine and an artificial intelligence model. The system has three main components: a server, a terminal, and a user. The role of each component is explained below.

[1140] Initial Setup

[1141] The system's terminals are equipped with interfaces that support voice and text input. Voice input uses a microphone and compatible software (e.g., Google Speech-to-Text API), while text input uses a keyboard or touchscreen. The server incorporates an emotion engine (e.g., IBM Watson Tone Analyzer) and an artificial intelligence model (e.g., GPT-4).

[1142] User donation suggestions

[1143] The user accesses the donation suggestion function via their device and types or speaks, for example, "Please tell me where I should donate to environmental conservation." The device converts the voice data into text and analyzes it with an emotion engine. After analysis, the emotion data and text data are sent to the server.

[1144] The server analyzes the user's emotions using an emotion engine and inputs a prompt to the AI ​​model. For example, "Please suggest donation destinations for positive users who are interested in environmental protection." The AI ​​model generates a list of relevant donation destinations based on the prompt.

[1145] The generated donation list is sent from the server to the terminal and displayed or audibly notified to the user, allowing the user to find the most suitable donation destination based on their feelings and interests.

[1146] Donation history management

[1147] The donation history made by the user is stored in a database on the server (e.g., MySQL). The user sends a request from the terminal, and the server retrieves the donation history from the database and displays it on the terminal. This allows the user to understand their past donation activity at a glance.

[1148] Predicting the impact of donations

[1149] The user inputs the donation amount and donation recipient, as well as their emotions at the time. The device sends the information to the server, which uses an emotion engine and an artificial intelligence model to predict the impact of the donation. The prediction results are sent to the device and displayed to the user, allowing them to see the future impact of their donation.

[1150] Creative Material Generation

[1151] The donor inputs the campaign description and emotion information. The device sends this to the server, which then uses a generation engine (e.g., DALL-E) and emotion engine to generate creative materials. The generated materials are sent to the device, and the donor can use them to develop their campaign.

[1152] Voice suggestions

[1153] When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server understands the user's intention and suggests the most appropriate donation destination. The device then conveys the results to the user via voice.

[1154] Gamification elements

[1155] The system incorporates gamification elements to make donations more enjoyable and sustainable. When a user makes a donation and positive emotions are analyzed, points are awarded. Points are managed on the server and displayed on the device.

[1156] Specific examples

[1157] When a user voice-inputs "Please tell me where to donate to environmental conservation," the device converts the speech to text using the Google Speech-to-Text API and then performs sentiment analysis using IBM Watson Tone Analyzer. The analysis results are sent to the server, which then inputs the prompt into a GPT-4 model to generate a list of donations. The list is then sent to the device and notified to the user via voice. This series of processes allows the user to find appropriate donation destinations for environmental conservation.

[1158] As described above, the system of the present invention supports optimal donation activities based on the user's emotions and interests. By utilizing generative AI models and prompts, the efficiency and effectiveness of donation activities can be significantly improved.

[1159] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1160] Step 1:

[1161] The user accesses the donation suggestion function. The user either inputs text or voice into the device's input interface, saying, "Please tell me where I can donate to environmental conservation." In the case of voice input, the device collects the voice and converts it into text. This converts the voice data into text data.

[1162] Input: User text or voice input

[1163] Output: Text data

[1164] Step 2:

[1165] The text data collected by the device is sent to a server for sentiment analysis. The server receives the text data and passes it to an emotion engine (e.g., IBM Watson Tone Analyzer) for sentiment analysis. Here, the user's emotional state is analyzed, and positive emotions, for example, are detected. The results of this analysis are also saved as data.

[1166] Input: Text data

[1167] Output: Emotion analysis results

[1168] Step 3:

[1169] The server combines the sentiment analysis results with the text data to input a prompt into an AI model (e.g., GPT-4). The prompt takes the form of "Please suggest donation destinations for positive users who are interested in environmental protection." The generative AI model then uses this prompt and the data to suggest appropriate donation destinations.

[1170] Input: Sentiment analysis results and text data

[1171] Output: Donation list

[1172] Step 4:

[1173] The server sends the generated list of donation recipients to the device. The device displays the list of donation recipients received from the server to the user. If voice input is used, the device synthesizes voice and tells the user the results by voice. This allows the user to find the most suitable donation recipient.

[1174] Input: Donation list

[1175] Output: Display or audio notification

[1176] Step 5:

[1177] The user selects a donation recipient and makes a donation. The device sends the donation information to the server. The server saves the donation history in a database and manages new history data. This data is saved so that the user can refer to it later.

[1178] Input: Donation information

[1179] Output: Database update

[1180] Step 6:

[1181] When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the user's donation history from the database and sends it to the device. The device then displays the received history data to the user.

[1182] Input: History confirmation request

[1183] Output: Donation history data

[1184] Step 7:

[1185] When a donor starts a new campaign, they input a campaign description and emotional information. The device sends this information to the server, which then uses a generation engine (e.g., DALL-E) and an emotional engine to generate creative materials. The generated materials are sent to the device, where the donor receives and uses them.

[1186] Input: Campaign description and sentiment information

[1187] Output: Creative materials

[1188] Step 8:

[1189] To encourage donations, the system incorporates gamification elements. When a user makes a donation and positive emotions are analyzed, the system awards points. The point information is managed on the server and displayed on the device.

[1190] Input: Donation information and sentiment analysis results

[1191] Output: Display of points awarded and point information

[1192] (Application example 2)

[1193] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1194] Conventional donation support systems make suggestions and predictions without considering the user's emotions, which means they are unable to fully attract the user's attention. Furthermore, in the advertising field, personalization is lacking, preventing optimal ad display tailored to the user's emotions. Furthermore, generating ads in real time is difficult, which can sometimes detract from the user experience. To solve these issues, a comprehensive system that combines emotion analysis and generative AI models is needed.

[1195] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1196] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing the user's emotions using an emotion analysis engine and personalizing the suggested information, and means for generating advertisements to be displayed on the smart device in real time, thereby enabling optimal donation destination suggestions based on the user's emotions, personalized advertisement display, and real-time advertisement generation.

[1197] An "artificial intelligence model" is a computer program used to suggest optimal donation destinations through analysis of user data.

[1198] "Donation history" is data that records and manages detailed information about donations made by a user in the past.

[1199] "Donation effect prediction" is a function that predicts the future social impact of a donation based on a user's donation behavior.

[1200] A "generative AI model" is an artificial intelligence algorithm used to automatically generate advertising or creative materials.

[1201] An "emotion analysis engine" is a system that analyzes a user's emotional state from their facial expressions and voice, and makes appropriate suggestions based on that data.

[1202] "Personalization" refers to optimizing information and services to suit the individual interests and feelings of each user.

[1203] "Real-time" refers to the process of acquiring data, analyzing it, and providing the results being carried out instantly.

[1204] "Smart devices" are portable electronic devices with advanced computing capabilities, such as smartphones and smart glasses.

[1205] "Advertising" means information intended to promote a product or service.

[1206] MODE FOR CARRYING OUT THE INVENTION

[1207] This invention is a system that combines an emotion engine and a generative AI model to support donation activities and personalize advertisements based on user emotions. This system interacts with users through smart devices such as smartphones and smart glasses.

[1208] Hardware and software used

[1209] Hardware:

[1210] Smartphone

[1211] Smart Glasses

[1212] server

[1213] Audio input device

[1214] software:

[1215] Emotion Analysis Engine (EmotionEngine)

[1216] Ad generation AI model (AdGenerator)

[1217] User Data Management System

[1218] System processing explanation

[1219] 1. Acquiring emotion data:

[1220] When a user uses a smart device to consider where to donate, the device collects emotional data in real time through facial recognition and voice analysis. For example, the camera in smart glasses can read the user's facial expressions and analyze them with an emotion analysis engine.

[1221] 2. Use of sentiment analysis results:

[1222] The acquired emotional data is sent to a server and analyzed by an emotion analysis engine (EmotionEngine). Based on the results of this analysis, the most appropriate donation recipients and advertisements are selected.

[1223] 3. Suggested donations:

[1224] The server uses an artificial intelligence model to combine the analysis results with the user's past donation history to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and has positive feelings, relevant non-profit organizations will be suggested.

[1225] 4. Ad generation and display:

[1226] Based on the results of the sentiment analysis, an ad generation AI model (AdGenerator) generates ads in real time and displays them on smart devices. For example, if a user is excited, an ad for a new gadget will be displayed on the HUD of smart glasses.

[1227] 5. Analysis of voice input:

[1228] The system also supports voice input, so when a user voices their preference for a donation destination, the device converts the voice into text, performs sentiment analysis, and sends it to the server. The server then uses text analysis and an emotion engine to understand the user's intent and suggests the most appropriate donation destination.

[1229] Specific examples

[1230] The user puts on the smart glasses and speaks, "Please tell me where I should donate to environmental conservation." This voice data is picked up through the smart glasses' microphone and analyzed by the sentiment analysis engine. If the user's sentiment is confirmed to be positive, the server suggests relevant nonprofit organizations. The generative AI model then generates appropriate creative materials, and this information is displayed on the smart glasses' HUD.

[1231] Example prompt sentence:

[1232] "The user's current emotion is excitement. Create an ad for a new electronic gadget that builds on this emotion. The target users are men in their 20s who are interested in the latest technology."

[1233] The above is a detailed description of the embodiment of the present invention, which enables suggestions of donation destinations based on the user's emotions and generation of personalized real-time advertisements.

[1234] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1235] Step 1:

[1236] The device acquires the user's emotional data. The device captures the user's facial expressions and voice using a camera and microphone through a smart device (for example, smart glasses or a smartphone). The input is facial expression data and voice data, and the output is input data to the emotion analysis engine. Specifically, the device takes a picture of the user's face and acquires the image data.

[1237] Step 2:

[1238] The device sends the acquired emotional data to an emotion analysis engine, which analyzes the data and identifies the user's emotional state. The input is facial expression data and voice data, and the output is emotional state information. Specifically, the emotion analysis engine identifies the user's current emotion (e.g., positive, negative, excited, etc.) from the facial expression data.

[1239] Step 3:

[1240] The server generates optimal donation destinations and advertisements based on the results of the sentiment analysis. It uses an AI model to make optimal suggestions based on the sentiment analysis results and the user's past donation history. The input is emotional state information and donation history, and the output is donation destination suggestions or advertising content. Specifically, the AI ​​model selects nonprofit organizations and advertisements that are appropriate for the emotional state.

[1241] Step 4:

[1242] The server passes the generated advertising content to a generative AI model, which generates creative materials (e.g., text, images) based on the prompt. The input is the advertising content and the prompt, and the output is the generated creative materials. Specifically, the generative AI model generates advertising copy and images based on the specified prompt.

[1243] Step 5:

[1244] The server sends the generated creative materials to the device. The device receives them and displays them to the user. The input is the generated creative materials, and the output is the content displayed to the user. Specifically, the device displays advertisements on the HUD of smart glasses or on the screen of a smartphone.

[1245] Step 6:

[1246] The user confirms the displayed content and takes adaptive action (e.g., making a donation or clicking on an advertisement). The input is the displayed advertisement and donation proposal, and the output is the user's behavioral data. Specifically, the user confirms the donation selection and completes the donation procedure on their smartphone.

[1247] As described above, through the specific processing performed at each step, optimal donation destination suggestions and personalized advertisement displays based on the user's emotions are realized.

[1248] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1249] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1250] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1251] [Third embodiment]

[1252] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1253] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1254] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1255] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1256] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1257] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1258] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1259] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1260] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1261] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1262] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1263] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1264] The present invention provides a comprehensive system for solving various problems in donation activities. The system unifies the management of online and offline donation activities and supports donation activities for both users and donors.

[1265] User donation suggestions

[1266] This system uses an artificial intelligence model to make optimal suggestions when users choose a donation recipient. When a user inputs their interests, the server passes that information to the artificial intelligence model, which then suggests appropriate donation recipients. For example, if a user is interested in environmental protection, the system will suggest relevant nonprofit organizations.

