System

Abstract

A system is provided.SOLUTION: A system, comprising: a user terminal inputting a question and selecting an advisor; an application server receiving and analyzing the question and advisor information; the application server sending a request to a generative artificial intelligence model server based on the analysis result; the generative artificial intelligence model server generating an advice based on the request; the generative artificial intelligence model server returning the generated advice to the application server; the application server sending the returned advice to the user terminal; and the user terminal displaying the advice.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] Describe the "problem that the invention aims to solve" and the "means for solving the problem."

[0005] ---

[0006] When people reach a crossroads in their lives, many hope to receive accurate advice from celebrities, but few have the opportunity to receive such advice directly. Furthermore, advice based on existing generative AI models suffers from low credibility and inaccuracy. Therefore, there is a need for a system that can provide appropriate advice to users using reliable official information. [Means for solving the problem]

[0007] The present invention provides a system including a question and advisor selection means input by a user terminal, a means for an application server to receive and analyze the question and advisor information, a means for sending a request to a generating artificial intelligence model server based on the analysis results, a means for the generating artificial intelligence model server to generate advice based on the request, a means for the generating artificial intelligence model server to return the advice generated by the generating artificial intelligence model server to the application server, a means for the application server to send the returned advice to the user terminal, and a means for the user terminal to display the advice. The generating artificial intelligence model server uses a model that has learned the quotes, personal experiences, and past advice of multiple famous people, and provides advice based on the quotes, personal experiences, and past advice of the advisor selected by the user terminal, making it possible to provide the user with appropriate advice based on reliable information.

[0008] ---

[0009] ---

[0010] A "user terminal" is an information processing device that a user uses to input a question and select an advisor.

[0011] The "application server" is an intermediate processing device that analyzes questions and advisor information sent from a user terminal and sends a request to the generation artificial intelligence model server.

[0012] The "generative artificial intelligence model server" is an information processing device that generates advice based on a user's question using an artificial intelligence model that has learned the famous quotes, personal experiences, and past advice of multiple famous people.

[0013] A "question" is a question about a problem or concern the user is facing.

[0014] "Advisors" are famous people who provide quotes and personal experiences that users can choose from when seeking advice.

[0015] "Analysis" refers to understanding and appropriately processing data based on the user's input questions and selected advisors.

[0016] "Generate" refers to the AI ​​model generating appropriate advice in response to a user's question.

[0017] "Return" refers to sending the generated advice back to the application server that originally sent it.

[0018] "Display" refers to the user terminal presenting the received advice in a visually visible form to the user.

[0019] --- [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] ---

[0042] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Specifically, it includes the following processes.

[0043] First, the user inputs a question using a terminal and selects the desired advisor from the provided list. This information is sent from the user terminal to the application server. The sent data includes the user ID, the question, and the information of the selected advisor.

[0044] The application server receives the data sent from the user terminal, analyzes the question content and the selected advisor, and based on the analysis results, constructs and sends a request to the generation artificial intelligence model server.

[0045] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous words, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[0046] The application server then formats the received advice and sends it back to the user terminal, which visually displays the received advice to the user.

[0047] For example, if a user enters the question "I'm worried about my career path. What should I do?" and selects "Mr. A" as an advisor, the system will operate as follows:

[0048] 1. The user selects a question and "Mr. A" through the device.

[0049] 2. The user device sends the question data and selected advisor information to the application server.

[0050] 3. The application server analyzes the received data and sends a request to an artificial intelligence model based on "Mr. A."

[0051] 4. The generation AI model server generates advice using a model that has learned from Mr. A's famous quotes, personal experiences, and past advice.

[0052] 5. The generated AI model server returns the generated advice to the application server.

[0053] 6. The application server formats the advice and sends it to the user device.

[0054] 7. The user device displays the advice and provides "Mr. A's" advice to the user.

[0055] In this way, the system of the present invention can provide reliable advice to the user.

[0056] ---

[0057] The processing flow will be explained below.

[0058] ---

[0059] Step 1:

[0060] The user uses a terminal to enter a question and selects an advisor from a provided list.

[0061] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. A."

[0062] Step 2:

[0063] The user terminal transmits the input question and the information of the selected advisor to the application server.

[0064] Specifically, a data packet containing the user ID, the question, and information about the selected advisor is generated and sent to the application server.

[0065] Step 3:

[0066] The application server receives the data sent from the user terminal.

[0067] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[0068] Step 4:

[0069] The application server parses the received data and extracts the question and the selected advisor information.

[0070] Specifically, the question content and advisor information are extracted from the data packet and preparations for the next process are made.

[0071] Step 5:

[0072] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[0073] Specifically, a request including the extracted question and advisor information is generated and sent to the generation artificial intelligence model server.

[0074] Step 6:

[0075] A generating artificial intelligence model server receives the request sent from the application server.

[0076] Specifically, the request data is received and the content is analyzed.

[0077] Step 7:

[0078] A generative artificial intelligence model server generates advice based on the request using quotes, experiences, and past advice of the designated advisor.

[0079] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice for the question.

[0080] Step 8:

[0081] The generating artificial intelligence model server returns the generated advice to the application server.

[0082] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[0083] Step 9:

[0084] The application server formats the received advice for transmission to the user terminal.

[0085] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[0086] Step 10:

[0087] The application server sends the formatted advice to the user terminal.

[0088] Specifically, the generated data packet is transmitted to the user terminal.

[0089] Step 11:

[0090] The user terminal displays the received advice to the user.

[0091] Specifically, advice is output to a display interface so that the user can visually confirm it.

[0092] ---

[0093] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[0094] Example 1

[0095] 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."

[0096] Conventional advice-giving systems lack the flexibility to provide appropriate advice for individual user questions. In particular, it is difficult to provide specific advice based on famous quotes or personal experiences from specific experts. To solve this problem, a system is needed that utilizes the knowledge and experience of experts selected by the user to provide customized advice for each individual question.

[0097] 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.

[0098] In this invention, the server includes a means for selecting questions and proposers input by a user terminal, a means for an application server to receive and analyze the questions and proposer information, and a means for the application server to send a request to a generative AI model server based on the analysis results. This makes it possible to quickly and accurately provide appropriate advice based on the quotes and experiences of selected experts in response to questions individually input by users.

[0099] "User terminal" refers to a device on which a user inputs questions and selects proposers, and includes PCs, smartphones, tablets, etc.

[0100] The "proposer selection means" is a function or interface that allows a user to select a desired proposer from multiple proposers (such as experts).

[0101] The "application server" is a central processing unit that receives and analyzes the question content and proposer information sent from the user terminal.

[0102] The "means for receiving and analyzing" is a function by which the application server receives data from the user terminal and analyzes its contents.

[0103] The "generative artificial intelligence model server" is a server that operates an AI model to generate advice based on analyzed information.

[0104] The "means for sending a request" is a function by which the application server sends data to the artificial intelligence model server based on the analysis results.

[0105] The "means for generating advice" is a function in which the artificial intelligence model server generates advice for a user's question based on the famous quotes, personal experiences, and past advice of a designated proposer.

[0106] The "means for returning" is a function for transmitting the advice generated by the generating artificial intelligence model server to the application server.

[0107] The "formatting means" is a function that formats the advice received by the application server into a format that is easy to display on the user terminal.

[0108] The "display means" is a function that allows the user terminal to visually present the advice sent from the application server to the user.

[0109] "Famous quotes, personal experiences, and past advice" refers to useful words, stories based on experience, and advice given by the proposer in the past.

[0110] The present invention is a system that uses a user terminal, an application server, and a generative artificial intelligence model server to provide appropriate advice based on the quotes, personal experiences, and past advice of a proposer selected by the user.

[0111] Overall system configuration

[0112] The system consists of three main hardware and software components:

[0113] User devices: Devices such as PCs, smartphones, tablets, etc. These devices operate through a web browser or dedicated applications.

[0114] Application server: This server runs on a cloud service such as Amazon Web Services (AWS) or Google Cloud Platform (GCP) and handles the main processing such as receiving and analyzing data. The backend is built using Python or Node.js.

[0115] Generative AI model server: This server utilizes generative AI models such as OpenAI's GPT-3 and BERT. This server is essential for generating advice.

[0116] Software used and data processing

[0117] 1. User device operation

[0118] A user accesses the system using a terminal, inputs a question, and selects the desired proposer from the provided list. For example, a user inputs a question such as "I'm worried about my career path. What should I do?" and selects "Mr. A" as the proposer.

[0119] 2. Data transmission

[0120] The user terminal sends the entered question and the selected proposer information to the application server as JSON format data.

[0121] json

[0122] {

[0123] "userID": "user123",

[0124] "question": "I'm worried about my career path. What should I do?"

[0125] "advisor": "Mr. A"

[0126] }

[0127] 3. Data analysis and request generation

[0128] The application server analyzes the received data and constructs a request to the generative AI model based on the question and the proposer. Specifically, it generates the following prompt:

[0129] Prompt: "You are a well-known career counselor, Mr. A. The user's question is, 'I'm worried about my career path. What should I do?' Please provide appropriate advice based on Mr. A's past advice and famous quotes."

[0130] This prompt sentence is sent to the generation AI model server.

[0131] 4. Generating Advice

[0132] The generation AI model server generates advice for the user's question based on the received prompt sentence, taking into account the famous quotes, personal experiences, and past advice of the designated proposer. For example, the generated advice might look like this:

[0133] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[0134] 5. Formatting and Submission of Advice

[0135] The application server receives the generated advice, formats it into a format that is easy to display on the user terminal, and then transmits the formatted advice to the user terminal.

[0136] 6. Displaying Advice

[0137] The user device visually displays the received advice to the user, for example, on the device screen as follows:

[0138] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[0139] This system allows users to get fast, reliable advice.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] The user enters a question and selects a proposer

[0143] A user accesses the system using a terminal, inputs a question, and selects a desired proposer from a provided list.

[0144] Specific behavior:

[0145] A user types into an input field, "I'm having trouble deciding on my career path. What should I do?"

[0146] The user selects "Mr. A" from the drop-down list.

[0147] The user clicks the "Submit" button.

[0148] Input: User's question and selected proposer information

[0149] Output: Data including question content and proposer information

[0150] Step 2:

[0151] The device sends data to the application server

[0152] The device sends the question entered by the user and the information of the selected proposer to the application server. The data sent is in JSON format and includes the user ID, question, and information of the selected proposer.

[0153] Specific behavior:

[0154] The terminal generates JSON data and sends it to the application server as an HTTP POST request.

[0155] Input: Question content entered by the user and selected proposer information

[0156] Output: JSON data sent to the application server

[0157] Step 3:

[0158] The application server analyzes the data and sends a request to the AI ​​model server

[0159] The application server analyzes the received data and constructs and sends a request to the generative AI model based on the question content and proposer information.

[0160] Specific behavior:

[0161] The application server analyzes the received JSON data and extracts the question content and proposer information.

[0162] The application server generates a prompt sentence and sends it to the generation AI model server as an HTTP POST request.

[0163] Input: Received JSON data (including question content and proposer information)

[0164] Output: The prompt sent to the generative AI model server

[0165] Step 4:

[0166] Generative AI model server generates advice

[0167] The generation AI model server generates advice for the user's question based on the received prompt sentence and by referring to the designated proposer's famous quotes, personal experiences, and past advice.

[0168] Specific behavior:

[0169] The generative AI model server parses the prompt sentence and generates advice using the AI ​​model.

[0170] The generated advice is sent back to the application server.

[0171] Input: prompt statement

[0172] Output: Generated advice

[0173] Step 5:

[0174] The application server formats the advice and sends it to the user terminal.

[0175] The application server formats the advice received from the generation AI model server and sends it back to the user's device. The advice is formatted in a format that is easy to display on the user's device.

[0176] Specific behavior:

[0177] The application server takes the received advice and formats it into HTML.

[0178] The formatted advice is sent to the user device as an HTTP response.

[0179] Input: Generated advice

[0180] Output: Formatted advice

[0181] Step 6:

[0182] The user device displays the advice.

[0183] The user terminal visually displays the received advice to the user, who then checks the presented advice to obtain an answer to their question.

[0184] Specific behavior:

[0185] The user terminal receives the advice in HTML format and displays it on the screen.

[0186] Input: Formatted advice

[0187] Output: Advice displayed to the user

[0188] In this way, the system executes a series of processes to provide prompt and accurate advice in response to a user's question.

[0189] (Application example 1)

[0190] 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."

[0191] Conventional advice-giving systems have the problem that it is difficult for users to receive appropriate advice based on famous quotes or advice from specific celebrities. Furthermore, when users use different devices, such as smartphones, there is a lack of a way to display advice in a visually easy-to-read format. This results in a poor user experience.

[0192] 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.

[0193] In this invention, the server includes a question and advisor selection means input by a user terminal, a means for an application server to receive and analyze the question and advisor information, a means for the application server to send a request to a generating artificial intelligence model server based on the analysis result, a means for the generating artificial intelligence model server to generate advice based on the request, a means for the generating artificial intelligence model server to return the advice generated by the generating artificial intelligence model server to the application server, a means for the application server to send the returned advice to the user terminal, and a means for the user terminal to display the advice. This enables a user to easily receive advice based on the quotes and advice of a selected celebrity using a mobile device such as a smartphone, and display the advice in a visually easy-to-read format.

