System

Abstract

A system is provided.SOLUTION: This system is provided with an input means for inputting and selecting what a user of generation system artificial intelligence wants to do, a retrieval means for retrieving a related prompt template based on information received from the input means, and a display means for displaying the prompt template retrieved by the retrieval means. A system comprising: prompt generating means for generating a specific prompt corresponding to a specific task; executing means for executing the task using the generated prompt; posting means for posting the prompt created by a prompt provider; saving means for saving the posted prompt in a database so that other users can search for the prompt; recording means for recording the number of times the prompt is used by the executing means; and reward calculating means for calculating a consideration based on the number of times recorded by the recording means and paying a reward to the prompt provider.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] Accurate prompts are crucial for the correct and effective use of generative AI. However, prompts are not copyrighted, and the number of prompt engineers is not increasing. Another problem is that many companies are unable to visualize specific ways to utilize generative AI, which hinders its adoption. Furthermore, there is no easy way for users of generative AI to obtain appropriate prompts to turn abstract ideas into concrete forms, limiting its scope of application. Therefore, new methods are needed to promote the use of generative AI and improve AI services. [Means for solving the problem]

[0005] The present invention includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for relevant prompt templates based on information received from the input means, a display means for displaying the searched prompt templates, and a prompt generation means for generating specific prompts corresponding to specific tasks by the user answering additional questions. This allows users to easily obtain appropriate prompts. Furthermore, the present invention also includes a posting means for prompt providers to post prompts they have created, a storage means for saving posted prompts so that other users can search for them, and a reward calculation means for recording the number of times a prompt is used and calculating a reward based on that number of times, allowing prompt providers to receive rewards. This provides a system that matches users of generative artificial intelligence with prompt providers, promoting the use of generative artificial intelligence and improving AI services.

[0006] "Generative AI" is an AI technology that automatically generates new data and content based on instructions and information entered by the user.

[0007] "User" refers to a person or organization that intends to use generative artificial intelligence to perform a specific task.

[0008] A "prompt" refers to text data containing instructions or questions that a generative artificial intelligence needs to perform a specific task.

[0009] A "prompt template" refers to a basic template of a prompt to be applied to a specific task.

[0010] A "prompt engineer" is an expert who creates appropriate prompts for generative artificial intelligence and maximizes its effectiveness.

[0011] "Input means" refers to the interface through which users input what they want to do and the necessary information into the generative artificial intelligence.

[0012] "Search means" refers to a function that searches a database for relevant prompt templates based on information received from an input means.

[0013] The "display means" refers to an interface that displays to the user the prompt templates obtained by the search means and the generated prompts.

[0014] "Prompt generation means" refers to a function that generates specific prompts corresponding to specific tasks by having the user answer additional questions.

[0015] "Execution means" refers to the function of executing a task using prompts generated using generative artificial intelligence.

[0016] "Posting means" refers to an interface that allows a prompt provider to post a created prompt to the system.

[0017] "Storage means" refers to a function that stores prompts posted by the posting means in a database so that other users can search for them.

[0018] The "recording means" refers to a function for recording the number of times a prompt is used.

[0019] The "reward calculation means" refers to a function that calculates a fee based on the number of uses recorded by the recording means and pays a reward to the prompt provider.

[0020] "Prompt Provider" refers to a person or organization that creates and submits prompts to the system. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for relevant prompt templates based on information received from the input means, a display means for displaying the prompt templates searched by the search means, and a prompt generation means for generating specific prompts corresponding to specific tasks in response to additional questions from the user. It also includes a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for saving the posted prompt so that other users can search for it, and a reward calculation means for recording the number of times the prompt is used and calculating a reward based on the number of times it is used. Hereinafter, we will explain how this system is specifically implemented.

[0043] System Program Processing

[0044] The program for this system mainly aims to exchange data between the server and the user's terminal, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with some concrete examples.

[0045] Program processing

[0046] User Registration and Login

[0047] 1. A user visits the sign-up page and enters their name, email address, and password.

[0048] The terminal transmits the input information to the server.

[0049] The server validates the received information and stores it in the database.

[0050] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[0051] 2. The user enters their credentials on the login page and the device sends them to the server.

[0052] The server checks the authentication information and, if successful, creates a session or token and allows login.

[0053] Prompted Search and Select

[0054] 1. The user uses the input means to input what they want to do (e.g., "generate blog content").

[0055] The terminal transmits the input information to the server.

[0056] The server searches the database for the relevant prompt template and returns the result to the terminal.

[0057] The terminal displays the results and the user selects the appropriate template.

[0058] Further questions and clarification

[0059] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[0060] The user answers the questions and the terminal sends the answers to the server.

[0061] The server analyzes the received answers and generates specific prompts.

[0062] The server sends the generated prompt to the terminal for display to the user.

[0063] Providing and Using Prompts

[0064] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[0065] The server stores the received prompts in a database.

[0066] Other users can use the search function to find and use your prompt.

[0067] The terminal sends prompt usage data to the server.

[0068] The server records the number of uses and calculates the reward.

[0069] The calculated reward is paid to the provider.

[0070] Specific examples

[0071] 1. User Registration and Login

[0072] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[0073] 2. Prompt search and selection

[0074] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[0075] 3. Additional questions and clarification

[0076] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the question. The server generates a specific prompt and displays it on the device.

[0077] 4. Providing and Using Prompts

[0078] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt, the server records the number of times it is used and calculates and pays a reward.

[0079] The system embodying the present invention thus provides a mechanism by which users can easily obtain appropriate prompts and prompt providers can receive rewards.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] A user visits the sign-up page and enters their name, email address, and password.

[0083] The terminal transmits the input information to the server.

[0084] Step 2:

[0085] Validate the information received by the server.

[0086] Check the email address format

[0087] Password Strength Check

[0088] Check for required fields

[0089] Step 3:

[0090] The server saves the validated information to the database.

[0091] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[0092] Step 4:

[0093] The user enters their email address and password on the login page.

[0094] The terminal sends the input data to the server.

[0095] Step 5:

[0096] The server checks the authentication information received.

[0097] Hashed password verification

[0098] Generate a session or JWT token upon successful authentication.

[0099] Step 6:

[0100] The server sends the session information along with a message of successful authentication to the terminal.

[0101] The user is redirected to the dashboard page.

[0102] Step 7:

[0103] The user types what they want to do (e.g., "generate blog content") into the search bar.

[0104] The terminal transmits the entered search keyword to the server.

[0105] Step 8:

[0106] The server searches the database for relevant prompt templates and returns the results to the terminal.

[0107] The terminal displays the received data and the user selects the appropriate template.

[0108] Step 9:

[0109] The server generates an additional question form based on the selected template and sends it to the terminal.

[0110] The user answers the additional questions and transmits the answer data from the terminal to the server.

[0111] Step 10:

[0112] The server uses the user's answers to generate specific prompts tailored to the particular task.

[0113] The server sends the generated specific prompt to the terminal for presentation to the user.

[0114] Step 11:

[0115] The prompt provider accesses the submission form and enters their prompt.

[0116] The terminal sends the entered prompt information to the server.

[0117] Step 12:

[0118] The server saves the prompts in a database.

[0119] Other users can find and use the prompts you provide in the search bar.

[0120] Step 13:

[0121] The terminal sends prompt usage data to the server.

[0122] The server records the number of uses and calculates the reward.

[0123] Step 14:

[0124] The server notifies the provider of the calculated reward and processes the payment of the reward.

[0125] This provides a system that matches users of generative AI with prompt providers, promoting the use of generative AI and improving AI services.

[0126] Example 1

[0127] 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."

[0128] In conventional generative AI systems, the search and selection of prompts is complicated, making it difficult for users to find appropriate prompts. Furthermore, there is no well-established mechanism for accurately recording the number of times prompts created by prompt providers are used and calculating appropriate rewards based on that information. Furthermore, there is a lack of a system for safely and efficiently performing user registration and authentication processes.

[0129] 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.

[0130] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the prompt posted by the posting means in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, an authentication means for receiving and verifying the user's authentication information, and a storage means for the authentication means to store the user's information in a database. This enables users to easily and efficiently search for, select, and generate appropriate prompts, enables prompt providers to receive fair rewards, and provides a system in which user registration and authentication processes are performed safely and efficiently.

[0131] "Generative AI" is an AI technology that generates new data and information based on input data.

[0132] "Input means" refers to a device or function that allows a user to input information or commands to a system.

[0133] A "search means" is a processing function for finding specific information from a database or storage.

[0134] "Display means" refers to a device or function for visually presenting information to a user.

[0135] The "prompt generator" is a function that creates specific prompts based on received information and follow-up questions.

[0136] An "execution means" is a function for performing a specific task based on the generated prompt.

[0137] The "posting means" is a function that allows a prompt provider to send a prompt that they have created to the system.

[0138] "Storage means" is a function for storing received information and data in a database or other storage.

[0139] The "recording means" is a function for recording the number of times a prompt is used and other usage data.

[0140] The "reward calculation means" is a function that calculates rewards to prompt providers based on the recorded usage data.

[0141] "Authentication means" is a function for verifying a user's identity and qualifications.

[0142] A "database" is a system for efficiently storing, managing, and searching information and data.

[0143] The present invention provides a generative artificial intelligence system that allows users to efficiently input and select what they want to do, generates and provides appropriate prompts based on the input, and pays rewards to the providers. The following describes in detail the embodiments of the present invention.

[0144] This system consists of a server and a user terminal. The main functions are concentrated on the server, and the user terminal acts as an interface for communicating with users.

[0145] 1. User Registration and Authentication

[0146] A user accesses the new registration page and enters authentication information such as name, email address, and password. For example, the user enters "Name: Taro", "Email address: taro@example.com", and "Password: password123". The device sends this to the server, which validates the received information and saves it in the database. After saving is complete, the server returns a "Registration complete" message to the device.

[0147] Next, the user enters their authentication information on the login page, and the device sends it to the server. The server checks the authentication information against the database, and if successful, generates a session ID and allows login. If successful, a "Login successful" message and session information are returned to the device, and if unsuccessful, an "Authentication failed" error message is returned.

[0148] 2. Prompt search and selection

[0149] The user enters what they want to do into an input means (for example, a text box). For example, they might enter "create blog content." This information is sent from the device to the server. The server searches the database to find relevant prompt templates (for example, "blog prompt for product reviews," "travel blog prompt") and sends the search results to the device. The device then displays the search results in a list format, allowing the user to make a selection.

[0150] 3. Follow-up questions and prompt generation

[0151] When a user selects a specific prompt template, the server generates an additional question form (e.g., "Which product would you like to review?") based on that template and sends it to the device. The user answers this form (e.g., "A new smartphone"), and the device sends it to the server. The server then generates a specific prompt (e.g., "Please review the performance of the new smartphone in detail") based on the answer received and sends it to the device.

[0152] 4. Submitting and Using Prompts

[0153] The prompt provider inputs a prompt they have created and sends it from their device to the server. The server stores the received prompt in a database. Other users can then use the search function to find, select, and use the prompt. The device sends prompt usage data to the server, which records the number of times the prompt has been used.

[0154] 5. Remuneration calculation

[0155] The server calculates the reward based on the number of recorded uses and pays it to the prompt provider. This reward is transferred based on the provider's registered payment information. The reward calculation is, for example, $0.1 per use.

[0156] In this way, users can easily and efficiently search, select, and generate appropriate prompts, prompt providers can earn rewards, and the entire system operates safely and smoothly.

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1:

[0159] A user visits the sign-up page and enters their name, email address, and password.

[0160] Input: The user enters their name, email address, and password into the text fields.

[0161] The terminal transmits the input information to the server.

[0162] Validate the information received by the server (e.g., check that the email address is formatted correctly and does not already exist).

[0163] Output: If validation is successful, the user information is saved in the database and a "Registration complete" message is returned to the terminal. If validation fails, an error message is returned.

[0164] Step 2:

[0165] The user enters their authentication information on the login page, and the device sends it to the server.

[0166] Input: The user enters their email address and password into the login form.

[0167] The device sends the authentication information to the server.

[0168] The server checks the received authentication information against the database and generates a session ID or JWT token if it is correct, or an error message if it is invalid.

[0169] Output: If correct authentication information is provided, the session information is returned to the terminal and the user is logged in. If unsuccessful, an "Authentication failed" message is returned.

[0170] Step 3:

[0171] The user uses the input means to input what he or she wants to do.

[0172] Input: The user inputs "Create blog content" into the input means (text box).

[0173] The terminal transmits the input information to the server.

[0174] The server searches the database for prompt templates related to "blog content generation" and extracts the found templates.

[0175] Output: The prompt templates (e.g. "Blog prompt for product reviews", "Travel blog prompt") as search results are sent to the terminal and displayed in list format.

[0176] Step 4:

[0177] The user selects a prompt template from the search results.

[0178] Input: User clicks to select "Blog prompt for product reviews" from the list.

[0179] The terminal transmits the selection information to the server.

[0180] The server generates additional questions related to the selected prompt template and creates a question form.

[0181] Output: A form with additional questions (e.g., "Which product would you like to review?") is displayed on the terminal.

[0182] Step 5:

[0183] The user answers additional questions to generate the actual prompt.

[0184] Input: The user enters "new smartphone" as an answer into the question form.

[0185] The terminal sends the user's answer to the server.

[0186] The server analyzes the received answers and generates a specific prompt (e.g., "Please provide a detailed review of the performance of your new smartphone").

[0187] Output: The specific prompt is sent to the terminal and displayed to the user.

[0188] Step 6:

[0189] Prompt contributors post prompts they have created themselves.

[0190] Input: The prompt giver enters a "Prompt for a Travel Guidebook."

[0191] The terminal sends the prompt entered by the provider to the server.

[0192] The server stores the received prompts in a database.

[0193] Output: A message indicating that the data has been saved is displayed on the provider's terminal.

[0194] Step 7:

[0195] Use prompts posted by other users.

[0196] Input: The user uses the search function to find and select "Prompt for Travel Guidebook."

[0197] The terminal transmits usage information to the server.

[0198] The server keeps track of the number of times a prompt is used.

[0199] Output: The number of times the prompt is used is recorded in a database.

[0200] Step 8:

[0201] Calculate rewards for prompt providers.

[0202] Input: The server uses the recorded number of prompt usages as input data.

[0203] The server calculates the reward based on the number of uses (e.g., $0.10 per use).

[0204] Output: The calculated reward is added to the contributor's account.

[0205] (Application example 1)

[0206] 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."

[0207] The problem is that there is a lack of efficient means for generating and managing prompts using generative artificial intelligence in electronic payment services. In particular, it is difficult to establish a system that allows users to easily generate and manage appropriate prompts and allows prompt providers to receive rewards.

[0208] 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.

[0209] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the posted prompt in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, a prompt generation means for generating an administrative prompt for an electronic payment service, and a smartphone application for displaying the specific prompt for the electronic payment service generated by the prompt generation means to the user. This allows users to easily generate administrative prompts for electronic payment services and allows prompt providers to receive rewards.

[0210] "Generative AI" is an AI technology that generates content such as text and images based on user instructions.

[0211] "User" refers to the person or organization that uses generative artificial intelligence to perform prompts and tasks.

[0212] "Input means" refers to the interface that allows users of generative artificial intelligence to input and select what they want to do.

[0213] A "prompt template" is a template that contains instructions for a generative artificial intelligence to use when performing a specific task.

[0214] "Search means" refers to a mechanism that searches a database for relevant prompt templates based on information received from an input means.

[0215] "Display means" means an interface for displaying to the user the prompt templates retrieved by the retrieval means.

[0216] A "prompt generator" is a mechanism that generates specific prompts corresponding to specific tasks by having the user answer additional questions.

[0217] The "execution means" refers to a system or process for executing a task using the prompt generated by the prompt generation means.

[0218] "Posting means" refers to an interface for prompt providers to post prompts they have created.

[0219] The "storage means" is a mechanism for storing prompts posted by the posting means in a database so that other users can search for them.

[0220] The "recording means" refers to a mechanism that records the number of times a prompt is used.

[0221] The "reward calculation means" is a mechanism for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[0222] "Electronic payment service" is a general term for services that allow online electronic payments.

[0223] "Smartphone application" refers to software that runs on a smartphone and provides specific functions.

[0224] This invention is a system that uses generative artificial intelligence to generate, manage, and use management prompts for electronic payment services. The system is operated primarily using a server and a smartphone.

[0225] The server has multiple functions and performs multi-stage data processing and calculation. Specifically, the following hardware and software are used:

[0226] Hardware Configuration

[0227] Server: A server machine with high-speed data processing capabilities

[0228] Smartphone: A mobile device used by users as an interface.

[0229] Software Configuration

[0230] Python: Server-side program logic

[0231] Flask (web framework): Realizes communication between the user interface and the server

[0232] Database system: Prompts and user information storage

[0233] Generative AI model: Prompt template generation and management

[0234] The server processes the data in the following steps:

[0235] User Registration and Login

[0236] A user uses a smartphone to enter their name, email address, and password to access the new registration page. The server validates the received information and saves it in the database. Once saved, the server returns a "Registration Complete" message. In the case of login, the user enters authentication information, the server checks the information, generates a session or token, and allows the user to log in.

[0237] Prompted Search and Select

[0238] When a user inputs their desired action (e.g., "create a payment reminder") into the smartphone interface, the server receives the information and searches the database for relevant prompt templates. The templates are then displayed as a list on the smartphone, and the user can select the appropriate template.

[0239] Further questions and clarification

[0240] The server generates a follow-up question form based on the selected template and sends it to the user's smartphone. The user answers the questions, and the server receives and analyzes them to generate a specific prompt. The generated prompt is then sent back to the smartphone and displayed to the user.

[0241] Posting and Using Prompts

[0242] Prompt providers use their smartphones to post their own prompts. The server stores the received prompts in a database and makes them available for other users to search. When other users use the prompt, the server records the number of times it is used and calculates a reward. The calculated reward is paid to the prompt provider.

[0243] Specific examples

[0244] Example of user registration and login:

[0245] The user enters "Name: Tanaka Taro, Email address: tanaka@example.com, Password: password123" on the new registration page and submits it. The server responds with "Registration complete."

[0246] Examples of prompted search and selection:

[0247] The user types "create payment reminder," the server searches for relevant prompt templates, and displays a list on the smartphone.

[0248] Example of generating prompts:

[0249] For the "Payment Reminder" template, an additional question is displayed: "Which payment would you like to be reminded about?" If the user answers "Credit card payments," a specific prompt is generated: "Remind me about my next credit card payment."

[0250] This system allows users to easily create and manage prompts for electronic payment services, and allows prompt providers to earn rewards.

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1:

[0253] User Registration

[0254] The user enters their name, email address, and password on the smartphone's new registration page. The device sends this information to the server. The server validates the received information and stores it in a database. After saving, the server returns a "Registration Complete" message to the device.

[0255] Input: Name, Email Address, Password

[0256] Output: "Registration complete" message

[0257] Specific operation: The server establishes a database connection, checks the input information, and if the information is correct, registers it in the database.

[0258] Step 2:

[0259] Log in

[0260] The user enters their credentials on a login page on their smartphone, and the device sends them to the server, which verifies the credentials and, if successful, creates a session or token and allows the user to log in.

[0261] Input: Email address, Password

[0262] Output: Session or token, login success message

[0263] Specific operation: The server retrieves user information from the database, compares it with the input information, and if the information is correct, issues a session or token.

[0264] Step 3:

[0265] Prompted Search

[0266] The user types what they want to do on their smartphone (e.g., "Create a payment reminder"), and the device sends this information to the server, which searches a database for relevant prompt templates and returns the results to the device.

[0267] Input: What the user wants to do (e.g., "Create a payment reminder")

[0268] Output: A list of related prompt templates

[0269] What it does: The server analyzes user input using natural language processing, generates a database query, retrieves a template from the database, and returns the results.

[0270] Step 4:

[0271] Prompt Selection

[0272] The user selects an appropriate prompt template from the displayed list, and the terminal transmits the user's selection to the server.

[0273] Input: User prompt template selection

[0274] Output: Selected template

[0275] Specific actions: The server retrieves the selected template information and prepares additional questions.

[0276] Step 5:

[0277] Additional question generation

[0278] The server generates a follow-up question form based on the selected prompt template and sends it to the terminal, where the user answers the question and the terminal sends it back to the server.

[0279] Input: prompt template, answers to follow-up questions

[0280] Output: Specific prompt

[0281] Specific action: The server generates a specific prompt based on the template and the user's answer and sends it to the terminal.

[0282] Step 6:

[0283] Prompt generation and display

[0284] The server analyzes the user's answers and generates specific prompts, which are sent to the terminal and displayed to the user.

[0285] Input: Answer to the user's follow-up question

[0286] Output: Specific prompt

[0287] What it does: The server uses the generative AI model to generate a prompt and sends the result to the device.

[0288] Step 7:

[0289] Prompted Posts

[0290] The prompt provider inputs their own prompt and sends it from their terminal to the server, which stores the received prompt in a database.