[1267] Donation history management

[1268] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[1269] Predicting the impact of donations

[1270] When a user makes a donation, the system also provides a function to predict the future impact of that donation. When a user inputs the donation amount and the recipient, the server uses an artificial intelligence model based on that information to predict the impact and communicates the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[1271] Creative Material Generation

[1272] The server has the ability to provide donors with creative materials using a generative AI model. When donors start a new campaign and need materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server. This allows donors to easily launch compelling campaigns.

[1273] Voice suggestions

[1274] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text, understands the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[1275] Gamification elements

[1276] The system incorporates gamification elements to make donations sustainable. Users are awarded points every time they donate, and can earn rewards based on those points. This point system makes donations fun and easy to continue.

[1277] Specific examples

[1278] Suppose a user is considering donating to a nonprofit organization but is unsure which one is best. The user accesses a device and speaks, "Please tell me where I can donate to environmental conservation." The device converts this speech into text and sends it to a server. The server passes this information to an artificial intelligence model, which generates several optimal suggestions. The server then returns the results to the device, which then verbally communicates them to the user. The user then selects a donation destination based on these suggestions and makes the donation.

[1279] As described above, the present invention provides a system for efficiently and effectively supporting donation activities for both users and donors.

[1280] The processing flow will be explained below.

[1281] Handling new user registrations

[1282] Step 1:

[1283] The user enters their username, password, and email address on the device and clicks the "Register" button.

[1284] Step 2:

[1285] The terminal generates a registration request including the input information and sends it to the server.

[1286] Step 3:

[1287] The server checks its database to see if the username already exists.

[1288] Step 4:

[1289] If the server determines that the user is new, it saves the user information in the database.

[1290] Step 5:

[1291] The server generates a registration success message and sends it to the terminal.

[1292] Step 6:

[1293] The terminal displays a registration success message to notify the user that registration is complete.

[1294] Processing user donation suggestions

[1295] Step 1:

[1296] The user enters their interests on the device and clicks the "Suggest" button.

[1297] Step 2:

[1298] The terminal generates a proposal request including the interest information and transmits it to the server.

[1299] Step 3:

[1300] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1301] Step 4:

[1302] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[1303] Step 5:

[1304] The server receives the suggestions and generates a response to send back to the user.

[1305] Step 6:

[1306] The device analyzes the proposal results and displays them to the user.

[1307] Processing donation history verification

[1308] Step 1:

[1309] The user clicks the button to display "Donation History" on the device.

[1310] Step 2:

[1311] The terminal generates a history request including the user ID and sends it to the server.

[1312] Step 3:

[1313] The server connects to the database based on the received user ID and retrieves past donation history.

[1314] Step 4:

[1315] The server formats the donation history and generates a response to send back to the user.

[1316] Step 5:

[1317] The terminal analyzes the received donation history and displays it to the user.

[1318] Processing donation impact forecasts

[1319] Step 1:

[1320] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[1321] Step 2:

[1322] The terminal generates an effect prediction request including the input information and transmits it to the server.

[1323] Step 3:

[1324] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[1325] Step 4:

[1326] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[1327] Step 5:

[1328] The server receives the prediction results and generates a response to send back to the user.

[1329] Step 6:

[1330] The terminal analyzes the received prediction results and displays them to the user.

[1331] Creative material generation process

[1332] Step 1:

[1333] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[1334] Step 2:

[1335] The terminal generates a generation request including the description information and transmits it to the server.

[1336] Step 3:

[1337] The server passes the received description information to the generative artificial intelligence model and requests the generation of creative materials.

[1338] Step 4:

[1339] A generative artificial intelligence model generates creative materials based on input information.

[1340] Step 5:

[1341] The server receives the generated creative material and generates a response to send back to the contributor.

[1342] Step 6:

[1343] The device analyzes the received creative material and displays it to the donor.

[1344] Processing donation suggestions via voice input

[1345] Step 1:

[1346] The user inputs voice information into the terminal to inquire about where to donate.

[1347] Step 2:

[1348] The device converts the speech to text, generates a suggestion request, and sends it to the server.

[1349] Step 3:

[1350] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1351] Step 4:

[1352] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[1353] Step 5:

[1354] The server receives the proposal results, performs speech synthesis, and generates a response.

[1355] Step 6:

[1356] The terminal plays back the received response to the user by voice.

[1357] Example 1

[1358] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1359] In conventional donation systems, users have difficulty finding appropriate donation recipients and lack the ability to predict the impact of donations. In addition, donors have to create the materials they need to launch effective campaigns, and there are limited ways to increase the sustainability of donation activities. Furthermore, the lack of voice input to suggest donation recipients and the lack of elements that make the donation activity itself enjoyable leads to problems with people not continuing to donate.

[1360] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1361] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the effectiveness of donations for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing voice input to suggest donation destinations for the user, and means for providing donation activities with gamification elements and awarding points when the user makes a donation. This not only allows users to easily find appropriate donation destinations and predict the effectiveness of their donations, but also allows donors to quickly launch effective campaigns. Furthermore, the donation suggestions using voice input and gamification elements make donation activities more enjoyable and sustainable.

[1362] The "artificial intelligence model" is a machine learning algorithm that suggests appropriate donation destinations based on user input information.

[1363] The "donation history management means" is a system that stores and manages the history of donations made by users in the past and provides information to users as needed.

[1364] The "donation effect prediction means" is a system that predicts the future effect of a donation based on the amount donated by the user and the donation recipient.

[1365] A "generative artificial intelligence model" is a machine learning algorithm that automatically generates creative materials (such as text and images) based on a description of a new campaign.

[1366] The "voice input analysis means" is a system that converts information input by voice by the user into text, analyzes it, and suggests appropriate donation destinations.

[1367] "Gamification elements" are elements that introduce point systems and rewards to make users' donation activities fun and easy to continue.

[1368] "Rewards" are rewards or benefits that users can earn based on the points they have been awarded.

[1369] The present invention is a system that supports effective donation activities for both users and donors. The system provides the following main functions:

[1370] User donation suggestions

[1371] When a user selects a donation destination, the system uses an artificial intelligence model to make the most appropriate suggestions. When a user inputs their interests into the device, the device sends the information to a server. The server passes it on to an artificial intelligence model, which then suggests the most appropriate donation destination. The artificial intelligence model used here is a machine learning algorithm built using Python. For example, if a user inputs "Please tell me where I should donate to environmental protection," the system will suggest relevant non-profit organizations.

[1372] Donation history management

[1373] A user's donation history is managed by the server. When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the history information from the database and displays it on the device. A relational database management system such as MySQL is used to manage this database. This allows users to see their past donation activity at a glance.

[1374] Predicting the impact of donations

[1375] When users make a donation, they are also provided with a function to predict the future impact of their donation. After the user enters the donation amount and recipient, the device sends that information to a server. The server uses an artificial intelligence model to predict the impact and returns the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[1376] Creative Material Generation

[1377] When a donor starts a new campaign, the server uses a generative AI model to provide creative materials. When a donor enters a campaign description, the generative AI model automatically creates creative materials such as images and text and sends them to the server. This generative AI model combines natural language processing (NLP) and computer vision (CV) technologies.

[1378] Voice suggestions

[1379] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice. This speech recognition uses voice recognition software (e.g., Google Speech-to-Text API).

[1380] Gamification elements

[1381] To make donations sustainable, the system incorporates gamification elements. Users are awarded points every time they donate, and can earn rewards based on those points. The point system is designed to increase user motivation.

[1382] Specific examples

[1383] Here is a specific example of a case where a user is unsure where to donate. The user voice-inputs into the device, "Please tell me where to donate to environmental conservation." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model to suggest the most suitable donation destination and transmits the result to the device. The device then replies with the result by voice to the user, who then chooses a donation destination based on the suggestions and makes the donation.

[1384] Example prompt for a generative AI model:

[1385] The user has indicated that they are interested in "environmental protection." Please suggest the best related donations.

[1386] The present invention provides a system that allows both users and donors to carry out donation activities efficiently and effectively.

[1387] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1388] Processing flow for user donation suggestions

[1389] Step 1:

[1390] The user inputs their interests into the terminal.

[1391] Specific operation: The user enters text of an area of ​​interest, such as "environmental protection," into the input form on the device.

[1392] Input: User-entered data (interests)

[1393] Output: Interest data entered into the device

[1394] Step 2:

[1395] The terminal sends the input information to the server.

[1396] Specific operation: The terminal forms user input data and transfers it to the server as an HTTP request.

[1397] Input: User-entered data

[1398] Output: Request data sent to the server

[1399] Step 3:

[1400] The server passes the information to an artificial intelligence model.

[1401] Specific operation: The server analyzes the received data and inputs it as prompts into the artificial intelligence model.

[1402] Input: Request data

[1403] Output: Prompt data

[1404] Step 4:

[1405] An artificial intelligence model generates the suggestions.

[1406] How it works: The AI ​​model generates relevant donation destinations based on the prompt data.

[1407] Input: prompt data

[1408] Output: Donation proposal data

[1409] Step 5:

[1410] The server sends the proposal results to the terminal.

[1411] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[1412] Input: Donation proposal data

[1413] Output: Proposal data sent to the device

[1414] Step 6:

[1415] The terminal displays the suggestion results to the user.

[1416] Specific operation: The terminal displays the received proposal data on the user interface.

[1417] Input: Proposal data

[1418] Output: The suggestions displayed to the user

[1419] Donation history management process flow

[1420] Step 1:

[1421] The server stores the user's donation history in a database.

[1422] Specific operation: The server writes the information of each donation operation to the database.

[1423] Input: Donation data

[1424] Output: Historical data stored in a database

[1425] Step 2:

[1426] The user sends a history check request from the terminal.

[1427] Specific operation: The user generates a request by pressing the "Check History" button on the device.

[1428] Input: User operation data

[1429] Output: Request data sent to the server

[1430] Step 3:

[1431] The server retrieves the history information from the database.

[1432] Specific operation: The server searches and retrieves the corresponding historical data from the database in response to the request.

[1433] Input: Request data

[1434] Output: Retrieved historical data

[1435] Step 4:

[1436] The server transmits the history information to the terminal.

[1437] Specific operation: The server sends the acquired history data to the terminal as an HTTP response.

[1438] Input: Historical data

[1439] Output: Historical data sent to the terminal

[1440] Step 5:

[1441] The terminal displays the history to the user.

[1442] Specific operation: The terminal displays the received history data on the user interface.

[1443] Input: Historical data

[1444] Output: History information displayed to the user

[1445] Donation effect prediction process flow

[1446] Step 1:

[1447] The user enters the donation amount and donation destination into the terminal.

[1448] Specific operation: The user enters the donation amount and donation destination into the donation form.

[1449] Input: Donation amount and donation recipient data

[1450] Output: Donation data entered into the terminal

[1451] Step 2:

[1452] The terminal sends the input information to the server.

[1453] Specific operation: The terminal inputs donation data and transmits it to the server as an HTTP request.

[1454] Input: Donation data

[1455] Output: Request data sent to the server

[1456] Step 3:

[1457] The server uses an artificial intelligence model to predict the effectiveness of donations.

[1458] Specific operation: The server inputs the received data into the AI ​​model and makes a prediction.

[1459] Input: Donation data

[1460] Output: Prediction result data

[1461] Step 4:

[1462] The server sends the prediction results to the device.

[1463] Specific operation: The server sends the generated prediction result data to the terminal as an HTTP response.

[1464] Input: Prediction result data

[1465] Output: Prediction result data sent to the device

[1466] Step 5:

[1467] The terminal displays the predicted effect to the user.

[1468] Specific operation: The terminal displays the received prediction result data on the user interface.

[1469] Input: Prediction result data

[1470] Output: Predicted effect information displayed to the user

[1471] Creative material generation process flow

[1472] Step 1:

[1473] A donor types a new campaign description into a terminal.

[1474] Specific operation: The donor enters a description of the campaign into the input form on the terminal.

[1475] Input: Campaign description data

[1476] Output: Campaign data entered into the terminal

[1477] Step 2:

[1478] The terminal sends the input information to the server.