[0194] A "user terminal" is a device that a user uses to input questions and select advisors, and specifically, is a mobile device such as a smartphone.

[0195] "Application Server" refers to a central processing system for receiving questions and advisor information sent from user terminals, analyzing the information, and sending requests to the generation artificial intelligence model server.

[0196] The "generative artificial intelligence model server" is a server that references the famous quotes, personal experiences, and advice information of designated advisors to generate advice in response to user questions.

[0197] The "question and advisor selection means" is a means for a user to input a question through a terminal and select a desired advisor.

[0198] The "means for analyzing" refers to a means for analyzing the question and advisor information received by the application server and generating a request to an appropriate AI model.

[0199] The "means for sending a request" is a means by which the application server sends a request to the generation artificial intelligence model server based on the analysis results.

[0200] The "means for generating advice" refers to the means by which the artificial intelligence model server generates appropriate advice in response to a user's question based on a designated advisor.

[0201] The "means for returning advice" is a means for returning advice generated by the generating artificial intelligence model server to the application server.

[0202] The "means for sending advice" refers to the means by which the application server sends the generated advice to the user terminal.

[0203] The "means for displaying advice" refers to a means for visually displaying the advice received by the user terminal to the user.

[0204] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. This system will be described in detail below.

[0205] First, the user inputs a question using a user device such as a smartphone and selects the desired advisor from a provided list. This information is sent from the user device to the application server. The data sent includes the user ID, question content, and information about the selected advisor. The hardware used is a smartphone, and the software used by the user to input information is assumed to be a user interface (UI) application.

[0206] The application server receives the data sent from the user's device and analyzes the question and the selected advisor. Based on the analysis results, the application server constructs and sends a request to the generative AI model server. Here, it is assumed that requests between servers will be processed using a programming language such as Python.

[0207] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server. A high-performance natural language processing model such as GPT-4 could be used as the generative AI model. An example of a prompt sentence is, "A user is requesting advice from Mr. B about stress caused by excessive work. Please advise the user on how to deal with stress from Mr. B's perspective."

[0208] The application server then formats the received advice and sends it back to the user's device, where the application on the smartphone visually displays the advice to the user, allowing the user to easily receive reliable advice based on the quotes and experiences of the selected celebrity.

[0209] For example, if a user types in the question "I'm having trouble deciding on my career path. What should I do?" and selects "famous business leader" as their advisor, the following will happen:

[0210] 1. The user selects a question and a "famous business leader" via smartphone.

[0211] 2. The user terminal sends the question data and selected advisor information to the application server.

[0212] 3. The application server analyzes the incoming data and sends a request to an AI model based on "famous business leaders."

[0213] 4. The generation AI model server generates advice using a model that has learned from quotes, personal experiences, and past advice from "famous business leaders."

[0214] 5. The generated AI model server returns the generated advice to the application server.

[0215] 6. The application server formats the advice and sends it to the user terminal.

[0216] 7. The user's device will display advice and provide the user with advice from "famous business leaders."

[0217] This allows the system of the present invention to provide reliable advice to users and improve the user experience.

[0218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0219] Step 1:

[0220] The user inputs a question and the desired advisor using a user device such as a smartphone. The input data includes the user ID, question content, and information about the selected advisor. This data is then sent to the application server using a communication protocol. The input data (question information, advisor information) from the user device is collected through the interface.

[0221] Step 2:

[0222] The user terminal sends the entered question data and selected advisor information to the application server. This transmission is carried out via a communication protocol such as an HTTP request. The data sent from the user terminal to the application server includes the user ID, question content, and selected advisor information.

[0223] Step 3:

[0224] The application server analyzes the question and advisor information received from the user device. During the analysis, natural language processing (NLP) is used to understand the question in detail and identify the user's intention. The application server analyzes the user ID, question content, and advisor information, and builds data to generate a request to the generation artificial intelligence model server.

[0225] Step 4:

[0226] Based on the analysis results, the application server sends a request to the generative AI model server. This request includes the question content and information about the selected advisor. The data sent is in a format that includes a prompt sentence to generate appropriate advice for the generative AI model. For example, it may include the following: "The user is worried about his / her career path. Please give us some advice from the perspective of the specified advisor."

[0227] Step 5:

[0228] The generative AI model server receives the request and generates advice for the user's question by referencing the database of the specified advisor. Here, a generative AI model (e.g., GPT-4) is used to generate appropriate advice based on the prompt. The generative AI model server receives the question content and advisor information as input, generates advice, and outputs it.

[0229] Step 6:

[0230] The generating AI model server returns the generated advice to the application server. This return is made via an HTTP response containing the generated advice data. The generated advice is sent to the application server, and the advice content is returned either as is or in a formatted form.

[0231] Step 7:

[0232] The application server formats the received advice and sends it to the user's device. In this step, the advice content is formatted so that it is easy for the user to understand visually. The application server sends the formatted advice data to the user's device and provides it as an HTTP response.

[0233] Step 8:

[0234] The user device displays the advice received from the application server. The user device displays the advice content in a visually easy-to-understand format, allowing the user to receive appropriate advice. The display on the user device uses methods such as text display and infographics.

[0235] The above steps create a system that allows users to easily receive reliable advice based on their questions.

[0236] 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.

[0237] ---

[0238] This system uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[0239] Specifically, the process includes the following:

[0240] First, the user inputs a question using the terminal and selects the desired advisor from the provided list. The user terminal is further equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotion information. This information (question content, selected advisor, emotion information) is sent from the user terminal to the application server.

[0241] The application server receives the data sent from the user terminal and analyzes the question content, advisor information, and emotion information. Based on the analysis results, the application server constructs and sends a request to the generation AI model server, which also includes the user's emotion information.

[0242] Based on the received request, the generative artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[0243] The application server then formats the received advice and sends it back to the user terminal, which displays the received advice to the user.

[0244] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will operate as follows:

[0245] 1. The user selects a question and "Mr. B" through the device, and the emotion engine recognizes the user's emotional state as "anxiety."

[0246] 2. The user terminal sends the question data, selected advisor information, and emotion information to the application server.

[0247] 3. The application server analyzes the received data and sends a request to an AI model based on "Mr. B," including the emotional information "anxiety."

[0248] 4. The artificial intelligence model server generates advice taking into account Mr. B's "anxiety" using a model that has learned from his famous quotes, personal experiences, and past advice.

[0249] 5. The generated AI model server returns the generated advice to the application server.

[0250] 6. The application server formats the received advice and sends it to the user terminal.

[0251] 7. The user device displays the advice and provides "Mr. B"'s advice to the user.

[0252] In this way, the system of the present invention can provide reliable advice that takes into account the user's emotional state.

[0253] ---

[0254] The processing flow will be explained below.

[0255] ---

[0256] Step 1:

[0257] The user uses a terminal to enter a question and selects an advisor from a provided list.

[0258] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. B."

[0259] Step 2:

[0260] The emotion engine installed in the user's device recognizes the user's emotions from their facial expressions, tone of voice, content of the text, etc.

[0261] Specifically, the system uses a camera, microphone, and text analysis algorithm to determine that the user's emotion is "anxiety."

[0262] Step 3:

[0263] The user terminal transmits the question content, the selected advisor information, and the emotion information to the application server.

[0264] Specifically, a data packet containing the user ID, question content, information about the selected advisor, and emotion information is generated and sent to the application server.

[0265] Step 4:

[0266] The application server receives the data sent from the user terminal.

[0267] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[0268] Step 5:

[0269] The application server analyzes the received data and extracts the question content, advisor information, and emotion information.

[0270] Specifically, the question content, advisor information, and emotion information are extracted from the data packet, and preparations for the next process are made.

[0271] Step 6:

[0272] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[0273] Specifically, a request including the extracted question, advisor information, and emotion information is generated and sent to the generation artificial intelligence model server.

[0274] Step 7:

[0275] A generating artificial intelligence model server receives the request sent from the application server.

[0276] Specifically, the request data is received and the content is analyzed.

[0277] Step 8:

[0278] The generation artificial intelligence model server uses quotes, experiences, and past advice of the advisor specified based on the request to generate advice that takes into account the user's emotional information.

[0279] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice to alleviate the "anxiety."

[0280] Step 9:

[0281] The generating artificial intelligence model server returns the generated advice to the application server.

[0282] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[0283] Step 10:

[0284] The application server formats the received advice for transmission to the user terminal.

[0285] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[0286] Step 11:

[0287] The application server sends the formatted advice to the user terminal.

[0288] Specifically, the generated data packet is transmitted to the user terminal.

[0289] Step 12:

[0290] The user terminal displays the received advice to the user.

[0291] Specifically, advice is output to a display interface so that the user can visually confirm it.

[0292] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will provide advice based on "Mr. B's" famous quotes and experiences, such as, "When you feel anxious, it's important to believe in yourself and keep moving forward."

[0293] ---

[0294] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[0295] Example 2

[0296] 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."

[0297] In today's world, people face a wide variety of problems and worries, and they need ways to get appropriate advice. However, there are few systems that can provide advice that is optimal for individual situations and emotional states, and efficient solutions do not exist. In particular, advanced technology is required to generate appropriate advice that takes into account the user's emotional state. This makes it difficult for users to instantly receive advice that is most appropriate for their situation.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0299] In this invention, the server includes a question and advisor selection means input by the user terminal, a means for recognizing the user's emotional state in real time and generating emotional information, a means for the application server to receive and analyze the question, advisor information, and emotional information, and a means for the application server to send a request to the generation artificial intelligence model server based on the analysis result, thereby making it possible to instantly provide advanced and personalized advice based on the user's emotional state and selected advisor.

[0300] A "user terminal" is a device used by a user to input data, such as a smartphone or PC.

[0301] "Advisor selection means" refers to an interface or function that allows a user to select a desired advisor.

[0302] An "emotion engine" refers to software or hardware that recognizes a user's emotional state in real time and generates emotional information.

[0303] "Application server" refers to a server that receives and analyzes data sent from a user terminal and acts as a relay for communication with other servers.

[0304] "Generative AI model server" refers to a server that generates advice using an AI model based on data and returns it to other servers.

[0305] "Analysis means" refers to the functions and software used to analyze received data and extract and organize necessary information.

[0306] "Means for sending requests" refers to the functions and processes for sending requests to other servers based on the analyzed data.

[0307] A "famous quote" is a highly valued and widely known expression or statement spoken by a famous person or expert.

[0308] "Testimonials" refer to information that describes events that individuals have experienced and the insights they have gained from them.

[0309] "Prior advice" refers to advice or suggestions that an advisor has previously provided in a particular situation.

[0310] MODE FOR CARRYING OUT THE INVENTION

[0311] This invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on the quotes, personal experiences, and past advice of an advisor selected by the user. In addition, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[0312] Hardware and software used

[0313] User device: Devices such as smartphones and computers

[0314] Emotion engine: Software that recognizes the user's emotional state in real time, such as "Amazon Rekognition" and "Microsoft Azure Emotion API"

[0315] Application server: A server that runs on a cloud service (e.g., AWS, GCP)

[0316] Generative AI model server: A server that generates advice using AI models, such as "OpenAI GPT" generative AI models

[0317] Specific operation of the system

[0318] 1. Enter your question and select an advisor

[0319] Users use a terminal to enter their question and select their preferred advisor from a list provided.

[0320] Example: A user types into the device, "I'm having trouble deciding on my career path. What should I do?" and selects "Mr. B."

[0321] 2. Collecting emotional information

[0322] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[0323] Example: An emotion engine analyzes a user's facial and voice data and recognizes that the user is "anxious."

[0324] 3. Data transmission

[0325] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[0326] Specifically, the device sends the following data:

[0327] Q: I'm having trouble deciding on my career path. What should I do?

[0328] Advisor: Mr. B

[0329] Emotion: Anxiety

[0330] 4. Data Analysis

[0331] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[0332] Based on the results of this analysis, the necessary data is sent as a request to the generative artificial intelligence model server that holds the AI ​​model.

[0333] 5. Generating Advice

[0334] Based on the received request, the generation artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice.

[0335] Example: Based on past quotes and advice from "Mr. B," the model generates advice such as, "To overcome your anxiety, it is important to first set small goals."

[0336] 6. Advice Format

[0337] The application server formats the received advice and sends it back to the user terminal.

[0338] 7. Displaying Advice

[0339] The user terminal displays the received advice to the user.

[0340] For example, the following advice will be displayed on the terminal screen:

[0341] To overcome your anxiety, it's important to start by setting small goals.

[0342] Mr. B

[0343] Prompt Sentence Examples

[0344] An example of a prompt to input to the generative AI model is as follows:

[0345] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[0346] In this way, the system can provide highly accurate advice based on the user's emotional state as well as the information of the selected advisor.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Program processing flow and specific explanation

[0349] Step 1: Enter your question and choose an advisor

[0350] Users enter their questions using a device such as a smartphone or computer and select the advisor of their choice from a list provided.