[0291] Input: A prompt created by the prompt provider

[0292] Output: Prompts saved to the database

[0293] Specific operation: The server receives the prompt information, saves it in the database, and returns a save completion message to the provider.

[0294] Step 8:

[0295] Using and recording prompts

[0296] Other users search for and use the saved prompts. The device sends usage data to the server, which records the number of usages and uses them to calculate rewards.

[0297] Input: Prompt usage information

[0298] Output: Record of prompt usage, reward calculation data

[0299] Specific operation: The server receives prompt usage information, records the number of times in the database, and calculates the reward according to the reward calculation algorithm.

[0300] Step 9:

[0301] Reward calculation and payment

[0302] The server calculates a reward based on the recorded number of uses and pays the reward to the prompt provider.

[0303] Input: Prompt usage count

[0304] Output: Reward payment to prompter

[0305] Specific operation: The server calculates the reward using the reward calculation method and adds the reward to the provider's account.

[0306] 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.

[0307] The present invention provides a system that includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, and an emotion engine for recognizing the user's emotions. Hereinafter, we will explain how this system is specifically implemented.

[0308] System Program Processing

[0309] The program for this system mainly aims to exchange data between the server, terminal, and user, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with concrete examples.

[0310] Program processing

[0311] User Registration and Login

[0312] 1. A user visits the sign-up page and enters their name, email address, and password.

[0313] The terminal transmits the input information to the server.

[0314] The server validates the received information and stores it in the database.

[0315] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[0316] 2. The user enters their email address and password on the login page.

[0317] The terminal sends the input data to the server.

[0318] The server checks the received authentication information and, if successful, generates a session or JWT token and allows login.

[0319] Prompted Search and Select

[0320] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[0321] The terminal transmits the entered search keyword to the server.

[0322] The server searches the database for relevant prompt templates and returns the results to the terminal.

[0323] The terminal displays the results and the user selects the appropriate template.

[0324] Emotion Recognition and Prompt Generation

[0325] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[0326] The user answers the questions and transmits the answer data from the terminal to the server.

[0327] The server analyzes the answers it receives and generates specific prompts tailored to the particular task.

[0328] The server sends the generated specific prompt to the terminal for presentation to the user.

[0329] 2. The emotion engine analyzes emotions based on the user's input and behavioral history.

[0330] The emotion engine provides the results of the analysis to the prompt generator to adjust the generated prompts.

[0331] Providing and Using Prompts

[0332] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[0333] The server stores the received prompts in a database.

[0334] Other users can use the search function to find and use your prompt.

[0335] The terminal sends prompt usage data to the server.

[0336] The server records the number of uses and calculates the reward.

[0337] The server notifies the provider of the calculated reward and processes the payment of the reward.

[0338] Specific examples

[0339] 1. User Registration and Login

[0340] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[0341] 2. Prompt search and selection

[0342] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[0343] 3. Emotion Recognition and Prompt Generation

[0344] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the response. The server generates a specific prompt, sends it to the device, and displays it to the user.

[0345] The emotion engine analyzes the user's emotions based on their input and behavioral history, and then generates prompts based on the results. For example, if the user expresses anxiety, the prompts will be softer and more reassuring.

[0346] 4. Providing and Using Prompts

[0347] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt using the search function and record the number of times it is used, the server calculates a reward and pays it to the provider.

[0348] The system embodying the present invention provides a mechanism that allows users to easily obtain appropriate prompts and prompt providers to receive rewards, and also provides more appropriate prompts by recognizing the user's emotions and reflecting them in the generation of prompts.

[0349] The processing flow will be explained below.

[0350] Step 1:

[0351] A user visits the sign-up page and enters their name, email address, and password.

[0352] The terminal transmits the input information to the server.

[0353] Step 2:

[0354] Validate the information received by the server.

[0355] Check the email address format

[0356] Password Strength Check

[0357] Check for required fields

[0358] Step 3:

[0359] The server saves the validated information to the database.

[0360] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[0361] Step 4:

[0362] The user enters their email address and password on the login page.

[0363] The terminal sends the input data to the server.

[0364] Step 5:

[0365] The server checks the authentication information received.

[0366] Hashed password verification

[0367] Generate a session or JWT token upon successful authentication.

[0368] Step 6:

[0369] The server sends the session information along with a message of successful authentication to the terminal.

[0370] The user is redirected to the dashboard page.

[0371] Step 7:

[0372] The user types what they want to do (e.g., "generate blog content") into the search bar.

[0373] The terminal transmits the entered search keyword to the server.

[0374] Step 8:

[0375] The server searches the database for relevant prompt templates and returns the results to the terminal.

[0376] The terminal displays the received data and the user selects the appropriate template.

[0377] Step 9:

[0378] The server generates an additional question form based on the selected template and sends it to the terminal.

[0379] The user answers the additional questions and transmits the answer data from the terminal to the server.

[0380] Step 10:

[0381] The server uses the user's answers to generate specific prompts tailored to the particular task.

[0382] The server sends the generated specific prompt to the terminal for presentation to the user.

[0383] Step 11:

[0384] The emotion engine analyzes emotions based on user input and behavioral history.

[0385] The emotion engine extracts emotional information from the input.

[0386] The emotion engine analyzes emotions inferred from the user's operation history.

[0387] Step 12:

[0388] The emotion engine sends the analysis results to the server.

[0389] The server adjusts the prompts based on the emotional information.

[0390] Step 13:

[0391] A prompt provider inputs a prompt that he or she has created using an input means and transmits it from the terminal to the server.

[0392] The server stores the received prompts in a database.

[0393] Step 14:

[0394] Other users can use the search function to find and use your prompt.

[0395] The terminal sends prompt usage data to the server.

[0396] Step 15:

[0397] The server records the number of uses.

[0398] The server calculates the reward based on the number of recorded uses.

[0399] Step 16:

[0400] The server notifies the prompt provider of the calculated reward and processes the payment of the reward.

[0401] As a result, a system that combines an emotion engine will operate effectively, matching users of generative AI with prompt providers and improving AI services.

[0402] Example 2

[0403] 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."

[0404] It takes a lot of time and effort for users of generative AI to efficiently search, select, generate, and use prompts that best suit their purposes. Furthermore, since prompts cannot be generated taking into account the user's emotions, it is difficult to provide appropriate prompts. Furthermore, there is no well-established system for prompt providers to receive appropriate compensation, making it difficult to promote the provision of high-quality prompts.

[0405] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: input means for a user of the generative artificial intelligence to input and select what he or she wants to do; search means for searching for a relevant prompt template based on information received from the input means; display means for displaying the prompt template searched by the search means; prompt generation means for generating a specific prompt corresponding to a specific task based on the user's answer to additional questions; execution means for executing a task using the prompt generated by the prompt generation means; posting means for a prompt provider to post a prompt created by the prompt provider; storage means for storing the prompt posted by the posting means in a database so that other users can search for it; recording means for recording the number of times a prompt is used by the execution means; reward calculation means for calculating a fee based on the number of times it is used recorded by the recording means and paying a reward to the prompt provider; and emotion recognition means for recognizing emotions from the user's input content and behavioral history and reflecting the result in prompt generation. This enables users to efficiently obtain, generate, and use prompts that suit their purposes, and also enables prompts to be generated that correspond to emotions, thereby enabling accurate reward payment to prompt providers.

[0406] "Input means" refers to the means by which users of generative artificial intelligence input and select what they want to do.

[0407] The "search means" is a means for searching for a relevant prompt template based on the information received from the input means.

[0408] The "display means" is a means for displaying the prompt template retrieved by the retrieval means.

[0409] A "prompt generation means" is a means for generating a specific prompt corresponding to a specific task by having the user answer additional questions.

[0410] The "execution means" is a means for executing a task using the prompt generated by the prompt generation means.

[0411] A "posting means" is a means for a prompt provider to post a prompt that they have created.

[0412] The "storage means" is a means for storing the prompt posted by the posting means in a database so that other users can search for it.

[0413] The "recording means" is a means for recording the number of times a prompt is used when it is used by the execution means.

[0414] The "reward calculation means" is a means for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[0415] The "emotion recognition means" is a means for recognizing the user's emotions from their input content and behavioral history, and reflecting the results in generating prompts.

[0416] This invention relates to a system that enables users of generative artificial intelligence to efficiently search, generate, and use appropriate prompts. The system transfers data between a server, a terminal, and a user, enabling the provision of prompts that are optimal for the user's purpose.

[0417] System configuration

[0418] The system includes the following hardware and software:

[0419] 1. The server has the basic computer infrastructure to run a database management system, an authentication system, an emotion recognition engine, etc. Specifically, it is equipped with a database management system such as MySQL, an authentication system using JWT, and an emotion recognition engine that performs natural language processing.

[0420] 2. A terminal is an interface through which a user accesses the system and inputs and receives various information. This includes web browsers and mobile applications.

[0421] 3. The user is responsible for inputting what they want to do with the system and for selecting, generating, and using prompts.

[0422] Program processing description

[0423] User Registration and Login

[0424] 1. A user accesses the new registration page and enters their name, email address, and password. The device then sends the entered information to the server. The server validates the entered information and saves it in the database. After saving is complete, a "Registration Complete" message is returned to the device.

[0425] 2. When the user enters their email address and password on the login page, the device sends this to the server, which checks the authentication information and, if successful, generates a session or JWT token and allows login.

[0426] Prompted Search and Select

[0427] 1. When a user enters what they want to do (e.g., "generate blog content") into the search bar, the device sends the search keywords to the server. The server searches the database for relevant prompt templates and returns the results to the device. The device displays them, and the user can select an appropriate template.

[0428] Emotion Recognition and Prompt Generation

[0429] 1. The server generates an additional question form based on the selected template and sends it to the terminal. The user answers the question and the answer data is sent from the terminal to the server. The server analyzes the answer and generates a specific prompt.

[0430] 2. The emotion engine analyzes the user's input and behavioral history in real time and provides the results to the server, which then uses the emotion information to send more personalized prompts to the device and present them to the user.

[0431] Providing and Using Prompts

[0432] 1. The prompt provider creates a prompt using an input method and sends it from the terminal to the server, which stores the prompt in a database.

[0433] 2. Other users use the search function to find and use the prompt. The device sends usage data to the server, which records the number of uses, calculates the reward, and pays it to the provider.

[0434] Specific examples

[0435] Example 1: User registration and login

[0436] A user enters the name "Taro Tanaka," the email address "tanaka@example.com," and the password "password123" on the new registration page. The entered information is sent from the device to the server and stored in the database. After that, the "Registration Complete" message is displayed.

[0437] Example 2: Prompted search and select

[0438] A user types "blog content generation" in the search bar, the server searches for relevant prompt templates and displays a list on the device. If the user selects "blog prompt for product review", its details are displayed.

[0439] Example 3: Emotion recognition and prompt generation

[0440] The server generates and displays a follow-up question: "Which product would you like to review?" The user answers "A new smartphone" and submits the question. The server generates a specific prompt and displays the message: "To write a review of a new smartphone, please use the following structure as a guide."

[0441] The emotion engine analyzes the user's emotions based on their input and behavioral history, and if the user expresses anxiety, for example, the prompts are softened to provide a sense of security.

[0442] Example 4: Providing and using prompts

[0443] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt in the search function, the number of uses is recorded, and the server calculates and pays the provider a reward.

[0444] This system provides a mechanism for users to easily obtain appropriate prompts and for providers to receive rewards, and also generates prompts that take into account the user's emotions.

[0445] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0446] Step 1: User Registration

[0447] 1. A user visits the sign-up page and enters their name, email address, and password.

[0448] Input: Name, Email Address, Password

[0449] The terminal transmits the input information to the server.

[0450] Validate the information received by the server.

[0451] Data processing: Email address format check, password strength check, etc.

[0452] The server saves the data that passes the validation in the database.

[0453] Output: "Registration complete" message

[0454] The server returns a "registration complete" message to the terminal.

[0455] The device will display a "Registration complete" message.

[0456] Step 2: Log in

[0457] 1. The user enters their email address and password on the login page.

[0458] Input: Email address, password

[0459] The terminal sends the input data to the server.

[0460] The server checks the received authentication information against a database.

[0461] Data calculation: Email address and password matching

[0462] If authentication is successful, a session or JWT token is generated.

[0463] Output: Session ID or JWT token

[0464] The server returns a session ID or JWT token to the device.

[0465] The terminal notifies the user that authentication was successful.

[0466] Step 3: Prompted Search

[0467] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[0468] Input: Search keyword

[0469] The device sends the search keywords to the server.

[0470] The server retrieves the relevant prompt template from the database.

[0471] Data calculations: keyword matching, relevance score calculation

[0472] Output: Search result list

[0473] The server returns the search results to the device.

[0474] Your device will display a list of search results.

[0475] Step 4: Prompt details and selection

[0476] 1. The user selects the appropriate template from the displayed list.

[0477] Input: Selected template

[0478] The device sends the selection to the server.

[0479] The server retrieves the details of the selected template from the database.

[0480] Data processing: Obtaining detailed template information

[0481] Output: Template details

[0482] The server returns detailed information about the template to the terminal.

[0483] The device will display more information.

[0484] Step 5: Emotion recognition and prompt generation

[0485] 1. The server generates a follow-up question form based on the selected template.

[0486] Input: Selected template

[0487] Data processing: Generation of additional question form

[0488] A question form is sent to the terminal and displayed.

[0489] The user answers the questions and inputs the answer data.

[0490] Input: Answer data to questions

[0491] The terminal transmits the response data to the server.

[0492] The server analyzes the received answers and generates specific prompts.

[0493] Data arithmetic: Response analysis, prompt generation

[0494] Output: Specific prompt

[0495] The server generates a prompt and sends it to the terminal for display.

[0496] The emotion recognition means analyzes the user's responses and behavior history and provides emotion information to the server.

[0497] The server adjusts the prompts based on the emotional information.

[0498] Step 6: Provide a prompt

[0499] 1. The prompt provider creates a prompt using an input means and sends it from the terminal to the server.

[0500] Input: Created prompt

[0501] The terminal sends the input data to the server.

[0502] The server stores the received prompts in a database.

[0503] Data Transformation: Save Prompt

[0504] Output: Save completion notification

[0505] The server sends a save completion notification to the terminal.

[0506] Step 7: Use prompts

[0507] 1. Other users find your prompt using the search feature.

[0508] Input: Search keyword

[0509] The device sends the search keywords to the server.

[0510] The server retrieves the relevant prompt from the database.

[0511] Data calculations: keyword matching, relevance score calculation

[0512] Output: Search result list

[0513] The server returns the search results to the device.

[0514] Your device will display a list of search results.

[0515] The user selects and uses the prompt.

[0516] Input: Selected prompt

[0517] The device sends usage data to the server.

[0518] The server records the number of uses.

[0519] Data processing: Recording number of uses

[0520] A reward calculation means calculates and pays a reward to the prompt provider.

[0521] Data calculation: Reward calculation

[0522] Output: Reward amount

[0523] The server processes the reward payment and notifies the provider.

[0524] (Application example 2)

[0525] 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."

[0526] Conventional generative AI systems do not consider emotions when generating specific prompts, limiting their ability to improve the user experience. Even when users prefer to use voice input to generate and display prompts using smart devices, they face difficulties converting the speech into text and processing it appropriately. Furthermore, feedback on generated prompts is lacking, leading to ineffective reward calculations for prompt providers. There is a need to address these issues and provide a more interactive and user-friendly system.

[0527] 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.

[0528] In this invention, the server includes: an input means for inputting and selecting what a user of the generative artificial intelligence wants to do; a search means for searching for a relevant prompt template based on information received from the input means; a display means for displaying the prompt template searched by the search means; a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions; an execution means for executing a task using the prompt generated by the prompt generation means; a posting means for a prompt provider to post a prompt created by the prompt provider; a storage means for storing the posted prompt in a database so that other users can search for the prompt; a recording means for recording the number of times a prompt is used by the execution means; a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider; an emotion engine for recognizing a user's emotions; an adjustment means for adjusting the display content or prompt content based on emotion information analyzed by the emotion engine; a speech recognition means for converting a user's voice input into text; and an edge device means for generating and displaying prompts via a smart device. This enables prompt generation and display that take the user's emotions into consideration, thereby enabling smooth prompt operation on a smart device using voice input. Furthermore, it is possible to realize appropriate reward calculation for prompt providers, and to provide a more interactive and user-friendly system.

[0529] "Generative AI" is an AI system that automatically generates content such as text and images based on user input and selections.

[0530] "Input means" refers to an interface that allows a user to input or select what they want to do, and includes a keyboard, touch screen, voice recognition, etc.

[0531] A "search mechanism" is an algorithm or system for searching for relevant prompt templates based on information received from an input mechanism.

[0532] A "display means" is a device or interface for visually presenting retrieved prompt templates and generated prompts to a user.

[0533] A "prompt generator" is a system or algorithm that generates specific prompts for a particular task based on the user's answers to follow-up questions.

[0534] The "execution means" is a function for executing a specific task using the prompt generated by the prompt generation means.

[0535] The "posting means" is an interface for inputting and sending a prompt created by a prompt provider.

[0536] The "storage means" is a system for storing prompts posted by the posting means in a database so that other users can search for them.

[0537] A "recording means" is a system or algorithm for tracking and recording the number of times a prompt is used by the execution means.

[0538] The "reward calculation means" is a system for calculating compensation based on the number of uses recorded by the recording means and providing a reward to the prompt provider.

[0539] An "emotion engine" is software or algorithms that analyze and recognize emotions based on user input and behavioral history.

[0540] The "adjustment means" is a function for adjusting the display content or prompt content based on the emotion information analyzed by the emotion engine.

[0541] A "speech recognizer" is a system or algorithm for converting a user's voice input into text.

[0542] An "edge device means" is a local or network-connected device for generating and displaying prompts through a smart device.

[0543] The present invention is a system that uses generative artificial intelligence to generate and display appropriate prompts while taking into account the user's emotions. This system is intended for use as a shopping assistant application on smart devices.

[0544] Program processing

[0545] The program in this system mainly exchanges data between the server and the smart device (e.g., smart glasses). Each element is explained below.

[0546] User Registration and Login

[0547] 1. The user registers by entering their name, email address, and password using voice input or touch gestures on their smart device. The device sends the entered information to the server, which validates the received information and stores it in the database. After saving, the message "Registration Complete" appears on the smart device's display.

[0548] Prompted Search and Select

[0549] 1. The user uses the voice input function of the smart device to say, for example, "I'd like to know reviews of the new smartphone." The device converts this voice data into text using a speech recognition method (e.g., Google Speech-to-Text API) and sends the search keywords to the server. The server searches for relevant prompt templates in its database and returns the results to the device. The smart device then displays the results on its screen, and the user selects the appropriate template.

[0550] Emotion Recognition and Prompt Generation

[0551] 1. The server generates additional questions based on the selected template and sends them to the smart device. The user answers by voice, and the device converts the voice into text and sends it to the server. The server analyzes the received answer data and generates a specific prompt (e.g., "Show me reviews of Apple's latest smartphones"). The generated specific prompt is then displayed on the smart device.

[0552] 2. An emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's tone of voice and behavioral history to determine their emotions. If the user expresses anxiety, the generated prompt content is adjusted to be more reassuring (e.g., "You can check the information with peace of mind. Here is a review of Apple's latest smartphone").

[0553] Providing and Using Prompts

[0554] 1. Prompt providers enter and submit prompts through a web interface, and the server stores them in a database, making them available for other users to find and use using the search function on their smart devices.

[0555] 2. When a prompt is used, the terminal transmits usage data to the server, which records the number of times the prompt is used. Based on the recorded data, the reward calculation means calculates the compensation and provides a reward to the prompt provider.

[0556] Specific examples

[0557] User Registration and Login

[0558] The user speaks into the smart device, "New registration, name: User A, email address: usera@example.com, password: password123." The device converts the voice to text and sends it to the server, completing the registration.

[0559] Prompted Search and Select

[0560] The user speaks into their smart device, saying, "I'd like to know reviews of the new smartphone." The device converts the speech into text, and the server returns a template, such as "Reviews of Apple's latest smartphone," which is then displayed.

[0561] Emotion Recognition and Prompt Generation

[0562] The server generates the question "What brand are you looking for?" and displays it on the smart device. The user responds with "Apple," and the voice data is converted into text and sent to the server. The server generates a prompt and sends it to the device. If the emotion engine detects anxiety in the user's tone of voice, it adjusts the prompt and displays, "You can rest assured that we're here to help you. We'll show you reviews of Apple's latest smartphones."

[0563] Prompt Sentence Examples

[0564] "Please enter the brand name of the smartphone you want to see reviews for."

[0565] The system is analyzing user sentiment...

[0566] "Please check out our review of Apple's latest smartphone here. If you have any questions, please let us know."

[0567] This system enables prompt generation and display that takes the user's emotions into account, allowing for smooth prompt operation on smart devices using voice input. It also provides an interactive and user-friendly system that appropriately calculates rewards for prompt providers.