[1479] Specific operation: The device sends campaign data to the server as an HTTP request.

[1480] Input: Campaign description data

[1481] Output: Request data sent to the server

[1482] Step 3:

[1483] The server generates creative materials using generative AI models.

[1484] Specific operation: The server inputs the received data into a generative AI model to generate creative materials.

[1485] Input: Campaign description data

[1486] Output: Generated creative material data

[1487] Step 4:

[1488] The server transmits the generated material to the terminal.

[1489] Specific operation: The server sends the generated material data to the terminal as an HTTP response.

[1490] Input: Creative material data

[1491] Output: Material data sent to the device

[1492] Step 5:

[1493] The device displays the creative material to the donor.

[1494] Specific operation: The terminal displays the received creative material data on the user interface.

[1495] Input: Creative material data

[1496] Output: Creative material displayed to donors

[1497] Voice suggestion process flow

[1498] Step 1:

[1499] The user speaks to the terminal about where to donate.

[1500] Specific operation: The user speaks into the microphone, saying something like, "Please tell me where to donate to environmental conservation."

[1501] Input: Audio data

[1502] Output: Audio data input to the device

[1503] Step 2:

[1504] The device converts the speech into text and sends it to the server.

[1505] Specific operation: The terminal converts the voice data into text data and transfers it to the server as an HTTP request.

[1506] Input: Audio data

[1507] Output: Text data sent to the server

[1508] Step 3:

[1509] The server analyzes the text and uses an artificial intelligence model to suggest donation destinations.

[1510] Specific operation: The server analyzes the received text data, inputs it into an artificial intelligence model, and generates the optimal donation destination.

[1511] Input: Text data

[1512] Output: Donation proposal data

[1513] Step 4:

[1514] The server sends the proposal results to the terminal.

[1515] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[1516] Input: Donation proposal data

[1517] Output: Proposal data sent to the device

[1518] Step 5:

[1519] The device returns the proposed results to the user by voice.

[1520] Specific operation: The device uses voice synthesis technology to output the received proposal data as a voice response to the user.

[1521] Input: Proposal data

[1522] Output: Spoken suggestions

[1523] Gamification element processing flow

[1524] Step 1:

[1525] A user makes a donation.

[1526] Specific operation: The user enters the donation amount and donation recipient into the donation form on the device and clicks the donate button.

[1527] Input: Donation data

[1528] Output: Donation data sent from the device to the server

[1529] Step 2:

[1530] The server awards points to the user.

[1531] Specific operation: The server receives the donation data, calculates the corresponding points and adds them to the user's account.

[1532] Input: Donation data

[1533] Output: Points added to the account

[1534] Step 3:

[1535] The server calculates rewards based on the points.

[1536] Specific operation: The server checks the user's accumulated points and calculates the reward accordingly.

[1537] Input: Point data

[1538] Output: Reward data

[1539] Step 4:

[1540] The server transmits the reward information to the terminal.

[1541] Specific operation: The server sends the calculated reward data to the terminal as an HTTP response.

[1542] Input: Reward data

[1543] Output: Reward data sent to the device

[1544] Step 5:

[1545] The terminal displays the reward to the user.

[1546] Specific operation: The terminal displays the received reward data on the user interface.

[1547] Input: Reward data

[1548] Output: Reward information displayed to the user

[1549] (Application example 1)

[1550] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1551] In modern donation activities, users have difficulty selecting appropriate donation recipients and there is a lack of ways to predict the impact of donations. Furthermore, donors are burdened with the task of creating attractive campaign materials. Furthermore, there is a lack of gamification elements to make donation activities sustainable.

[1552] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1553] In this invention, the server includes means for using an artificial intelligence model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative artificial intelligence model to generate creative materials for the donor, means for suggesting optimal donation destinations based on the user's purchase history and interests, means for checking the user's donation history using an application, and means for making donations at the same time as purchases and predicting and displaying the effects. This makes it easy for users to select appropriate donation destinations and predict and confirm the effects of donation activities. It also reduces the burden on donors and allows them to develop attractive campaigns, allowing them to continue enjoying donation activities.

[1554] An "artificial intelligence model" is a computer program that analyzes user data and suggests appropriate donation destinations.

[1555] "Donation history" is detailed information about donations made by a user in the past, including donation recipients, donation amounts, donation dates, and the like.

[1556] "Donation impact" is the result that predicts how a user's donation will benefit a particular cause.

[1557] A "generative artificial intelligence model" is a computer program that automatically generates creative materials for contributors.

[1558] "User purchase history" is detailed information about products purchased by the user in the past, and is data including product names, purchase dates, purchase amounts, and the like.

[1559] "User interests" refers to information about themes or fields in which a user is particularly interested.

[1560] "Means for checking through the application" refers to a means by which users can view their donation history through the software they use.

[1561] The "means for predicting and displaying the effect of donation activities" is a means for calculating how useful a donation will be when a user makes a donation and displaying the result to the user.

[1562] "Gamification elements" are ideas and mechanisms that make donation activities fun, like a game, and easier to continue sustainably.

[1563] The "means for awarding points" is a points system that awards points to users who make donations.

[1564] The present invention is a system for facilitating users' donation activities. This system has various functions for suggesting donation destinations for users, managing donation history, predicting the impact of donations, and providing creative materials to donors.

[1565] System Configuration

[1566] The system mainly consists of the following elements:

[1567] Artificial Intelligence Model

[1568] Generative AI Model

[1569] Database

[1570] server

[1571] User devices (smartphones, tablets, PCs, etc.)

[1572] Program Generation

[1573] First, the system collects interest and purchase history data from users. When users choose a donation destination, an AI model uses this data to suggest the most appropriate donation destination. For example, if a user enters data indicating an interest in "environmental protection," the system will suggest related nonprofit organizations.

[1574] Next, the user's donation history is stored in a database, and when the user requests it, the server retrieves the information and displays it on the terminal, allowing the user to easily check their past donation activity.

[1575] Furthermore, the donation amount and donation recipient information are sent to the server to predict the impact of the user's donation. The server then uses this information to make a prediction using an artificial intelligence model, which then returns the results to the user. For example, if a user donates a specific amount to an environmental protection project, the server predicts and displays the impact that the donation will have.

[1576] Fundraisers can also use generative artificial intelligence models to automatically generate creative materials for their campaigns. Fundraisers enter a description of their campaign, and the system generates materials such as text and images based on that description.

[1577] System action

[1578] The following hardware and software are used for processing in this system:

[1579] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[1580] Software: Artificial intelligence models (e.g., OpenAI API), databases (e.g., MySQL or PostgreSQL), generative AI (e.g., OpenAI GPT-3)

[1581] Specific examples

[1582] The user selects "environmental protection" as a topic of interest and then voice-inputs, "Please tell me where I can donate to environmental protection." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model based on this information to suggest the most appropriate donation destination and returns the result to the device.

[1583] Example prompt sentence:

[1584] "Create a persuasive advertisement for the following campaign: New fundraising campaign for forest restoration."

[1585] In this way, the system can efficiently and effectively support donation activities by suggesting donation destinations, managing donation history, predicting donation effects, and providing creative materials using generative AI models. This system makes donation activities more convenient for both users and donors.

[1586] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1587] Step 1:

[1588] Users input their interest data and purchase history data. The device receives this data and sends it to the server. The input data includes areas of interest (e.g., "environmental protection") and detailed information about purchased products (e.g., "eco-friendly toothbrushes"). The server receives this data and stores it in a database.

[1589] Step 2:

[1590] A user requests donation suggestions. For example, they can say, "Please tell me where to donate to environmental conservation." The device converts this speech into text and sends it to the server. The input is voice data, and the output is text data. The server inputs the text into an artificial intelligence model and generates a list of optimal donation destinations.

[1591] Step 3:

[1592] The server returns a list of donation recipients suggested by the AI ​​model to the device. The user reviews the list and selects a donation recipient. The generated list includes multiple nonprofit organizations and projects. Once the user makes a selection, the selection data is sent to the server.

[1593] Step 4:

[1594] When a user decides to donate, the device sends donation information (donation recipient, donation amount, etc.) to the server. The server records this information in a database and uses an artificial intelligence model to predict the impact of the donation. The input data is the donation recipient and donation amount, and the output data is the predicted impact.

[1595] Step 5:

[1596] The server sends the predicted donation effect to the terminal and displays it to the user, who can see the specific effect of the donation (e.g., "Donating $100 will plant 10 trees").

[1597] Step 6:

[1598] When a donor starts a new campaign, they send a campaign description from their device to the server, which then inputs it into a generative AI model to generate creative materials (text, images, etc.). The input is the campaign description text, and the output is the creative materials.

[1599] Step 7:

[1600] The generated creative materials are sent from the server to the donor's device, where they can be viewed and used, enabling the donor to launch an engaging campaign in a short space of time.

[1601] Step 8:

[1602] When a user wants to check their donation history, they send a request from their device. The server retrieves the user's donation history from the database and sends it to the device. The input is the user ID, and the output is the donation history data.

[1603] Step 9:

[1604] The system provides gamification elements, awarding points each time a user makes a donation. The points based on the user's donation behavior are calculated on the server and recorded in a database. This allows users to have fun while contributing to society through donations.

[1605] As a result, this system can efficiently and effectively support donation activities for both users and donors.

[1606] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1607] This invention provides a comprehensive system that combines an emotion engine to solve various problems in donation activities. This system analyzes users' emotions and, based on this, makes donation suggestions, predicts donation effects, and generates creative materials.

[1608] User donation suggestions

[1609] When a user selects a donation destination, this system uses an artificial intelligence model and an emotion engine to make optimal suggestions. When a user inputs their interests and emotions, the server passes that information to the emotion engine and artificial intelligence model to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and expresses positive emotions, the system will suggest relevant non-profit organizations.

[1610] Donation history management

[1611] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[1612] Predicting the impact of donations

[1613] When a user makes a donation, the system also provides a function to predict the future impact of that donation. The user enters the donation amount, the donation recipient, and their emotion at the time. The server uses this information to predict the impact using an artificial intelligence model and emotion engine, and notifies the user of the results. For example, if the emotion engine detects the user's excited state, the donation may be predicted to be more impactful.

[1614] Creative Material Generation

[1615] The server has the function of providing donors with creative materials using a generative AI model and emotion engine. When a donor starts a new campaign and needs materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server and the donor's emotional information. This allows donors to easily launch compelling campaigns.

[1616] Voice suggestions

[1617] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server uses text analysis and an emotion engine to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[1618] Gamification elements

[1619] The system incorporates gamification elements to make donations sustainable. If positive emotions are detected each time a user makes a donation, more points are awarded. This makes donations fun and easy to continue.

[1620] Specific examples

[1621] Suppose a user is unsure where to donate, but is interested in environmental protection and expresses positive emotions. The user accesses the device and speaks, "Please tell me where to donate to environmental protection." The device converts this speech into text, analyzes the emotion using an emotion engine, and sends it to the server. The server passes this information to an AI model and emotion engine, which suggests several optimal donation destinations. The server then returns the results to the device, which then communicates them to the user via voice. The user chooses a donation destination based on these suggestions and makes a donation.

[1622] As described above, the present invention provides a system that analyzes user emotions to more effectively suggest donations, predict the effects of donations, and generate creative materials, thereby enabling efficient and effective support for donation activities for both users and donors.

[1623] The processing flow will be explained below.

[1624] Handling new user registrations

[1625] Step 1:

[1626] The user enters their username, password, and email address on the device and clicks the "Register" button.

[1627] Step 2:

[1628] The terminal generates a registration request including the input information and sends it to the server.

[1629] Step 3:

[1630] The server checks its database to see if the username already exists.

[1631] Step 4:

[1632] If the server determines that the user is new, it saves the user information in the database.

[1633] Step 5:

[1634] The server generates a registration success message and sends it to the terminal.

[1635] Step 6:

[1636] The terminal displays a registration success message to notify the user that registration is complete.

[1637] Processing user donation suggestions

[1638] Step 1:

[1639] The user enters their interests on the device and clicks the "Suggest" button.