[0351] Input: Text data question: "I'm worried about my career path. What should I do?", selected advisor: "Mr. B"

[0352] Output: Question and advisor information

[0353] Specific operation: The user enters a question into a text box on the terminal interface and selects an advisor using a drop-down list or button.

[0354] Step 2: Collecting emotional information

[0355] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[0356] Input: User's face and voice data

[0357] Output: Emotional information (e.g., "anxiety")

[0358] What it does: An emotion engine (e.g., Microsoft Azure Emotion API) analyzes data from the user's camera and microphone and identifies the user as "anxious."

[0359] Step 3: Sending data

[0360] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[0361] Input: Question content, advisor information, emotional information

[0362] Output: Sends data to the application server as an HTTP POST request

[0363] Specific operation: The data including the question "I'm worried about my career path. What should I do?", advisor "Mr. B", and emotion "anxiety" is sent to the application server in JSON format.

[0364] Step 4: Analyze the data

[0365] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[0366] Input: Data sent from the device (question content, advisor information, emotional information)

[0367] Output: Structured information of the parsed data

[0368] What happens: The application server parses the received JSON data and extracts information from the question, advisor, and sentiment fields.

[0369] Step 5: Building the Request

[0370] The application server constructs a request based on the analyzed data to be sent to the generation artificial intelligence model server.

[0371] Input: Analyzed data (question content, advisor information, emotional information)

[0372] Output: Prompt sentence to the generative AI model

[0373] Specific behavior: Generates a prompt like this:

[0374] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[0375] Step 6: Generating Advice

[0376] The generation artificial intelligence model server receives a request from the application server and generates advice based on the specified advisor's famous words, personal experiences, and past advice.

[0377] Input: Prompt sentence for generative AI model

[0378] Output: Generated advice

[0379] How it works: A generative AI model (e.g., OpenAI GPT-3) analyzes the prompt and generates advice based on quotes and personal experiences related to "Mr. B," such as "To overcome your anxiety, it's important to first set small goals."

[0380] Step 7: Formatting the advice

[0381] The application server formats the received advice into an appropriate format and sends it back to the user terminal.

[0382] Input: Advice returned from the generative AI model server

[0383] Output: Formatted advice

[0384] Specific behavior: The advice is formatted and sent as an HTTP response in a user-friendly format.

[0385] Step 8: Viewing Advice

[0386] The user terminal displays the advice received from the application server to the user.

[0387] Input: formatted advice

[0388] Output: Advice displayed to the user

[0389] What happens: The following message will be displayed on the device screen:

[0390] To overcome your anxiety, it's important to start by setting small goals.

[0391] Mr. B

[0392] Through the above processing steps, the system is able to provide highly accurate advice that takes into account the user's questions and emotions.

[0393] (Application example 2)

[0394] 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."

[0395] Previously, there were systems that provided expert advice when users purchased products online, but they had the problem of not being able to provide individualized support that took into account the user's emotional state. Providing appropriate advice in response to changes in emotions would improve the user's purchasing experience, but such a system had not yet been realized.

[0396] 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.

[0397] In this invention, the server includes: a question and advisor selection means input by a user terminal; a means for an application server to receive and analyze the question and advisor information; a means for the application server to send a request to a generative artificial intelligence model server based on the analysis result; a means for the generative artificial intelligence model server to generate advice based on the request; a means for the generative artificial intelligence model server to return the advice generated by the generative artificial intelligence model server to the application server; a means for the application server to send the returned advice to the user terminal; a means for the user terminal to display the advice; a means for the user terminal to have an emotion engine installed, to recognize the user's emotional state in real time and generate emotion information; a means for the application server to include the emotion information in the request; and a means for the generative artificial intelligence model server to generate advice taking the emotion information into consideration. This enables individual advice that takes the user's emotional state into consideration.

[0398] The "user terminal" is a device where users can input questions and select advisors. It also has an emotion engine and is capable of recognizing the user's emotional state in real time.

[0399] An "application server" is a device that analyzes questions and advisor information received from a user terminal and sends a request to the artificial intelligence model generation server based on the analysis results.

[0400] The "generative artificial intelligence model server" is a device that generates advice based on a request from the application server and returns the generated advice to the application server.

[0401] An "emotion engine" is a function or software that recognizes a user's emotional state in real time and generates emotional information.

[0402] An "advisor" is a celebrity or expert selected by the user who provides advice based on their famous quotes, experiences, and past advice.

[0403] A "question" is a consultation or question entered by a user.

[0404] "Advice" refers to answers or suggestions generated by the generative artificial intelligence model server taking into account the user's question and emotional state.

[0405] "Emotion information" is data that represents the user's emotional state, recognized and generated by the emotion engine.

[0406] A "request" is request data including question content, advisor information, and emotion information, sent from the application server to the generation artificial intelligence model server.

[0407] "Analysis" is the process by which the application server processes the question and advisor information received from the user and generates a request to the appropriate generative artificial intelligence model server.

[0408] The present invention is a system that provides advice that takes into account emotional states using a user terminal, an application server, and a generative artificial intelligence model server. The system of the present invention allows users to receive advice from specific celebrities or experts, and uses an emotion engine to provide personalized support based on the user's emotional state.

[0409] The user terminal provides an interface for users to input questions and select advisors. In addition, it is equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotional information. The data obtained from the user terminal (question content, selected advisor, emotional information) is sent to the application server.

[0410] The application server receives the data sent from the user terminal, analyzes the question content and advisor information, and based on the analysis result, constructs an appropriate request to the generative artificial intelligence model server and sends the request including the emotion information.

[0411] The generative AI model server generates advice based on the received request. This server uses a generative AI model that has learned quotes, personal experiences, and past advice from multiple celebrities and experts, and generates optimal advice taking into account the user's emotional information. The generated advice is then sent back from the generative AI model server to the application server.

[0412] The application server formats the returned advice into an appropriate format and sends it to the user terminal, which displays the received advice and provides it to the user.

[0413] For example, if a user inputs the question "I'm having trouble deciding what to buy. What should I do?" and selects "Mr. A" as the advisor, the system will operate as follows: If the emotion engine recognizes that the user's emotion is "anxiety," the system will generate advice that takes "anxiety" into consideration. This allows the user to receive appropriate advice according to their individual emotions.

[0414] Example prompt sentence:

[0415] Input Question: "I'm having trouble making a purchasing decision. What should I do?"

[0416] Selection Advisor: "Mr. A"

[0417] Recognized emotion: "Anxiety"

[0418] Actual advice:

[0419] "It's natural to feel anxious. In Mr. A's words, it's important to gather enough information and take the time to process your emotions."

[0420] In this way, by understanding the user's emotions and responding appropriately, the system can increase user satisfaction.The present invention enables emotion-based personalized responses in online shopping and other virtual experiences.

[0421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0422] Step 1:

[0423] The user terminal inputs a question and selects an advisor. The user inputs the consultation content and question through the application interface and selects the desired advisor from the provided list. This generates information about the user's question and the selected advisor.

[0424] Input: Question, Selected Advisor

[0425] Output: Questions, selected advisor information

[0426] Step 2:

[0427] The user device uses an emotion engine to recognize the user's emotional state and generate emotion information. The emotion engine analyzes the user's emotions in real time and outputs the resulting emotion information.

[0428] Input: User's facial expressions and voice information

[0429] Output: Emotional information (e.g., anxiety, joy, excitement, etc.)

[0430] Step 3:

[0431] The user terminal transmits the question content, selected advisor information, and emotion information to the application server, which then aggregates the necessary data.

[0432] Input: Question, selected advisor information, sentiment information

[0433] Output: Sending data to the application server

[0434] Step 4:

[0435] The application server analyzes the received data and constructs an appropriate request to the generative AI model server. The server analyzes the question content and advisor information, and generates a request including emotion information based on the results.

[0436] Input: Question, selected advisor information, sentiment information

[0437] Output: Request to the generative AI model server

[0438] Step 5:

[0439] The generative AI model server receives the request and generates advice based on the specified advisor's quotes, experiences, and advice. The generative AI model uses the learned data and takes emotional information into account to generate appropriate advice.

[0440] Input: Question, selected advisor information, sentiment information

[0441] Output: Advice

[0442] Step 6:

[0443] The generating artificial intelligence model server sends the generated advice back to the application server, which then prepares the generated advice to be provided to the user.

[0444] Input: Advice

[0445] Output: Advice returned to the application server

[0446] Step 7:

[0447] The application server formats the received advice and sends it to the user's terminal, where it is formatted in a format that can be displayed.

[0448] Input: Advice

[0449] Output: Formatted advice, sent to user terminal

[0450] Step 8:

[0451] The user's device will display the received advice, allowing the user to refer to the displayed advice and obtain the necessary information.

[0452] Input: Formatted advice

[0453] Output: Advice displayed to the user

[0454] 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.

[0455] 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.

[0456] 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.

[0457] [Second embodiment]

[0458] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0469] 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."

[0470] ---

[0471] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Specifically, it includes the following processes.

[0472] First, the user inputs a question using a terminal and selects the desired advisor from the provided list. This information is sent from the user terminal to the application server. The sent data includes the user ID, the question, and the information of the selected advisor.

[0473] The application server receives the data sent from the user terminal, analyzes the question content and the selected advisor, and based on the analysis results, constructs and sends a request to the generation artificial intelligence model server.

[0474] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous words, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[0475] The application server then formats the received advice and sends it back to the user terminal, which visually displays the received advice to the user.

[0476] For example, if a user enters the question "I'm worried about my career path. What should I do?" and selects "Mr. A" as an advisor, the system will operate as follows:

[0477] 1. The user selects a question and "Mr. A" through the device.

[0478] 2. The user device sends the question data and selected advisor information to the application server.

[0479] 3. The application server analyzes the received data and sends a request to an artificial intelligence model based on "Mr. A."

[0480] 4. The generation AI model server generates advice using a model that has learned from Mr. A's famous quotes, personal experiences, and past advice.

[0481] 5. The generated AI model server returns the generated advice to the application server.

[0482] 6. The application server formats the advice and sends it to the user device.

[0483] 7. The user device displays the advice and provides "Mr. A's" advice to the user.

[0484] In this way, the system of the present invention can provide reliable advice to the user.

[0485] ---

[0486] The processing flow will be explained below.

[0487] ---

[0488] Step 1:

[0489] The user uses a terminal to enter a question and selects an advisor from a provided list.

[0490] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. A."

[0491] Step 2:

[0492] The user terminal transmits the input question and the information of the selected advisor to the application server.

[0493] Specifically, a data packet containing the user ID, the question, and information about the selected advisor is generated and sent to the application server.

[0494] Step 3:

[0495] The application server receives the data sent from the user terminal.

[0496] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[0497] Step 4:

[0498] The application server parses the received data and extracts the question and the selected advisor information.

[0499] Specifically, the question content and advisor information are extracted from the data packet and preparations for the next process are made.

[0500] Step 5:

[0501] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[0502] Specifically, a request including the extracted question and advisor information is generated and sent to the generation artificial intelligence model server.

[0503] Step 6:

[0504] A generating artificial intelligence model server receives the request sent from the application server.

[0505] Specifically, the request data is received and the content is analyzed.

[0506] Step 7:

[0507] A generative artificial intelligence model server generates advice based on the request using quotes, experiences, and past advice of the designated advisor.

[0508] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice for the question.

[0509] Step 8:

[0510] The generating artificial intelligence model server returns the generated advice to the application server.

[0511] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[0512] Step 9:

[0513] The application server formats the received advice for transmission to the user terminal.

[0514] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[0515] Step 10:

[0516] The application server sends the formatted advice to the user terminal.

[0517] Specifically, the generated data packet is transmitted to the user terminal.

[0518] Step 11:

[0519] The user terminal displays the received advice to the user.

[0520] Specifically, advice is output to a display interface so that the user can visually confirm it.

[0521] ---

[0522] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[0523] Example 1

[0524] 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."

[0525] Conventional advice-giving systems lack the flexibility to provide appropriate advice for individual user questions. In particular, it is difficult to provide specific advice based on famous quotes or personal experiences from specific experts. To solve this problem, a system is needed that utilizes the knowledge and experience of experts selected by the user to provide customized advice for each individual question.

[0526] 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.

[0527] In this invention, the server includes a means for selecting questions and proposers input by a user terminal, a means for an application server to receive and analyze the questions and proposer information, and a means for the application server to send a request to a generative AI model server based on the analysis results. This makes it possible to quickly and accurately provide appropriate advice based on the quotes and experiences of selected experts in response to questions individually input by users.

[0528] "User terminal" refers to a device on which a user inputs questions and selects proposers, and includes PCs, smartphones, tablets, etc.

[0529] The "proposer selection means" is a function or interface that allows a user to select a desired proposer from multiple proposers (such as experts).

[0530] The "application server" is a central processing unit that receives and analyzes the question content and proposer information sent from the user terminal.