[0568] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0569] Step 1:

[0570] The user registers by entering their name, email address, and password using the voice input function of their smart device. The entered information is converted into text data by the terminal's voice recognition means (input: voice data, output: text data). The terminal then sends the text data to the server. The server validates the sent information and stores it in a database. Once registration is complete, the server sends a "Registration Complete" message to the terminal, which is displayed on the smart device's display (input: text data, output: registration complete message).

[0571] Step 2:

[0572] The user uses the voice input function of the smart device to say, "I'd like to know reviews of the new smartphone." The device converts this voice data into text using a speech recognition means (input: voice data, output: text data). The converted text data is sent to the server. The server searches the database for relevant prompt templates and returns the search results to the device (input: text data, output: prompt template). The search results are then displayed on the smart device's display.

[0573] Step 3:

[0574] The user selects an appropriate template from those displayed on the terminal display. The selection information is sent from the terminal to the server (input: user selection, output: selection information). The server generates a follow-up question based on the selected template and sends it to the terminal (input: selection information, output: follow-up question). The follow-up question is then displayed on the smart device.

[0575] Step 4:

[0576] The user answers the follow-up questions by voice. The device converts the voice data into text data using a voice recognition means (input: voice data, output: text data). The answer text data is sent to the server. The server analyzes the received answer data and generates a specific prompt (input: text data, output: specific prompt). The generated prompt is displayed on the smart device.

[0577] Step 5:

[0578] The emotion engine analyzes the user's voice tone and behavioral history to determine their emotions. The analysis results are sent to the server, which then adjusts the prompt content (input: data such as voice tone, output: adjusted prompt). The adjusted prompt is sent to the device and displayed on the smart device's screen.

[0579] Step 6:

[0580] A prompt provider uses a web interface to input and submit prompts, which are received by the server and stored in a database (input: prompt data, output: saving to database).

[0581] Step 7:

[0582] Other users can use the saved prompts by using the search function. When a prompt is used, the device sends the usage data to the server, and the server records the number of times it is used (input: usage data, output: record of number of times it is used).

[0583] Step 8:

[0584] The reward calculation means calculates the compensation based on the recorded number of uses. The calculation result is added as credit to the prompt provider's account, and a reward is provided to the provider (input: number of uses, output: reward calculation result). The prompt provider is notified of the reward provision.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] [Second embodiment]

[0589] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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).

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] In the smart glasses 214, 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.

[0600] 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."

[0601] The present invention includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for relevant prompt templates based on information received from the input means, a display means for displaying the prompt templates searched by the search means, and a prompt generation means for generating specific prompts corresponding to specific tasks in response to additional questions from the user. It also includes a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for saving the posted prompt so that other users can search for it, and a reward calculation means for recording the number of times the prompt is used and calculating a reward based on the number of times it is used. Hereinafter, we will explain how this system is specifically implemented.

[0602] System Program Processing

[0603] The program for this system mainly aims to exchange data between the server and the user's terminal, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with some concrete examples.

[0604] Program processing

[0605] User Registration and Login

[0606] 1. A user visits the sign-up page and enters their name, email address, and password.

[0607] The terminal transmits the input information to the server.

[0608] The server validates the received information and stores it in the database.

[0609] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[0610] 2. The user enters their credentials on the login page and the device sends them to the server.

[0611] The server checks the authentication information and, if successful, creates a session or token and allows login.

[0612] Prompted Search and Select

[0613] 1. The user uses the input means to input what they want to do (e.g., "generate blog content").

[0614] The terminal transmits the input information to the server.

[0615] The server searches the database for the relevant prompt template and returns the result to the terminal.

[0616] The terminal displays the results and the user selects the appropriate template.

[0617] Further questions and clarification

[0618] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[0619] The user answers the questions and the terminal sends the answers to the server.

[0620] The server analyzes the received answers and generates specific prompts.

[0621] The server sends the generated prompt to the terminal for display to the user.

[0622] Providing and Using Prompts

[0623] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[0624] The server stores the received prompts in a database.

[0625] Other users can use the search function to find and use your prompt.

[0626] The terminal sends prompt usage data to the server.

[0627] The server records the number of uses and calculates the reward.

[0628] The calculated reward is paid to the provider.

[0629] Specific examples

[0630] 1. User Registration and Login

[0631] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[0632] 2. Prompt search and selection

[0633] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[0634] 3. Additional questions and clarification

[0635] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the question. The server generates a specific prompt and displays it on the device.

[0636] 4. Providing and Using Prompts

[0637] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt, the server records the number of times it is used and calculates and pays a reward.

[0638] The system embodying the present invention thus provides a mechanism by which users can easily obtain appropriate prompts and prompt providers can receive rewards.

[0639] The processing flow will be explained below.

[0640] Step 1:

[0641] A user visits the sign-up page and enters their name, email address, and password.

[0642] The terminal transmits the input information to the server.

[0643] Step 2:

[0644] Validate the information received by the server.

[0645] Check the email address format

[0646] Password Strength Check

[0647] Check for required fields

[0648] Step 3:

[0649] The server saves the validated information to the database.

[0650] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[0651] Step 4:

[0652] The user enters their email address and password on the login page.

[0653] The terminal sends the input data to the server.

[0654] Step 5:

[0655] The server checks the authentication information received.

[0656] Hashed password verification

[0657] Generate a session or JWT token upon successful authentication.

[0658] Step 6:

[0659] The server sends the session information along with a message of successful authentication to the terminal.

[0660] The user is redirected to the dashboard page.

[0661] Step 7:

[0662] The user types what they want to do (e.g., "generate blog content") into the search bar.

[0663] The terminal transmits the entered search keyword to the server.

[0664] Step 8:

[0665] The server searches the database for relevant prompt templates and returns the results to the terminal.

[0666] The terminal displays the received data and the user selects the appropriate template.

[0667] Step 9:

[0668] The server generates an additional question form based on the selected template and sends it to the terminal.

[0669] The user answers the additional questions and transmits the answer data from the terminal to the server.

[0670] Step 10:

[0671] The server uses the user's answers to generate specific prompts tailored to the particular task.

[0672] The server sends the generated specific prompt to the terminal for presentation to the user.

[0673] Step 11:

[0674] The prompt provider accesses the submission form and enters their prompt.

[0675] The terminal sends the entered prompt information to the server.

[0676] Step 12:

[0677] The server saves the prompts in a database.

[0678] Other users can find and use the prompts you provide in the search bar.

[0679] Step 13:

[0680] The terminal sends prompt usage data to the server.

[0681] The server records the number of uses and calculates the reward.

[0682] Step 14:

[0683] The server notifies the provider of the calculated reward and processes the payment of the reward.

[0684] This provides a system that matches users of generative AI with prompt providers, promoting the use of generative AI and improving AI services.

[0685] Example 1

[0686] 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."

[0687] In conventional generative AI systems, the search and selection of prompts is complicated, making it difficult for users to find appropriate prompts. Furthermore, there is no well-established mechanism for accurately recording the number of times prompts created by prompt providers are used and calculating appropriate rewards based on that information. Furthermore, there is a lack of a system for safely and efficiently performing user registration and authentication processes.

[0688] 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.

[0689] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the prompt posted by the posting means in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, an authentication means for receiving and verifying the user's authentication information, and a storage means for the authentication means to store the user's information in a database. This enables users to easily and efficiently search for, select, and generate appropriate prompts, enables prompt providers to receive fair rewards, and provides a system in which user registration and authentication processes are performed safely and efficiently.

[0690] "Generative AI" is an AI technology that generates new data and information based on input data.

[0691] "Input means" refers to a device or function that allows a user to input information or commands to a system.

[0692] A "search means" is a processing function for finding specific information from a database or storage.

[0693] "Display means" refers to a device or function for visually presenting information to a user.

[0694] The "prompt generator" is a function that creates specific prompts based on received information and follow-up questions.

[0695] An "execution means" is a function for performing a specific task based on the generated prompt.

[0696] The "posting means" is a function that allows a prompt provider to send a prompt that they have created to the system.

[0697] "Storage means" is a function for storing received information and data in a database or other storage.

[0698] The "recording means" is a function for recording the number of times a prompt is used and other usage data.

[0699] The "reward calculation means" is a function that calculates rewards to prompt providers based on the recorded usage data.

[0700] "Authentication means" is a function for verifying a user's identity and qualifications.

[0701] A "database" is a system for efficiently storing, managing, and searching information and data.

[0702] The present invention provides a generative artificial intelligence system that allows users to efficiently input and select what they want to do, generates and provides appropriate prompts based on the input, and pays rewards to the providers. The following describes in detail the embodiments of the present invention.

[0703] This system consists of a server and a user terminal. The main functions are concentrated on the server, and the user terminal acts as an interface for communicating with users.

[0704] 1. User Registration and Authentication

[0705] A user accesses the new registration page and enters authentication information such as name, email address, and password. For example, the user enters "Name: Taro", "Email address: taro@example.com", and "Password: password123". The device sends this to the server, which validates the received information and saves it in the database. After saving is complete, the server returns a "Registration complete" message to the device.

[0706] Next, the user enters their authentication information on the login page, and the device sends it to the server. The server checks the authentication information against the database, and if successful, generates a session ID and allows login. If successful, a "Login successful" message and session information are returned to the device, and if unsuccessful, an "Authentication failed" error message is returned.

[0707] 2. Prompt search and selection

[0708] The user enters what they want to do into an input means (for example, a text box). For example, they might enter "create blog content." This information is sent from the device to the server. The server searches the database to find relevant prompt templates (for example, "blog prompt for product reviews," "travel blog prompt") and sends the search results to the device. The device then displays the search results in a list format, allowing the user to make a selection.

[0709] 3. Follow-up questions and prompt generation

[0710] When a user selects a specific prompt template, the server generates an additional question form (e.g., "Which product would you like to review?") based on that template and sends it to the device. The user answers this form (e.g., "A new smartphone"), and the device sends it to the server. The server then generates a specific prompt (e.g., "Please review the performance of the new smartphone in detail") based on the answer received and sends it to the device.

[0711] 4. Submitting and Using Prompts

[0712] The prompt provider inputs a prompt they have created and sends it from their device to the server. The server stores the received prompt in a database. Other users can then use the search function to find, select, and use the prompt. The device sends prompt usage data to the server, which records the number of times the prompt has been used.

[0713] 5. Remuneration calculation

[0714] The server calculates the reward based on the number of recorded uses and pays it to the prompt provider. This reward is transferred based on the provider's registered payment information. The reward calculation is, for example, $0.1 per use.

[0715] In this way, users can easily and efficiently search, select, and generate appropriate prompts, prompt providers can earn rewards, and the entire system operates safely and smoothly.

[0716] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0717] Step 1:

[0718] A user visits the sign-up page and enters their name, email address, and password.

[0719] Input: The user enters their name, email address, and password into the text fields.

[0720] The terminal transmits the input information to the server.

[0721] Validate the information received by the server (e.g., check that the email address is formatted correctly and does not already exist).

[0722] Output: If validation is successful, the user information is saved in the database and a "Registration complete" message is returned to the terminal. If validation fails, an error message is returned.

[0723] Step 2:

[0724] The user enters their authentication information on the login page, and the device sends it to the server.

[0725] Input: The user enters their email address and password into the login form.

[0726] The device sends the authentication information to the server.

[0727] The server checks the received authentication information against the database and generates a session ID or JWT token if it is correct, or an error message if it is invalid.

[0728] Output: If correct authentication information is provided, the session information is returned to the terminal and the user is logged in. If unsuccessful, an "Authentication failed" message is returned.

[0729] Step 3:

[0730] The user uses the input means to input what he or she wants to do.

[0731] Input: The user inputs "Create blog content" into the input means (text box).

[0732] The terminal transmits the input information to the server.

[0733] The server searches the database for prompt templates related to "blog content generation" and extracts the found templates.

[0734] Output: The prompt templates (e.g. "Blog prompt for product reviews", "Travel blog prompt") as search results are sent to the terminal and displayed in list format.

[0735] Step 4:

[0736] The user selects a prompt template from the search results.

[0737] Input: User clicks to select "Blog prompt for product reviews" from the list.

[0738] The terminal transmits the selection information to the server.

[0739] The server generates additional questions related to the selected prompt template and creates a question form.

[0740] Output: A form with additional questions (e.g., "Which product would you like to review?") is displayed on the terminal.

[0741] Step 5:

[0742] The user answers additional questions to generate the actual prompt.

[0743] Input: The user enters "new smartphone" as an answer into the question form.

[0744] The terminal sends the user's answer to the server.

[0745] The server analyzes the received answers and generates a specific prompt (e.g., "Please provide a detailed review of the performance of your new smartphone").

[0746] Output: The specific prompt is sent to the terminal and displayed to the user.

[0747] Step 6:

[0748] Prompt contributors post prompts they have created themselves.

[0749] Input: The prompt giver enters a "Prompt for a Travel Guidebook."

[0750] The terminal sends the prompt entered by the provider to the server.

[0751] The server stores the received prompts in a database.

[0752] Output: A message indicating that the data has been saved is displayed on the provider's terminal.

[0753] Step 7:

[0754] Use prompts posted by other users.

[0755] Input: The user uses the search function to find and select "Prompt for Travel Guidebook."

[0756] The terminal transmits usage information to the server.

[0757] The server keeps track of the number of times a prompt is used.

[0758] Output: The number of times the prompt is used is recorded in a database.

[0759] Step 8:

[0760] Calculate rewards for prompt providers.

[0761] Input: The server uses the recorded number of prompt usages as input data.

[0762] The server calculates the reward based on the number of uses (e.g., $0.10 per use).

[0763] Output: The calculated reward is added to the contributor's account.

[0764] (Application example 1)

[0765] 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."

[0766] The problem is that there is a lack of efficient means for generating and managing prompts using generative artificial intelligence in electronic payment services. In particular, it is difficult to establish a system that allows users to easily generate and manage appropriate prompts and allows prompt providers to receive rewards.

[0767] 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.

[0768] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the posted prompt in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, a prompt generation means for generating an administrative prompt for an electronic payment service, and a smartphone application for displaying the specific prompt for the electronic payment service generated by the prompt generation means to the user. This allows users to easily generate administrative prompts for electronic payment services and allows prompt providers to receive rewards.

[0769] "Generative AI" is an AI technology that generates content such as text and images based on user instructions.

[0770] "User" refers to the person or organization that uses generative artificial intelligence to perform prompts and tasks.

[0771] "Input means" refers to the interface that allows users of generative artificial intelligence to input and select what they want to do.

[0772] A "prompt template" is a template that contains instructions for a generative artificial intelligence to use when performing a specific task.

[0773] "Search means" refers to a mechanism that searches a database for relevant prompt templates based on information received from an input means.

[0774] "Display means" means an interface for displaying to the user the prompt templates retrieved by the retrieval means.

[0775] A "prompt generator" is a mechanism that generates specific prompts corresponding to specific tasks by having the user answer additional questions.

[0776] The "execution means" refers to a system or process for executing a task using the prompt generated by the prompt generation means.

[0777] "Posting means" refers to an interface for prompt providers to post prompts they have created.

[0778] The "storage means" is a mechanism for storing prompts posted by the posting means in a database so that other users can search for them.

[0779] The "recording means" refers to a mechanism that records the number of times a prompt is used.

[0780] The "reward calculation means" is a mechanism for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[0781] "Electronic payment service" is a general term for services that allow online electronic payments.

[0782] "Smartphone application" refers to software that runs on a smartphone and provides specific functions.

[0783] This invention is a system that uses generative artificial intelligence to generate, manage, and use management prompts for electronic payment services. The system is operated primarily using a server and a smartphone.

[0784] The server has multiple functions and performs multi-stage data processing and calculation. Specifically, the following hardware and software are used:

[0785] Hardware Configuration

[0786] Server: A server machine with high-speed data processing capabilities

[0787] Smartphone: A mobile device used by users as an interface.

[0788] Software Configuration

[0789] Python: Server-side program logic

[0790] Flask (web framework): Realizes communication between the user interface and the server

[0791] Database system: Prompts and user information storage

[0792] Generative AI model: Prompt template generation and management

[0793] The server processes the data in the following steps:

[0794] User Registration and Login

[0795] A user uses a smartphone to enter their name, email address, and password to access the new registration page. The server validates the received information and saves it in the database. Once saved, the server returns a "Registration Complete" message. In the case of login, the user enters authentication information, the server checks the information, generates a session or token, and allows the user to log in.

[0796] Prompted Search and Select

[0797] When a user inputs their desired action (e.g., "create a payment reminder") into the smartphone interface, the server receives the information and searches the database for relevant prompt templates. The templates are then displayed as a list on the smartphone, and the user can select the appropriate template.

[0798] Further questions and clarification

[0799] The server generates a follow-up question form based on the selected template and sends it to the user's smartphone. The user answers the questions, and the server receives and analyzes them to generate a specific prompt. The generated prompt is then sent back to the smartphone and displayed to the user.

[0800] Posting and Using Prompts

[0801] Prompt providers use their smartphones to post their own prompts. The server stores the received prompts in a database and makes them available for other users to search. When other users use the prompt, the server records the number of times it is used and calculates a reward. The calculated reward is paid to the prompt provider.

[0802] Specific examples

[0803] Example of user registration and login:

[0804] The user enters "Name: Tanaka Taro, Email address: tanaka@example.com, Password: password123" on the new registration page and submits it. The server responds with "Registration complete."

[0805] Examples of prompted search and selection:

[0806] The user types "create payment reminder," the server searches for relevant prompt templates, and displays a list on the smartphone.

[0807] Example of generating prompts:

[0808] For the "Payment Reminder" template, an additional question is displayed: "Which payment would you like to be reminded about?" If the user answers "Credit card payments," a specific prompt is generated: "Remind me about my next credit card payment."

[0809] This system allows users to easily create and manage prompts for electronic payment services, and allows prompt providers to earn rewards.

[0810] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0811] Step 1:

[0812] User Registration

[0813] The user enters their name, email address, and password on the smartphone's new registration page. The device sends this information to the server. The server validates the received information and stores it in a database. After saving, the server returns a "Registration Complete" message to the device.

[0814] Input: Name, Email Address, Password

[0815] Output: "Registration complete" message

[0816] Specific operation: The server establishes a database connection, checks the input information, and if the information is correct, registers it in the database.

[0817] Step 2:

[0818] Log in

[0819] The user enters their credentials on a login page on their smartphone, and the device sends them to the server, which verifies the credentials and, if successful, creates a session or token and allows the user to log in.

[0820] Input: Email address, Password

[0821] Output: Session or token, login success message

[0822] Specific operation: The server retrieves user information from the database, compares it with the input information, and if the information is correct, issues a session or token.

[0823] Step 3:

[0824] Prompted Search

[0825] The user types what they want to do on their smartphone (e.g., "Create a payment reminder"), and the device sends this information to the server, which searches a database for relevant prompt templates and returns the results to the device.

[0826] Input: What the user wants to do (e.g., "Create a payment reminder")

[0827] Output: A list of related prompt templates

[0828] What it does: The server analyzes user input using natural language processing, generates a database query, retrieves a template from the database, and returns the results.

[0829] Step 4:

[0830] Prompt Selection

[0831] The user selects an appropriate prompt template from the displayed list, and the terminal transmits the user's selection to the server.

[0832] Input: User prompt template selection

[0833] Output: Selected template

[0834] Specific actions: The server retrieves the selected template information and prepares additional questions.

[0835] Step 5:

[0836] Additional question generation

[0837] The server generates a follow-up question form based on the selected prompt template and sends it to the terminal, where the user answers the question and the terminal sends it back to the server.

[0838] Input: prompt template, answers to follow-up questions

[0839] Output: Specific prompt

[0840] Specific action: The server generates a specific prompt based on the template and the user's answer and sends it to the terminal.

[0841] Step 6:

[0842] Prompt generation and display

[0843] The server analyzes the user's answers and generates specific prompts, which are sent to the terminal and displayed to the user.

[0844] Input: Answer to the user's follow-up question

[0845] Output: Specific prompt

[0846] What it does: The server uses the generative AI model to generate a prompt and sends the result to the device.

[0847] Step 7:

[0848] Prompted Posts

[0849] The prompt provider inputs their own prompt and sends it from their terminal to the server, which stores the received prompt in a database.

[0850] Input: A prompt created by the prompt provider

[0851] Output: Prompts saved to the database

[0852] Specific operation: The server receives the prompt information, saves it in the database, and returns a save completion message to the provider.

[0853] Step 8:

[0854] Using and recording prompts

[0855] Other users search for and use the saved prompts. The device sends usage data to the server, which records the number of usages and uses them to calculate rewards.

[0856] Input: Prompt usage information

[0857] Output: Record of prompt usage, reward calculation data

[0858] Specific operation: The server receives prompt usage information, records the number of times in the database, and calculates the reward according to the reward calculation algorithm.

[0859] Step 9:

[0860] Reward calculation and payment

[0861] The server calculates a reward based on the recorded number of uses and pays the reward to the prompt provider.

[0862] Input: Prompt usage count

[0863] Output: Reward payment to prompter

[0864] Specific operation: The server calculates the reward using the reward calculation method and adds the reward to the provider's account.

[0865] 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.