[1640] Step 2:

[1641] The terminal generates a proposal request including the interest information and transmits it to the server.

[1642] Step 3:

[1643] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1644] Step 4:

[1645] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[1646] Step 5:

[1647] The server receives the suggestions and generates a response to send back to the user.

[1648] Step 6:

[1649] The device analyzes the proposal results and displays them to the user.

[1650] Processing donation history verification

[1651] Step 1:

[1652] The user clicks the button to display "Donation History" on the device.

[1653] Step 2:

[1654] The terminal generates a history request including the user ID and sends it to the server.

[1655] Step 3:

[1656] The server connects to the database based on the received user ID and retrieves past donation history.

[1657] Step 4:

[1658] The server formats the donation history and generates a response to send back to the user.

[1659] Step 5:

[1660] The terminal analyzes the received donation history and displays it to the user.

[1661] Processing donation impact forecasts

[1662] Step 1:

[1663] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[1664] Step 2:

[1665] The terminal generates an effect prediction request including the input information and transmits it to the server.

[1666] Step 3:

[1667] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[1668] Step 4:

[1669] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[1670] Step 5:

[1671] The server receives the prediction results and generates a response to send back to the user.

[1672] Step 6:

[1673] The terminal analyzes the received prediction results and displays them to the user.

[1674] Creative material generation process

[1675] Step 1:

[1676] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[1677] Step 2:

[1678] The terminal generates a generation request including the description information and transmits it to the server.

[1679] Step 3:

[1680] The server passes the received description information to the generative AI model and requests the generation of creative materials.

[1681] Step 4:

[1682] A generative AI model generates creative materials based on input information.

[1683] Step 5:

[1684] The server receives the generated creative material and generates a response to send back to the contributor.

[1685] Step 6:

[1686] The device analyzes the received creative material and displays it to the donor.

[1687] Processing donation suggestions via voice input

[1688] Step 1:

[1689] The user inputs voice information into the terminal to inquire about where to donate.

[1690] Step 2:

[1691] The device converts the speech into text, performs sentiment analysis, generates a proposal request, and sends it to the server.

[1692] Step 3:

[1693] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1694] Step 4:

[1695] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[1696] Step 5:

[1697] The server receives the proposal results, performs speech synthesis, and generates a response.

[1698] Step 6:

[1699] The terminal plays back the received response to the user by voice.

[1700] Processing donation suggestions using an emotion engine

[1701] Step 1:

[1702] The user inputs their interests and emotions into the terminal, and then inputs or speaks their emotions.

[1703] Step 2:

[1704] The terminal generates a proposal request including interest information and emotion information and transmits it to the server.

[1705] Step 3:

[1706] The server passes the received interest information and emotion information to the artificial intelligence model and emotion engine, and requests suggestions for appropriate donation destinations.

[1707] Step 4:

[1708] An artificial intelligence model and emotion engine analyze the input information and suggest the most suitable donation destination.

[1709] Step 5:

[1710] The server receives the suggestions and generates a response to send back to the user.

[1711] Step 6:

[1712] The device analyzes the proposal results and displays them to the user.

[1713] Processing donation effect prediction using emotion engine

[1714] Step 1:

[1715] The user inputs the donation amount and donation recipient on the terminal, and also inputs their feelings.

[1716] Step 2:

[1717] The terminal generates an effect prediction request including input information and emotion information and transmits it to the server.

[1718] Step 3:

[1719] The server passes the received information to the artificial intelligence model and emotion engine and requests an effect prediction.

[1720] Step 4:

[1721] The artificial intelligence model and emotion engine predict the effects based on the input information and generate the predicted results.

[1722] Step 5:

[1723] The server receives the prediction results and generates a response to send back to the user.

[1724] Step 6:

[1725] The terminal analyzes the received prediction results and displays them to the user.

[1726] Processing creative material generation using emotion engine

[1727] Step 1:

[1728] The donor enters the campaign description and sentiment information on the terminal and clicks the "Generate" button.

[1729] Step 2:

[1730] The terminal generates a generation request including description information and emotion information and transmits it to the server.

[1731] Step 3:

[1732] The server passes the received description and emotion information to the generative AI model and requests the generation of creative materials.

[1733] Step 4:

[1734] A generative AI model generates creative materials based on input information.

[1735] Step 5:

[1736] The server receives the generated creative material and generates a response to send back to the contributor.

[1737] Step 6:

[1738] The device analyzes the received creative material and displays it to the donor.

[1739] Example 2

[1740] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1741] In conventional donation campaigns, it was difficult for users to find the best donation recipients and there was a lack of means to predict the effectiveness of donations. Furthermore, there was a lack of support for donors to generate effective creative materials, which reduced the sustainability and efficiency of donation campaigns. Furthermore, there was a lack of voice input to suggest donation recipients and gamification elements to promote donations.

[1742] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1743] In this invention, the server includes means for analyzing a user's emotions and suggesting donation destinations, means for managing the user's donation history, means for predicting the future effects of a user's donation when the user makes a donation, and means for using a generation engine to generate creative materials for those soliciting donations. This allows users to find the optimal donation destination based on their emotions and interests, and by predicting the future effects of donations, it becomes possible to confirm the effectiveness of donation activities. In addition, donation solicitors can easily generate effective creative materials, thereby increasing the sustainability and efficiency of donation activities.

[1744] A "user" is an individual or organization that uses the system to select a donation recipient and carry out a donation activity.

[1745] "Analyzing emotions" refers to the process of identifying the user's emotional state from their input data and providing appropriate donation destinations and suggestions based on that emotion.

[1746] A "donation recipient" is an organization or group selected by the user to receive the donation.

[1747] "Managing donation history" refers to the process of recording information about donations made by a user in the past and making that information available for viewing as needed.

[1748] "Predicting the future effects of donations" refers to the process of predicting what impact a donation made by a user will have in the future and presenting the results to the user.

[1749] "Creative materials" are content materials such as text and images used by donors when conducting campaigns and promotions.

[1750] "Generative engine" refers to an artificial intelligence model or algorithm that automatically generates creative materials based on input data.

[1751] "Voice input" is a method in which a user gives instructions or asks questions to a system using a voice input device such as a microphone.

[1752] "Gamification" is a system that introduces game elements and point systems to encourage users to donate, thereby increasing user involvement.

[1753] This invention supports users' donation activities through a system that combines an emotion engine and an artificial intelligence model. The system has three main components: a server, a terminal, and a user. The role of each component is explained below.

[1754] Initial Setup

[1755] The system's terminals are equipped with interfaces that support voice and text input. Voice input uses a microphone and compatible software (e.g., Google Speech-to-Text API), while text input uses a keyboard or touchscreen. The server incorporates an emotion engine (e.g., IBM Watson Tone Analyzer) and an artificial intelligence model (e.g., GPT-4).

[1756] User donation suggestions

[1757] The user accesses the donation suggestion function via their device and types or speaks, for example, "Please tell me where I should donate to environmental conservation." The device converts the voice data into text and analyzes it with an emotion engine. After analysis, the emotion data and text data are sent to the server.

[1758] The server analyzes the user's emotions using an emotion engine and inputs a prompt to the AI ​​model. For example, "Please suggest donation destinations for positive users who are interested in environmental protection." The AI ​​model generates a list of relevant donation destinations based on the prompt.

[1759] The generated donation list is sent from the server to the terminal and displayed or audibly notified to the user, allowing the user to find the most suitable donation destination based on their feelings and interests.

[1760] Donation history management

[1761] The donation history made by the user is stored in a database on the server (e.g., MySQL). The user sends a request from the terminal, and the server retrieves the donation history from the database and displays it on the terminal. This allows the user to understand their past donation activity at a glance.

[1762] Predicting the impact of donations

[1763] The user inputs the donation amount and donation recipient, as well as their emotions at the time. The device sends the information to the server, which uses an emotion engine and an artificial intelligence model to predict the impact of the donation. The prediction results are sent to the device and displayed to the user, allowing them to see the future impact of their donation.

[1764] Creative Material Generation

[1765] The donor inputs the campaign description and emotion information. The device sends this to the server, which then uses a generation engine (e.g., DALL-E) and emotion engine to generate creative materials. The generated materials are sent to the device, and the donor can use them to develop their campaign.

[1766] Voice suggestions

[1767] When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server understands the user's intention and suggests the most appropriate donation destination. The device then conveys the results to the user via voice.

[1768] Gamification elements

[1769] The system incorporates gamification elements to make donations more enjoyable and sustainable. When a user makes a donation and positive emotions are analyzed, points are awarded. Points are managed on the server and displayed on the device.

[1770] Specific examples

[1771] When a user voice-inputs "Please tell me where to donate to environmental conservation," the device converts the speech to text using the Google Speech-to-Text API and then performs sentiment analysis using IBM Watson Tone Analyzer. The analysis results are sent to the server, which then inputs the prompt into a GPT-4 model to generate a list of donations. The list is then sent to the device and notified to the user via voice. This series of processes allows the user to find appropriate donation destinations for environmental conservation.

[1772] As described above, the system of the present invention supports optimal donation activities based on the user's emotions and interests. By utilizing generative AI models and prompts, the efficiency and effectiveness of donation activities can be significantly improved.

[1773] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1774] Step 1:

[1775] The user accesses the donation suggestion function. The user either inputs text or voice into the device's input interface, saying, "Please tell me where I can donate to environmental conservation." In the case of voice input, the device collects the voice and converts it into text. This converts the voice data into text data.

[1776] Input: User text or voice input

[1777] Output: Text data

[1778] Step 2:

[1779] The text data collected by the device is sent to a server for sentiment analysis. The server receives the text data and passes it to an emotion engine (e.g., IBM Watson Tone Analyzer) for sentiment analysis. Here, the user's emotional state is analyzed, and positive emotions, for example, are detected. The results of this analysis are also saved as data.

[1780] Input: Text data

[1781] Output: Emotion analysis results

[1782] Step 3:

[1783] The server combines the sentiment analysis results with the text data to input a prompt into an AI model (e.g., GPT-4). The prompt takes the form of "Please suggest donation destinations for positive users who are interested in environmental protection." The generative AI model then uses this prompt and the data to suggest appropriate donation destinations.

[1784] Input: Sentiment analysis results and text data

[1785] Output: Donation list

[1786] Step 4:

[1787] The server sends the generated list of donation recipients to the device. The device displays the list of donation recipients received from the server to the user. If voice input is used, the device synthesizes voice and tells the user the results by voice. This allows the user to find the most suitable donation recipient.

[1788] Input: Donation list

[1789] Output: Display or audio notification

[1790] Step 5:

[1791] The user selects a donation recipient and makes a donation. The device sends the donation information to the server. The server saves the donation history in a database and manages new history data. This data is saved so that the user can refer to it later.

[1792] Input: Donation information

[1793] Output: Database update

[1794] Step 6:

[1795] When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the user's donation history from the database and sends it to the device. The device then displays the received history data to the user.

[1796] Input: History confirmation request

[1797] Output: Donation history data

[1798] Step 7:

[1799] When a donor starts a new campaign, they input a campaign description and emotional information. The device sends this information to the server, which then uses a generation engine (e.g., DALL-E) and an emotional engine to generate creative materials. The generated materials are sent to the device, where the donor receives and uses them.

[1800] Input: Campaign description and sentiment information

[1801] Output: Creative materials

[1802] Step 8:

[1803] To encourage donations, the system incorporates gamification elements. When a user makes a donation and positive emotions are analyzed, the system awards points. The point information is managed on the server and displayed on the device.

[1804] Input: Donation information and sentiment analysis results

[1805] Output: Display of points awarded and point information

[1806] (Application example 2)

[1807] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1808] Conventional donation support systems make suggestions and predictions without considering the user's emotions, which means they are unable to fully attract the user's attention. Furthermore, in the advertising field, personalization is lacking, preventing optimal ad display tailored to the user's emotions. Furthermore, generating ads in real time is difficult, which can sometimes detract from the user experience. To solve these issues, a comprehensive system that combines emotion analysis and generative AI models is needed.