[0531] The "means for receiving and analyzing" is a function by which the application server receives data from the user terminal and analyzes its contents.

[0532] The "generative artificial intelligence model server" is a server that operates an AI model to generate advice based on analyzed information.

[0533] The "means for sending a request" is a function by which the application server sends data to the artificial intelligence model server based on the analysis results.

[0534] The "means for generating advice" is a function in which the artificial intelligence model server generates advice for a user's question based on the famous quotes, personal experiences, and past advice of a designated proposer.

[0535] The "means for returning" is a function for transmitting the advice generated by the generating artificial intelligence model server to the application server.

[0536] The "formatting means" is a function that formats the advice received by the application server into a format that is easy to display on the user terminal.

[0537] The "display means" is a function that allows the user terminal to visually present the advice sent from the application server to the user.

[0538] "Famous quotes, personal experiences, and past advice" refers to useful words, stories based on experience, and advice given by the proposer in the past.

[0539] The present invention is a system that uses a user terminal, an application server, and a generative artificial intelligence model server to provide appropriate advice based on the quotes, personal experiences, and past advice of a proposer selected by the user.

[0540] Overall system configuration

[0541] The system consists of three main hardware and software components:

[0542] User devices: Devices such as PCs, smartphones, tablets, etc. These devices operate through a web browser or dedicated applications.

[0543] Application server: This server runs on a cloud service such as Amazon Web Services (AWS) or Google Cloud Platform (GCP) and handles the main processing such as receiving and analyzing data. The backend is built using Python or Node.js.

[0544] Generative AI model server: This server utilizes generative AI models such as OpenAI's GPT-3 and BERT. This server is essential for generating advice.

[0545] Software used and data processing

[0546] 1. User device operation

[0547] A user accesses the system using a terminal, inputs a question, and selects the desired proposer from the provided list. For example, a user inputs a question such as "I'm worried about my career path. What should I do?" and selects "Mr. A" as the proposer.

[0548] 2. Data transmission

[0549] The user terminal sends the entered question and the selected proposer information to the application server as JSON format data.

[0550] json

[0551] {

[0552] "userID": "user123",

[0553] "question": "I'm worried about my career path. What should I do?"

[0554] "advisor": "Mr. A"

[0555] }

[0556] 3. Data analysis and request generation

[0557] The application server analyzes the received data and constructs a request to the generative AI model based on the question and the proposer. Specifically, it generates the following prompt:

[0558] Prompt: "You are a well-known career counselor, Mr. A. The user's question is, 'I'm worried about my career path. What should I do?' Please provide appropriate advice based on Mr. A's past advice and famous quotes."

[0559] This prompt sentence is sent to the generation AI model server.

[0560] 4. Generating Advice

[0561] The generation AI model server generates advice for the user's question based on the received prompt sentence, taking into account the famous quotes, personal experiences, and past advice of the designated proposer. For example, the generated advice might look like this:

[0562] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[0563] 5. Formatting and Submission of Advice

[0564] The application server receives the generated advice, formats it into a format that is easy to display on the user terminal, and then transmits the formatted advice to the user terminal.

[0565] 6. Displaying Advice

[0566] The user device visually displays the received advice to the user, for example, on the device screen as follows:

[0567] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[0568] This system allows users to get fast, reliable advice.

[0569] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0570] Step 1:

[0571] The user enters a question and selects a proposer

[0572] A user accesses the system using a terminal, inputs a question, and selects a desired proposer from a provided list.

[0573] Specific behavior:

[0574] A user types into an input field, "I'm having trouble deciding on my career path. What should I do?"

[0575] The user selects "Mr. A" from the drop-down list.

[0576] The user clicks the "Submit" button.

[0577] Input: User's question and selected proposer information

[0578] Output: Data including question content and proposer information

[0579] Step 2:

[0580] The device sends data to the application server

[0581] The device sends the question entered by the user and the information of the selected proposer to the application server. The data sent is in JSON format and includes the user ID, question, and information of the selected proposer.

[0582] Specific behavior:

[0583] The terminal generates JSON data and sends it to the application server as an HTTP POST request.

[0584] Input: Question content entered by the user and selected proposer information

[0585] Output: JSON data sent to the application server

[0586] Step 3:

[0587] The application server analyzes the data and sends a request to the AI ​​model server

[0588] The application server analyzes the received data and constructs and sends a request to the generative AI model based on the question content and proposer information.

[0589] Specific behavior:

[0590] The application server analyzes the received JSON data and extracts the question content and proposer information.

[0591] The application server generates a prompt sentence and sends it to the generation AI model server as an HTTP POST request.

[0592] Input: Received JSON data (including question content and proposer information)

[0593] Output: The prompt sent to the generative AI model server

[0594] Step 4:

[0595] Generative AI model server generates advice

[0596] The generation AI model server generates advice for the user's question based on the received prompt sentence and by referring to the designated proposer's famous quotes, personal experiences, and past advice.

[0597] Specific behavior:

[0598] The generative AI model server parses the prompt sentence and generates advice using the AI ​​model.

[0599] The generated advice is sent back to the application server.

[0600] Input: prompt statement

[0601] Output: Generated advice

[0602] Step 5:

[0603] The application server formats the advice and sends it to the user terminal.

[0604] The application server formats the advice received from the generation AI model server and sends it back to the user's device. The advice is formatted in a format that is easy to display on the user's device.

[0605] Specific behavior:

[0606] The application server takes the received advice and formats it into HTML.

[0607] The formatted advice is sent to the user device as an HTTP response.

[0608] Input: Generated advice

[0609] Output: Formatted advice

[0610] Step 6:

[0611] The user device displays the advice.

[0612] The user terminal visually displays the received advice to the user, who then checks the presented advice to obtain an answer to their question.

[0613] Specific behavior:

[0614] The user terminal receives the advice in HTML format and displays it on the screen.

[0615] Input: Formatted advice

[0616] Output: Advice displayed to the user

[0617] In this way, the system executes a series of processes to provide prompt and accurate advice in response to a user's question.

[0618] (Application example 1)

[0619] 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."

[0620] Conventional advice-giving systems have the problem that it is difficult for users to receive appropriate advice based on famous quotes or advice from specific celebrities. Furthermore, when users use different devices, such as smartphones, there is a lack of a way to display advice in a visually easy-to-read format. This results in a poor user experience.

[0621] 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.

[0622] In this invention, the server includes a question and advisor selection means input by a user terminal, a means for an application server to receive and analyze the question and advisor information, a means for the application server to send a request to a generating artificial intelligence model server based on the analysis result, a means for the generating artificial intelligence model server to generate advice based on the request, a means for the generating artificial intelligence model server to return the advice generated by the generating artificial intelligence model server to the application server, a means for the application server to send the returned advice to the user terminal, and a means for the user terminal to display the advice. This enables a user to easily receive advice based on the quotes and advice of a selected celebrity using a mobile device such as a smartphone, and display the advice in a visually easy-to-read format.

[0623] A "user terminal" is a device that a user uses to input questions and select advisors, and specifically, is a mobile device such as a smartphone.

[0624] "Application Server" refers to a central processing system for receiving questions and advisor information sent from user terminals, analyzing the information, and sending requests to the generation artificial intelligence model server.

[0625] The "generative artificial intelligence model server" is a server that references the famous quotes, personal experiences, and advice information of designated advisors to generate advice in response to user questions.

[0626] The "question and advisor selection means" is a means for a user to input a question through a terminal and select a desired advisor.

[0627] The "means for analyzing" refers to a means for analyzing the question and advisor information received by the application server and generating a request to an appropriate AI model.

[0628] The "means for sending a request" is a means by which the application server sends a request to the generation artificial intelligence model server based on the analysis results.

[0629] The "means for generating advice" refers to the means by which the artificial intelligence model server generates appropriate advice in response to a user's question based on a designated advisor.

[0630] The "means for returning advice" is a means for returning advice generated by the generating artificial intelligence model server to the application server.

[0631] The "means for sending advice" refers to the means by which the application server sends the generated advice to the user terminal.

[0632] The "means for displaying advice" refers to a means for visually displaying the advice received by the user terminal to the user.

[0633] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. This system will be described in detail below.

[0634] First, the user inputs a question using a user device such as a smartphone and selects the desired advisor from a provided list. This information is sent from the user device to the application server. The data sent includes the user ID, question content, and information about the selected advisor. The hardware used is a smartphone, and the software used by the user to input information is assumed to be a user interface (UI) application.

[0635] The application server receives the data sent from the user's device and analyzes the question and the selected advisor. Based on the analysis results, the application server constructs and sends a request to the generative AI model server. Here, it is assumed that requests between servers will be processed using a programming language such as Python.

[0636] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server. A high-performance natural language processing model such as GPT-4 could be used as the generative AI model. An example of a prompt sentence is, "A user is requesting advice from Mr. B about stress caused by excessive work. Please advise the user on how to deal with stress from Mr. B's perspective."

[0637] The application server then formats the received advice and sends it back to the user's device, where the application on the smartphone visually displays the advice to the user, allowing the user to easily receive reliable advice based on the quotes and experiences of the selected celebrity.

[0638] For example, if a user types in the question "I'm having trouble deciding on my career path. What should I do?" and selects "famous business leader" as their advisor, the following will happen:

[0639] 1. The user selects a question and a "famous business leader" via smartphone.

[0640] 2. The user terminal sends the question data and selected advisor information to the application server.

[0641] 3. The application server analyzes the incoming data and sends a request to an AI model based on "famous business leaders."

[0642] 4. The generation AI model server generates advice using a model that has learned from quotes, personal experiences, and past advice from "famous business leaders."

[0643] 5. The generated AI model server returns the generated advice to the application server.

[0644] 6. The application server formats the advice and sends it to the user terminal.

[0645] 7. The user's device will display advice and provide the user with advice from "famous business leaders."

[0646] This allows the system of the present invention to provide reliable advice to users and improve the user experience.

[0647] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0648] Step 1:

[0649] The user inputs a question and the desired advisor using a user device such as a smartphone. The input data includes the user ID, question content, and information about the selected advisor. This data is then sent to the application server using a communication protocol. The input data (question information, advisor information) from the user device is collected through the interface.

[0650] Step 2:

[0651] The user terminal sends the entered question data and selected advisor information to the application server. This transmission is carried out via a communication protocol such as an HTTP request. The data sent from the user terminal to the application server includes the user ID, question content, and selected advisor information.

[0652] Step 3:

[0653] The application server analyzes the question and advisor information received from the user device. During the analysis, natural language processing (NLP) is used to understand the question in detail and identify the user's intention. The application server analyzes the user ID, question content, and advisor information, and builds data to generate a request to the generation artificial intelligence model server.

[0654] Step 4:

[0655] Based on the analysis results, the application server sends a request to the generative AI model server. This request includes the question content and information about the selected advisor. The data sent is in a format that includes a prompt sentence to generate appropriate advice for the generative AI model. For example, it may include the following: "The user is worried about his / her career path. Please give us some advice from the perspective of the specified advisor."

[0656] Step 5:

[0657] The generative AI model server receives the request and generates advice for the user's question by referencing the database of the specified advisor. Here, a generative AI model (e.g., GPT-4) is used to generate appropriate advice based on the prompt. The generative AI model server receives the question content and advisor information as input, generates advice, and outputs it.

[0658] Step 6:

[0659] The generating AI model server returns the generated advice to the application server. This return is made via an HTTP response containing the generated advice data. The generated advice is sent to the application server, and the advice content is returned either as is or in a formatted form.

[0660] Step 7:

[0661] The application server formats the received advice and sends it to the user's device. In this step, the advice content is formatted so that it is easy for the user to understand visually. The application server sends the formatted advice data to the user's device and provides it as an HTTP response.

[0662] Step 8:

[0663] The user device displays the advice received from the application server. The user device displays the advice content in a visually easy-to-understand format, allowing the user to receive appropriate advice. The display on the user device uses methods such as text display and infographics.

[0664] The above steps create a system that allows users to easily receive reliable advice based on their questions.

[0665] 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.

[0666] ---

[0667] This system uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[0668] Specifically, the process includes the following:

[0669] First, the user inputs a question using the terminal and selects the desired advisor from the provided list. The user terminal is further equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotion information. This information (question content, selected advisor, emotion information) is sent from the user terminal to the application server.

[0670] The application server receives the data sent from the user terminal and analyzes the question content, advisor information, and emotion information. Based on the analysis results, the application server constructs and sends a request to the generation AI model server, which also includes the user's emotion information.

[0671] Based on the received request, the generative artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[0672] The application server then formats the received advice and sends it back to the user terminal, which displays the received advice to the user.

[0673] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will operate as follows:

[0674] 1. The user selects a question and "Mr. B" through the device, and the emotion engine recognizes the user's emotional state as "anxiety."

[0675] 2. The user terminal sends the question data, selected advisor information, and emotion information to the application server.

[0676] 3. The application server analyzes the received data and sends a request to an AI model based on "Mr. B," including the emotional information "anxiety."