[0866] The present invention provides a system that includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, and an emotion engine for recognizing the user's emotions. Hereinafter, we will explain how this system is specifically implemented.

[0867] System Program Processing

[0868] The program for this system mainly aims to exchange data between the server, terminal, and user, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with concrete examples.

[0869] Program processing

[0870] User Registration and Login

[0871] 1. A user visits the sign-up page and enters their name, email address, and password.

[0872] The terminal transmits the input information to the server.

[0873] The server validates the received information and stores it in the database.

[0874] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[0875] 2. The user enters their email address and password on the login page.

[0876] The terminal sends the input data to the server.

[0877] The server checks the received authentication information and, if successful, generates a session or JWT token and allows login.

[0878] Prompted Search and Select

[0879] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[0880] The terminal transmits the entered search keyword to the server.

[0881] The server searches the database for relevant prompt templates and returns the results to the terminal.

[0882] The terminal displays the results and the user selects the appropriate template.

[0883] Emotion Recognition and Prompt Generation

[0884] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[0885] The user answers the questions and transmits the answer data from the terminal to the server.

[0886] The server analyzes the answers it receives and generates specific prompts tailored to the particular task.

[0887] The server sends the generated specific prompt to the terminal for presentation to the user.

[0888] 2. The emotion engine analyzes emotions based on the user's input and behavioral history.

[0889] The emotion engine provides the results of the analysis to the prompt generator to adjust the generated prompts.

[0890] Providing and Using Prompts

[0891] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[0892] The server stores the received prompts in a database.

[0893] Other users can use the search function to find and use your prompt.

[0894] The terminal sends prompt usage data to the server.

[0895] The server records the number of uses and calculates the reward.

[0896] The server notifies the provider of the calculated reward and processes the payment of the reward.

[0897] Specific examples

[0898] 1. User Registration and Login

[0899] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[0900] 2. Prompt search and selection

[0901] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[0902] 3. Emotion Recognition and Prompt Generation

[0903] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the response. The server generates a specific prompt, sends it to the device, and displays it to the user.

[0904] The emotion engine analyzes the user's emotions based on their input and behavioral history, and then generates prompts based on the results. For example, if the user expresses anxiety, the prompts will be softer and more reassuring.

[0905] 4. Providing and Using Prompts

[0906] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt using the search function and record the number of times it is used, the server calculates a reward and pays it to the provider.

[0907] The system embodying the present invention provides a mechanism that allows users to easily obtain appropriate prompts and prompt providers to receive rewards, and also provides more appropriate prompts by recognizing the user's emotions and reflecting them in the generation of prompts.

[0908] The processing flow will be explained below.

[0909] Step 1:

[0910] A user visits the sign-up page and enters their name, email address, and password.

[0911] The terminal transmits the input information to the server.

[0912] Step 2:

[0913] Validate the information received by the server.

[0914] Check the email address format

[0915] Password Strength Check

[0916] Check for required fields

[0917] Step 3:

[0918] The server saves the validated information to the database.

[0919] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[0920] Step 4:

[0921] The user enters their email address and password on the login page.

[0922] The terminal sends the input data to the server.

[0923] Step 5:

[0924] The server checks the authentication information received.

[0925] Hashed password verification

[0926] Generate a session or JWT token upon successful authentication.

[0927] Step 6:

[0928] The server sends the session information along with a message of successful authentication to the terminal.

[0929] The user is redirected to the dashboard page.

[0930] Step 7:

[0931] The user types what they want to do (e.g., "generate blog content") into the search bar.

[0932] The terminal transmits the entered search keyword to the server.

[0933] Step 8:

[0934] The server searches the database for relevant prompt templates and returns the results to the terminal.

[0935] The terminal displays the received data and the user selects the appropriate template.

[0936] Step 9:

[0937] The server generates an additional question form based on the selected template and sends it to the terminal.

[0938] The user answers the additional questions and transmits the answer data from the terminal to the server.

[0939] Step 10:

[0940] The server uses the user's answers to generate specific prompts tailored to the particular task.

[0941] The server sends the generated specific prompt to the terminal for presentation to the user.

[0942] Step 11:

[0943] The emotion engine analyzes emotions based on user input and behavioral history.

[0944] The emotion engine extracts emotional information from the input.

[0945] The emotion engine analyzes emotions inferred from the user's operation history.

[0946] Step 12:

[0947] The emotion engine sends the analysis results to the server.

[0948] The server adjusts the prompts based on the emotional information.

[0949] Step 13:

[0950] A prompt provider inputs a prompt that he or she has created using an input means and transmits it from the terminal to the server.

[0951] The server stores the received prompts in a database.

[0952] Step 14:

[0953] Other users can use the search function to find and use your prompt.

[0954] The terminal sends prompt usage data to the server.

[0955] Step 15:

[0956] The server records the number of uses.

[0957] The server calculates the reward based on the number of recorded uses.

[0958] Step 16:

[0959] The server notifies the prompt provider of the calculated reward and processes the payment of the reward.

[0960] As a result, a system that combines an emotion engine will operate effectively, matching users of generative AI with prompt providers and improving AI services.

[0961] Example 2

[0962] 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."

[0963] It takes a lot of time and effort for users of generative AI to efficiently search, select, generate, and use prompts that best suit their purposes. Furthermore, since prompts cannot be generated taking into account the user's emotions, it is difficult to provide appropriate prompts. Furthermore, there is no well-established system for prompt providers to receive appropriate compensation, making it difficult to promote the provision of high-quality prompts.

[0964] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: input means for a user of the generative artificial intelligence to input and select what he or she wants to do; search means for searching for a relevant prompt template based on information received from the input means; display means for displaying the prompt template searched by the search means; prompt generation means for generating a specific prompt corresponding to a specific task based on the user's answer to additional questions; execution means for executing a task using the prompt generated by the prompt generation means; posting means for a prompt provider to post a prompt created by the prompt provider; storage means for storing the prompt posted by the posting means in a database so that other users can search for it; recording means for recording the number of times a prompt is used by the execution means; reward calculation means for calculating a fee based on the number of times it is used recorded by the recording means and paying a reward to the prompt provider; and emotion recognition means for recognizing emotions from the user's input content and behavioral history and reflecting the result in prompt generation. This enables users to efficiently obtain, generate, and use prompts that suit their purposes, and also enables prompts to be generated that correspond to emotions, thereby enabling accurate reward payment to prompt providers.

[0965] "Input means" refers to the means by which users of generative artificial intelligence input and select what they want to do.

[0966] The "search means" is a means for searching for a relevant prompt template based on the information received from the input means.

[0967] The "display means" is a means for displaying the prompt template retrieved by the retrieval means.

[0968] A "prompt generation means" is a means for generating a specific prompt corresponding to a specific task by having the user answer additional questions.

[0969] The "execution means" is a means for executing a task using the prompt generated by the prompt generation means.

[0970] A "posting means" is a means for a prompt provider to post a prompt that they have created.

[0971] The "storage means" is a means for storing the prompt posted by the posting means in a database so that other users can search for it.

[0972] The "recording means" is a means for recording the number of times a prompt is used when it is used by the execution means.

[0973] The "reward calculation means" is a means for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[0974] The "emotion recognition means" is a means for recognizing the user's emotions from their input content and behavioral history, and reflecting the results in generating prompts.

[0975] This invention relates to a system that enables users of generative artificial intelligence to efficiently search, generate, and use appropriate prompts. The system transfers data between a server, a terminal, and a user, enabling the provision of prompts that are optimal for the user's purpose.

[0976] System configuration

[0977] The system includes the following hardware and software:

[0978] 1. The server has the basic computer infrastructure to run a database management system, an authentication system, an emotion recognition engine, etc. Specifically, it is equipped with a database management system such as MySQL, an authentication system using JWT, and an emotion recognition engine that performs natural language processing.

[0979] 2. A terminal is an interface through which a user accesses the system and inputs and receives various information. This includes web browsers and mobile applications.

[0980] 3. The user is responsible for inputting what they want to do with the system and for selecting, generating, and using prompts.

[0981] Program processing description

[0982] User Registration and Login

[0983] 1. A user accesses the new registration page and enters their name, email address, and password. The device then sends the entered information to the server. The server validates the entered information and saves it in the database. After saving is complete, a "Registration Complete" message is returned to the device.

[0984] 2. When the user enters their email address and password on the login page, the device sends this to the server, which checks the authentication information and, if successful, generates a session or JWT token and allows login.

[0985] Prompted Search and Select

[0986] 1. When a user enters what they want to do (e.g., "generate blog content") into the search bar, the device sends the search keywords to the server. The server searches the database for relevant prompt templates and returns the results to the device. The device displays them, and the user can select an appropriate template.

[0987] Emotion Recognition and Prompt Generation

[0988] 1. The server generates an additional question form based on the selected template and sends it to the terminal. The user answers the question and the answer data is sent from the terminal to the server. The server analyzes the answer and generates a specific prompt.

[0989] 2. The emotion engine analyzes the user's input and behavioral history in real time and provides the results to the server, which then uses the emotion information to send more personalized prompts to the device and present them to the user.

[0990] Providing and Using Prompts

[0991] 1. The prompt provider creates a prompt using an input method and sends it from the terminal to the server, which stores the prompt in a database.

[0992] 2. Other users use the search function to find and use the prompt. The device sends usage data to the server, which records the number of uses, calculates the reward, and pays it to the provider.

[0993] Specific examples

[0994] Example 1: User registration and login

[0995] A user enters the name "Taro Tanaka," the email address "tanaka@example.com," and the password "password123" on the new registration page. The entered information is sent from the device to the server and stored in the database. After that, the "Registration Complete" message is displayed.

[0996] Example 2: Prompted search and select

[0997] A user types "blog content generation" in the search bar, the server searches for relevant prompt templates and displays a list on the device. If the user selects "blog prompt for product review", its details are displayed.

[0998] Example 3: Emotion recognition and prompt generation

[0999] The server generates and displays a follow-up question: "Which product would you like to review?" The user answers "A new smartphone" and submits the question. The server generates a specific prompt and displays the message: "To write a review of a new smartphone, please use the following structure as a guide."

[1000] The emotion engine analyzes the user's emotions based on their input and behavioral history, and if the user expresses anxiety, for example, the prompts are softened to provide a sense of security.

[1001] Example 4: Providing and using prompts

[1002] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt in the search function, the number of uses is recorded, and the server calculates and pays the provider a reward.

[1003] This system provides a mechanism for users to easily obtain appropriate prompts and for providers to receive rewards, and also generates prompts that take into account the user's emotions.

[1004] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1005] Step 1: User Registration

[1006] 1. A user visits the sign-up page and enters their name, email address, and password.

[1007] Input: Name, Email Address, Password

[1008] The terminal transmits the input information to the server.

[1009] Validate the information received by the server.

[1010] Data processing: Email address format check, password strength check, etc.

[1011] The server saves the data that passes the validation in the database.

[1012] Output: "Registration complete" message

[1013] The server returns a "registration complete" message to the terminal.

[1014] The device will display a "Registration complete" message.

[1015] Step 2: Log in

[1016] 1. The user enters their email address and password on the login page.

[1017] Input: Email address, password

[1018] The terminal sends the input data to the server.

[1019] The server checks the received authentication information against a database.

[1020] Data calculation: Email address and password matching

[1021] If authentication is successful, a session or JWT token is generated.

[1022] Output: Session ID or JWT token

[1023] The server returns a session ID or JWT token to the device.

[1024] The terminal notifies the user that authentication was successful.

[1025] Step 3: Prompted Search

[1026] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[1027] Input: Search keyword

[1028] The device sends the search keywords to the server.

[1029] The server retrieves the relevant prompt template from the database.

[1030] Data calculations: keyword matching, relevance score calculation

[1031] Output: Search result list

[1032] The server returns the search results to the device.

[1033] Your device will display a list of search results.

[1034] Step 4: Prompt details and selection

[1035] 1. The user selects the appropriate template from the displayed list.

[1036] Input: Selected template

[1037] The device sends the selection to the server.

[1038] The server retrieves the details of the selected template from the database.

[1039] Data processing: Obtaining detailed template information

[1040] Output: Template details

[1041] The server returns detailed information about the template to the terminal.

[1042] The device will display more information.

[1043] Step 5: Emotion recognition and prompt generation

[1044] 1. The server generates a follow-up question form based on the selected template.

[1045] Input: Selected template

[1046] Data processing: Generation of additional question form

[1047] A question form is sent to the terminal and displayed.

[1048] The user answers the questions and inputs the answer data.

[1049] Input: Answer data to questions

[1050] The terminal transmits the response data to the server.

[1051] The server analyzes the received answers and generates specific prompts.

[1052] Data arithmetic: Response analysis, prompt generation

[1053] Output: Specific prompt

[1054] The server generates a prompt and sends it to the terminal for display.

[1055] The emotion recognition means analyzes the user's responses and behavior history and provides emotion information to the server.

[1056] The server adjusts the prompts based on the emotional information.

[1057] Step 6: Provide a prompt

[1058] 1. The prompt provider creates a prompt using an input means and sends it from the terminal to the server.

[1059] Input: Created prompt

[1060] The terminal sends the input data to the server.

[1061] The server stores the received prompts in a database.

[1062] Data Transformation: Save Prompt

[1063] Output: Save completion notification

[1064] The server sends a save completion notification to the terminal.

[1065] Step 7: Use prompts

[1066] 1. Other users find your prompt using the search feature.

[1067] Input: Search keyword

[1068] The device sends the search keywords to the server.

[1069] The server retrieves the relevant prompt from the database.

[1070] Data calculations: keyword matching, relevance score calculation

[1071] Output: Search result list

[1072] The server returns the search results to the device.

[1073] Your device will display a list of search results.

[1074] The user selects and uses the prompt.

[1075] Input: Selected prompt

[1076] The device sends usage data to the server.

[1077] The server records the number of uses.

[1078] Data processing: Recording number of uses

[1079] A reward calculation means calculates and pays a reward to the prompt provider.

[1080] Data calculation: Reward calculation

[1081] Output: Reward amount

[1082] The server processes the reward payment and notifies the provider.

[1083] (Application example 2)

[1084] 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."

[1085] Conventional generative AI systems do not consider emotions when generating specific prompts, limiting their ability to improve the user experience. Even when users prefer to use voice input to generate and display prompts using smart devices, they face difficulties converting the speech into text and processing it appropriately. Furthermore, feedback on generated prompts is lacking, leading to ineffective reward calculations for prompt providers. There is a need to address these issues and provide a more interactive and user-friendly system.

[1086] 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.

[1087] In this invention, the server includes: an input means for inputting and selecting what a user of the generative artificial intelligence wants to do; a search means for searching for a relevant prompt template based on information received from the input means; a display means for displaying the prompt template searched by the search means; a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions; an execution means for executing a task using the prompt generated by the prompt generation means; a posting means for a prompt provider to post a prompt created by the prompt provider; a storage means for storing the posted prompt in a database so that other users can search for the prompt; a recording means for recording the number of times a prompt is used by the execution means; a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider; an emotion engine for recognizing a user's emotions; an adjustment means for adjusting the display content or prompt content based on emotion information analyzed by the emotion engine; a speech recognition means for converting a user's voice input into text; and an edge device means for generating and displaying prompts via a smart device. This enables prompt generation and display that take the user's emotions into consideration, thereby enabling smooth prompt operation on a smart device using voice input. Furthermore, it is possible to realize appropriate reward calculation for prompt providers, and to provide a more interactive and user-friendly system.

[1088] "Generative AI" is an AI system that automatically generates content such as text and images based on user input and selections.

[1089] "Input means" refers to an interface that allows a user to input or select what they want to do, and includes a keyboard, touch screen, voice recognition, etc.

[1090] A "search mechanism" is an algorithm or system for searching for relevant prompt templates based on information received from an input mechanism.

[1091] A "display means" is a device or interface for visually presenting retrieved prompt templates and generated prompts to a user.

[1092] A "prompt generator" is a system or algorithm that generates specific prompts for a particular task based on the user's answers to follow-up questions.

[1093] The "execution means" is a function for executing a specific task using the prompt generated by the prompt generation means.

[1094] The "posting means" is an interface for inputting and sending a prompt created by a prompt provider.

[1095] The "storage means" is a system for storing prompts posted by the posting means in a database so that other users can search for them.

[1096] A "recording means" is a system or algorithm for tracking and recording the number of times a prompt is used by the execution means.

[1097] The "reward calculation means" is a system for calculating compensation based on the number of uses recorded by the recording means and providing a reward to the prompt provider.

[1098] An "emotion engine" is software or algorithms that analyze and recognize emotions based on user input and behavioral history.

[1099] The "adjustment means" is a function for adjusting the display content or prompt content based on the emotion information analyzed by the emotion engine.

[1100] A "speech recognizer" is a system or algorithm for converting a user's voice input into text.

[1101] An "edge device means" is a local or network-connected device for generating and displaying prompts through a smart device.

[1102] The present invention is a system that uses generative artificial intelligence to generate and display appropriate prompts while taking into account the user's emotions. This system is intended for use as a shopping assistant application on smart devices.

[1103] Program processing

[1104] The program in this system mainly exchanges data between the server and the smart device (e.g., smart glasses). Each element is explained below.

[1105] User Registration and Login

[1106] 1. The user registers by entering their name, email address, and password using voice input or touch gestures on their smart device. The device sends the entered information to the server, which validates the received information and stores it in the database. After saving, the message "Registration Complete" appears on the smart device's display.

[1107] Prompted Search and Select

[1108] 1. The user uses the voice input function of the smart device to say, for example, "I'd like to know reviews of the new smartphone." The device converts this voice data into text using a speech recognition method (e.g., Google Speech-to-Text API) and sends the search keywords to the server. The server searches for relevant prompt templates in its database and returns the results to the device. The smart device then displays the results on its screen, and the user selects the appropriate template.

[1109] Emotion Recognition and Prompt Generation

[1110] 1. The server generates additional questions based on the selected template and sends them to the smart device. The user answers by voice, and the device converts the voice into text and sends it to the server. The server analyzes the received answer data and generates a specific prompt (e.g., "Show me reviews of Apple's latest smartphones"). The generated specific prompt is then displayed on the smart device.

[1111] 2. An emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's tone of voice and behavioral history to determine their emotions. If the user expresses anxiety, the generated prompt content is adjusted to be more reassuring (e.g., "You can check the information with peace of mind. Here is a review of Apple's latest smartphone").

[1112] Providing and Using Prompts

[1113] 1. Prompt providers enter and submit prompts through a web interface, and the server stores them in a database, making them available for other users to find and use using the search function on their smart devices.

[1114] 2. When a prompt is used, the terminal transmits usage data to the server, which records the number of times the prompt is used. Based on the recorded data, the reward calculation means calculates the compensation and provides a reward to the prompt provider.

[1115] Specific examples

[1116] User Registration and Login

[1117] The user speaks into the smart device, "New registration, name: User A, email address: usera@example.com, password: password123." The device converts the voice to text and sends it to the server, completing the registration.

[1118] Prompted Search and Select

[1119] The user speaks into their smart device, saying, "I'd like to know reviews of the new smartphone." The device converts the speech into text, and the server returns a template, such as "Reviews of Apple's latest smartphone," which is then displayed.

[1120] Emotion Recognition and Prompt Generation

[1121] The server generates the question "What brand are you looking for?" and displays it on the smart device. The user responds with "Apple," and the voice data is converted into text and sent to the server. The server generates a prompt and sends it to the device. If the emotion engine detects anxiety in the user's tone of voice, it adjusts the prompt and displays, "You can rest assured that we're here to help you. We'll show you reviews of Apple's latest smartphones."

[1122] Prompt Sentence Examples

[1123] "Please enter the brand name of the smartphone you want to see reviews for."

[1124] The system is analyzing user sentiment...

[1125] "Please check out our review of Apple's latest smartphone here. If you have any questions, please let us know."

[1126] This system enables prompt generation and display that takes the user's emotions into account, allowing for smooth prompt operation on smart devices using voice input. It also provides an interactive and user-friendly system that appropriately calculates rewards for prompt providers.

[1127] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1128] Step 1:

[1129] The user registers by entering their name, email address, and password using the voice input function of their smart device. The entered information is converted into text data by the terminal's voice recognition means (input: voice data, output: text data). The terminal then sends the text data to the server. The server validates the sent information and stores it in a database. Once registration is complete, the server sends a "Registration Complete" message to the terminal, which is displayed on the smart device's display (input: text data, output: registration complete message).

[1130] Step 2:

[1131] The user uses the voice input function of the smart device to say, "I'd like to know reviews of the new smartphone." The device converts this voice data into text using a speech recognition means (input: voice data, output: text data). The converted text data is sent to the server. The server searches the database for relevant prompt templates and returns the search results to the device (input: text data, output: prompt template). The search results are then displayed on the smart device's display.

[1132] Step 3:

[1133] The user selects an appropriate template from those displayed on the terminal display. The selection information is sent from the terminal to the server (input: user selection, output: selection information). The server generates a follow-up question based on the selected template and sends it to the terminal (input: selection information, output: follow-up question). The follow-up question is then displayed on the smart device.