[1809] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1810] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing the user's emotions using an emotion analysis engine and personalizing the suggested information, and means for generating advertisements to be displayed on the smart device in real time, thereby enabling optimal donation destination suggestions based on the user's emotions, personalized advertisement display, and real-time advertisement generation.

[1811] An "artificial intelligence model" is a computer program used to suggest optimal donation destinations through analysis of user data.

[1812] "Donation history" is data that records and manages detailed information about donations made by a user in the past.

[1813] "Donation effect prediction" is a function that predicts the future social impact of a donation based on a user's donation behavior.

[1814] A "generative AI model" is an artificial intelligence algorithm used to automatically generate advertising or creative materials.

[1815] An "emotion analysis engine" is a system that analyzes a user's emotional state from their facial expressions and voice, and makes appropriate suggestions based on that data.

[1816] "Personalization" refers to optimizing information and services to suit the individual interests and feelings of each user.

[1817] "Real-time" refers to the process of acquiring data, analyzing it, and providing the results being carried out instantly.

[1818] "Smart devices" are portable electronic devices with advanced computing capabilities, such as smartphones and smart glasses.

[1819] "Advertising" means information intended to promote a product or service.

[1820] MODE FOR CARRYING OUT THE INVENTION

[1821] This invention is a system that combines an emotion engine and a generative AI model to support donation activities and personalize advertisements based on user emotions. This system interacts with users through smart devices such as smartphones and smart glasses.

[1822] Hardware and software used

[1823] Hardware:

[1824] Smartphone

[1825] Smart Glasses

[1826] server

[1827] Audio input device

[1828] software:

[1829] Emotion Analysis Engine (EmotionEngine)

[1830] Ad generation AI model (AdGenerator)

[1831] User Data Management System

[1832] System processing explanation

[1833] 1. Acquiring emotion data:

[1834] When a user uses a smart device to consider where to donate, the device collects emotional data in real time through facial recognition and voice analysis. For example, the camera in smart glasses can read the user's facial expressions and analyze them with an emotion analysis engine.

[1835] 2. Use of sentiment analysis results:

[1836] The acquired emotional data is sent to a server and analyzed by an emotion analysis engine (EmotionEngine). Based on the results of this analysis, the most appropriate donation recipients and advertisements are selected.

[1837] 3. Suggested donations:

[1838] The server uses an artificial intelligence model to combine the analysis results with the user's past donation history to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and has positive feelings, relevant non-profit organizations will be suggested.

[1839] 4. Ad generation and display:

[1840] Based on the results of the sentiment analysis, an ad generation AI model (AdGenerator) generates ads in real time and displays them on smart devices. For example, if a user is excited, an ad for a new gadget will be displayed on the HUD of smart glasses.

[1841] 5. Analysis of voice input:

[1842] The system also supports voice input, so when a user voices their preference for a donation destination, the device converts the voice into text, performs sentiment analysis, and sends it to the server. The server then uses text analysis and an emotion engine to understand the user's intent and suggests the most appropriate donation destination.

[1843] Specific examples

[1844] The user puts on the smart glasses and speaks, "Please tell me where I should donate to environmental conservation." This voice data is picked up through the smart glasses' microphone and analyzed by the sentiment analysis engine. If the user's sentiment is confirmed to be positive, the server suggests relevant nonprofit organizations. The generative AI model then generates appropriate creative materials, and this information is displayed on the smart glasses' HUD.

[1845] Example prompt sentence:

[1846] "The user's current emotion is excitement. Create an ad for a new electronic gadget that builds on this emotion. The target users are men in their 20s who are interested in the latest technology."

[1847] The above is a detailed description of the embodiment of the present invention, which enables suggestions of donation destinations based on the user's emotions and generation of personalized real-time advertisements.

[1848] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1849] Step 1:

[1850] The device acquires the user's emotional data. The device captures the user's facial expressions and voice using a camera and microphone through a smart device (for example, smart glasses or a smartphone). The input is facial expression data and voice data, and the output is input data to the emotion analysis engine. Specifically, the device takes a picture of the user's face and acquires the image data.

[1851] Step 2:

[1852] The device sends the acquired emotional data to an emotion analysis engine, which analyzes the data and identifies the user's emotional state. The input is facial expression data and voice data, and the output is emotional state information. Specifically, the emotion analysis engine identifies the user's current emotion (e.g., positive, negative, excited, etc.) from the facial expression data.

[1853] Step 3:

[1854] The server generates optimal donation destinations and advertisements based on the results of the sentiment analysis. It uses an AI model to make optimal suggestions based on the sentiment analysis results and the user's past donation history. The input is emotional state information and donation history, and the output is donation destination suggestions or advertising content. Specifically, the AI ​​model selects nonprofit organizations and advertisements that are appropriate for the emotional state.

[1855] Step 4:

[1856] The server passes the generated advertising content to a generative AI model, which generates creative materials (e.g., text, images) based on the prompt. The input is the advertising content and the prompt, and the output is the generated creative materials. Specifically, the generative AI model generates advertising copy and images based on the specified prompt.

[1857] Step 5:

[1858] The server sends the generated creative materials to the device. The device receives them and displays them to the user. The input is the generated creative materials, and the output is the content displayed to the user. Specifically, the device displays advertisements on the HUD of smart glasses or on the screen of a smartphone.

[1859] Step 6:

[1860] The user confirms the displayed content and takes adaptive action (e.g., making a donation or clicking on an advertisement). The input is the displayed advertisement and donation proposal, and the output is the user's behavioral data. Specifically, the user confirms the donation selection and completes the donation procedure on their smartphone.

[1861] As described above, through the specific processing performed at each step, optimal donation destination suggestions and personalized advertisement displays based on the user's emotions are realized.

[1862] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1863] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1864] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1865] [Fourth embodiment]

[1866] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1867] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1868] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1869] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1870] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1871] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1872] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1873] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1874] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1875] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1876] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1877] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1878] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1879] The present invention provides a comprehensive system for solving various problems in donation activities. The system unifies the management of online and offline donation activities and supports donation activities for both users and donors.

[1880] User donation suggestions

[1881] This system uses an artificial intelligence model to make optimal suggestions when users choose a donation recipient. When a user inputs their interests, the server passes that information to the artificial intelligence model, which then suggests appropriate donation recipients. For example, if a user is interested in environmental protection, the system will suggest relevant nonprofit organizations.

[1882] Donation history management

[1883] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[1884] Predicting the impact of donations

[1885] When a user makes a donation, the system also provides a function to predict the future impact of that donation. When a user inputs the donation amount and the recipient, the server uses an artificial intelligence model based on that information to predict the impact and communicates the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[1886] Creative Material Generation

[1887] The server has the ability to provide donors with creative materials using a generative AI model. When donors start a new campaign and need materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server. This allows donors to easily launch compelling campaigns.

[1888] Voice suggestions

[1889] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text, understands the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[1890] Gamification elements

[1891] The system incorporates gamification elements to make donations sustainable. Users are awarded points every time they donate, and can earn rewards based on those points. This point system makes donations fun and easy to continue.

[1892] Specific examples

[1893] Suppose a user is considering donating to a nonprofit organization but is unsure which one is best. The user accesses a device and speaks, "Please tell me where I can donate to environmental conservation." The device converts this speech into text and sends it to a server. The server passes this information to an artificial intelligence model, which generates several optimal suggestions. The server then returns the results to the device, which then verbally communicates them to the user. The user then selects a donation destination based on these suggestions and makes the donation.

[1894] As described above, the present invention provides a system for efficiently and effectively supporting donation activities for both users and donors.

[1895] The processing flow will be explained below.

[1896] Handling new user registrations

[1897] Step 1:

[1898] The user enters their username, password, and email address on the device and clicks the "Register" button.

[1899] Step 2:

[1900] The terminal generates a registration request including the input information and sends it to the server.

[1901] Step 3:

[1902] The server checks its database to see if the username already exists.

[1903] Step 4:

[1904] If the server determines that the user is new, it saves the user information in the database.

[1905] Step 5:

[1906] The server generates a registration success message and sends it to the terminal.

[1907] Step 6:

[1908] The terminal displays a registration success message to notify the user that registration is complete.

[1909] Processing user donation suggestions

[1910] Step 1:

[1911] The user enters their interests on the device and clicks the "Suggest" button.

[1912] Step 2:

[1913] The terminal generates a proposal request including the interest information and transmits it to the server.

[1914] Step 3:

[1915] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1916] Step 4:

[1917] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[1918] Step 5:

[1919] The server receives the suggestions and generates a response to send back to the user.

[1920] Step 6:

[1921] The device analyzes the proposal results and displays them to the user.

[1922] Processing donation history verification

[1923] Step 1:

[1924] The user clicks the button to display "Donation History" on the device.

[1925] Step 2:

[1926] The terminal generates a history request including the user ID and sends it to the server.

[1927] Step 3:

[1928] The server connects to the database based on the received user ID and retrieves past donation history.

[1929] Step 4:

[1930] The server formats the donation history and generates a response to send back to the user.

[1931] Step 5:

[1932] The terminal analyzes the received donation history and displays it to the user.

[1933] Processing donation impact forecasts

[1934] Step 1:

[1935] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[1936] Step 2:

[1937] The terminal generates an effect prediction request including the input information and transmits it to the server.

[1938] Step 3:

[1939] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[1940] Step 4:

[1941] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[1942] Step 5:

[1943] The server receives the prediction results and generates a response to send back to the user.

[1944] Step 6:

[1945] The terminal analyzes the received prediction results and displays them to the user.

[1946] Creative material generation process

[1947] Step 1:

[1948] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[1949] Step 2:

[1950] The terminal generates a generation request including the description information and transmits it to the server.

[1951] Step 3:

[1952] The server passes the received description information to the generative artificial intelligence model and requests the generation of creative materials.

[1953] Step 4:

[1954] A generative artificial intelligence model generates creative materials based on input information.

[1955] Step 5:

[1956] The server receives the generated creative material and generates a response to send back to the contributor.

[1957] Step 6:

[1958] The device analyzes the received creative material and displays it to the donor.

[1959] Processing donation suggestions via voice input

[1960] Step 1:

[1961] The user inputs voice information into the terminal to inquire about where to donate.

[1962] Step 2:

[1963] The device converts the speech to text, generates a suggestion request, and sends it to the server.

[1964] Step 3:

[1965] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[1966] Step 4:

[1967] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[1968] Step 5:

[1969] The server receives the proposal results, performs speech synthesis, and generates a response.

[1970] Step 6:

[1971] The terminal plays back the received response to the user by voice.

[1972] Example 1

[1973] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1974] In conventional donation systems, users have difficulty finding appropriate donation recipients and lack the ability to predict the impact of donations. In addition, donors have to create the materials they need to launch effective campaigns, and there are limited ways to increase the sustainability of donation activities. Furthermore, the lack of voice input to suggest donation recipients and the lack of elements that make the donation activity itself enjoyable leads to problems with people not continuing to donate.

[1975] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1976] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the effectiveness of donations for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing voice input to suggest donation destinations for the user, and means for providing donation activities with gamification elements and awarding points when the user makes a donation. This not only allows users to easily find appropriate donation destinations and predict the effectiveness of their donations, but also allows donors to quickly launch effective campaigns. Furthermore, the donation suggestions using voice input and gamification elements make donation activities more enjoyable and sustainable.

[1977] The "artificial intelligence model" is a machine learning algorithm that suggests appropriate donation destinations based on user input information.

[1978] The "donation history management means" is a system that stores and manages the history of donations made by users in the past and provides information to users as needed.

[1979] The "donation effect prediction means" is a system that predicts the future effect of a donation based on the amount donated by the user and the donation recipient.

[1980] A "generative artificial intelligence model" is a machine learning algorithm that automatically generates creative materials (such as text and images) based on a description of a new campaign.

[1981] The "voice input analysis means" is a system that converts information input by voice by the user into text, analyzes it, and suggests appropriate donation destinations.

[1982] "Gamification elements" are elements that introduce point systems and rewards to make users' donation activities fun and easy to continue.

[1983] "Rewards" are rewards or benefits that users can earn based on the points they have been awarded.