[0677] 4. The artificial intelligence model server generates advice taking into account Mr. B's "anxiety" using a model that has learned from his famous quotes, personal experiences, and past advice.

[0678] 5. The generated AI model server returns the generated advice to the application server.

[0679] 6. The application server formats the received advice and sends it to the user terminal.

[0680] 7. The user device displays the advice and provides "Mr. B"'s advice to the user.

[0681] In this way, the system of the present invention can provide reliable advice that takes into account the user's emotional state.

[0682] ---

[0683] The processing flow will be explained below.

[0684] ---

[0685] Step 1:

[0686] The user uses a terminal to enter a question and selects an advisor from a provided list.

[0687] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. B."

[0688] Step 2:

[0689] The emotion engine installed in the user's device recognizes the user's emotions from their facial expressions, tone of voice, content of the text, etc.

[0690] Specifically, the system uses a camera, microphone, and text analysis algorithm to determine that the user's emotion is "anxiety."

[0691] Step 3:

[0692] The user terminal transmits the question content, the selected advisor information, and the emotion information to the application server.

[0693] Specifically, a data packet containing the user ID, question content, information about the selected advisor, and emotion information is generated and sent to the application server.

[0694] Step 4:

[0695] The application server receives the data sent from the user terminal.

[0696] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[0697] Step 5:

[0698] The application server analyzes the received data and extracts the question content, advisor information, and emotion information.

[0699] Specifically, the question content, advisor information, and emotion information are extracted from the data packet, and preparations for the next process are made.

[0700] Step 6:

[0701] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[0702] Specifically, a request including the extracted question, advisor information, and emotion information is generated and sent to the generation artificial intelligence model server.

[0703] Step 7:

[0704] A generating artificial intelligence model server receives the request sent from the application server.

[0705] Specifically, the request data is received and the content is analyzed.

[0706] Step 8:

[0707] The generation artificial intelligence model server uses quotes, experiences, and past advice of the advisor specified based on the request to generate advice that takes into account the user's emotional information.

[0708] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice to alleviate the "anxiety."

[0709] Step 9:

[0710] The generating artificial intelligence model server returns the generated advice to the application server.

[0711] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[0712] Step 10:

[0713] The application server formats the received advice for transmission to the user terminal.

[0714] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[0715] Step 11:

[0716] The application server sends the formatted advice to the user terminal.

[0717] Specifically, the generated data packet is transmitted to the user terminal.

[0718] Step 12:

[0719] The user terminal displays the received advice to the user.

[0720] Specifically, advice is output to a display interface so that the user can visually confirm it.

[0721] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will provide advice based on "Mr. B's" famous quotes and experiences, such as, "When you feel anxious, it's important to believe in yourself and keep moving forward."

[0722] ---

[0723] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[0724] Example 2

[0725] 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."

[0726] In today's world, people face a wide variety of problems and worries, and they need ways to get appropriate advice. However, there are few systems that can provide advice that is optimal for individual situations and emotional states, and efficient solutions do not exist. In particular, advanced technology is required to generate appropriate advice that takes into account the user's emotional state. This makes it difficult for users to instantly receive advice that is most appropriate for their situation.

[0727] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0728] In this invention, the server includes a question and advisor selection means input by the user terminal, a means for recognizing the user's emotional state in real time and generating emotional information, a means for the application server to receive and analyze the question, advisor information, and emotional information, and a means for the application server to send a request to the generation artificial intelligence model server based on the analysis result, thereby making it possible to instantly provide advanced and personalized advice based on the user's emotional state and selected advisor.

[0729] A "user terminal" is a device used by a user to input data, such as a smartphone or PC.

[0730] "Advisor selection means" refers to an interface or function that allows a user to select a desired advisor.

[0731] An "emotion engine" refers to software or hardware that recognizes a user's emotional state in real time and generates emotional information.

[0732] "Application server" refers to a server that receives and analyzes data sent from a user terminal and acts as a relay for communication with other servers.

[0733] "Generative AI model server" refers to a server that generates advice using an AI model based on data and returns it to other servers.

[0734] "Analysis means" refers to the functions and software used to analyze received data and extract and organize necessary information.

[0735] "Means for sending requests" refers to the functions and processes for sending requests to other servers based on the analyzed data.

[0736] A "famous quote" is a highly valued and widely known expression or statement spoken by a famous person or expert.

[0737] "Testimonials" refer to information that describes events that individuals have experienced and the insights they have gained from them.

[0738] "Prior advice" refers to advice or suggestions that an advisor has previously provided in a particular situation.

[0739] MODE FOR CARRYING OUT THE INVENTION

[0740] This invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on the quotes, personal experiences, and past advice of an advisor selected by the user. In addition, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[0741] Hardware and software used

[0742] User device: Devices such as smartphones and computers

[0743] Emotion engine: Software that recognizes the user's emotional state in real time, such as "Amazon Rekognition" and "Microsoft Azure Emotion API"

[0744] Application server: A server that runs on a cloud service (e.g., AWS, GCP)

[0745] Generative AI model server: A server that generates advice using AI models, such as "OpenAI GPT" generative AI models

[0746] Specific operation of the system

[0747] 1. Enter your question and select an advisor

[0748] Users use a terminal to enter their question and select their preferred advisor from a list provided.

[0749] Example: A user types into the device, "I'm having trouble deciding on my career path. What should I do?" and selects "Mr. B."

[0750] 2. Collecting emotional information

[0751] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[0752] Example: An emotion engine analyzes a user's facial and voice data and recognizes that the user is "anxious."

[0753] 3. Data transmission

[0754] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[0755] Specifically, the device sends the following data:

[0756] Q: I'm having trouble deciding on my career path. What should I do?

[0757] Advisor: Mr. B

[0758] Emotion: Anxiety

[0759] 4. Data Analysis

[0760] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[0761] Based on the results of this analysis, the necessary data is sent as a request to the generative artificial intelligence model server that holds the AI ​​model.

[0762] 5. Generating Advice

[0763] Based on the received request, the generation artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice.

[0764] Example: Based on past quotes and advice from "Mr. B," the model generates advice such as, "To overcome your anxiety, it is important to first set small goals."

[0765] 6. Advice Format

[0766] The application server formats the received advice and sends it back to the user terminal.

[0767] 7. Displaying Advice

[0768] The user terminal displays the received advice to the user.

[0769] For example, the following advice will be displayed on the terminal screen:

[0770] To overcome your anxiety, it's important to start by setting small goals.

[0771] Mr. B

[0772] Prompt Sentence Examples

[0773] An example of a prompt to input to the generative AI model is as follows:

[0774] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[0775] In this way, the system can provide highly accurate advice based on the user's emotional state as well as the information of the selected advisor.

[0776] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0777] Program processing flow and specific explanation

[0778] Step 1: Enter your question and choose an advisor

[0779] Users enter their questions using a device such as a smartphone or computer and select the advisor of their choice from a list provided.

[0780] Input: Text data question: "I'm worried about my career path. What should I do?", selected advisor: "Mr. B"

[0781] Output: Question and advisor information

[0782] Specific operation: The user enters a question into a text box on the terminal interface and selects an advisor using a drop-down list or button.

[0783] Step 2: Collecting emotional information

[0784] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[0785] Input: User's face and voice data

[0786] Output: Emotional information (e.g., "anxiety")

[0787] What it does: An emotion engine (e.g., Microsoft Azure Emotion API) analyzes data from the user's camera and microphone and identifies the user as "anxious."

[0788] Step 3: Sending data

[0789] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[0790] Input: Question content, advisor information, emotional information

[0791] Output: Sends data to the application server as an HTTP POST request

[0792] Specific operation: The data including the question "I'm worried about my career path. What should I do?", advisor "Mr. B", and emotion "anxiety" is sent to the application server in JSON format.

[0793] Step 4: Analyze the data

[0794] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[0795] Input: Data sent from the device (question content, advisor information, emotional information)

[0796] Output: Structured information of the parsed data

[0797] What happens: The application server parses the received JSON data and extracts information from the question, advisor, and sentiment fields.

[0798] Step 5: Building the Request

[0799] The application server constructs a request based on the analyzed data to be sent to the generation artificial intelligence model server.

[0800] Input: Analyzed data (question content, advisor information, emotional information)

[0801] Output: Prompt sentence to the generative AI model

[0802] Specific behavior: Generates a prompt like this:

[0803] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[0804] Step 6: Generating Advice

[0805] The generation artificial intelligence model server receives a request from the application server and generates advice based on the specified advisor's famous words, personal experiences, and past advice.

[0806] Input: Prompt sentence for generative AI model

[0807] Output: Generated advice

[0808] How it works: A generative AI model (e.g., OpenAI GPT-3) analyzes the prompt and generates advice based on quotes and personal experiences related to "Mr. B," such as "To overcome your anxiety, it's important to first set small goals."

[0809] Step 7: Formatting the advice

[0810] The application server formats the received advice into an appropriate format and sends it back to the user terminal.

[0811] Input: Advice returned from the generative AI model server

[0812] Output: Formatted advice

[0813] Specific behavior: The advice is formatted and sent as an HTTP response in a user-friendly format.

[0814] Step 8: Viewing Advice

[0815] The user terminal displays the advice received from the application server to the user.

[0816] Input: formatted advice

[0817] Output: Advice displayed to the user

[0818] What happens: The following message will be displayed on the device screen:

[0819] To overcome your anxiety, it's important to start by setting small goals.

[0820] Mr. B

[0821] Through the above processing steps, the system is able to provide highly accurate advice that takes into account the user's questions and emotions.

[0822] (Application example 2)

[0823] 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."

[0824] Previously, there were systems that provided expert advice when users purchased products online, but they had the problem of not being able to provide individualized support that took into account the user's emotional state. Providing appropriate advice in response to changes in emotions would improve the user's purchasing experience, but such a system had not yet been realized.

[0825] 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.

[0826] In this invention, the server includes: a question and advisor selection means input by a user terminal; a means for an application server to receive and analyze the question and advisor information; a means for the application server to send a request to a generative artificial intelligence model server based on the analysis result; a means for the generative artificial intelligence model server to generate advice based on the request; a means for the generative artificial intelligence model server to return the advice generated by the generative artificial intelligence model server to the application server; a means for the application server to send the returned advice to the user terminal; a means for the user terminal to display the advice; a means for the user terminal to have an emotion engine installed, to recognize the user's emotional state in real time and generate emotion information; a means for the application server to include the emotion information in the request; and a means for the generative artificial intelligence model server to generate advice taking the emotion information into consideration. This enables individual advice that takes the user's emotional state into consideration.

[0827] The "user terminal" is a device where users can input questions and select advisors. It also has an emotion engine and is capable of recognizing the user's emotional state in real time.

[0828] An "application server" is a device that analyzes questions and advisor information received from a user terminal and sends a request to the artificial intelligence model generation server based on the analysis results.

[0829] The "generative artificial intelligence model server" is a device that generates advice based on a request from the application server and returns the generated advice to the application server.

[0830] An "emotion engine" is a function or software that recognizes a user's emotional state in real time and generates emotional information.

[0831] An "advisor" is a celebrity or expert selected by the user who provides advice based on their famous quotes, experiences, and past advice.

[0832] A "question" is a consultation or question entered by a user.

[0833] "Advice" refers to answers or suggestions generated by the generative artificial intelligence model server taking into account the user's question and emotional state.

[0834] "Emotion information" is data that represents the user's emotional state, recognized and generated by the emotion engine.

[0835] A "request" is request data including question content, advisor information, and emotion information, sent from the application server to the generation artificial intelligence model server.

[0836] "Analysis" is the process by which the application server processes the question and advisor information received from the user and generates a request to the appropriate generative artificial intelligence model server.

[0837] The present invention is a system that provides advice that takes into account emotional states using a user terminal, an application server, and a generative artificial intelligence model server. The system of the present invention allows users to receive advice from specific celebrities or experts, and uses an emotion engine to provide personalized support based on the user's emotional state.

[0838] The user terminal provides an interface for users to input questions and select advisors. In addition, it is equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotional information. The data obtained from the user terminal (question content, selected advisor, emotional information) is sent to the application server.

[0839] The application server receives the data sent from the user terminal, analyzes the question content and advisor information, and based on the analysis result, constructs an appropriate request to the generative artificial intelligence model server and sends the request including the emotion information.

[0840] The generative AI model server generates advice based on the received request. This server uses a generative AI model that has learned quotes, personal experiences, and past advice from multiple celebrities and experts, and generates optimal advice taking into account the user's emotional information. The generated advice is then sent back from the generative AI model server to the application server.

[0841] The application server formats the returned advice into an appropriate format and sends it to the user terminal, which displays the received advice and provides it to the user.

[0842] For example, if a user inputs the question "I'm having trouble deciding what to buy. What should I do?" and selects "Mr. A" as the advisor, the system will operate as follows: If the emotion engine recognizes that the user's emotion is "anxiety," the system will generate advice that takes "anxiety" into consideration. This allows the user to receive appropriate advice according to their individual emotions.

[0843] Example prompt sentence:

[0844] Input Question: "I'm having trouble making a purchasing decision. What should I do?"