[1134] Step 4:

[1135] The user answers the follow-up questions by voice. The device converts the voice data into text data using a voice recognition means (input: voice data, output: text data). The answer text data is sent to the server. The server analyzes the received answer data and generates a specific prompt (input: text data, output: specific prompt). The generated prompt is displayed on the smart device.

[1136] Step 5:

[1137] The emotion engine analyzes the user's voice tone and behavioral history to determine their emotions. The analysis results are sent to the server, which then adjusts the prompt content (input: data such as voice tone, output: adjusted prompt). The adjusted prompt is sent to the device and displayed on the smart device's screen.

[1138] Step 6:

[1139] A prompt provider uses a web interface to input and submit prompts, which are received by the server and stored in a database (input: prompt data, output: saving to database).

[1140] Step 7:

[1141] Other users can use the saved prompts by using the search function. When a prompt is used, the device sends the usage data to the server, and the server records the number of times it is used (input: usage data, output: record of number of times it is used).

[1142] Step 8:

[1143] The reward calculation means calculates the compensation based on the recorded number of uses. The calculation result is added as credit to the prompt provider's account, and a reward is provided to the provider (input: number of uses, output: reward calculation result). The prompt provider is notified of the reward provision.

[1144] 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.

[1145] 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.

[1146] 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.

[1147] [Third embodiment]

[1148] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1149] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1150] 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).

[1151] 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.

[1152] 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.

[1153] 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).

[1154] 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.

[1155] 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.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] 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."

[1160] The present invention includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for relevant prompt templates based on information received from the input means, a display means for displaying the prompt templates searched by the search means, and a prompt generation means for generating specific prompts corresponding to specific tasks in response to additional questions from the user. It also includes a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for saving the posted prompt so that other users can search for it, and a reward calculation means for recording the number of times the prompt is used and calculating a reward based on the number of times it is used. Hereinafter, we will explain how this system is specifically implemented.

[1161] System Program Processing

[1162] The program for this system mainly aims to exchange data between the server and the user's terminal, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with some concrete examples.

[1163] Program processing

[1164] User Registration and Login

[1165] 1. A user visits the sign-up page and enters their name, email address, and password.

[1166] The terminal transmits the input information to the server.

[1167] The server validates the received information and stores it in the database.

[1168] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[1169] 2. The user enters their credentials on the login page and the device sends them to the server.

[1170] The server checks the authentication information and, if successful, creates a session or token and allows login.

[1171] Prompted Search and Select

[1172] 1. The user uses the input means to input what they want to do (e.g., "generate blog content").

[1173] The terminal transmits the input information to the server.

[1174] The server searches the database for the relevant prompt template and returns the result to the terminal.

[1175] The terminal displays the results and the user selects the appropriate template.

[1176] Further questions and clarification

[1177] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[1178] The user answers the questions and the terminal sends the answers to the server.

[1179] The server analyzes the received answers and generates specific prompts.

[1180] The server sends the generated prompt to the terminal for display to the user.

[1181] Providing and Using Prompts

[1182] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[1183] The server stores the received prompts in a database.

[1184] Other users can use the search function to find and use your prompt.

[1185] The terminal sends prompt usage data to the server.

[1186] The server records the number of uses and calculates the reward.

[1187] The calculated reward is paid to the provider.

[1188] Specific examples

[1189] 1. User Registration and Login

[1190] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[1191] 2. Prompt search and selection

[1192] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[1193] 3. Additional questions and clarification

[1194] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the question. The server generates a specific prompt and displays it on the device.

[1195] 4. Providing and Using Prompts

[1196] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt, the server records the number of times it is used and calculates and pays a reward.

[1197] The system embodying the present invention thus provides a mechanism by which users can easily obtain appropriate prompts and prompt providers can receive rewards.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] A user visits the sign-up page and enters their name, email address, and password.

[1201] The terminal transmits the input information to the server.

[1202] Step 2:

[1203] Validate the information received by the server.

[1204] Check the email address format

[1205] Password Strength Check

[1206] Check for required fields

[1207] Step 3:

[1208] The server saves the validated information to the database.

[1209] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[1210] Step 4:

[1211] The user enters their email address and password on the login page.

[1212] The terminal sends the input data to the server.

[1213] Step 5:

[1214] The server checks the authentication information received.

[1215] Hashed password verification

[1216] Generate a session or JWT token upon successful authentication.

[1217] Step 6:

[1218] The server sends the session information along with a message of successful authentication to the terminal.

[1219] The user is redirected to the dashboard page.

[1220] Step 7:

[1221] The user types what they want to do (e.g., "generate blog content") into the search bar.

[1222] The terminal transmits the entered search keyword to the server.

[1223] Step 8:

[1224] The server searches the database for relevant prompt templates and returns the results to the terminal.

[1225] The terminal displays the received data and the user selects the appropriate template.

[1226] Step 9:

[1227] The server generates an additional question form based on the selected template and sends it to the terminal.

[1228] The user answers the additional questions and transmits the answer data from the terminal to the server.

[1229] Step 10:

[1230] The server uses the user's answers to generate specific prompts tailored to the particular task.

[1231] The server sends the generated specific prompt to the terminal for presentation to the user.

[1232] Step 11:

[1233] The prompt provider accesses the submission form and enters their prompt.

[1234] The terminal sends the entered prompt information to the server.

[1235] Step 12:

[1236] The server saves the prompts in a database.

[1237] Other users can find and use the prompts you provide in the search bar.

[1238] Step 13:

[1239] The terminal sends prompt usage data to the server.

[1240] The server records the number of uses and calculates the reward.

[1241] Step 14:

[1242] The server notifies the provider of the calculated reward and processes the payment of the reward.

[1243] This provides a system that matches users of generative AI with prompt providers, promoting the use of generative AI and improving AI services.

[1244] Example 1

[1245] 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."

[1246] In conventional generative AI systems, the search and selection of prompts is complicated, making it difficult for users to find appropriate prompts. Furthermore, there is no well-established mechanism for accurately recording the number of times prompts created by prompt providers are used and calculating appropriate rewards based on that information. Furthermore, there is a lack of a system for safely and efficiently performing user registration and authentication processes.

[1247] 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.

[1248] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the prompt posted by the posting means in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, an authentication means for receiving and verifying the user's authentication information, and a storage means for the authentication means to store the user's information in a database. This enables users to easily and efficiently search for, select, and generate appropriate prompts, enables prompt providers to receive fair rewards, and provides a system in which user registration and authentication processes are performed safely and efficiently.

[1249] "Generative AI" is an AI technology that generates new data and information based on input data.

[1250] "Input means" refers to a device or function that allows a user to input information or commands to a system.

[1251] A "search means" is a processing function for finding specific information from a database or storage.

[1252] "Display means" refers to a device or function for visually presenting information to a user.

[1253] The "prompt generator" is a function that creates specific prompts based on received information and follow-up questions.

[1254] An "execution means" is a function for performing a specific task based on the generated prompt.

[1255] The "posting means" is a function that allows a prompt provider to send a prompt that they have created to the system.

[1256] "Storage means" is a function for storing received information and data in a database or other storage.

[1257] The "recording means" is a function for recording the number of times a prompt is used and other usage data.

[1258] The "reward calculation means" is a function that calculates rewards to prompt providers based on the recorded usage data.

[1259] "Authentication means" is a function for verifying a user's identity and qualifications.

[1260] A "database" is a system for efficiently storing, managing, and searching information and data.

[1261] The present invention provides a generative artificial intelligence system that allows users to efficiently input and select what they want to do, generates and provides appropriate prompts based on the input, and pays rewards to the providers. The following describes in detail the embodiments of the present invention.

[1262] This system consists of a server and a user terminal. The main functions are concentrated on the server, and the user terminal acts as an interface for communicating with users.

[1263] 1. User Registration and Authentication

[1264] A user accesses the new registration page and enters authentication information such as name, email address, and password. For example, the user enters "Name: Taro", "Email address: taro@example.com", and "Password: password123". The device sends this to the server, which validates the received information and saves it in the database. After saving is complete, the server returns a "Registration complete" message to the device.

[1265] Next, the user enters their authentication information on the login page, and the device sends it to the server. The server checks the authentication information against the database, and if successful, generates a session ID and allows login. If successful, a "Login successful" message and session information are returned to the device, and if unsuccessful, an "Authentication failed" error message is returned.

[1266] 2. Prompt search and selection

[1267] The user enters what they want to do into an input means (for example, a text box). For example, they might enter "create blog content." This information is sent from the device to the server. The server searches the database to find relevant prompt templates (for example, "blog prompt for product reviews," "travel blog prompt") and sends the search results to the device. The device then displays the search results in a list format, allowing the user to make a selection.

[1268] 3. Follow-up questions and prompt generation

[1269] When a user selects a specific prompt template, the server generates an additional question form (e.g., "Which product would you like to review?") based on that template and sends it to the device. The user answers this form (e.g., "A new smartphone"), and the device sends it to the server. The server then generates a specific prompt (e.g., "Please review the performance of the new smartphone in detail") based on the answer received and sends it to the device.

[1270] 4. Submitting and Using Prompts

[1271] The prompt provider inputs a prompt they have created and sends it from their device to the server. The server stores the received prompt in a database. Other users can then use the search function to find, select, and use the prompt. The device sends prompt usage data to the server, which records the number of times the prompt has been used.

[1272] 5. Remuneration calculation

[1273] The server calculates the reward based on the number of recorded uses and pays it to the prompt provider. This reward is transferred based on the provider's registered payment information. The reward calculation is, for example, $0.1 per use.

[1274] In this way, users can easily and efficiently search, select, and generate appropriate prompts, prompt providers can earn rewards, and the entire system operates safely and smoothly.

[1275] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1276] Step 1:

[1277] A user visits the sign-up page and enters their name, email address, and password.

[1278] Input: The user enters their name, email address, and password into the text fields.

[1279] The terminal transmits the input information to the server.

[1280] Validate the information received by the server (e.g., check that the email address is formatted correctly and does not already exist).

[1281] Output: If validation is successful, the user information is saved in the database and a "Registration complete" message is returned to the terminal. If validation fails, an error message is returned.

[1282] Step 2:

[1283] The user enters their authentication information on the login page, and the device sends it to the server.

[1284] Input: The user enters their email address and password into the login form.

[1285] The device sends the authentication information to the server.

[1286] The server checks the received authentication information against the database and generates a session ID or JWT token if it is correct, or an error message if it is invalid.

[1287] Output: If correct authentication information is provided, the session information is returned to the terminal and the user is logged in. If unsuccessful, an "Authentication failed" message is returned.

[1288] Step 3:

[1289] The user uses the input means to input what he or she wants to do.

[1290] Input: The user inputs "Create blog content" into the input means (text box).

[1291] The terminal transmits the input information to the server.

[1292] The server searches the database for prompt templates related to "blog content generation" and extracts the found templates.

[1293] Output: The prompt templates (e.g. "Blog prompt for product reviews", "Travel blog prompt") as search results are sent to the terminal and displayed in list format.

[1294] Step 4:

[1295] The user selects a prompt template from the search results.

[1296] Input: User clicks to select "Blog prompt for product reviews" from the list.

[1297] The terminal transmits the selection information to the server.

[1298] The server generates additional questions related to the selected prompt template and creates a question form.

[1299] Output: A form with additional questions (e.g., "Which product would you like to review?") is displayed on the terminal.

[1300] Step 5:

[1301] The user answers additional questions to generate the actual prompt.

[1302] Input: The user enters "new smartphone" as an answer into the question form.

[1303] The terminal sends the user's answer to the server.

[1304] The server analyzes the received answers and generates a specific prompt (e.g., "Please provide a detailed review of the performance of your new smartphone").

[1305] Output: The specific prompt is sent to the terminal and displayed to the user.

[1306] Step 6:

[1307] Prompt contributors post prompts they have created themselves.

[1308] Input: The prompt giver enters a "Prompt for a Travel Guidebook."

[1309] The terminal sends the prompt entered by the provider to the server.

[1310] The server stores the received prompts in a database.

[1311] Output: A message indicating that the data has been saved is displayed on the provider's terminal.

[1312] Step 7:

[1313] Use prompts posted by other users.

[1314] Input: The user uses the search function to find and select "Prompt for Travel Guidebook."

[1315] The terminal transmits usage information to the server.

[1316] The server keeps track of the number of times a prompt is used.

[1317] Output: The number of times the prompt is used is recorded in a database.

[1318] Step 8:

[1319] Calculate rewards for prompt providers.

[1320] Input: The server uses the recorded number of prompt usages as input data.

[1321] The server calculates the reward based on the number of uses (e.g., $0.10 per use).

[1322] Output: The calculated reward is added to the contributor's account.

[1323] (Application example 1)

[1324] 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."

[1325] The problem is that there is a lack of efficient means for generating and managing prompts using generative artificial intelligence in electronic payment services. In particular, it is difficult to establish a system that allows users to easily generate and manage appropriate prompts and allows prompt providers to receive rewards.

[1326] 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.

[1327] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the posted prompt in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, a prompt generation means for generating an administrative prompt for an electronic payment service, and a smartphone application for displaying the specific prompt for the electronic payment service generated by the prompt generation means to the user. This allows users to easily generate administrative prompts for electronic payment services and allows prompt providers to receive rewards.

[1328] "Generative AI" is an AI technology that generates content such as text and images based on user instructions.

[1329] "User" refers to the person or organization that uses generative artificial intelligence to perform prompts and tasks.

[1330] "Input means" refers to the interface that allows users of generative artificial intelligence to input and select what they want to do.

[1331] A "prompt template" is a template that contains instructions for a generative artificial intelligence to use when performing a specific task.

[1332] "Search means" refers to a mechanism that searches a database for relevant prompt templates based on information received from an input means.

[1333] "Display means" means an interface for displaying to the user the prompt templates retrieved by the retrieval means.

[1334] A "prompt generator" is a mechanism that generates specific prompts corresponding to specific tasks by having the user answer additional questions.

[1335] The "execution means" refers to a system or process for executing a task using the prompt generated by the prompt generation means.

[1336] "Posting means" refers to an interface for prompt providers to post prompts they have created.

[1337] The "storage means" is a mechanism for storing prompts posted by the posting means in a database so that other users can search for them.

[1338] The "recording means" refers to a mechanism that records the number of times a prompt is used.

[1339] The "reward calculation means" is a mechanism for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[1340] "Electronic payment service" is a general term for services that allow online electronic payments.

[1341] "Smartphone application" refers to software that runs on a smartphone and provides specific functions.

[1342] This invention is a system that uses generative artificial intelligence to generate, manage, and use management prompts for electronic payment services. The system is operated primarily using a server and a smartphone.

[1343] The server has multiple functions and performs multi-stage data processing and calculation. Specifically, the following hardware and software are used:

[1344] Hardware Configuration

[1345] Server: A server machine with high-speed data processing capabilities

[1346] Smartphone: A mobile device used by users as an interface.

[1347] Software Configuration

[1348] Python: Server-side program logic

[1349] Flask (web framework): Realizes communication between the user interface and the server

[1350] Database system: Prompts and user information storage

[1351] Generative AI model: Prompt template generation and management

[1352] The server processes the data in the following steps:

[1353] User Registration and Login

[1354] A user uses a smartphone to enter their name, email address, and password to access the new registration page. The server validates the received information and saves it in the database. Once saved, the server returns a "Registration Complete" message. In the case of login, the user enters authentication information, the server checks the information, generates a session or token, and allows the user to log in.

[1355] Prompted Search and Select

[1356] When a user inputs their desired action (e.g., "create a payment reminder") into the smartphone interface, the server receives the information and searches the database for relevant prompt templates. The templates are then displayed as a list on the smartphone, and the user can select the appropriate template.

[1357] Further questions and clarification

[1358] The server generates a follow-up question form based on the selected template and sends it to the user's smartphone. The user answers the questions, and the server receives and analyzes them to generate a specific prompt. The generated prompt is then sent back to the smartphone and displayed to the user.

[1359] Posting and Using Prompts

[1360] Prompt providers use their smartphones to post their own prompts. The server stores the received prompts in a database and makes them available for other users to search. When other users use the prompt, the server records the number of times it is used and calculates a reward. The calculated reward is paid to the prompt provider.

[1361] Specific examples

[1362] Example of user registration and login:

[1363] The user enters "Name: Tanaka Taro, Email address: tanaka@example.com, Password: password123" on the new registration page and submits it. The server responds with "Registration complete."

[1364] Examples of prompted search and selection:

[1365] The user types "create payment reminder," the server searches for relevant prompt templates, and displays a list on the smartphone.

[1366] Example of generating prompts:

[1367] For the "Payment Reminder" template, an additional question is displayed: "Which payment would you like to be reminded about?" If the user answers "Credit card payments," a specific prompt is generated: "Remind me about my next credit card payment."

[1368] This system allows users to easily create and manage prompts for electronic payment services, and allows prompt providers to earn rewards.

[1369] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1370] Step 1:

[1371] User Registration

[1372] The user enters their name, email address, and password on the smartphone's new registration page. The device sends this information to the server. The server validates the received information and stores it in a database. After saving, the server returns a "Registration Complete" message to the device.

[1373] Input: Name, Email Address, Password

[1374] Output: "Registration complete" message

[1375] Specific operation: The server establishes a database connection, checks the input information, and if the information is correct, registers it in the database.

[1376] Step 2:

[1377] Log in

[1378] The user enters their credentials on a login page on their smartphone, and the device sends them to the server, which verifies the credentials and, if successful, creates a session or token and allows the user to log in.

[1379] Input: Email address, Password

[1380] Output: Session or token, login success message

[1381] Specific operation: The server retrieves user information from the database, compares it with the input information, and if the information is correct, issues a session or token.

[1382] Step 3:

[1383] Prompted Search

[1384] The user types what they want to do on their smartphone (e.g., "Create a payment reminder"), and the device sends this information to the server, which searches a database for relevant prompt templates and returns the results to the device.

[1385] Input: What the user wants to do (e.g., "Create a payment reminder")

[1386] Output: A list of related prompt templates

[1387] What it does: The server analyzes user input using natural language processing, generates a database query, retrieves a template from the database, and returns the results.

[1388] Step 4:

[1389] Prompt Selection

[1390] The user selects an appropriate prompt template from the displayed list, and the terminal transmits the user's selection to the server.

[1391] Input: User prompt template selection

[1392] Output: Selected template

[1393] Specific actions: The server retrieves the selected template information and prepares additional questions.

[1394] Step 5:

[1395] Additional question generation

[1396] The server generates a follow-up question form based on the selected prompt template and sends it to the terminal, where the user answers the question and the terminal sends it back to the server.

[1397] Input: prompt template, answers to follow-up questions

[1398] Output: Specific prompt

[1399] Specific action: The server generates a specific prompt based on the template and the user's answer and sends it to the terminal.

[1400] Step 6:

[1401] Prompt generation and display

[1402] The server analyzes the user's answers and generates specific prompts, which are sent to the terminal and displayed to the user.

[1403] Input: Answer to the user's follow-up question

[1404] Output: Specific prompt

[1405] What it does: The server uses the generative AI model to generate a prompt and sends the result to the device.

[1406] Step 7:

[1407] Prompted Posts

[1408] The prompt provider inputs their own prompt and sends it from their terminal to the server, which stores the received prompt in a database.

[1409] Input: A prompt created by the prompt provider

[1410] Output: Prompts saved to the database

[1411] Specific operation: The server receives the prompt information, saves it in the database, and returns a save completion message to the provider.

[1412] Step 8:

[1413] Using and recording prompts

[1414] Other users search for and use the saved prompts. The device sends usage data to the server, which records the number of usages and uses them to calculate rewards.

[1415] Input: Prompt usage information

[1416] Output: Record of prompt usage, reward calculation data

[1417] Specific operation: The server receives prompt usage information, records the number of times in the database, and calculates the reward according to the reward calculation algorithm.

[1418] Step 9:

[1419] Reward calculation and payment

[1420] The server calculates a reward based on the recorded number of uses and pays the reward to the prompt provider.

[1421] Input: Prompt usage count

[1422] Output: Reward payment to prompter

[1423] Specific operation: The server calculates the reward using the reward calculation method and adds the reward to the provider's account.

[1424] 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.

[1425] The present invention provides a system that includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, and an emotion engine for recognizing the user's emotions. Hereinafter, we will explain how this system is specifically implemented.

[1426] System Program Processing

[1427] The program for this system mainly aims to exchange data between the server, terminal, and user, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with concrete examples.

[1428] Program processing

[1429] User Registration and Login

[1430] 1. A user visits the sign-up page and enters their name, email address, and password.

[1431] The terminal transmits the input information to the server.

[1432] The server validates the received information and stores it in the database.

[1433] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[1434] 2. The user enters their email address and password on the login page.

[1435] The terminal sends the input data to the server.

[1436] The server checks the received authentication information and, if successful, generates a session or JWT token and allows login.

[1437] Prompted Search and Select

[1438] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[1439] The terminal transmits the entered search keyword to the server.

[1440] The server searches the database for relevant prompt templates and returns the results to the terminal.

[1441] The terminal displays the results and the user selects the appropriate template.