[1984] The present invention is a system that supports effective donation activities for both users and donors. The system provides the following main functions:

[1985] User donation suggestions

[1986] When a user selects a donation destination, the system uses an artificial intelligence model to make the most appropriate suggestions. When a user inputs their interests into the device, the device sends the information to a server. The server passes it on to an artificial intelligence model, which then suggests the most appropriate donation destination. The artificial intelligence model used here is a machine learning algorithm built using Python. For example, if a user inputs "Please tell me where I should donate to environmental protection," the system will suggest relevant non-profit organizations.

[1987] Donation history management

[1988] A user's donation history is managed by the server. When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the history information from the database and displays it on the device. A relational database management system such as MySQL is used to manage this database. This allows users to see their past donation activity at a glance.

[1989] Predicting the impact of donations

[1990] When users make a donation, they are also provided with a function to predict the future impact of their donation. After the user enters the donation amount and recipient, the device sends that information to a server. The server uses an artificial intelligence model to predict the impact and returns the results to the user. For example, if a specific amount is donated to an education-related project, it predicts how many students the donation will benefit.

[1991] Creative Material Generation

[1992] When a donor starts a new campaign, the server uses a generative AI model to provide creative materials. When a donor enters a campaign description, the generative AI model automatically creates creative materials such as images and text and sends them to the server. This generative AI model combines natural language processing (NLP) and computer vision (CV) technologies.

[1993] Voice suggestions

[1994] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text and sends it to the server. The server then analyzes the text to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice. This speech recognition uses voice recognition software (e.g., Google Speech-to-Text API).

[1995] Gamification elements

[1996] To make donations sustainable, the system incorporates gamification elements. Users are awarded points every time they donate, and can earn rewards based on those points. The point system is designed to increase user motivation.

[1997] Specific examples

[1998] Here is a specific example of a case where a user is unsure where to donate. The user voice-inputs into the device, "Please tell me where to donate to environmental conservation." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model to suggest the most suitable donation destination and transmits the result to the device. The device then replies with the result by voice to the user, who then chooses a donation destination based on the suggestions and makes the donation.

[1999] Example prompt for a generative AI model:

[2000] The user has indicated that they are interested in "environmental protection." Please suggest the best related donations.

[2001] The present invention provides a system that allows both users and donors to carry out donation activities efficiently and effectively.

[2002] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2003] Processing flow for user donation suggestions

[2004] Step 1:

[2005] The user inputs their interests into the terminal.

[2006] Specific operation: The user enters text of an area of ​​interest, such as "environmental protection," into the input form on the device.

[2007] Input: User-entered data (interests)

[2008] Output: Interest data entered into the device

[2009] Step 2:

[2010] The terminal sends the input information to the server.

[2011] Specific operation: The terminal forms user input data and transfers it to the server as an HTTP request.

[2012] Input: User-entered data

[2013] Output: Request data sent to the server

[2014] Step 3:

[2015] The server passes the information to an artificial intelligence model.

[2016] Specific operation: The server analyzes the received data and inputs it as prompts into the artificial intelligence model.

[2017] Input: Request data

[2018] Output: Prompt data

[2019] Step 4:

[2020] An artificial intelligence model generates the suggestions.

[2021] How it works: The AI ​​model generates relevant donation destinations based on the prompt data.

[2022] Input: prompt data

[2023] Output: Donation proposal data

[2024] Step 5:

[2025] The server sends the proposal results to the terminal.

[2026] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[2027] Input: Donation proposal data

[2028] Output: Proposal data sent to the device

[2029] Step 6:

[2030] The terminal displays the suggestion results to the user.

[2031] Specific operation: The terminal displays the received proposal data on the user interface.

[2032] Input: Proposal data

[2033] Output: The suggestions displayed to the user

[2034] Donation history management process flow

[2035] Step 1:

[2036] The server stores the user's donation history in a database.

[2037] Specific operation: The server writes the information of each donation operation to the database.

[2038] Input: Donation data

[2039] Output: Historical data stored in a database

[2040] Step 2:

[2041] The user sends a history check request from the terminal.

[2042] Specific operation: The user generates a request by pressing the "Check History" button on the device.

[2043] Input: User operation data

[2044] Output: Request data sent to the server

[2045] Step 3:

[2046] The server retrieves the history information from the database.

[2047] Specific operation: The server searches and retrieves the corresponding historical data from the database in response to the request.

[2048] Input: Request data

[2049] Output: Retrieved historical data

[2050] Step 4:

[2051] The server transmits the history information to the terminal.

[2052] Specific operation: The server sends the acquired history data to the terminal as an HTTP response.

[2053] Input: Historical data

[2054] Output: Historical data sent to the terminal

[2055] Step 5:

[2056] The terminal displays the history to the user.

[2057] Specific operation: The terminal displays the received history data on the user interface.

[2058] Input: Historical data

[2059] Output: History information displayed to the user

[2060] Donation effect prediction process flow

[2061] Step 1:

[2062] The user enters the donation amount and donation destination into the terminal.

[2063] Specific operation: The user enters the donation amount and donation destination into the donation form.

[2064] Input: Donation amount and donation recipient data

[2065] Output: Donation data entered into the terminal

[2066] Step 2:

[2067] The terminal sends the input information to the server.

[2068] Specific operation: The terminal inputs donation data and transmits it to the server as an HTTP request.

[2069] Input: Donation data

[2070] Output: Request data sent to the server

[2071] Step 3:

[2072] The server uses an artificial intelligence model to predict the effectiveness of donations.

[2073] Specific operation: The server inputs the received data into the AI ​​model and makes a prediction.

[2074] Input: Donation data

[2075] Output: Prediction result data

[2076] Step 4:

[2077] The server sends the prediction results to the terminal.

[2078] Specific operation: The server sends the generated prediction result data to the terminal as an HTTP response.

[2079] Input: Prediction result data

[2080] Output: Prediction result data sent to the device

[2081] Step 5:

[2082] The terminal displays the predicted effect to the user.

[2083] Specific operation: The terminal displays the received prediction result data on the user interface.

[2084] Input: Prediction result data

[2085] Output: Predicted effect information displayed to the user

[2086] Creative material generation process flow

[2087] Step 1:

[2088] A donor types a new campaign description into a terminal.

[2089] Specific operation: The donor enters a description of the campaign into the input form on the terminal.

[2090] Input: Campaign description data

[2091] Output: Campaign data entered into the terminal

[2092] Step 2:

[2093] The terminal sends the input information to the server.

[2094] Specific operation: The device sends campaign data to the server as an HTTP request.

[2095] Input: Campaign description data

[2096] Output: Request data sent to the server

[2097] Step 3:

[2098] The server generates creative materials using generative AI models.

[2099] Specific operation: The server inputs the received data into a generative AI model to generate creative materials.

[2100] Input: Campaign description data

[2101] Output: Generated creative material data

[2102] Step 4:

[2103] The server transmits the generated material to the terminal.

[2104] Specific operation: The server sends the generated material data to the terminal as an HTTP response.

[2105] Input: Creative material data

[2106] Output: Material data sent to the device

[2107] Step 5:

[2108] The device displays the creative material to the donor.

[2109] Specific operation: The terminal displays the received creative material data on the user interface.

[2110] Input: Creative material data

[2111] Output: Creative material displayed to donors

[2112] Voice suggestion process flow

[2113] Step 1:

[2114] The user speaks to the terminal about where to donate.

[2115] Specific operation: The user speaks into the microphone, saying something like, "Please tell me where to donate to environmental conservation."

[2116] Input: Audio data

[2117] Output: Audio data input to the device

[2118] Step 2:

[2119] The device converts the speech into text and sends it to the server.

[2120] Specific operation: The terminal converts the voice data into text data and transfers it to the server as an HTTP request.

[2121] Input: Audio data

[2122] Output: Text data sent to the server

[2123] Step 3:

[2124] The server analyzes the text and uses an artificial intelligence model to suggest donation destinations.

[2125] Specific operation: The server analyzes the received text data, inputs it into an artificial intelligence model, and generates the optimal donation destination.

[2126] Input: Text data

[2127] Output: Donation proposal data

[2128] Step 4:

[2129] The server sends the proposal results to the terminal.

[2130] Specific operation: The server sends the generated donation suggestion data to the terminal as an HTTP response.

[2131] Input: Donation proposal data

[2132] Output: Proposal data sent to the device

[2133] Step 5:

[2134] The device returns the proposed results to the user by voice.

[2135] Specific operation: The device uses voice synthesis technology to output the received proposal data as a voice response to the user.

[2136] Input: Proposal data

[2137] Output: Spoken suggestions

[2138] Gamification element processing flow

[2139] Step 1:

[2140] A user makes a donation.

[2141] Specific operation: The user enters the donation amount and donation recipient into the donation form on the device and clicks the donate button.

[2142] Input: Donation data

[2143] Output: Donation data sent from the device to the server

[2144] Step 2:

[2145] The server awards points to the user.

[2146] Specific operation: The server receives the donation data, calculates the corresponding points and adds them to the user's account.

[2147] Input: Donation data

[2148] Output: Points added to the account

[2149] Step 3:

[2150] The server calculates rewards based on the points.

[2151] Specific operation: The server checks the user's accumulated points and calculates the reward accordingly.

[2152] Input: Point data

[2153] Output: Reward data

[2154] Step 4:

[2155] The server transmits the reward information to the terminal.

[2156] Specific operation: The server sends the calculated reward data to the terminal as an HTTP response.

[2157] Input: Reward data

[2158] Output: Reward data sent to the device

[2159] Step 5:

[2160] The terminal displays the reward to the user.

[2161] Specific operation: The terminal displays the received reward data on the user interface.

[2162] Input: Reward data

[2163] Output: Reward information displayed to the user

[2164] (Application example 1)

[2165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2166] In modern donation activities, users have difficulty selecting appropriate donation recipients and there is a lack of ways to predict the impact of donations. Furthermore, donors are burdened with the task of creating attractive campaign materials. Furthermore, there is a lack of gamification elements to make donation activities sustainable.

[2167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2168] In this invention, the server includes means for using an artificial intelligence model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative artificial intelligence model to generate creative materials for the donor, means for suggesting optimal donation destinations based on the user's purchase history and interests, means for checking the user's donation history using an application, and means for making donations at the same time as purchases and predicting and displaying the effects. This makes it easy for users to select appropriate donation destinations and predict and confirm the effects of donation activities. It also reduces the burden on donors and allows them to develop attractive campaigns, allowing them to continue enjoying donation activities.

[2169] An "artificial intelligence model" is a computer program that analyzes user data and suggests appropriate donation destinations.

[2170] "Donation history" is detailed information about donations made by a user in the past, including donation recipients, donation amounts, donation dates, and the like.

[2171] "Donation impact" is the result that predicts how a user's donation will benefit a particular cause.

[2172] A "generative artificial intelligence model" is a computer program that automatically generates creative materials for contributors.

[2173] "User purchase history" is detailed information about products purchased by the user in the past, and is data including product names, purchase dates, purchase amounts, and the like.

[2174] "User interests" refers to information about themes or fields in which a user is particularly interested.

[2175] "Means for checking through the application" refers to a means by which users can view their donation history through the software they use.

[2176] The "means for predicting and displaying the effect of donation activities" is a means for calculating how useful a donation will be when a user makes a donation and displaying the result to the user.

[2177] "Gamification elements" are ideas and mechanisms that make donation activities fun, like a game, and easier to continue sustainably.

[2178] The "means for awarding points" is a points system that awards points to users who make donations.

[2179] The present invention is a system for facilitating users' donation activities. This system has various functions for suggesting donation destinations for users, managing donation history, predicting the impact of donations, and providing creative materials to donors.

[2180] System Configuration

[2181] The system mainly consists of the following elements:

[2182] Artificial Intelligence Model

[2183] Generative AI Model

[2184] Database

[2185] server

[2186] User devices (smartphones, tablets, PCs, etc.)

[2187] Program Generation

[2188] First, the system collects interest and purchase history data from users. When users choose a donation destination, an AI model uses this data to suggest the most appropriate donation destination. For example, if a user enters data indicating an interest in "environmental protection," the system will suggest related nonprofit organizations.