[0845] Selection Advisor: "Mr. A"

[0846] Recognized emotion: "Anxiety"

[0847] Actual advice:

[0848] "It's natural to feel anxious. In Mr. A's words, it's important to gather enough information and take the time to process your emotions."

[0849] In this way, by understanding the user's emotions and responding appropriately, the system can increase user satisfaction.The present invention enables emotion-based personalized responses in online shopping and other virtual experiences.

[0850] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0851] Step 1:

[0852] The user terminal inputs a question and selects an advisor. The user inputs the consultation content and question through the application interface and selects the desired advisor from the provided list. This generates information about the user's question and the selected advisor.

[0853] Input: Question, Selected Advisor

[0854] Output: Questions, selected advisor information

[0855] Step 2:

[0856] The user device uses an emotion engine to recognize the user's emotional state and generate emotion information. The emotion engine analyzes the user's emotions in real time and outputs the resulting emotion information.

[0857] Input: User's facial expressions and voice information

[0858] Output: Emotional information (e.g., anxiety, joy, excitement, etc.)

[0859] Step 3:

[0860] The user terminal transmits the question content, selected advisor information, and emotion information to the application server, which then aggregates the necessary data.

[0861] Input: Question, selected advisor information, sentiment information

[0862] Output: Sending data to the application server

[0863] Step 4:

[0864] The application server analyzes the received data and constructs an appropriate request to the generative AI model server. The server analyzes the question content and advisor information, and generates a request including emotion information based on the results.

[0865] Input: Question, selected advisor information, sentiment information

[0866] Output: Request to the generative AI model server

[0867] Step 5:

[0868] The generative AI model server receives the request and generates advice based on the specified advisor's quotes, experiences, and advice. The generative AI model uses the learned data and takes emotional information into account to generate appropriate advice.

[0869] Input: Question, selected advisor information, sentiment information

[0870] Output: Advice

[0871] Step 6:

[0872] The generating artificial intelligence model server sends the generated advice back to the application server, which then prepares the generated advice to be provided to the user.

[0873] Input: Advice

[0874] Output: Advice returned to the application server

[0875] Step 7:

[0876] The application server formats the received advice and sends it to the user's terminal, where it is formatted in a format that can be displayed.

[0877] Input: Advice

[0878] Output: Formatted advice, sent to user terminal

[0879] Step 8:

[0880] The user's device will display the received advice, allowing the user to refer to the displayed advice and obtain the necessary information.

[0881] Input: Formatted advice

[0882] Output: Advice displayed to the user

[0883] 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.

[0884] 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.

[0885] 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.

[0886] [Third embodiment]

[0887] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0888] 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.

[0889] 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).

[0890] 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.

[0891] 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.

[0892] 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).

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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."

[0899] ---

[0900] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Specifically, it includes the following processes.

[0901] First, the user inputs a question using a terminal and selects the desired advisor from the provided list. This information is sent from the user terminal to the application server. The sent data includes the user ID, the question, and the information of the selected advisor.

[0902] The application server receives the data sent from the user terminal, analyzes the question content and the selected advisor, and based on the analysis results, constructs and sends a request to the generation artificial intelligence model server.

[0903] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous words, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[0904] The application server then formats the received advice and sends it back to the user terminal, which visually displays the received advice to the user.

[0905] For example, if a user enters the question "I'm worried about my career path. What should I do?" and selects "Mr. A" as an advisor, the system will operate as follows:

[0906] 1. The user selects a question and "Mr. A" through the device.

[0907] 2. The user device sends the question data and selected advisor information to the application server.

[0908] 3. The application server analyzes the received data and sends a request to an artificial intelligence model based on "Mr. A."

[0909] 4. The generation AI model server generates advice using a model that has learned from Mr. A's famous quotes, personal experiences, and past advice.

[0910] 5. The generated AI model server returns the generated advice to the application server.

[0911] 6. The application server formats the advice and sends it to the user device.

[0912] 7. The user device displays the advice and provides "Mr. A's" advice to the user.

[0913] In this way, the system of the present invention can provide reliable advice to the user.

[0914] ---

[0915] The processing flow will be explained below.

[0916] ---

[0917] Step 1:

[0918] The user uses a terminal to enter a question and selects an advisor from a provided list.

[0919] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. A."

[0920] Step 2:

[0921] The user terminal transmits the input question and the information of the selected advisor to the application server.

[0922] Specifically, a data packet containing the user ID, the question, and information about the selected advisor is generated and sent to the application server.

[0923] Step 3:

[0924] The application server receives the data sent from the user terminal.

[0925] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[0926] Step 4:

[0927] The application server parses the received data and extracts the question and the selected advisor information.

[0928] Specifically, the question content and advisor information are extracted from the data packet and preparations for the next process are made.

[0929] Step 5:

[0930] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[0931] Specifically, a request including the extracted question and advisor information is generated and sent to the generation artificial intelligence model server.

[0932] Step 6:

[0933] A generating artificial intelligence model server receives the request sent from the application server.

[0934] Specifically, the request data is received and the content is analyzed.

[0935] Step 7:

[0936] A generative artificial intelligence model server generates advice based on the request using quotes, experiences, and past advice of the designated advisor.

[0937] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice for the question.

[0938] Step 8:

[0939] The generating artificial intelligence model server returns the generated advice to the application server.

[0940] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[0941] Step 9:

[0942] The application server formats the received advice for transmission to the user terminal.

[0943] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[0944] Step 10:

[0945] The application server sends the formatted advice to the user terminal.

[0946] Specifically, the generated data packet is transmitted to the user terminal.

[0947] Step 11:

[0948] The user terminal displays the received advice to the user.

[0949] Specifically, advice is output to a display interface so that the user can visually confirm it.

[0950] ---

[0951] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[0952] Example 1

[0953] 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."

[0954] Conventional advice-giving systems lack the flexibility to provide appropriate advice for individual user questions. In particular, it is difficult to provide specific advice based on famous quotes or personal experiences from specific experts. To solve this problem, a system is needed that utilizes the knowledge and experience of experts selected by the user to provide customized advice for each individual question.

[0955] 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.

[0956] In this invention, the server includes a means for selecting questions and proposers input by a user terminal, a means for an application server to receive and analyze the questions and proposer information, and a means for the application server to send a request to a generative AI model server based on the analysis results. This makes it possible to quickly and accurately provide appropriate advice based on the quotes and experiences of selected experts in response to questions individually input by users.

[0957] "User terminal" refers to a device on which a user inputs questions and selects proposers, and includes PCs, smartphones, tablets, etc.

[0958] The "proposer selection means" is a function or interface that allows a user to select a desired proposer from multiple proposers (such as experts).

[0959] The "application server" is a central processing unit that receives and analyzes the question content and proposer information sent from the user terminal.

[0960] The "means for receiving and analyzing" is a function by which the application server receives data from the user terminal and analyzes its contents.

[0961] The "generative artificial intelligence model server" is a server that operates an AI model to generate advice based on analyzed information.

[0962] The "means for sending a request" is a function by which the application server sends data to the artificial intelligence model server based on the analysis results.

[0963] The "means for generating advice" is a function in which the artificial intelligence model server generates advice for a user's question based on the famous quotes, personal experiences, and past advice of a designated proposer.

[0964] The "means for returning" is a function for transmitting the advice generated by the generating artificial intelligence model server to the application server.

[0965] The "formatting means" is a function that formats the advice received by the application server into a format that is easy to display on the user terminal.

[0966] The "display means" is a function that allows the user terminal to visually present the advice sent from the application server to the user.

[0967] "Famous quotes, personal experiences, and past advice" refers to useful words, stories based on experience, and advice given by the proposer in the past.

[0968] The present invention is a system that uses a user terminal, an application server, and a generative artificial intelligence model server to provide appropriate advice based on the quotes, personal experiences, and past advice of a proposer selected by the user.

[0969] Overall system configuration

[0970] The system consists of three main hardware and software components:

[0971] User devices: Devices such as PCs, smartphones, tablets, etc. These devices operate through a web browser or dedicated applications.

[0972] Application server: This server runs on a cloud service such as Amazon Web Services (AWS) or Google Cloud Platform (GCP) and handles the main processing such as receiving and analyzing data. The backend is built using Python or Node.js.

[0973] Generative AI model server: This server utilizes generative AI models such as OpenAI's GPT-3 and BERT. This server is essential for generating advice.

[0974] Software used and data processing

[0975] 1. User device operation

[0976] A user accesses the system using a terminal, inputs a question, and selects the desired proposer from the provided list. For example, a user inputs a question such as "I'm worried about my career path. What should I do?" and selects "Mr. A" as the proposer.

[0977] 2. Data transmission

[0978] The user terminal sends the entered question and the selected proposer information to the application server as JSON format data.

[0979] json

[0980] {

[0981] "userID": "user123",

[0982] "question": "I'm worried about my career path. What should I do?"

[0983] "advisor": "Mr. A"

[0984] }

[0985] 3. Data analysis and request generation

[0986] The application server analyzes the received data and constructs a request to the generative AI model based on the question and the proposer. Specifically, it generates the following prompt:

[0987] Prompt: "You are a well-known career counselor, Mr. A. The user's question is, 'I'm worried about my career path. What should I do?' Please provide appropriate advice based on Mr. A's past advice and famous quotes."

[0988] This prompt sentence is sent to the generation AI model server.

[0989] 4. Generating Advice

[0990] The generation AI model server generates advice for the user's question based on the received prompt sentence, taking into account the famous quotes, personal experiences, and past advice of the designated proposer. For example, the generated advice might look like this:

[0991] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[0992] 5. Formatting and Submission of Advice

[0993] The application server receives the generated advice, formats it into a format that is easy to display on the user terminal, and then transmits the formatted advice to the user terminal.

[0994] 6. Displaying Advice

[0995] The user device visually displays the received advice to the user, for example, on the device screen as follows:

[0996] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[0997] This system allows users to get fast, reliable advice.

[0998] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0999] Step 1:

[1000] The user enters a question and selects a proposer

[1001] A user accesses the system using a terminal, inputs a question, and selects a desired proposer from a provided list.

[1002] Specific behavior:

[1003] A user types into an input field, "I'm having trouble deciding on my career path. What should I do?"

[1004] The user selects "Mr. A" from the drop-down list.

[1005] The user clicks the "Submit" button.

[1006] Input: User's question and selected proposer information

[1007] Output: Data including question content and proposer information

[1008] Step 2:

[1009] The device sends data to the application server

[1010] The device sends the question entered by the user and the information of the selected proposer to the application server. The data sent is in JSON format and includes the user ID, question, and information of the selected proposer.

[1011] Specific behavior:

[1012] The terminal generates JSON data and sends it to the application server as an HTTP POST request.

[1013] Input: Question content entered by the user and selected proposer information

[1014] Output: JSON data sent to the application server

[1015] Step 3:

[1016] The application server analyzes the data and sends a request to the AI ​​model server

[1017] The application server analyzes the received data and constructs and sends a request to the generative AI model based on the question content and proposer information.

[1018] Specific behavior:

[1019] The application server analyzes the received JSON data and extracts the question content and proposer information.

[1020] The application server generates a prompt sentence and sends it to the generation AI model server as an HTTP POST request.

[1021] Input: Received JSON data (including question content and proposer information)

[1022] Output: The prompt sent to the generative AI model server

[1023] Step 4:

[1024] Generative AI model server generates advice

[1025] The generation AI model server generates advice for the user's question based on the received prompt sentence and by referring to the designated proposer's famous quotes, personal experiences, and past advice.

[1026] Specific behavior:

[1027] The generative AI model server parses the prompt sentence and generates advice using the AI ​​model.

[1028] The generated advice is sent back to the application server.

[1029] Input: prompt statement

[1030] Output: Generated advice

[1031] Step 5:

[1032] The application server formats the advice and sends it to the user terminal.

[1033] The application server formats the advice received from the generation AI model server and sends it back to the user's device. The advice is formatted in a format that is easy to display on the user's device.

[1034] Specific behavior:

[1035] The application server takes the received advice and formats it into HTML.

[1036] The formatted advice is sent to the user device as an HTTP response.

[1037] Input: Generated advice

[1038] Output: Formatted advice

[1039] Step 6:

[1040] The user device displays the advice.

[1041] The user terminal visually displays the received advice to the user, who then checks the presented advice to obtain an answer to their question.

[1042] Specific behavior:

[1043] The user terminal receives the advice in HTML format and displays it on the screen.

[1044] Input: Formatted advice

[1045] Output: Advice displayed to the user

[1046] In this way, the system executes a series of processes to provide prompt and accurate advice in response to a user's question.

[1047] (Application example 1)

[1048] 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."

[1049] Conventional advice-giving systems have the problem that it is difficult for users to receive appropriate advice based on famous quotes or advice from specific celebrities. Furthermore, when users use different devices, such as smartphones, there is a lack of a way to display advice in a visually easy-to-read format. This results in a poor user experience.

[1050] 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.