[1442] Emotion Recognition and Prompt Generation

[1443] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[1444] The user answers the questions and transmits the answer data from the terminal to the server.

[1445] The server analyzes the answers it receives and generates specific prompts tailored to the particular task.

[1446] The server sends the generated specific prompt to the terminal for presentation to the user.

[1447] 2. The emotion engine analyzes emotions based on the user's input and behavioral history.

[1448] The emotion engine provides the results of the analysis to the prompt generator to adjust the generated prompts.

[1449] Providing and Using Prompts

[1450] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[1451] The server stores the received prompts in a database.

[1452] Other users can use the search function to find and use your prompt.

[1453] The terminal sends prompt usage data to the server.

[1454] The server records the number of uses and calculates the reward.

[1455] The server notifies the provider of the calculated reward and processes the payment of the reward.

[1456] Specific examples

[1457] 1. User Registration and Login

[1458] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[1459] 2. Prompt search and selection

[1460] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[1461] 3. Emotion Recognition and Prompt Generation

[1462] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the response. The server generates a specific prompt, sends it to the device, and displays it to the user.

[1463] The emotion engine analyzes the user's emotions based on their input and behavioral history, and then generates prompts based on the results. For example, if the user expresses anxiety, the prompts will be softer and more reassuring.

[1464] 4. Providing and Using Prompts

[1465] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt using the search function and record the number of times it is used, the server calculates a reward and pays it to the provider.

[1466] The system embodying the present invention provides a mechanism that allows users to easily obtain appropriate prompts and prompt providers to receive rewards, and also provides more appropriate prompts by recognizing the user's emotions and reflecting them in the generation of prompts.

[1467] The processing flow will be explained below.

[1468] Step 1:

[1469] A user visits the sign-up page and enters their name, email address, and password.

[1470] The terminal transmits the input information to the server.

[1471] Step 2:

[1472] Validate the information received by the server.

[1473] Check the email address format

[1474] Password Strength Check

[1475] Check for required fields

[1476] Step 3:

[1477] The server saves the validated information to the database.

[1478] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[1479] Step 4:

[1480] The user enters their email address and password on the login page.

[1481] The terminal sends the input data to the server.

[1482] Step 5:

[1483] The server checks the authentication information received.

[1484] Hashed password verification

[1485] Generate a session or JWT token upon successful authentication.

[1486] Step 6:

[1487] The server sends the session information along with a message of successful authentication to the terminal.

[1488] The user is redirected to the dashboard page.

[1489] Step 7:

[1490] The user types what they want to do (e.g., "generate blog content") into the search bar.

[1491] The terminal transmits the entered search keyword to the server.

[1492] Step 8:

[1493] The server searches the database for relevant prompt templates and returns the results to the terminal.

[1494] The terminal displays the received data and the user selects the appropriate template.

[1495] Step 9:

[1496] The server generates an additional question form based on the selected template and sends it to the terminal.

[1497] The user answers the additional questions and transmits the answer data from the terminal to the server.

[1498] Step 10:

[1499] The server uses the user's answers to generate specific prompts tailored to the particular task.

[1500] The server sends the generated specific prompt to the terminal for presentation to the user.

[1501] Step 11:

[1502] The emotion engine analyzes emotions based on user input and behavioral history.

[1503] The emotion engine extracts emotional information from the input.

[1504] The emotion engine analyzes emotions inferred from the user's operation history.

[1505] Step 12:

[1506] The emotion engine sends the analysis results to the server.

[1507] The server adjusts the prompts based on the emotional information.

[1508] Step 13:

[1509] A prompt provider inputs a prompt that he or she has created using an input means and transmits it from the terminal to the server.

[1510] The server stores the received prompts in a database.

[1511] Step 14:

[1512] Other users can use the search function to find and use your prompt.

[1513] The terminal sends prompt usage data to the server.

[1514] Step 15:

[1515] The server records the number of uses.

[1516] The server calculates the reward based on the number of recorded uses.

[1517] Step 16:

[1518] The server notifies the prompt provider of the calculated reward and processes the payment of the reward.

[1519] As a result, a system that combines an emotion engine will operate effectively, matching users of generative AI with prompt providers and improving AI services.

[1520] Example 2

[1521] 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."

[1522] It takes a lot of time and effort for users of generative AI to efficiently search, select, generate, and use prompts that best suit their purposes. Furthermore, since prompts cannot be generated taking into account the user's emotions, it is difficult to provide appropriate prompts. Furthermore, there is no well-established system for prompt providers to receive appropriate compensation, making it difficult to promote the provision of high-quality prompts.

[1523] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: input means for a user of the generative artificial intelligence to input and select what he or she wants to do; search means for searching for a relevant prompt template based on information received from the input means; display means for displaying the prompt template searched by the search means; prompt generation means for generating a specific prompt corresponding to a specific task based on the user's answer to additional questions; execution means for executing a task using the prompt generated by the prompt generation means; posting means for a prompt provider to post a prompt created by the prompt provider; storage means for storing the prompt posted by the posting means in a database so that other users can search for it; recording means for recording the number of times a prompt is used by the execution means; reward calculation means for calculating a fee based on the number of times it is used recorded by the recording means and paying a reward to the prompt provider; and emotion recognition means for recognizing emotions from the user's input content and behavioral history and reflecting the result in prompt generation. This enables users to efficiently obtain, generate, and use prompts that suit their purposes, and also enables prompts to be generated that correspond to emotions, thereby enabling accurate reward payment to prompt providers.

[1524] "Input means" refers to the means by which users of generative artificial intelligence input and select what they want to do.

[1525] The "search means" is a means for searching for a relevant prompt template based on the information received from the input means.

[1526] The "display means" is a means for displaying the prompt template retrieved by the retrieval means.

[1527] A "prompt generation means" is a means for generating a specific prompt corresponding to a specific task by having the user answer additional questions.

[1528] The "execution means" is a means for executing a task using the prompt generated by the prompt generation means.

[1529] A "posting means" is a means for a prompt provider to post a prompt that they have created.

[1530] The "storage means" is a means for storing the prompt posted by the posting means in a database so that other users can search for it.

[1531] The "recording means" is a means for recording the number of times a prompt is used when it is used by the execution means.

[1532] The "reward calculation means" is a means for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[1533] The "emotion recognition means" is a means for recognizing the user's emotions from their input content and behavioral history, and reflecting the results in generating prompts.

[1534] This invention relates to a system that enables users of generative artificial intelligence to efficiently search, generate, and use appropriate prompts. The system transfers data between a server, a terminal, and a user, enabling the provision of prompts that are optimal for the user's purpose.

[1535] System configuration

[1536] The system includes the following hardware and software:

[1537] 1. The server has the basic computer infrastructure to run a database management system, an authentication system, an emotion recognition engine, etc. Specifically, it is equipped with a database management system such as MySQL, an authentication system using JWT, and an emotion recognition engine that performs natural language processing.

[1538] 2. A terminal is an interface through which a user accesses the system and inputs and receives various information. This includes web browsers and mobile applications.

[1539] 3. The user is responsible for inputting what they want to do with the system and for selecting, generating, and using prompts.

[1540] Program processing description

[1541] User Registration and Login

[1542] 1. A user accesses the new registration page and enters their name, email address, and password. The device then sends the entered information to the server. The server validates the entered information and saves it in the database. After saving is complete, a "Registration Complete" message is returned to the device.

[1543] 2. When the user enters their email address and password on the login page, the device sends this to the server, which checks the authentication information and, if successful, generates a session or JWT token and allows login.

[1544] Prompted Search and Select

[1545] 1. When a user enters what they want to do (e.g., "generate blog content") into the search bar, the device sends the search keywords to the server. The server searches the database for relevant prompt templates and returns the results to the device. The device displays them, and the user can select an appropriate template.

[1546] Emotion Recognition and Prompt Generation

[1547] 1. The server generates an additional question form based on the selected template and sends it to the terminal. The user answers the question and the answer data is sent from the terminal to the server. The server analyzes the answer and generates a specific prompt.

[1548] 2. The emotion engine analyzes the user's input and behavioral history in real time and provides the results to the server, which then uses the emotion information to send more personalized prompts to the device and present them to the user.

[1549] Providing and Using Prompts

[1550] 1. The prompt provider creates a prompt using an input method and sends it from the terminal to the server, which stores the prompt in a database.

[1551] 2. Other users use the search function to find and use the prompt. The device sends usage data to the server, which records the number of uses, calculates the reward, and pays it to the provider.

[1552] Specific examples

[1553] Example 1: User registration and login

[1554] A user enters the name "Taro Tanaka," the email address "tanaka@example.com," and the password "password123" on the new registration page. The entered information is sent from the device to the server and stored in the database. After that, the "Registration Complete" message is displayed.

[1555] Example 2: Prompted search and select

[1556] A user types "blog content generation" in the search bar, the server searches for relevant prompt templates and displays a list on the device. If the user selects "blog prompt for product review", its details are displayed.

[1557] Example 3: Emotion recognition and prompt generation

[1558] The server generates and displays a follow-up question: "Which product would you like to review?" The user answers "A new smartphone" and submits the question. The server generates a specific prompt and displays the message: "To write a review of a new smartphone, please use the following structure as a guide."

[1559] The emotion engine analyzes the user's emotions based on their input and behavioral history, and if the user expresses anxiety, for example, the prompts are softened to provide a sense of security.

[1560] Example 4: Providing and using prompts

[1561] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt in the search function, the number of uses is recorded, and the server calculates and pays the provider a reward.

[1562] This system provides a mechanism for users to easily obtain appropriate prompts and for providers to receive rewards, and also generates prompts that take into account the user's emotions.

[1563] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1564] Step 1: User Registration

[1565] 1. A user visits the sign-up page and enters their name, email address, and password.

[1566] Input: Name, Email Address, Password

[1567] The terminal transmits the input information to the server.

[1568] Validate the information received by the server.

[1569] Data processing: Email address format check, password strength check, etc.

[1570] The server saves the data that passes the validation in the database.

[1571] Output: "Registration complete" message

[1572] The server returns a "registration complete" message to the terminal.

[1573] The device will display a "Registration complete" message.

[1574] Step 2: Log in

[1575] 1. The user enters their email address and password on the login page.

[1576] Input: Email address, password

[1577] The terminal sends the input data to the server.

[1578] The server checks the received authentication information against a database.

[1579] Data calculation: Email address and password matching

[1580] If authentication is successful, a session or JWT token is generated.

[1581] Output: Session ID or JWT token

[1582] The server returns a session ID or JWT token to the device.

[1583] The terminal notifies the user that authentication was successful.

[1584] Step 3: Prompted Search

[1585] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[1586] Input: Search keyword

[1587] The device sends the search keywords to the server.

[1588] The server retrieves the relevant prompt template from the database.

[1589] Data calculations: keyword matching, relevance score calculation

[1590] Output: Search result list

[1591] The server returns the search results to the device.

[1592] Your device will display a list of search results.

[1593] Step 4: Prompt details and selection

[1594] 1. The user selects the appropriate template from the displayed list.

[1595] Input: Selected template

[1596] The device sends the selection to the server.

[1597] The server retrieves the details of the selected template from the database.

[1598] Data processing: Obtaining detailed template information

[1599] Output: Template details

[1600] The server returns detailed information about the template to the terminal.

[1601] The device will display more information.

[1602] Step 5: Emotion recognition and prompt generation

[1603] 1. The server generates a follow-up question form based on the selected template.

[1604] Input: Selected template

[1605] Data processing: Generation of additional question form

[1606] A question form is sent to the terminal and displayed.

[1607] The user answers the questions and inputs the answer data.

[1608] Input: Answer data to questions

[1609] The terminal transmits the response data to the server.

[1610] The server analyzes the received answers and generates specific prompts.

[1611] Data arithmetic: Response analysis, prompt generation

[1612] Output: Specific prompt

[1613] The server generates a prompt and sends it to the terminal for display.

[1614] The emotion recognition means analyzes the user's responses and behavior history and provides emotion information to the server.

[1615] The server adjusts the prompts based on the emotional information.

[1616] Step 6: Provide a prompt

[1617] 1. The prompt provider creates a prompt using an input means and sends it from the terminal to the server.

[1618] Input: Created prompt

[1619] The terminal sends the input data to the server.

[1620] The server stores the received prompts in a database.

[1621] Data Transformation: Save Prompt

[1622] Output: Save completion notification

[1623] The server sends a save completion notification to the terminal.

[1624] Step 7: Use prompts

[1625] 1. Other users find your prompt using the search feature.

[1626] Input: Search keyword

[1627] The device sends the search keywords to the server.

[1628] The server retrieves the relevant prompt from the database.

[1629] Data calculations: keyword matching, relevance score calculation

[1630] Output: Search result list

[1631] The server returns the search results to the device.

[1632] Your device will display a list of search results.

[1633] The user selects and uses the prompt.

[1634] Input: Selected prompt

[1635] The device sends usage data to the server.

[1636] The server records the number of uses.

[1637] Data processing: Recording number of uses

[1638] A reward calculation means calculates and pays a reward to the prompt provider.

[1639] Data calculation: Reward calculation

[1640] Output: Reward amount

[1641] The server processes the reward payment and notifies the provider.

[1642] (Application example 2)

[1643] 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."

[1644] Conventional generative AI systems do not consider emotions when generating specific prompts, limiting their ability to improve the user experience. Even when users prefer to use voice input to generate and display prompts using smart devices, they face difficulties converting the speech into text and processing it appropriately. Furthermore, feedback on generated prompts is lacking, leading to ineffective reward calculations for prompt providers. There is a need to address these issues and provide a more interactive and user-friendly system.

[1645] 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.

[1646] In this invention, the server includes: an input means for inputting and selecting what a user of the generative artificial intelligence wants to do; a search means for searching for a relevant prompt template based on information received from the input means; a display means for displaying the prompt template searched by the search means; a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions; an execution means for executing a task using the prompt generated by the prompt generation means; a posting means for a prompt provider to post a prompt created by the prompt provider; a storage means for storing the posted prompt in a database so that other users can search for the prompt; a recording means for recording the number of times a prompt is used by the execution means; a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider; an emotion engine for recognizing a user's emotions; an adjustment means for adjusting the display content or prompt content based on emotion information analyzed by the emotion engine; a speech recognition means for converting a user's voice input into text; and an edge device means for generating and displaying prompts via a smart device. This enables prompt generation and display that take the user's emotions into consideration, thereby enabling smooth prompt operation on a smart device using voice input. Furthermore, it is possible to realize appropriate reward calculation for prompt providers, and to provide a more interactive and user-friendly system.

[1647] "Generative AI" is an AI system that automatically generates content such as text and images based on user input and selections.

[1648] "Input means" refers to an interface that allows a user to input or select what they want to do, and includes a keyboard, touch screen, voice recognition, etc.

[1649] A "search mechanism" is an algorithm or system for searching for relevant prompt templates based on information received from an input mechanism.

[1650] A "display means" is a device or interface for visually presenting retrieved prompt templates and generated prompts to a user.

[1651] A "prompt generator" is a system or algorithm that generates specific prompts for a particular task based on the user's answers to follow-up questions.

[1652] The "execution means" is a function for executing a specific task using the prompt generated by the prompt generation means.

[1653] The "posting means" is an interface for inputting and sending a prompt created by a prompt provider.

[1654] The "storage means" is a system for storing prompts posted by the posting means in a database so that other users can search for them.

[1655] A "recording means" is a system or algorithm for tracking and recording the number of times a prompt is used by the execution means.

[1656] The "reward calculation means" is a system for calculating compensation based on the number of uses recorded by the recording means and providing a reward to the prompt provider.

[1657] An "emotion engine" is software or algorithms that analyze and recognize emotions based on user input and behavioral history.

[1658] The "adjustment means" is a function for adjusting the display content or prompt content based on the emotion information analyzed by the emotion engine.

[1659] A "speech recognizer" is a system or algorithm for converting a user's voice input into text.

[1660] An "edge device means" is a local or network-connected device for generating and displaying prompts through a smart device.

[1661] The present invention is a system that uses generative artificial intelligence to generate and display appropriate prompts while taking into account the user's emotions. This system is intended for use as a shopping assistant application on smart devices.

[1662] Program processing

[1663] The program in this system mainly exchanges data between the server and the smart device (e.g., smart glasses). Each element is explained below.

[1664] User Registration and Login

[1665] 1. The user registers by entering their name, email address, and password using voice input or touch gestures on their smart device. The device sends the entered information to the server, which validates the received information and stores it in the database. After saving, the message "Registration Complete" appears on the smart device's display.

[1666] Prompted Search and Select

[1667] 1. The user uses the voice input function of the smart device to say, for example, "I'd like to know reviews of the new smartphone." The device converts this voice data into text using a speech recognition method (e.g., Google Speech-to-Text API) and sends the search keywords to the server. The server searches for relevant prompt templates in its database and returns the results to the device. The smart device then displays the results on its screen, and the user selects the appropriate template.

[1668] Emotion Recognition and Prompt Generation

[1669] 1. The server generates additional questions based on the selected template and sends them to the smart device. The user answers by voice, and the device converts the voice into text and sends it to the server. The server analyzes the received answer data and generates a specific prompt (e.g., "Show me reviews of Apple's latest smartphones"). The generated specific prompt is then displayed on the smart device.

[1670] 2. An emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's tone of voice and behavioral history to determine their emotions. If the user expresses anxiety, the generated prompt content is adjusted to be more reassuring (e.g., "You can check the information with peace of mind. Here is a review of Apple's latest smartphone").

[1671] Providing and Using Prompts

[1672] 1. Prompt providers enter and submit prompts through a web interface, and the server stores them in a database, making them available for other users to find and use using the search function on their smart devices.

[1673] 2. When a prompt is used, the terminal transmits usage data to the server, which records the number of times the prompt is used. Based on the recorded data, the reward calculation means calculates the compensation and provides a reward to the prompt provider.

[1674] Specific examples

[1675] User Registration and Login

[1676] The user speaks into the smart device, "New registration, name: User A, email address: usera@example.com, password: password123." The device converts the voice to text and sends it to the server, completing the registration.

[1677] Prompted Search and Select

[1678] The user speaks into their smart device, saying, "I'd like to know reviews of the new smartphone." The device converts the speech into text, and the server returns a template, such as "Reviews of Apple's latest smartphone," which is then displayed.

[1679] Emotion Recognition and Prompt Generation

[1680] The server generates the question "What brand are you looking for?" and displays it on the smart device. The user responds with "Apple," and the voice data is converted into text and sent to the server. The server generates a prompt and sends it to the device. If the emotion engine detects anxiety in the user's tone of voice, it adjusts the prompt and displays, "You can rest assured that we're here to help you. We'll show you reviews of Apple's latest smartphones."

[1681] Prompt Sentence Examples

[1682] "Please enter the brand name of the smartphone you want to see reviews for."

[1683] The system is analyzing user sentiment...

[1684] "Please check out our review of Apple's latest smartphone here. If you have any questions, please let us know."

[1685] This system enables prompt generation and display that takes the user's emotions into account, allowing for smooth prompt operation on smart devices using voice input. It also provides an interactive and user-friendly system that appropriately calculates rewards for prompt providers.

[1686] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1687] Step 1:

[1688] The user registers by entering their name, email address, and password using the voice input function of their smart device. The entered information is converted into text data by the terminal's voice recognition means (input: voice data, output: text data). The terminal then sends the text data to the server. The server validates the sent information and stores it in a database. Once registration is complete, the server sends a "Registration Complete" message to the terminal, which is displayed on the smart device's display (input: text data, output: registration complete message).

[1689] Step 2:

[1690] The user uses the voice input function of the smart device to say, "I'd like to know reviews of the new smartphone." The device converts this voice data into text using a speech recognition means (input: voice data, output: text data). The converted text data is sent to the server. The server searches the database for relevant prompt templates and returns the search results to the device (input: text data, output: prompt template). The search results are then displayed on the smart device's display.

[1691] Step 3:

[1692] The user selects an appropriate template from those displayed on the terminal display. The selection information is sent from the terminal to the server (input: user selection, output: selection information). The server generates a follow-up question based on the selected template and sends it to the terminal (input: selection information, output: follow-up question). The follow-up question is then displayed on the smart device.

[1693] Step 4:

[1694] The user answers the follow-up questions by voice. The device converts the voice data into text data using a voice recognition means (input: voice data, output: text data). The answer text data is sent to the server. The server analyzes the received answer data and generates a specific prompt (input: text data, output: specific prompt). The generated prompt is displayed on the smart device.

[1695] Step 5:

[1696] The emotion engine analyzes the user's voice tone and behavioral history to determine their emotions. The analysis results are sent to the server, which then adjusts the prompt content (input: data such as voice tone, output: adjusted prompt). The adjusted prompt is sent to the device and displayed on the smart device's screen.

[1697] Step 6:

[1698] A prompt provider uses a web interface to input and submit prompts, which are received by the server and stored in a database (input: prompt data, output: saving to database).

[1699] Step 7:

[1700] Other users can use the saved prompts by using the search function. When a prompt is used, the device sends the usage data to the server, and the server records the number of times it is used (input: usage data, output: record of number of times it is used).