[2189] Next, the user's donation history is stored in a database, and when the user requests it, the server retrieves the information and displays it on the terminal, allowing the user to easily check their past donation activity.

[2190] Furthermore, the donation amount and donation recipient information are sent to the server to predict the impact of the user's donation. The server then uses this information to make a prediction using an artificial intelligence model, which then returns the results to the user. For example, if a user donates a specific amount to an environmental protection project, the server predicts and displays the impact that the donation will have.

[2191] Fundraisers can also use generative artificial intelligence models to automatically generate creative materials for their campaigns. Fundraisers enter a description of their campaign, and the system generates materials such as text and images based on that description.

[2192] System action

[2193] The following hardware and software are used for processing in this system:

[2194] Hardware: Servers, user devices (smartphones, tablets, PCs, etc.)

[2195] Software: Artificial intelligence models (e.g., OpenAI API), databases (e.g., MySQL or PostgreSQL), generative AI (e.g., OpenAI GPT-3)

[2196] Specific examples

[2197] The user selects "environmental protection" as a topic of interest and then voice-inputs, "Please tell me where I can donate to environmental protection." The device converts this voice into text and sends it to the server. The server uses an artificial intelligence model based on this information to suggest the most appropriate donation destination and returns the result to the device.

[2198] Example prompt sentence:

[2199] "Create a persuasive advertisement for the following campaign: New fundraising campaign for forest restoration."

[2200] In this way, the system can efficiently and effectively support donation activities by suggesting donation destinations, managing donation history, predicting donation effects, and providing creative materials using generative AI models. This system makes donation activities more convenient for both users and donors.

[2201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2202] Step 1:

[2203] Users input their interest data and purchase history data. The device receives this data and sends it to the server. The input data includes areas of interest (e.g., "environmental protection") and detailed information about purchased products (e.g., "eco-friendly toothbrushes"). The server receives this data and stores it in a database.

[2204] Step 2:

[2205] A user requests donation suggestions. For example, they can say, "Please tell me where to donate to environmental conservation." The device converts this speech into text and sends it to the server. The input is voice data, and the output is text data. The server inputs the text into an artificial intelligence model and generates a list of optimal donation destinations.

[2206] Step 3:

[2207] The server returns a list of donation recipients suggested by the AI ​​model to the device. The user reviews the list and selects a donation recipient. The generated list includes multiple nonprofit organizations and projects. Once the user makes a selection, the selection data is sent to the server.

[2208] Step 4:

[2209] When a user decides to donate, the device sends donation information (donation recipient, donation amount, etc.) to the server. The server records this information in a database and uses an artificial intelligence model to predict the impact of the donation. The input data is the donation recipient and donation amount, and the output data is the predicted impact.

[2210] Step 5:

[2211] The server sends the predicted donation effect to the terminal and displays it to the user, who can see the specific effect of the donation (e.g., "Donating $100 will plant 10 trees").

[2212] Step 6:

[2213] When a donor starts a new campaign, they send a campaign description from their device to the server, which then inputs it into a generative AI model to generate creative materials (text, images, etc.). The input is the campaign description text, and the output is the creative materials.

[2214] Step 7:

[2215] The generated creative materials are sent from the server to the donor's device, where they can be viewed and used, enabling the donor to launch an engaging campaign in a short space of time.

[2216] Step 8:

[2217] When a user wants to check their donation history, they send a request from their device. The server retrieves the user's donation history from the database and sends it to the device. The input is the user ID, and the output is the donation history data.

[2218] Step 9:

[2219] The system provides gamification elements, awarding points each time a user makes a donation. The points based on the user's donation behavior are calculated on the server and recorded in a database. This allows users to have fun while contributing to society through donations.

[2220] As a result, this system can efficiently and effectively support donation activities for both users and donors.

[2221] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2222] This invention provides a comprehensive system that combines an emotion engine to solve various problems in donation activities. This system analyzes users' emotions and, based on this, makes donation suggestions, predicts donation effects, and generates creative materials.

[2223] User donation suggestions

[2224] When a user selects a donation destination, this system uses an artificial intelligence model and an emotion engine to make optimal suggestions. When a user inputs their interests and emotions, the server passes that information to the emotion engine and artificial intelligence model to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and expresses positive emotions, the system will suggest relevant non-profit organizations.

[2225] Donation history management

[2226] The server manages the user's donation history. When a user wants to check their donation history, they send a request from their device to the server, which retrieves the history information from the database and displays it on the device. This allows the user to see their donation history at a glance.

[2227] Predicting the impact of donations

[2228] When a user makes a donation, the system also provides a function to predict the future impact of that donation. The user enters the donation amount, the donation recipient, and their emotion at the time. The server uses this information to predict the impact using an artificial intelligence model and emotion engine, and notifies the user of the results. For example, if the emotion engine detects the user's excited state, the donation may be predicted to be more impactful.

[2229] Creative Material Generation

[2230] The server has the function of providing donors with creative materials using a generative AI model and emotion engine. When a donor starts a new campaign and needs materials such as text or images, the generative AI automatically creates the materials based on the campaign description entered into the server and the donor's emotional information. This allows donors to easily launch compelling campaigns.

[2231] Voice suggestions

[2232] The system also supports voice input. When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server uses text analysis and an emotion engine to understand the user's intent, suggests the most appropriate donation destination, and returns the results to the user via voice.

[2233] Gamification elements

[2234] The system incorporates gamification elements to make donations sustainable. If positive emotions are detected each time a user makes a donation, more points are awarded. This makes donations fun and easy to continue.

[2235] Specific examples

[2236] Suppose a user is unsure where to donate, but is interested in environmental protection and expresses positive emotions. The user accesses the device and speaks, "Please tell me where to donate to environmental protection." The device converts this speech into text, analyzes the emotion using an emotion engine, and sends it to the server. The server passes this information to an AI model and emotion engine, which suggests several optimal donation destinations. The server then returns the results to the device, which then communicates them to the user via voice. The user chooses a donation destination based on these suggestions and makes a donation.

[2237] As described above, the present invention provides a system that analyzes user emotions to more effectively suggest donations, predict the effects of donations, and generate creative materials, thereby enabling efficient and effective support for donation activities for both users and donors.

[2238] The processing flow will be explained below.

[2239] Handling new user registrations

[2240] Step 1:

[2241] The user enters their username, password, and email address on the device and clicks the "Register" button.

[2242] Step 2:

[2243] The terminal generates a registration request including the input information and sends it to the server.

[2244] Step 3:

[2245] The server checks its database to see if the username already exists.

[2246] Step 4:

[2247] If the server determines that the user is new, it saves the user information in the database.

[2248] Step 5:

[2249] The server generates a registration success message and sends it to the terminal.

[2250] Step 6:

[2251] The terminal displays a registration success message to notify the user that registration is complete.

[2252] Processing user donation suggestions

[2253] Step 1:

[2254] The user enters their interests on the device and clicks the "Suggest" button.

[2255] Step 2:

[2256] The terminal generates a proposal request including the interest information and transmits it to the server.

[2257] Step 3:

[2258] The server passes the received interest information to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[2259] Step 4:

[2260] An artificial intelligence model analyzes the input information and suggests the most appropriate donation destination.

[2261] Step 5:

[2262] The server receives the suggestions and generates a response to send back to the user.

[2263] Step 6:

[2264] The device analyzes the proposal results and displays them to the user.

[2265] Processing donation history verification

[2266] Step 1:

[2267] The user clicks the button to display "Donation History" on the device.

[2268] Step 2:

[2269] The terminal generates a history request including the user ID and sends it to the server.

[2270] Step 3:

[2271] The server connects to the database based on the received user ID and retrieves past donation history.

[2272] Step 4:

[2273] The server formats the donation history and generates a response to send back to the user.

[2274] Step 5:

[2275] The terminal analyzes the received donation history and displays it to the user.

[2276] Processing donation impact forecasts

[2277] Step 1:

[2278] The user enters the donation amount and donation recipient on the device and clicks the "Effectiveness Estimate" button.

[2279] Step 2:

[2280] The terminal generates an effect prediction request including the input information and transmits it to the server.

[2281] Step 3:

[2282] The server passes the received information to the artificial intelligence model and requests an effect prediction.

[2283] Step 4:

[2284] The artificial intelligence model predicts the effects based on the input information and generates the predicted results.

[2285] Step 5:

[2286] The server receives the prediction results and generates a response to send back to the user.

[2287] Step 6:

[2288] The terminal analyzes the received prediction results and displays them to the user.

[2289] Creative material generation process

[2290] Step 1:

[2291] The donor enters a campaign description on the terminal and clicks the "Generate" button.

[2292] Step 2:

[2293] The terminal generates a generation request including the description information and transmits it to the server.

[2294] Step 3:

[2295] The server passes the received description information to the generative AI model and requests the generation of creative materials.

[2296] Step 4:

[2297] A generative AI model generates creative materials based on input information.

[2298] Step 5:

[2299] The server receives the generated creative material and generates a response to send back to the contributor.

[2300] Step 6:

[2301] The device analyzes the received creative material and displays it to the donor.

[2302] Processing donation suggestions via voice input

[2303] Step 1:

[2304] The user inputs voice information into the terminal to inquire about where to donate.

[2305] Step 2:

[2306] The device converts the speech into text, performs sentiment analysis, generates a proposal request, and sends it to the server.

[2307] Step 3:

[2308] The server passes the received text to an artificial intelligence model and requests suggestions for appropriate donation destinations.

[2309] Step 4:

[2310] An artificial intelligence model analyzes text information and suggests the most appropriate donation destination.

[2311] Step 5:

[2312] The server receives the proposal results, performs speech synthesis, and generates a response.

[2313] Step 6:

[2314] The terminal plays back the received response to the user by voice.

[2315] Processing donation suggestions using an emotion engine

[2316] Step 1:

[2317] The user inputs their interests and emotions into the terminal, and then inputs or speaks their emotions.

[2318] Step 2:

[2319] The terminal generates a proposal request including interest information and emotion information and transmits it to the server.

[2320] Step 3:

[2321] The server passes the received interest information and emotion information to the artificial intelligence model and emotion engine, and requests suggestions for appropriate donation destinations.

[2322] Step 4:

[2323] An artificial intelligence model and emotion engine analyze the input information and suggest the most suitable donation destination.

[2324] Step 5:

[2325] The server receives the suggestions and generates a response to send back to the user.

[2326] Step 6:

[2327] The device analyzes the proposal results and displays them to the user.

[2328] Processing donation effect prediction using emotion engine

[2329] Step 1:

[2330] The user inputs the donation amount and donation recipient on the terminal, and also inputs their feelings.

[2331] Step 2:

[2332] The terminal generates an effect prediction request including input information and emotion information and transmits it to the server.

[2333] Step 3:

[2334] The server passes the received information to the artificial intelligence model and emotion engine and requests an effect prediction.

[2335] Step 4:

[2336] The artificial intelligence model and emotion engine predict the effects based on the input information and generate the predicted results.

[2337] Step 5:

[2338] The server receives the prediction results and generates a response to send back to the user.

[2339] Step 6:

[2340] The terminal analyzes the received prediction results and displays them to the user.

[2341] Processing creative material generation using emotion engine

[2342] Step 1:

[2343] The donor enters the campaign description and sentiment information on the terminal and clicks the "Generate" button.

[2344] Step 2:

[2345] The terminal generates a generation request including description information and emotion information and transmits it to the server.

[2346] Step 3:

[2347] The server passes the received description and emotion information to the generative AI model and requests the generation of creative materials.

[2348] Step 4:

[2349] A generative AI model generates creative materials based on input information.

[2350] Step 5:

[2351] The server receives the generated creative material and generates a response to send back to the contributor.

[2352] Step 6:

[2353] The device analyzes the received creative material and displays it to the donor.

[2354] Example 2

[2355] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2356] In conventional donation campaigns, it was difficult for users to find the best donation recipients and there was a lack of means to predict the effectiveness of donations. Furthermore, there was a lack of support for donors to generate effective creative materials, which reduced the sustainability and efficiency of donation campaigns. Furthermore, there was a lack of voice input to suggest donation recipients and gamification elements to promote donations.