[1051] In this invention, the server includes a question and advisor selection means input by a user terminal, a means for an application server to receive and analyze the question and advisor information, a means for the application server to send a request to a generating artificial intelligence model server based on the analysis result, a means for the generating artificial intelligence model server to generate advice based on the request, a means for the generating artificial intelligence model server to return the advice generated by the generating artificial intelligence model server to the application server, a means for the application server to send the returned advice to the user terminal, and a means for the user terminal to display the advice. This enables a user to easily receive advice based on the quotes and advice of a selected celebrity using a mobile device such as a smartphone, and display the advice in a visually easy-to-read format.

[1052] A "user terminal" is a device that a user uses to input questions and select advisors, and specifically, is a mobile device such as a smartphone.

[1053] "Application Server" refers to a central processing system for receiving questions and advisor information sent from user terminals, analyzing the information, and sending requests to the generation artificial intelligence model server.

[1054] The "generative artificial intelligence model server" is a server that references the famous quotes, personal experiences, and advice information of designated advisors to generate advice in response to user questions.

[1055] The "question and advisor selection means" is a means for a user to input a question through a terminal and select a desired advisor.

[1056] The "means for analyzing" refers to a means for analyzing the question and advisor information received by the application server and generating a request to an appropriate AI model.

[1057] The "means for sending a request" is a means by which the application server sends a request to the generation artificial intelligence model server based on the analysis results.

[1058] The "means for generating advice" refers to the means by which the artificial intelligence model server generates appropriate advice in response to a user's question based on a designated advisor.

[1059] The "means for returning advice" is a means for returning advice generated by the generating artificial intelligence model server to the application server.

[1060] The "means for sending advice" refers to the means by which the application server sends the generated advice to the user terminal.

[1061] The "means for displaying advice" refers to a means for visually displaying the advice received by the user terminal to the user.

[1062] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. This system will be described in detail below.

[1063] First, the user inputs a question using a user device such as a smartphone and selects the desired advisor from a provided list. This information is sent from the user device to the application server. The data sent includes the user ID, question content, and information about the selected advisor. The hardware used is a smartphone, and the software used by the user to input information is assumed to be a user interface (UI) application.

[1064] The application server receives the data sent from the user's device and analyzes the question and the selected advisor. Based on the analysis results, the application server constructs and sends a request to the generative AI model server. Here, it is assumed that requests between servers will be processed using a programming language such as Python.

[1065] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server. A high-performance natural language processing model such as GPT-4 could be used as the generative AI model. An example of a prompt sentence is, "A user is requesting advice from Mr. B about stress caused by excessive work. Please advise the user on how to deal with stress from Mr. B's perspective."

[1066] The application server then formats the received advice and sends it back to the user's device, where the application on the smartphone visually displays the advice to the user, allowing the user to easily receive reliable advice based on the quotes and experiences of the selected celebrity.

[1067] For example, if a user types in the question "I'm having trouble deciding on my career path. What should I do?" and selects "famous business leader" as their advisor, the following will happen:

[1068] 1. The user selects a question and a "famous business leader" via smartphone.

[1069] 2. The user terminal sends the question data and selected advisor information to the application server.

[1070] 3. The application server analyzes the incoming data and sends a request to an AI model based on "famous business leaders."

[1071] 4. The generation AI model server generates advice using a model that has learned from quotes, personal experiences, and past advice from "famous business leaders."

[1072] 5. The generated AI model server returns the generated advice to the application server.

[1073] 6. The application server formats the advice and sends it to the user terminal.

[1074] 7. The user's device will display advice and provide the user with advice from "famous business leaders."

[1075] This allows the system of the present invention to provide reliable advice to users and improve the user experience.

[1076] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1077] Step 1:

[1078] The user inputs a question and the desired advisor using a user device such as a smartphone. The input data includes the user ID, question content, and information about the selected advisor. This data is then sent to the application server using a communication protocol. The input data (question information, advisor information) from the user device is collected through the interface.

[1079] Step 2:

[1080] The user terminal sends the entered question data and selected advisor information to the application server. This transmission is carried out via a communication protocol such as an HTTP request. The data sent from the user terminal to the application server includes the user ID, question content, and selected advisor information.

[1081] Step 3:

[1082] The application server analyzes the question and advisor information received from the user device. During the analysis, natural language processing (NLP) is used to understand the question in detail and identify the user's intention. The application server analyzes the user ID, question content, and advisor information, and builds data to generate a request to the generation artificial intelligence model server.

[1083] Step 4:

[1084] Based on the analysis results, the application server sends a request to the generative AI model server. This request includes the question content and information about the selected advisor. The data sent is in a format that includes a prompt sentence to generate appropriate advice for the generative AI model. For example, it may include the following: "The user is worried about his / her career path. Please give us some advice from the perspective of the specified advisor."

[1085] Step 5:

[1086] The generative AI model server receives the request and generates advice for the user's question by referencing the database of the specified advisor. Here, a generative AI model (e.g., GPT-4) is used to generate appropriate advice based on the prompt. The generative AI model server receives the question content and advisor information as input, generates advice, and outputs it.

[1087] Step 6:

[1088] The generating AI model server returns the generated advice to the application server. This return is made via an HTTP response containing the generated advice data. The generated advice is sent to the application server, and the advice content is returned either as is or in a formatted form.

[1089] Step 7:

[1090] The application server formats the received advice and sends it to the user's device. In this step, the advice content is formatted so that it is easy for the user to understand visually. The application server sends the formatted advice data to the user's device and provides it as an HTTP response.

[1091] Step 8:

[1092] The user device displays the advice received from the application server. The user device displays the advice content in a visually easy-to-understand format, allowing the user to receive appropriate advice. The display on the user device uses methods such as text display and infographics.

[1093] The above steps create a system that allows users to easily receive reliable advice based on their questions.

[1094] 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.

[1095] ---

[1096] This system uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[1097] Specifically, the process includes the following:

[1098] First, the user inputs a question using the terminal and selects the desired advisor from the provided list. The user terminal is further equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotion information. This information (question content, selected advisor, emotion information) is sent from the user terminal to the application server.

[1099] The application server receives the data sent from the user terminal and analyzes the question content, advisor information, and emotion information. Based on the analysis results, the application server constructs and sends a request to the generation AI model server, which also includes the user's emotion information.

[1100] Based on the received request, the generative artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[1101] The application server then formats the received advice and sends it back to the user terminal, which displays the received advice to the user.

[1102] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will operate as follows:

[1103] 1. The user selects a question and "Mr. B" through the device, and the emotion engine recognizes the user's emotional state as "anxiety."

[1104] 2. The user terminal sends the question data, selected advisor information, and emotion information to the application server.

[1105] 3. The application server analyzes the received data and sends a request to an AI model based on "Mr. B," including the emotional information "anxiety."

[1106] 4. The artificial intelligence model server generates advice taking into account Mr. B's "anxiety" using a model that has learned from his famous quotes, personal experiences, and past advice.

[1107] 5. The generated AI model server returns the generated advice to the application server.

[1108] 6. The application server formats the received advice and sends it to the user terminal.

[1109] 7. The user device displays the advice and provides "Mr. B"'s advice to the user.

[1110] In this way, the system of the present invention can provide reliable advice that takes into account the user's emotional state.

[1111] ---

[1112] The processing flow will be explained below.

[1113] ---

[1114] Step 1:

[1115] The user uses a terminal to enter a question and selects an advisor from a provided list.

[1116] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. B."

[1117] Step 2:

[1118] The emotion engine installed in the user's device recognizes the user's emotions from their facial expressions, tone of voice, content of the text, etc.

[1119] Specifically, the system uses a camera, microphone, and text analysis algorithm to determine that the user's emotion is "anxiety."

[1120] Step 3:

[1121] The user terminal transmits the question content, the selected advisor information, and the emotion information to the application server.

[1122] Specifically, a data packet containing the user ID, question content, information about the selected advisor, and emotion information is generated and sent to the application server.

[1123] Step 4:

[1124] The application server receives the data sent from the user terminal.

[1125] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[1126] Step 5:

[1127] The application server analyzes the received data and extracts the question content, advisor information, and emotion information.

[1128] Specifically, the question content, advisor information, and emotion information are extracted from the data packet, and preparations for the next process are made.

[1129] Step 6:

[1130] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[1131] Specifically, a request including the extracted question, advisor information, and emotion information is generated and sent to the generation artificial intelligence model server.

[1132] Step 7:

[1133] A generating artificial intelligence model server receives the request sent from the application server.

[1134] Specifically, the request data is received and the content is analyzed.

[1135] Step 8:

[1136] The generation artificial intelligence model server uses quotes, experiences, and past advice of the advisor specified based on the request to generate advice that takes into account the user's emotional information.

[1137] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice to alleviate the "anxiety."

[1138] Step 9:

[1139] The generating artificial intelligence model server returns the generated advice to the application server.

[1140] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[1141] Step 10:

[1142] The application server formats the received advice for transmission to the user terminal.

[1143] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[1144] Step 11:

[1145] The application server sends the formatted advice to the user terminal.

[1146] Specifically, the generated data packet is transmitted to the user terminal.

[1147] Step 12:

[1148] The user terminal displays the received advice to the user.

[1149] Specifically, advice is output to a display interface so that the user can visually confirm it.

[1150] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will provide advice based on "Mr. B's" famous quotes and experiences, such as, "When you feel anxious, it's important to believe in yourself and keep moving forward."

[1151] ---

[1152] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[1153] Example 2

[1154] 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."

[1155] In today's world, people face a wide variety of problems and worries, and they need ways to get appropriate advice. However, there are few systems that can provide advice that is optimal for individual situations and emotional states, and efficient solutions do not exist. In particular, advanced technology is required to generate appropriate advice that takes into account the user's emotional state. This makes it difficult for users to instantly receive advice that is most appropriate for their situation.

[1156] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1157] In this invention, the server includes a question and advisor selection means input by the user terminal, a means for recognizing the user's emotional state in real time and generating emotional information, a means for the application server to receive and analyze the question, advisor information, and emotional information, and a means for the application server to send a request to the generation artificial intelligence model server based on the analysis result, thereby making it possible to instantly provide advanced and personalized advice based on the user's emotional state and selected advisor.

[1158] A "user terminal" is a device used by a user to input data, such as a smartphone or PC.

[1159] "Advisor selection means" refers to an interface or function that allows a user to select a desired advisor.

[1160] An "emotion engine" refers to software or hardware that recognizes a user's emotional state in real time and generates emotional information.

[1161] "Application server" refers to a server that receives and analyzes data sent from a user terminal and acts as a relay for communication with other servers.

[1162] "Generative AI model server" refers to a server that generates advice using an AI model based on data and returns it to other servers.

[1163] "Analysis means" refers to the functions and software used to analyze received data and extract and organize necessary information.

[1164] "Means for sending requests" refers to the functions and processes for sending requests to other servers based on the analyzed data.

[1165] A "famous quote" is a highly valued and widely known expression or statement spoken by a famous person or expert.

[1166] "Testimonials" refer to information that describes events that individuals have experienced and the insights they have gained from them.

[1167] "Prior advice" refers to advice or suggestions that an advisor has previously provided in a particular situation.

[1168] MODE FOR CARRYING OUT THE INVENTION

[1169] This invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on the quotes, personal experiences, and past advice of an advisor selected by the user. In addition, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[1170] Hardware and software used

[1171] User device: Devices such as smartphones and computers

[1172] Emotion engine: Software that recognizes the user's emotional state in real time, such as "Amazon Rekognition" and "Microsoft Azure Emotion API"

[1173] Application server: A server that runs on a cloud service (e.g., AWS, GCP)

[1174] Generative AI model server: A server that generates advice using AI models, such as "OpenAI GPT" generative AI models

[1175] Specific operation of the system

[1176] 1. Enter your question and select an advisor

[1177] Users use a terminal to enter their question and select their preferred advisor from a list provided.

[1178] Example: A user types into the device, "I'm having trouble deciding on my career path. What should I do?" and selects "Mr. B."

[1179] 2. Collecting emotional information

[1180] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[1181] Example: An emotion engine analyzes a user's facial and voice data and recognizes that the user is "anxious."

[1182] 3. Data transmission

[1183] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[1184] Specifically, the device sends the following data:

[1185] Q: I'm having trouble deciding on my career path. What should I do?

[1186] Advisor: Mr. B

[1187] Emotion: Anxiety

[1188] 4. Data Analysis

[1189] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[1190] Based on the results of this analysis, the necessary data is sent as a request to the generative artificial intelligence model server that holds the AI ​​model.

[1191] 5. Generating Advice

[1192] Based on the received request, the generation artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice.

[1193] Example: Based on past quotes and advice from "Mr. B," the model generates advice such as, "To overcome your anxiety, it is important to first set small goals."

[1194] 6. Advice Format

[1195] The application server formats the received advice and sends it back to the user terminal.

[1196] 7. Displaying Advice

[1197] The user terminal displays the received advice to the user.

[1198] For example, the following advice will be displayed on the terminal screen:

[1199] To overcome your anxiety, it's important to start by setting small goals.