[1701] Step 8:

[1702] The reward calculation means calculates the compensation based on the recorded number of uses. The calculation result is added as credit to the prompt provider's account, and a reward is provided to the provider (input: number of uses, output: reward calculation result). The prompt provider is notified of the reward provision.

[1703] 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.

[1704] 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.

[1705] 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.

[1706] [Fourth embodiment]

[1707] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1708] 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.

[1709] 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).

[1710] 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.

[1711] 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.

[1712] 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).

[1713] 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.

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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."

[1720] The present invention includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for relevant prompt templates based on information received from the input means, a display means for displaying the prompt templates searched by the search means, and a prompt generation means for generating specific prompts corresponding to specific tasks in response to additional questions from the user. It also includes a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for saving the posted prompt so that other users can search for it, and a reward calculation means for recording the number of times the prompt is used and calculating a reward based on the number of times it is used. Hereinafter, we will explain how this system is specifically implemented.

[1721] System Program Processing

[1722] The program for this system mainly aims to exchange data between the server and the user's terminal, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with some concrete examples.

[1723] Program processing

[1724] User Registration and Login

[1725] 1. A user visits the sign-up page and enters their name, email address, and password.

[1726] The terminal transmits the input information to the server.

[1727] The server validates the received information and stores it in the database.

[1728] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[1729] 2. The user enters their credentials on the login page and the device sends them to the server.

[1730] The server checks the authentication information and, if successful, creates a session or token and allows login.

[1731] Prompted Search and Select

[1732] 1. The user uses the input means to input what they want to do (e.g., "generate blog content").

[1733] The terminal transmits the input information to the server.

[1734] The server searches the database for the relevant prompt template and returns the result to the terminal.

[1735] The terminal displays the results and the user selects the appropriate template.

[1736] Further questions and clarification

[1737] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[1738] The user answers the questions and the terminal sends the answers to the server.

[1739] The server analyzes the received answers and generates specific prompts.

[1740] The server sends the generated prompt to the terminal for display to the user.

[1741] Providing and Using Prompts

[1742] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[1743] The server stores the received prompts in a database.

[1744] Other users can use the search function to find and use your prompt.

[1745] The terminal sends prompt usage data to the server.

[1746] The server records the number of uses and calculates the reward.

[1747] The calculated reward is paid to the provider.

[1748] Specific examples

[1749] 1. User Registration and Login

[1750] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[1751] 2. Prompt search and selection

[1752] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[1753] 3. Additional questions and clarification

[1754] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the question. The server generates a specific prompt and displays it on the device.

[1755] 4. Providing and Using Prompts

[1756] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt, the server records the number of times it is used and calculates and pays a reward.

[1757] The system embodying the present invention thus provides a mechanism by which users can easily obtain appropriate prompts and prompt providers can receive rewards.

[1758] The processing flow will be explained below.

[1759] Step 1:

[1760] A user visits the sign-up page and enters their name, email address, and password.

[1761] The terminal transmits the input information to the server.

[1762] Step 2:

[1763] Validate the information received by the server.

[1764] Check the email address format

[1765] Password Strength Check

[1766] Check for required fields

[1767] Step 3:

[1768] The server saves the validated information to the database.

[1769] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[1770] Step 4:

[1771] The user enters their email address and password on the login page.

[1772] The terminal sends the input data to the server.

[1773] Step 5:

[1774] The server checks the authentication information received.

[1775] Hashed password verification

[1776] Generate a session or JWT token upon successful authentication.

[1777] Step 6:

[1778] The server sends the session information along with a message of successful authentication to the terminal.

[1779] The user is redirected to the dashboard page.

[1780] Step 7:

[1781] The user types what they want to do (e.g., "generate blog content") into the search bar.

[1782] The terminal transmits the entered search keyword to the server.

[1783] Step 8:

[1784] The server searches the database for relevant prompt templates and returns the results to the terminal.

[1785] The terminal displays the received data and the user selects the appropriate template.

[1786] Step 9:

[1787] The server generates an additional question form based on the selected template and sends it to the terminal.

[1788] The user answers the additional questions and transmits the answer data from the terminal to the server.

[1789] Step 10:

[1790] The server uses the user's answers to generate specific prompts tailored to the particular task.

[1791] The server sends the generated specific prompt to the terminal for presentation to the user.

[1792] Step 11:

[1793] The prompt provider accesses the submission form and enters their prompt.

[1794] The terminal sends the entered prompt information to the server.

[1795] Step 12:

[1796] The server saves the prompts in a database.

[1797] Other users can find and use the prompts you provide in the search bar.

[1798] Step 13:

[1799] The terminal sends prompt usage data to the server.

[1800] The server records the number of uses and calculates the reward.

[1801] Step 14:

[1802] The server notifies the provider of the calculated reward and processes the payment of the reward.

[1803] This provides a system that matches users of generative AI with prompt providers, promoting the use of generative AI and improving AI services.

[1804] Example 1

[1805] 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."

[1806] In conventional generative AI systems, the search and selection of prompts is complicated, making it difficult for users to find appropriate prompts. Furthermore, there is no well-established mechanism for accurately recording the number of times prompts created by prompt providers are used and calculating appropriate rewards based on that information. Furthermore, there is a lack of a system for safely and efficiently performing user registration and authentication processes.

[1807] 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.

[1808] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the prompt posted by the posting means in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, an authentication means for receiving and verifying the user's authentication information, and a storage means for the authentication means to store the user's information in a database. This enables users to easily and efficiently search for, select, and generate appropriate prompts, enables prompt providers to receive fair rewards, and provides a system in which user registration and authentication processes are performed safely and efficiently.

[1809] "Generative AI" is an AI technology that generates new data and information based on input data.

[1810] "Input means" refers to a device or function that allows a user to input information or commands to a system.

[1811] A "search means" is a processing function for finding specific information from a database or storage.

[1812] "Display means" refers to a device or function for visually presenting information to a user.

[1813] The "prompt generator" is a function that creates specific prompts based on received information and follow-up questions.

[1814] An "execution means" is a function for performing a specific task based on the generated prompt.

[1815] The "posting means" is a function that allows a prompt provider to send a prompt that they have created to the system.

[1816] "Storage means" is a function for storing received information and data in a database or other storage.

[1817] The "recording means" is a function for recording the number of times a prompt is used and other usage data.

[1818] The "reward calculation means" is a function that calculates rewards to prompt providers based on the recorded usage data.

[1819] "Authentication means" is a function for verifying a user's identity and qualifications.

[1820] A "database" is a system for efficiently storing, managing, and searching information and data.

[1821] The present invention provides a generative artificial intelligence system that allows users to efficiently input and select what they want to do, generates and provides appropriate prompts based on the input, and pays rewards to the providers. The following describes in detail the embodiments of the present invention.

[1822] This system consists of a server and a user terminal. The main functions are concentrated on the server, and the user terminal acts as an interface for communicating with users.

[1823] 1. User Registration and Authentication

[1824] A user accesses the new registration page and enters authentication information such as name, email address, and password. For example, the user enters "Name: Taro", "Email address: taro@example.com", and "Password: password123". The device sends this to the server, which validates the received information and saves it in the database. After saving is complete, the server returns a "Registration complete" message to the device.

[1825] Next, the user enters their authentication information on the login page, and the device sends it to the server. The server checks the authentication information against the database, and if successful, generates a session ID and allows login. If successful, a "Login successful" message and session information are returned to the device, and if unsuccessful, an "Authentication failed" error message is returned.

[1826] 2. Prompt search and selection

[1827] The user enters what they want to do into an input means (for example, a text box). For example, they might enter "create blog content." This information is sent from the device to the server. The server searches the database to find relevant prompt templates (for example, "blog prompt for product reviews," "travel blog prompt") and sends the search results to the device. The device then displays the search results in a list format, allowing the user to make a selection.

[1828] 3. Follow-up questions and prompt generation

[1829] When a user selects a specific prompt template, the server generates an additional question form (e.g., "Which product would you like to review?") based on that template and sends it to the device. The user answers this form (e.g., "A new smartphone"), and the device sends it to the server. The server then generates a specific prompt (e.g., "Please review the performance of the new smartphone in detail") based on the answer received and sends it to the device.

[1830] 4. Submitting and Using Prompts

[1831] The prompt provider inputs a prompt they have created and sends it from their device to the server. The server stores the received prompt in a database. Other users can then use the search function to find, select, and use the prompt. The device sends prompt usage data to the server, which records the number of times the prompt has been used.

[1832] 5. Remuneration calculation

[1833] The server calculates the reward based on the number of recorded uses and pays it to the prompt provider. This reward is transferred based on the provider's registered payment information. The reward calculation is, for example, $0.1 per use.

[1834] In this way, users can easily and efficiently search, select, and generate appropriate prompts, prompt providers can earn rewards, and the entire system operates safely and smoothly.

[1835] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1836] Step 1:

[1837] A user visits the sign-up page and enters their name, email address, and password.

[1838] Input: The user enters their name, email address, and password into the text fields.

[1839] The terminal transmits the input information to the server.

[1840] Validate the information received by the server (e.g., check that the email address is formatted correctly and does not already exist).

[1841] Output: If validation is successful, the user information is saved in the database and a "Registration complete" message is returned to the terminal. If validation fails, an error message is returned.

[1842] Step 2:

[1843] The user enters their authentication information on the login page, and the device sends it to the server.

[1844] Input: The user enters their email address and password into the login form.

[1845] The device sends the authentication information to the server.

[1846] The server checks the received authentication information against the database and generates a session ID or JWT token if it is correct, or an error message if it is invalid.

[1847] Output: If correct authentication information is provided, the session information is returned to the terminal and the user is logged in. If unsuccessful, an "Authentication failed" message is returned.

[1848] Step 3:

[1849] The user uses the input means to input what he or she wants to do.

[1850] Input: The user inputs "Create blog content" into the input means (text box).

[1851] The terminal transmits the input information to the server.

[1852] The server searches the database for prompt templates related to "blog content generation" and extracts the found templates.

[1853] Output: The prompt templates (e.g. "Blog prompt for product reviews", "Travel blog prompt") as search results are sent to the terminal and displayed in list format.

[1854] Step 4:

[1855] The user selects a prompt template from the search results.

[1856] Input: User clicks to select "Blog prompt for product reviews" from the list.

[1857] The terminal transmits the selection information to the server.

[1858] The server generates additional questions related to the selected prompt template and creates a question form.

[1859] Output: A form with additional questions (e.g., "Which product would you like to review?") is displayed on the terminal.

[1860] Step 5:

[1861] The user answers additional questions to generate the actual prompt.

[1862] Input: The user enters "new smartphone" as an answer into the question form.

[1863] The terminal sends the user's answer to the server.

[1864] The server analyzes the received answers and generates a specific prompt (e.g., "Please provide a detailed review of the performance of your new smartphone").

[1865] Output: The specific prompt is sent to the terminal and displayed to the user.

[1866] Step 6:

[1867] Prompt contributors post prompts they have created themselves.

[1868] Input: The prompt giver enters a "Prompt for a Travel Guidebook."

[1869] The terminal sends the prompt entered by the provider to the server.

[1870] The server stores the received prompts in a database.

[1871] Output: A message indicating that the data has been saved is displayed on the provider's terminal.

[1872] Step 7:

[1873] Use prompts posted by other users.

[1874] Input: The user uses the search function to find and select "Prompt for Travel Guidebook."

[1875] The terminal transmits usage information to the server.

[1876] The server keeps track of the number of times a prompt is used.

[1877] Output: The number of times the prompt is used is recorded in a database.

[1878] Step 8:

[1879] Calculate rewards for prompt providers.

[1880] Input: The server uses the recorded number of prompt usages as input data.

[1881] The server calculates the reward based on the number of uses (e.g., $0.10 per use).

[1882] Output: The calculated reward is added to the contributor's account.

[1883] (Application example 1)

[1884] 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."

[1885] The problem is that there is a lack of efficient means for generating and managing prompts using generative artificial intelligence in electronic payment services. In particular, it is difficult to establish a system that allows users to easily generate and manage appropriate prompts and allows prompt providers to receive rewards.

[1886] 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.

[1887] In this invention, the server includes an input means for a user of the generative artificial intelligence to input and select what he or she wants to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, an execution means for executing a task using the prompt generated by the prompt generation means, a posting means for a prompt provider to post a prompt created by the prompt provider, a storage means for storing the posted prompt in a database so that other users can search for the prompt, a recording means for recording the number of times the prompt is used by the execution means, a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider, a prompt generation means for generating an administrative prompt for an electronic payment service, and a smartphone application for displaying the specific prompt for the electronic payment service generated by the prompt generation means to the user. This allows users to easily generate administrative prompts for electronic payment services and allows prompt providers to receive rewards.

[1888] "Generative AI" is an AI technology that generates content such as text and images based on user instructions.

[1889] "User" refers to the person or organization that uses generative artificial intelligence to perform prompts and tasks.

[1890] "Input means" refers to the interface that allows users of generative artificial intelligence to input and select what they want to do.

[1891] A "prompt template" is a template that contains instructions for a generative artificial intelligence to use when performing a specific task.

[1892] "Search means" refers to a mechanism that searches a database for relevant prompt templates based on information received from an input means.

[1893] "Display means" means an interface for displaying to the user the prompt templates retrieved by the retrieval means.

[1894] A "prompt generator" is a mechanism that generates specific prompts corresponding to specific tasks by having the user answer additional questions.

[1895] The "execution means" refers to a system or process for executing a task using the prompt generated by the prompt generation means.

[1896] "Posting means" refers to an interface for prompt providers to post prompts they have created.

[1897] The "storage means" is a mechanism for storing prompts posted by the posting means in a database so that other users can search for them.

[1898] The "recording means" refers to a mechanism that records the number of times a prompt is used.

[1899] The "reward calculation means" is a mechanism for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[1900] "Electronic payment service" is a general term for services that allow online electronic payments.

[1901] "Smartphone application" refers to software that runs on a smartphone and provides specific functions.

[1902] This invention is a system that uses generative artificial intelligence to generate, manage, and use management prompts for electronic payment services. The system is operated primarily using a server and a smartphone.

[1903] The server has multiple functions and performs multi-stage data processing and calculation. Specifically, the following hardware and software are used:

[1904] Hardware Configuration

[1905] Server: A server machine with high-speed data processing capabilities

[1906] Smartphone: A mobile device used by users as an interface.

[1907] Software Configuration

[1908] Python: Server-side program logic

[1909] Flask (web framework): Realizes communication between the user interface and the server

[1910] Database system: Prompts and user information storage

[1911] Generative AI model: Prompt template generation and management

[1912] The server processes the data in the following steps:

[1913] User Registration and Login

[1914] A user uses a smartphone to enter their name, email address, and password to access the new registration page. The server validates the received information and saves it in the database. Once saved, the server returns a "Registration Complete" message. In the case of login, the user enters authentication information, the server checks the information, generates a session or token, and allows the user to log in.

[1915] Prompted Search and Select

[1916] When a user inputs their desired action (e.g., "create a payment reminder") into the smartphone interface, the server receives the information and searches the database for relevant prompt templates. The templates are then displayed as a list on the smartphone, and the user can select the appropriate template.

[1917] Further questions and clarification

[1918] The server generates a follow-up question form based on the selected template and sends it to the user's smartphone. The user answers the questions, and the server receives and analyzes them to generate a specific prompt. The generated prompt is then sent back to the smartphone and displayed to the user.

[1919] Posting and Using Prompts

[1920] Prompt providers use their smartphones to post their own prompts. The server stores the received prompts in a database and makes them available for other users to search. When other users use the prompt, the server records the number of times it is used and calculates a reward. The calculated reward is paid to the prompt provider.

[1921] Specific examples

[1922] Example of user registration and login:

[1923] The user enters "Name: Tanaka Taro, Email address: tanaka@example.com, Password: password123" on the new registration page and submits it. The server responds with "Registration complete."

[1924] Examples of prompted search and selection:

[1925] The user types "create payment reminder," the server searches for relevant prompt templates, and displays a list on the smartphone.

[1926] Example of generating prompts:

[1927] For the "Payment Reminder" template, an additional question is displayed: "Which payment would you like to be reminded about?" If the user answers "Credit card payments," a specific prompt is generated: "Remind me about my next credit card payment."

[1928] This system allows users to easily create and manage prompts for electronic payment services, and allows prompt providers to earn rewards.

[1929] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1930] Step 1:

[1931] User Registration

[1932] The user enters their name, email address, and password on the smartphone's new registration page. The device sends this information to the server. The server validates the received information and stores it in a database. After saving, the server returns a "Registration Complete" message to the device.

[1933] Input: Name, Email Address, Password

[1934] Output: "Registration complete" message

[1935] Specific operation: The server establishes a database connection, checks the input information, and if the information is correct, registers it in the database.

[1936] Step 2:

[1937] Log in

[1938] The user enters their credentials on a login page on their smartphone, and the device sends them to the server, which verifies the credentials and, if successful, creates a session or token and allows the user to log in.

[1939] Input: Email address, Password

[1940] Output: Session or token, login success message

[1941] Specific operation: The server retrieves user information from the database, compares it with the input information, and if the information is correct, issues a session or token.

[1942] Step 3:

[1943] Prompted Search

[1944] The user types what they want to do on their smartphone (e.g., "Create a payment reminder"), and the device sends this information to the server, which searches a database for relevant prompt templates and returns the results to the device.

[1945] Input: What the user wants to do (e.g., "Create a payment reminder")

[1946] Output: A list of related prompt templates

[1947] What it does: The server analyzes user input using natural language processing, generates a database query, retrieves a template from the database, and returns the results.

[1948] Step 4:

[1949] Prompt Selection

[1950] The user selects an appropriate prompt template from the displayed list, and the terminal transmits the user's selection to the server.

[1951] Input: User prompt template selection

[1952] Output: Selected template

[1953] Specific actions: The server retrieves the selected template information and prepares additional questions.

[1954] Step 5:

[1955] Additional question generation

[1956] The server generates a follow-up question form based on the selected prompt template and sends it to the terminal, where the user answers the question and the terminal sends it back to the server.

[1957] Input: prompt template, answers to follow-up questions

[1958] Output: Specific prompt

[1959] Specific action: The server generates a specific prompt based on the template and the user's answer and sends it to the terminal.

[1960] Step 6:

[1961] Prompt generation and display

[1962] The server analyzes the user's answers and generates specific prompts, which are sent to the terminal and displayed to the user.

[1963] Input: Answer to the user's follow-up question

[1964] Output: Specific prompt

[1965] What it does: The server uses the generative AI model to generate a prompt and sends the result to the device.

[1966] Step 7:

[1967] Prompted Posts

[1968] The prompt provider inputs their own prompt and sends it from their terminal to the server, which stores the received prompt in a database.

[1969] Input: A prompt created by the prompt provider

[1970] Output: Prompts saved to the database

[1971] Specific operation: The server receives the prompt information, saves it in the database, and returns a save completion message to the provider.

[1972] Step 8:

[1973] Using and recording prompts

[1974] Other users search for and use the saved prompts. The device sends usage data to the server, which records the number of usages and uses them to calculate rewards.

[1975] Input: Prompt usage information

[1976] Output: Record of prompt usage, reward calculation data

[1977] Specific operation: The server receives prompt usage information, records the number of times in the database, and calculates the reward according to the reward calculation algorithm.

[1978] Step 9:

[1979] Reward calculation and payment

[1980] The server calculates a reward based on the recorded number of uses and pays the reward to the prompt provider.

[1981] Input: Prompt usage count

[1982] Output: Reward payment to prompter

[1983] Specific operation: The server calculates the reward using the reward calculation method and adds the reward to the provider's account.

[1984] 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.

[1985] The present invention provides a system that includes an input means for a user of a generative artificial intelligence to input and select what they want to do, a search means for searching for a relevant prompt template based on information received from the input means, a display means for displaying the prompt template searched by the search means, a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions, and an emotion engine for recognizing the user's emotions. Hereinafter, we will explain how this system is specifically implemented.

[1986] System Program Processing

[1987] The program for this system mainly aims to exchange data between the server, terminal, and user, and to match prompt providers with users of the generative AI. Below, we will explain the program's processing in natural language, with concrete examples.

[1988] Program processing

[1989] User Registration and Login

[1990] 1. A user visits the sign-up page and enters their name, email address, and password.

[1991] The terminal transmits the input information to the server.

[1992] The server validates the received information and stores it in the database.

[1993] After the saving is complete, the server returns a "Registration Complete" message to the terminal.

[1994] 2. The user enters their email address and password on the login page.

[1995] The terminal sends the input data to the server.

[1996] The server checks the received authentication information and, if successful, generates a session or JWT token and allows login.

[1997] Prompted Search and Select

[1998] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[1999] The terminal transmits the entered search keyword to the server.

[2000] The server searches the database for relevant prompt templates and returns the results to the terminal.

[2001] The terminal displays the results and the user selects the appropriate template.

[2002] Emotion Recognition and Prompt Generation

[2003] 1. The server generates an additional question form based on the selected template and sends it to the terminal.