[2357] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2358] In this invention, the server includes means for analyzing a user's emotions and suggesting donation destinations, means for managing the user's donation history, means for predicting the future effects of a user's donation when the user makes a donation, and means for using a generation engine to generate creative materials for those soliciting donations. This allows users to find the optimal donation destination based on their emotions and interests, and by predicting the future effects of donations, it becomes possible to confirm the effectiveness of donation activities. In addition, donation solicitors can easily generate effective creative materials, thereby increasing the sustainability and efficiency of donation activities.

[2359] A "user" is an individual or organization that uses the system to select a donation recipient and carry out a donation activity.

[2360] "Analyzing emotions" refers to the process of identifying the user's emotional state from their input data and providing appropriate donation destinations and suggestions based on that emotion.

[2361] A "donation recipient" is an organization or group selected by the user to receive the donation.

[2362] "Managing donation history" refers to the process of recording information about donations made by a user in the past and making that information available for viewing as needed.

[2363] "Predicting the future effects of donations" refers to the process of predicting what impact a donation made by a user will have in the future and presenting the results to the user.

[2364] "Creative materials" are content materials such as text and images used by donors when conducting campaigns and promotions.

[2365] "Generative engine" refers to an artificial intelligence model or algorithm that automatically generates creative materials based on input data.

[2366] "Voice input" is a method in which a user gives instructions or asks questions to a system using a voice input device such as a microphone.

[2367] "Gamification" is a system that introduces game elements and point systems to encourage users to donate, thereby increasing user involvement.

[2368] This invention supports users' donation activities through a system that combines an emotion engine and an artificial intelligence model. The system has three main components: a server, a terminal, and a user. The role of each component is explained below.

[2369] Initial Setup

[2370] The system's terminals are equipped with interfaces that support voice and text input. Voice input uses a microphone and compatible software (e.g., Google Speech-to-Text API), while text input uses a keyboard or touchscreen. The server incorporates an emotion engine (e.g., IBM Watson Tone Analyzer) and an artificial intelligence model (e.g., GPT-4).

[2371] User donation suggestions

[2372] The user accesses the donation suggestion function via their device and types or speaks, for example, "Please tell me where I should donate to environmental conservation." The device converts the voice data into text and analyzes it with an emotion engine. After analysis, the emotion data and text data are sent to the server.

[2373] The server analyzes the user's emotions using an emotion engine and inputs a prompt to the AI ​​model. For example, "Please suggest donation destinations for positive users who are interested in environmental protection." The AI ​​model generates a list of relevant donation destinations based on the prompt.

[2374] The generated donation list is sent from the server to the terminal and displayed or audibly notified to the user, allowing the user to find the most suitable donation destination based on their feelings and interests.

[2375] Donation history management

[2376] The donation history made by the user is stored in a database on the server (e.g., MySQL). The user sends a request from the terminal, and the server retrieves the donation history from the database and displays it on the terminal. This allows the user to understand their past donation activity at a glance.

[2377] Predicting the impact of donations

[2378] The user inputs the donation amount and donation recipient, as well as their emotions at the time. The device sends the information to the server, which uses an emotion engine and an artificial intelligence model to predict the impact of the donation. The prediction results are sent to the device and displayed to the user, allowing them to see the future impact of their donation.

[2379] Creative Material Generation

[2380] The donor inputs the campaign description and emotion information. The device sends this to the server, which then uses a generation engine (e.g., DALL-E) and emotion engine to generate creative materials. The generated materials are sent to the device, and the donor can use them to develop their campaign.

[2381] Voice suggestions

[2382] When a user speaks to recommend a donation destination, the device converts the speech into text, performs sentiment analysis, and sends it to the server. The server understands the user's intention and suggests the most appropriate donation destination. The device then conveys the results to the user via voice.

[2383] Gamification elements

[2384] The system incorporates gamification elements to make donations more enjoyable and sustainable. When a user makes a donation and positive emotions are analyzed, points are awarded. Points are managed on the server and displayed on the device.

[2385] Specific examples

[2386] When a user voice-inputs "Please tell me where to donate to environmental conservation," the device converts the speech to text using the Google Speech-to-Text API and then performs sentiment analysis using IBM Watson Tone Analyzer. The analysis results are sent to the server, which then inputs the prompt into a GPT-4 model to generate a list of donations. The list is then sent to the device and notified to the user via voice. This series of processes allows the user to find appropriate donation destinations for environmental conservation.

[2387] As described above, the system of the present invention supports optimal donation activities based on the user's emotions and interests. By utilizing generative AI models and prompts, the efficiency and effectiveness of donation activities can be significantly improved.

[2388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2389] Step 1:

[2390] The user accesses the donation suggestion function. The user either inputs text or voice into the device's input interface, saying, "Please tell me where I can donate to environmental conservation." In the case of voice input, the device collects the voice and converts it into text. This converts the voice data into text data.

[2391] Input: User text or voice input

[2392] Output: Text data

[2393] Step 2:

[2394] The text data collected by the device is sent to a server for sentiment analysis. The server receives the text data and passes it to an emotion engine (e.g., IBM Watson Tone Analyzer) for sentiment analysis. Here, the user's emotional state is analyzed, and positive emotions, for example, are detected. The results of this analysis are also saved as data.

[2395] Input: Text data

[2396] Output: Emotion analysis results

[2397] Step 3:

[2398] The server combines the sentiment analysis results with the text data to input a prompt into an AI model (e.g., GPT-4). The prompt takes the form of "Please suggest donation destinations for positive users who are interested in environmental protection." The generative AI model then uses this prompt and the data to suggest appropriate donation destinations.

[2399] Input: Sentiment analysis results and text data

[2400] Output: Donation list

[2401] Step 4:

[2402] The server sends the generated list of donation recipients to the device. The device displays the list of donation recipients received from the server to the user. If voice input is used, the device synthesizes voice and tells the user the results by voice. This allows the user to find the most suitable donation recipient.

[2403] Input: Donation list

[2404] Output: Display or audio notification

[2405] Step 5:

[2406] The user selects a donation recipient and makes a donation. The device sends the donation information to the server. The server saves the donation history in a database and manages new history data. This data is saved so that the user can refer to it later.

[2407] Input: Donation information

[2408] Output: Database update

[2409] Step 6:

[2410] When a user wants to check their donation history, they send a request from their device to the server. The server retrieves the user's donation history from the database and sends it to the device. The device then displays the received history data to the user.

[2411] Input: History confirmation request

[2412] Output: Donation history data

[2413] Step 7:

[2414] When a donor starts a new campaign, they input a campaign description and emotional information. The device sends this information to the server, which then uses a generation engine (e.g., DALL-E) and an emotional engine to generate creative materials. The generated materials are sent to the device, where the donor receives and uses them.

[2415] Input: Campaign description and sentiment information

[2416] Output: Creative materials

[2417] Step 8:

[2418] To encourage donations, the system incorporates gamification elements. When a user makes a donation and positive emotions are analyzed, the system awards points. The point information is managed on the server and displayed on the device.

[2419] Input: Donation information and sentiment analysis results

[2420] Output: Display of points awarded and point information

[2421] (Application example 2)

[2422] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2423] Conventional donation support systems make suggestions and predictions without considering the user's emotions, which means they are unable to fully attract the user's attention. Furthermore, in the advertising field, personalization is lacking, preventing optimal ad display tailored to the user's emotions. Furthermore, generating ads in real time is difficult, which can sometimes detract from the user experience. To solve these issues, a comprehensive system that combines emotion analysis and generative AI models is needed.

[2424] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2425] In this invention, the server includes means for using an AI model to suggest donation destinations for the user, means for managing the user's donation history, means for predicting the donation effect for the user, means for using a generative AI model to generate creative materials for the donor, means for analyzing the user's emotions using an emotion analysis engine and personalizing the suggested information, and means for generating advertisements to be displayed on the smart device in real time, thereby enabling optimal donation destination suggestions based on the user's emotions, personalized advertisement display, and real-time advertisement generation.

[2426] An "artificial intelligence model" is a computer program used to suggest optimal donation destinations through analysis of user data.

[2427] "Donation history" is data that records and manages detailed information about donations made by a user in the past.

[2428] "Donation effect prediction" is a function that predicts the future social impact of a donation based on a user's donation behavior.

[2429] A "generative AI model" is an artificial intelligence algorithm used to automatically generate advertising or creative materials.

[2430] An "emotion analysis engine" is a system that analyzes a user's emotional state from their facial expressions and voice, and makes appropriate suggestions based on that data.

[2431] "Personalization" refers to optimizing information and services to suit the individual interests and feelings of each user.

[2432] "Real-time" refers to the process of acquiring data, analyzing it, and providing the results being carried out instantly.

[2433] "Smart devices" are portable electronic devices with advanced computing capabilities, such as smartphones and smart glasses.

[2434] "Advertising" means information intended to promote a product or service.

[2435] MODE FOR CARRYING OUT THE INVENTION

[2436] This invention is a system that combines an emotion engine and a generative AI model to support donation activities and personalize advertisements based on user emotions. This system interacts with users through smart devices such as smartphones and smart glasses.

[2437] Hardware and software used

[2438] Hardware:

[2439] Smartphone

[2440] Smart Glasses

[2441] server

[2442] Audio input device

[2443] software:

[2444] Emotion Analysis Engine (EmotionEngine)

[2445] Ad generation AI model (AdGenerator)

[2446] User Data Management System

[2447] System processing explanation

[2448] 1. Acquiring emotion data:

[2449] When a user uses a smart device to consider where to donate, the device collects emotional data in real time through facial recognition and voice analysis. For example, the camera in smart glasses can read the user's facial expressions and analyze them with an emotion analysis engine.

[2450] 2. Use of sentiment analysis results:

[2451] The acquired emotional data is sent to a server and analyzed by an emotion analysis engine (EmotionEngine). Based on the results of this analysis, the most appropriate donation recipients and advertisements are selected.

[2452] 3. Suggested donations:

[2453] The server uses an artificial intelligence model to combine the analysis results with the user's past donation history to suggest appropriate donation destinations. For example, if a user is interested in environmental protection and has positive feelings, relevant non-profit organizations will be suggested.

[2454] 4. Ad generation and display:

[2455] Based on the results of the sentiment analysis, an ad generation AI model (AdGenerator) generates ads in real time and displays them on smart devices. For example, if a user is excited, an ad for a new gadget will be displayed on the HUD of smart glasses.

[2456] 5. Analysis of voice input:

[2457] The system also supports voice input, so when a user voices their preference for a donation destination, the device converts the voice into text, performs sentiment analysis, and sends it to the server. The server then uses text analysis and an emotion engine to understand the user's intent and suggests the most appropriate donation destination.

[2458] Specific examples

[2459] The user puts on the smart glasses and speaks, "Please tell me where I should donate to environmental conservation." This voice data is picked up through the smart glasses' microphone and analyzed by the sentiment analysis engine. If the user's sentiment is confirmed to be positive, the server suggests relevant nonprofit organizations. The generative AI model then generates appropriate creative materials, and this information is displayed on the smart glasses' HUD.

[2460] Example prompt sentence:

[2461] "The user's current emotion is excitement. Create an ad for a new electronic gadget that builds on this emotion. The target users are men in their 20s who are interested in the latest technology."

[2462] The above is a detailed description of the embodiment of the present invention, which enables suggestion of donation destinations based on the user's emotions and generation of personalized real-time advertisements.

[2463] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2464] Step 1:

[2465] The device acquires the user's emotional data. The device captures the user's facial expre...

Claims

1. a means for using an artificial intelligence model to suggest donation destinations for the user; a means for managing a user's donation history; A means for predicting the effect of donations on users; a means for using a generative artificial intelligence model to generate creative materials for a contributor; A system including:

2. The system of claim 1 , further comprising means for analyzing the voice input to suggest donation destinations for the user.

3. The system of claim 1 , further comprising means for providing a donation activity with a gamification element and awarding points when a user makes a donation.

Images