[2004] The user answers the questions and transmits the answer data from the terminal to the server.

[2005] The server analyzes the answers it receives and generates specific prompts tailored to the particular task.

[2006] The server sends the generated specific prompt to the terminal for presentation to the user.

[2007] 2. The emotion engine analyzes emotions based on the user's input and behavioral history.

[2008] The emotion engine provides the results of the analysis to the prompt generator to adjust the generated prompts.

[2009] Providing and Using Prompts

[2010] 1. The prompt provider uses an input means to enter a prompt they have created and sends it from their terminal to the server.

[2011] The server stores the received prompts in a database.

[2012] Other users can use the search function to find and use your prompt.

[2013] The terminal sends prompt usage data to the server.

[2014] The server records the number of uses and calculates the reward.

[2015] The server notifies the provider of the calculated reward and processes the payment of the reward.

[2016] Specific examples

[2017] 1. User Registration and Login

[2018] The user enters their name, email address, and password on the new registration page. The device sends the entered information to the server, which validates it and stores it in the database. After saving, the message "Registration Complete" is displayed.

[2019] 2. Prompt search and selection

[2020] The user types "Generate blog content" and the server searches for and displays a list of relevant prompt templates. The user selects "Blog prompt for product reviews."

[2021] 3. Emotion Recognition and Prompt Generation

[2022] The server generates and displays a follow-up question: "What product would you like to review?" The user responds with "A new smartphone" and submits the response. The server generates a specific prompt, sends it to the device, and displays it to the user.

[2023] The emotion engine analyzes the user's emotions based on their input and behavioral history, and then generates prompts based on the results. For example, if the user expresses anxiety, the prompts will be softer and more reassuring.

[2024] 4. Providing and Using Prompts

[2025] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt using the search function and record the number of times it is used, the server calculates a reward and pays it to the provider.

[2026] The system embodying the present invention provides a mechanism that allows users to easily obtain appropriate prompts and prompt providers to receive rewards, and also provides more appropriate prompts by recognizing the user's emotions and reflecting them in the generation of prompts.

[2027] The processing flow will be explained below.

[2028] Step 1:

[2029] A user visits the sign-up page and enters their name, email address, and password.

[2030] The terminal transmits the input information to the server.

[2031] Step 2:

[2032] Validate the information received by the server.

[2033] Check the email address format

[2034] Password Strength Check

[2035] Check for required fields

[2036] Step 3:

[2037] The server saves the validated information to the database.

[2038] After the server has completed saving, it returns a "Registration Complete" message to the terminal.

[2039] Step 4:

[2040] The user enters their email address and password on the login page.

[2041] The terminal sends the input data to the server.

[2042] Step 5:

[2043] The server checks the authentication information received.

[2044] Hashed password verification

[2045] Generate a session or JWT token upon successful authentication.

[2046] Step 6:

[2047] The server sends the session information along with a message of successful authentication to the terminal.

[2048] The user is redirected to the dashboard page.

[2049] Step 7:

[2050] The user types what they want to do (e.g., "generate blog content") into the search bar.

[2051] The terminal transmits the entered search keyword to the server.

[2052] Step 8:

[2053] The server searches the database for relevant prompt templates and returns the results to the terminal.

[2054] The terminal displays the received data and the user selects the appropriate template.

[2055] Step 9:

[2056] The server generates an additional question form based on the selected template and sends it to the terminal.

[2057] The user answers the additional questions and transmits the answer data from the terminal to the server.

[2058] Step 10:

[2059] The server uses the user's answers to generate specific prompts tailored to the particular task.

[2060] The server sends the generated specific prompt to the terminal for presentation to the user.

[2061] Step 11:

[2062] The emotion engine analyzes emotions based on user input and behavioral history.

[2063] The emotion engine extracts emotional information from the input.

[2064] The emotion engine analyzes emotions inferred from the user's operation history.

[2065] Step 12:

[2066] The emotion engine sends the analysis results to the server.

[2067] The server adjusts the prompts based on the emotional information.

[2068] Step 13:

[2069] A prompt provider inputs a prompt that he or she has created using an input means and transmits it from the terminal to the server.

[2070] The server stores the received prompts in a database.

[2071] Step 14:

[2072] Other users can use the search function to find and use your prompt.

[2073] The terminal sends prompt usage data to the server.

[2074] Step 15:

[2075] The server records the number of uses.

[2076] The server calculates the reward based on the number of recorded uses.

[2077] Step 16:

[2078] The server notifies the prompt provider of the calculated reward and processes the payment of the reward.

[2079] As a result, a system that combines an emotion engine will operate effectively, matching users of generative AI with prompt providers and improving AI services.

[2080] Example 2

[2081] 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."

[2082] It takes a lot of time and effort for users of generative AI to efficiently search, select, generate, and use prompts that best suit their purposes. Furthermore, since prompts cannot be generated taking into account the user's emotions, it is difficult to provide appropriate prompts. Furthermore, there is no well-established system for prompt providers to receive appropriate compensation, making it difficult to promote the provision of high-quality prompts.

[2083] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: input means for a user of the generative artificial intelligence to input and select what he or she wants to do; search means for searching for a relevant prompt template based on information received from the input means; display means for displaying the prompt template searched by the search means; prompt generation means for generating a specific prompt corresponding to a specific task based on the user's answer to additional questions; execution means for executing a task using the prompt generated by the prompt generation means; posting means for a prompt provider to post a prompt created by the prompt provider; storage means for storing the prompt posted by the posting means in a database so that other users can search for it; recording means for recording the number of times a prompt is used by the execution means; reward calculation means for calculating a fee based on the number of times it is used recorded by the recording means and paying a reward to the prompt provider; and emotion recognition means for recognizing emotions from the user's input content and behavioral history and reflecting the result in prompt generation. This enables users to efficiently obtain, generate, and use prompts that suit their purposes, and also enables prompts to be generated that correspond to emotions, thereby enabling accurate reward payment to prompt providers.

[2084] "Input means" refers to the means by which users of generative artificial intelligence input and select what they want to do.

[2085] The "search means" is a means for searching for a relevant prompt template based on the information received from the input means.

[2086] The "display means" is a means for displaying the prompt template retrieved by the retrieval means.

[2087] A "prompt generation means" is a means for generating a specific prompt corresponding to a specific task by having the user answer additional questions.

[2088] The "execution means" is a means for executing a task using the prompt generated by the prompt generation means.

[2089] A "posting means" is a means for a prompt provider to post a prompt that they have created.

[2090] The "storage means" is a means for storing the prompt posted by the posting means in a database so that other users can search for it.

[2091] The "recording means" is a means for recording the number of times a prompt is used when it is used by the execution means.

[2092] The "reward calculation means" is a means for calculating a fee based on the number of uses recorded by the recording means and paying a fee to the prompt provider.

[2093] The "emotion recognition means" is a means for recognizing the user's emotions from their input content and behavioral history, and reflecting the results in generating prompts.

[2094] This invention relates to a system that enables users of generative artificial intelligence to efficiently search, generate, and use appropriate prompts. The system transfers data between a server, a terminal, and a user, enabling the provision of prompts that are optimal for the user's purpose.

[2095] System configuration

[2096] The system includes the following hardware and software:

[2097] 1. The server has the basic computer infrastructure to run a database management system, an authentication system, an emotion recognition engine, etc. Specifically, it is equipped with a database management system such as MySQL, an authentication system using JWT, and an emotion recognition engine that performs natural language processing.

[2098] 2. A terminal is an interface through which a user accesses the system and inputs and receives various information. This includes web browsers and mobile applications.

[2099] 3. The user is responsible for inputting what they want to do with the system and for selecting, generating, and using prompts.

[2100] Program processing description

[2101] User Registration and Login

[2102] 1. A user accesses the new registration page and enters their name, email address, and password. The device then sends the entered information to the server. The server validates the entered information and saves it in the database. After saving is complete, a "Registration Complete" message is returned to the device.

[2103] 2. When the user enters their email address and password on the login page, the device sends this to the server, which checks the authentication information and, if successful, generates a session or JWT token and allows login.

[2104] Prompted Search and Select

[2105] 1. When a user enters what they want to do (e.g., "generate blog content") into the search bar, the device sends the search keywords to the server. The server searches the database for relevant prompt templates and returns the results to the device. The device displays them, and the user can select an appropriate template.

[2106] Emotion Recognition and Prompt Generation

[2107] 1. The server generates an additional question form based on the selected template and sends it to the terminal. The user answers the question and the answer data is sent from the terminal to the server. The server analyzes the answer and generates a specific prompt.

[2108] 2. The emotion engine analyzes the user's input and behavioral history in real time and provides the results to the server, which then uses the emotion information to send more personalized prompts to the device and present them to the user.

[2109] Providing and Using Prompts

[2110] 1. The prompt provider creates a prompt using an input method and sends it from the terminal to the server, which stores the prompt in a database.

[2111] 2. Other users use the search function to find and use the prompt. The device sends usage data to the server, which records the number of uses, calculates the reward, and pays it to the provider.

[2112] Specific examples

[2113] Example 1: User registration and login

[2114] A user enters the name "Taro Tanaka," the email address "tanaka@example.com," and the password "password123" on the new registration page. The entered information is sent from the device to the server and stored in the database. After that, the "Registration Complete" message is displayed.

[2115] Example 2: Prompted search and select

[2116] A user types "blog content generation" in the search bar, the server searches for relevant prompt templates and displays a list on the device. If the user selects "blog prompt for product review", its details are displayed.

[2117] Example 3: Emotion recognition and prompt generation

[2118] The server generates and displays a follow-up question: "Which product would you like to review?" The user answers "A new smartphone" and submits the question. The server generates a specific prompt and displays the message: "To write a review of a new smartphone, please use the following structure as a guide."

[2119] The emotion engine analyzes the user's emotions based on their input and behavioral history, and if the user expresses anxiety, for example, the prompts are softened to provide a sense of security.

[2120] Example 4: Providing and using prompts

[2121] A prompt provider posts a "prompt for a travel guidebook," and the server stores it in a database. When other users use the prompt in the search function, the number of uses is recorded, and the server calculates and pays the provider a reward.

[2122] This system provides a mechanism for users to easily obtain appropriate prompts and for providers to receive rewards, and also generates prompts that take into account the user's emotions.

[2123] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2124] Step 1: User Registration

[2125] 1. A user visits the sign-up page and enters their name, email address, and password.

[2126] Input: Name, Email Address, Password

[2127] The terminal transmits the input information to the server.

[2128] Validate the information received by the server.

[2129] Data processing: Email address format check, password strength check, etc.

[2130] The server saves the data that passes the validation in the database.

[2131] Output: "Registration complete" message

[2132] The server returns a "registration complete" message to the terminal.

[2133] The device will display a "Registration complete" message.

[2134] Step 2: Log in

[2135] 1. The user enters their email address and password on the login page.

[2136] Input: Email address, password

[2137] The terminal sends the input data to the server.

[2138] The server checks the received authentication information against a database.

[2139] Data calculation: Email address and password matching

[2140] If authentication is successful, a session or JWT token is generated.

[2141] Output: Session ID or JWT token

[2142] The server returns a session ID or JWT token to the device.

[2143] The terminal notifies the user that authentication was successful.

[2144] Step 3: Prompted Search

[2145] 1. The user types what they want to do (e.g., "generate blog content") into the search bar.

[2146] Input: Search keyword

[2147] The device sends the search keywords to the server.

[2148] The server retrieves the relevant prompt template from the database.

[2149] Data calculations: keyword matching, relevance score calculation

[2150] Output: Search result list

[2151] The server returns the search results to the device.

[2152] Your device will display a list of search results.

[2153] Step 4: Prompt details and selection

[2154] 1. The user selects the appropriate template from the displayed list.

[2155] Input: Selected template

[2156] The device sends the selection to the server.

[2157] The server retrieves the details of the selected template from the database.

[2158] Data processing: Obtaining detailed template information

[2159] Output: Template details

[2160] The server returns detailed information about the template to the terminal.

[2161] The device will display more information.

[2162] Step 5: Emotion recognition and prompt generation

[2163] 1. The server generates a follow-up question form based on the selected template.

[2164] Input: Selected template

[2165] Data processing: Generation of additional question form

[2166] A question form is sent to the terminal and displayed.

[2167] The user answers the questions and inputs the answer data.

[2168] Input: Answer data to questions

[2169] The terminal transmits the response data to the server.

[2170] The server analyzes the received answers and generates specific prompts.

[2171] Data arithmetic: Response analysis, prompt generation

[2172] Output: Specific prompt

[2173] The server generates a prompt and sends it to the terminal for display.

[2174] The emotion recognition means analyzes the user's responses and behavior history and provides emotion information to the server.

[2175] The server adjusts the prompts based on the emotional information.

[2176] Step 6: Provide a prompt

[2177] 1. The prompt provider creates a prompt using an input means and sends it from the terminal to the server.

[2178] Input: Created prompt

[2179] The terminal sends the input data to the server.

[2180] The server stores the received prompts in a database.

[2181] Data Transformation: Save Prompt

[2182] Output: Save completion notification

[2183] The server sends a save completion notification to the terminal.

[2184] Step 7: Use prompts

[2185] 1. Other users find your prompt using the search feature.

[2186] Input: Search keyword

[2187] The device sends the search keywords to the server.

[2188] The server retrieves the relevant prompt from the database.

[2189] Data calculations: keyword matching, relevance score calculation

[2190] Output: Search result list

[2191] The server returns the search results to the device.

[2192] Your device will display a list of search results.

[2193] The user selects and uses the prompt.

[2194] Input: Selected prompt

[2195] The device sends usage data to the server.

[2196] The server records the number of uses.

[2197] Data processing: Recording number of uses

[2198] A reward calculation means calculates and pays a reward to the prompt provider.

[2199] Data calculation: Reward calculation

[2200] Output: Reward amount

[2201] The server processes the reward payment and notifies the provider.

[2202] (Application example 2)

[2203] 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."

[2204] Conventional generative AI systems do not consider emotions when generating specific prompts, limiting their ability to improve the user experience. Even when users prefer to use voice input to generate and display prompts using smart devices, they face difficulties converting the speech into text and processing it appropriately. Furthermore, feedback on generated prompts is lacking, leading to ineffective reward calculations for prompt providers. There is a need to address these issues and provide a more interactive and user-friendly system.

[2205] 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.

[2206] In this invention, the server includes: an input means for inputting and selecting what a user of the generative artificial intelligence wants to do; a search means for searching for a relevant prompt template based on information received from the input means; a display means for displaying the prompt template searched by the search means; a prompt generation means for generating a specific prompt corresponding to a specific task in response to a user's answer to additional questions; an execution means for executing a task using the prompt generated by the prompt generation means; a posting means for a prompt provider to post a prompt created by the prompt provider; a storage means for storing the posted prompt in a database so that other users can search for the prompt; a recording means for recording the number of times a prompt is used by the execution means; a reward calculation means for calculating a fee based on the number of times the prompt is used and paying a reward to the prompt provider; an emotion engine for recognizing a user's emotions; an adjustment means for adjusting the display content or prompt content based on emotion information analyzed by the emotion engine; a speech recognition means for converting a user's voice input into text; and an edge device means for generating and displaying prompts via a smart device. This enables prompt generation and display that take the user's emotions into consideration, thereby enabling smooth prompt operation on a smart device using voice input. Furthermore, it is possible to realize appropriate reward calculation for prompt providers, and to provide a more interactive and user-friendly system.

[2207] "Generative AI" is an AI system that automatically generates content such as text and images based on user input and selections.

[2208] "Input means" refers to an interface that allows a user to input or select what they want to do, and includes a keyboard, touch screen, voice recognition, etc.

[2209] A "search mechanism" is an algorithm or system for searching for relevant prompt templates based on information received from an input mechanism.

[2210] A "display means" is a device or interface for visually presenting retrieved prompt templates and generated prompts to a user.

[2211] A "prompt generator" is a system or algorithm that generates specific prompts for a particular task based on the user's answers to follow-up questions.

[2212] The "execution means" is a function for executing a specific task using the prompt generated by the prompt generation means.

[2213] The "posting means" is an interface for inputting and sending a prompt created by a prompt provider.

[2214] The "storage means" is a system for storing prompts posted by the posting means in a database so that other users can search for them.

[2215] A "recording means" is a system or algorithm for tracking and recording the number of times a prompt is used by the execution means.

[2216] The "reward calculation means" is a system for calculating compensation based on the number of uses recorded by the recording means and providing a reward to the prompt provider.

[2217] An "emotion engine" is software or algorithms that analyze and recognize emotions based on user input and behavioral history.

[2218] The "adjustment means" is a function for adjusting the display content or prompt content based on the emotion information analyzed by the emotion engine.

[2219] A "speech recognizer" is a system or algorithm for converting a user's voice input into text.

[2220] An "edge device means" is a local or network-connected device for generating and displaying prompts through a smart device.

[2221] The present invention is a system that uses generative artificial intelligence to generate and display appropriate prompts while taking into account the user's emotions. This system is intended for use as a shopping assistant application on smart devices.

[2222] Program processing

[2223] The program in this system mainly exchanges data between the server and the smart device (e.g., smart glasses). Each element is explained below.

[2224] User Registration and Login

[2225] 1. The user registers by entering their name, email address, and password using voice input or touch gestures on their smart device. The device sends the entered information to the server, which validates the received information and stores it in the database. After saving, the message "Registration Complete" appears on the smart device's display.

[2226] Prompted Search and Select

[2227] 1. The user uses the voice input function of the smart device to say, for example, "I'd like to know reviews of the new smartphone." The device converts this voice data into text using a speech recognition method (e.g., Google Speech-to-Text API) and sends the search keywords to the server. The server searches for relevant prompt templates in its database and returns the results to the device. The smart device then displays the results on its screen, and the user selects the appropriate template.

[2228] Emotion Recognition and Prompt Generation

[2229] 1. The server generates additional questions based on the selected template and sends them to the smart device. The user answers by voice, and the device converts the voice into text and sends it to the server. The server analyzes the received answer data and generates a specific prompt (e.g., "Show me reviews of Apple's latest smartphones"). The generated specific prompt is then displayed on the smart device.

[2230] 2. An emotion engine (e.g., Microsoft Azure Emotion API) analyzes the user's tone of voice and behavioral history to determine their emotions. If the user expresses anxiety, the generated prompt content is adjusted to be more reassuring (e.g., "You can check the information with peace of mind. Here is a review of Apple's latest smartphone").

[2231] Providing and Using Prompts

[2232] 1. Prompt providers enter and submit prompts through a web interface, and the server stores them in a database, making them available for other users to find and use using the search function on their smart devices.

[2233] 2. When a prompt is used, the terminal transmits usage data to the server, which records the number of times the prompt is used. Based on the recorded data, the reward calculation means calculates the compensation and provides a reward to the prompt provider.

[2234] Specific examples

[2235] User Registration and Login

[2236] The user speaks into the smart device, "New registration, name: User A, email address: usera@example.com, password: password123." The device converts the voice to text and sends it to the server, completing the registration.

[2237] Prompted Search and Select

[2238] The user speaks into their smart device, saying, "I'd like to know reviews of the new smartphone." The device converts the speech into text, and the server returns a template, such as "Reviews of Apple's latest smartphone," which is then displayed.

[2239] Emotion Recognition and Prompt Generation

[2240] The server generates the question "What brand are you looking for?" and displays it on the smart device. The user responds with "Apple," and the voice data is converted into text and sent to the server. The server generates a prompt and sends it to the device. If the emotion engine detects anxiety in the user's tone of voice, it adjusts the prompt and displays, "You can rest assured that we're here to help you. We'll show you reviews of Apple's latest smartphones."

[2241] Prompt Sentence Examples

[2242] "Please enter the brand name of the smartphone you want to see reviews for."

[2243] The system is analyzing user sentiment...

[2244] "Please check out our review of Apple's latest smartphone here. If you have any questions, please let us know."

[2245] This system enables prompt generation and display that takes the user's emotions into account, allowing for smooth prompt operation on smart devices using voice input. It also provides an interactive and user-friendly system that appropriately calculates rewards for prompt providers.

[2246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2247] Step 1:

[2248] The user registers by enteri...

Claims

1. An input means for users of the generative artificial intelligence to input and select what they want to do; a search means for searching for relevant prompt templates based on the information received from the input means; a display means for displaying the prompt template searched by the search means; a prompt generation means for generating specific prompts corresponding to a particular task by answering additional questions from the user; execution means for executing a task using the prompt generated by the prompt generation means; a posting means for posting a prompt created by a prompt provider; a storage means for storing the prompt posted by the posting means in a database so that other users can search for the prompt; a recording means for recording the number of times a prompt is used when the prompt is used by the execution means; and a reward calculation means for calculating a fee based on the number of times the prompt is used recorded by the recording means and paying a reward to the prompt provider.

2. 2. The system of claim 1, wherein the prompt generator includes a question generator for generating a follow-up question associated with the prompt template.

3. 2. The system according to claim 1, wherein said reward calculation means has a function of automatically calculating a reward for each use and adding credits to the provider's account.

Images