[1200] Mr. B

[1201] Prompt Sentence Examples

[1202] An example of a prompt to input to the generative AI model is as follows:

[1203] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[1204] In this way, the system can provide highly accurate advice based on the user's emotional state as well as the information of the selected advisor.

[1205] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1206] Program processing flow and specific explanation

[1207] Step 1: Enter your question and choose an advisor

[1208] Users enter their questions using a device such as a smartphone or computer and select the advisor of their choice from a list provided.

[1209] Input: Text data question: "I'm worried about my career path. What should I do?", selected advisor: "Mr. B"

[1210] Output: Question and advisor information

[1211] Specific operation: The user enters a question into a text box on the terminal interface and selects an advisor using a drop-down list or button.

[1212] Step 2: Collecting emotional information

[1213] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[1214] Input: User's face and voice data

[1215] Output: Emotional information (e.g., "anxiety")

[1216] What it does: An emotion engine (e.g., Microsoft Azure Emotion API) analyzes data from the user's camera and microphone and identifies the user as "anxious."

[1217] Step 3: Sending data

[1218] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[1219] Input: Question content, advisor information, emotional information

[1220] Output: Sends data to the application server as an HTTP POST request

[1221] Specific operation: The data including the question "I'm worried about my career path. What should I do?", advisor "Mr. B", and emotion "anxiety" is sent to the application server in JSON format.

[1222] Step 4: Analyze the data

[1223] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[1224] Input: Data sent from the device (question content, advisor information, emotional information)

[1225] Output: Structured information of the parsed data

[1226] What happens: The application server parses the received JSON data and extracts information from the question, advisor, and sentiment fields.

[1227] Step 5: Building the Request

[1228] The application server constructs a request based on the analyzed data to be sent to the generation artificial intelligence model server.

[1229] Input: Analyzed data (question content, advisor information, emotional information)

[1230] Output: Prompt sentence to the generative AI model

[1231] Specific behavior: Generates a prompt like this:

[1232] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[1233] Step 6: Generating Advice

[1234] The generation artificial intelligence model server receives a request from the application server and generates advice based on the specified advisor's famous words, personal experiences, and past advice.

[1235] Input: Prompt sentence for generative AI model

[1236] Output: Generated advice

[1237] How it works: A generative AI model (e.g., OpenAI GPT-3) analyzes the prompt and generates advice based on quotes and personal experiences related to "Mr. B," such as "To overcome your anxiety, it's important to first set small goals."

[1238] Step 7: Formatting the advice

[1239] The application server formats the received advice into an appropriate format and sends it back to the user terminal.

[1240] Input: Advice returned from the generative AI model server

[1241] Output: Formatted advice

[1242] Specific behavior: The advice is formatted and sent as an HTTP response in a user-friendly format.

[1243] Step 8: Viewing Advice

[1244] The user terminal displays the advice received from the application server to the user.

[1245] Input: formatted advice

[1246] Output: Advice displayed to the user

[1247] What happens: The following message will be displayed on the device screen:

[1248] To overcome your anxiety, it's important to start by setting small goals.

[1249] Mr. B

[1250] Through the above processing steps, the system is able to provide highly accurate advice that takes into account the user's questions and emotions.

[1251] (Application example 2)

[1252] 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."

[1253] Previously, there were systems that provided expert advice when users purchased products online, but they had the problem of not being able to provide individualized support that took into account the user's emotional state. Providing appropriate advice in response to changes in emotions would improve the user's purchasing experience, but such a system had not yet been realized.

[1254] 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.

[1255] In this invention, the server includes: a question and advisor selection means input by a user terminal; a means for an application server to receive and analyze the question and advisor information; a means for the application server to send a request to a generative artificial intelligence model server based on the analysis result; a means for the generative artificial intelligence model server to generate advice based on the request; a means for the generative artificial intelligence model server to return the advice generated by the generative artificial intelligence model server to the application server; a means for the application server to send the returned advice to the user terminal; a means for the user terminal to display the advice; a means for the user terminal to have an emotion engine installed, to recognize the user's emotional state in real time and generate emotion information; a means for the application server to include the emotion information in the request; and a means for the generative artificial intelligence model server to generate advice taking the emotion information into consideration. This enables individual advice that takes the user's emotional state into consideration.

[1256] The "user terminal" is a device where users can input questions and select advisors. It also has an emotion engine and is capable of recognizing the user's emotional state in real time.

[1257] An "application server" is a device that analyzes questions and advisor information received from a user terminal and sends a request to the artificial intelligence model generation server based on the analysis results.

[1258] The "generative artificial intelligence model server" is a device that generates advice based on a request from the application server and returns the generated advice to the application server.

[1259] An "emotion engine" is a function or software that recognizes a user's emotional state in real time and generates emotional information.

[1260] An "advisor" is a celebrity or expert selected by the user who provides advice based on their famous quotes, experiences, and past advice.

[1261] A "question" is a consultation or question entered by a user.

[1262] "Advice" refers to answers or suggestions generated by the generative artificial intelligence model server taking into account the user's question and emotional state.

[1263] "Emotion information" is data that represents the user's emotional state, recognized and generated by the emotion engine.

[1264] A "request" is request data including question content, advisor information, and emotion information, sent from the application server to the generation artificial intelligence model server.

[1265] "Analysis" is the process by which the application server processes the question and advisor information received from the user and generates a request to the appropriate generative artificial intelligence model server.

[1266] The present invention is a system that provides advice that takes into account emotional states using a user terminal, an application server, and a generative artificial intelligence model server. The system of the present invention allows users to receive advice from specific celebrities or experts, and uses an emotion engine to provide personalized support based on the user's emotional state.

[1267] The user terminal provides an interface for users to input questions and select advisors. In addition, it is equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotional information. The data obtained from the user terminal (question content, selected advisor, emotional information) is sent to the application server.

[1268] The application server receives the data sent from the user terminal, analyzes the question content and advisor information, and based on the analysis result, constructs an appropriate request to the generative artificial intelligence model server and sends the request including the emotion information.

[1269] The generative AI model server generates advice based on the received request. This server uses a generative AI model that has learned quotes, personal experiences, and past advice from multiple celebrities and experts, and generates optimal advice taking into account the user's emotional information. The generated advice is then sent back from the generative AI model server to the application server.

[1270] The application server formats the returned advice into an appropriate format and sends it to the user terminal, which displays the received advice and provides it to the user.

[1271] For example, if a user inputs the question "I'm having trouble deciding what to buy. What should I do?" and selects "Mr. A" as the advisor, the system will operate as follows: If the emotion engine recognizes that the user's emotion is "anxiety," the system will generate advice that takes "anxiety" into consideration. This allows the user to receive appropriate advice according to their individual emotions.

[1272] Example prompt sentence:

[1273] Input Question: "I'm having trouble making a purchasing decision. What should I do?"

[1274] Selection Advisor: "Mr. A"

[1275] Recognized emotion: "Anxiety"

[1276] Actual advice:

[1277] "It's natural to feel anxious. In Mr. A's words, it's important to gather enough information and take the time to process your emotions."

[1278] In this way, by understanding the user's emotions and responding appropriately, the system can increase user satisfaction.The present invention enables emotion-based personalized responses in online shopping and other virtual experiences.

[1279] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1280] Step 1:

[1281] The user terminal inputs a question and selects an advisor. The user inputs the consultation content and question through the application interface and selects the desired advisor from the provided list. This generates information about the user's question and the selected advisor.

[1282] Input: Question, Selected Advisor

[1283] Output: Questions, selected advisor information

[1284] Step 2:

[1285] The user device uses an emotion engine to recognize the user's emotional state and generate emotion information. The emotion engine analyzes the user's emotions in real time and outputs the resulting emotion information.

[1286] Input: User's facial expressions and voice information

[1287] Output: Emotional information (e.g., anxiety, joy, excitement, etc.)

[1288] Step 3:

[1289] The user terminal transmits the question content, selected advisor information, and emotion information to the application server, which then aggregates the necessary data.

[1290] Input: Question, selected advisor information, sentiment information

[1291] Output: Sending data to the application server

[1292] Step 4:

[1293] The application server analyzes the received data and constructs an appropriate request to the generative AI model server. The server analyzes the question content and advisor information, and generates a request including emotion information based on the results.

[1294] Input: Question, selected advisor information, sentiment information

[1295] Output: Request to the generative AI model server

[1296] Step 5:

[1297] The generative AI model server receives the request and generates advice based on the specified advisor's quotes, experiences, and advice. The generative AI model uses the learned data and takes emotional information into account to generate appropriate advice.

[1298] Input: Question, selected advisor information, sentiment information

[1299] Output: Advice

[1300] Step 6:

[1301] The generating artificial intelligence model server sends the generated advice back to the application server, which then prepares the generated advice to be provided to the user.

[1302] Input: Advice

[1303] Output: Advice returned to the application server

[1304] Step 7:

[1305] The application server formats the received advice and sends it to the user's terminal, where it is formatted in a format that can be displayed.

[1306] Input: Advice

[1307] Output: Formatted advice, sent to user terminal

[1308] Step 8:

[1309] The user's device will display the received advice, allowing the user to refer to the displayed advice and obtain the necessary information.

[1310] Input: Formatted advice

[1311] Output: Advice displayed to the user

[1312] 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.

[1313] 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.

[1314] 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.

[1315] [Fourth embodiment]

[1316] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1317] 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.

[1318] 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).

[1319] 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.

[1320] 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.

[1321] 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).

[1322] 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.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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."

[1329] ---

[1330] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Specifically, it includes the following processes.

[1331] First, the user inputs a question using a terminal and selects the desired advisor from the provided list. This information is sent from the user terminal to the application server. The sent data includes the user ID, the question, and the information of the selected advisor.

[1332] The application server receives the data sent from the user terminal, analyzes the question content and the selected advisor, and based on the analysis results, constructs and sends a request to the generation artificial intelligence model server.

[1333] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous words, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[1334] The application server then formats the received advice and sends it back to the user terminal, which visually displays the received advice to the user.

[1335] For example, if a user enters the question "I'm worried about my career path. What should I do?" and selects "Mr. A" as an advisor, the system will operate as follows:

[1336] 1. The user selects a question and "Mr. A" through the device.

[1337] 2. The user device sends the question data and selected advisor information to the application server.

[1338] 3. The application server analyzes the received data and sends a request to an artificial intelligence model based on "Mr. A."

[1339] 4. The generation AI model server generates advice using a model that has learned from Mr. A's famous quotes, personal experiences, and past advice.

[1340] 5. The generated AI model server returns the generated advice to the application server.

[1341] 6. The application server formats the advice and sends it to the user device.

[1342] 7. The user device displays the advice and provides "Mr. A's" advice to the user.

[1343] In this way, the system of the present invention can provide reliable advice to the user.

[1344] ---

[1345] The processing flow will be explained below.

[1346] ---

[1347] Step 1:

[1348] The user uses a terminal to enter a question and selects an advisor from a provided list.

[1349] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. A."

[1350] Step 2:

[1351] The user terminal transmits the input question and the information of the selected advisor to the application server.

[1352] Specifically, a data packet containing the user ID, the question, and information about the selected advisor is generated and sent to the application server.

[1353] Step 3:

[1354] The application server receives the data sent from the user terminal.

[1355] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[1356] Step 4:

[1357] The application server parses the received data and extracts the question and the selected advisor information.

[1358] Specifically, the question content and advisor information are extracted from the data packet and preparations for the next process are made.

[1359] Step 5:

[1360] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[1361] Specifically, a request including the extracted question and advisor information is generated and sent to the generation artificial intelligence model server.

[1362] Step 6:

[1363] A generating artificial intelligence model server receives the request sent from the application server.

[1364] Specifically, the request data is received and the content is analyzed.

[1365] Step 7:

[1366] A generative artificial intelligence model server generates advice based on the request using quotes, experiences, and past advice of the designated advisor.

[1367] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice for the question.

[1368] Step 8:

[1369] The generating artificial intelligence model server returns the generated advice to the application server.

[1370] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[1371] Step 9:

[1372] The application server formats the received advice for transmission to the user terminal.

[1373] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[1374] Step 10:

[1375] The application server sends the formatted advice to the user terminal.

[1376] Specifically, the generated data packet is transmitted to the user terminal.

[1377] Step 11:

[1378] The user terminal displays the received advice to the user.

[1379] Specifically, advice is output to a display interface so that the user can visually confirm it.

[1380] ---

[1381] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[1382] Example 1

[1383] 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."

[1384] Conventional advice-giving systems lack the flexibility to provide appropriate advice for individual user questions. In particular, it is difficult to provide specific advice based on famous quotes or personal experiences from specific experts. To solve this problem, a system is needed that utilizes the knowledge and experience of experts selected by the user to provide customized advice for each individual question.

[1385] 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.

[1386] In this invention, the server includes a means for selecting questions and proposers input by a user terminal, a means for an application server to receive and analyze the questions and proposer information, and a means for the application server to send a request to a generative AI model server based on the analysis results. This makes it possible to quickly and accurately provide appropriate advice based on the quotes and experiences of selected experts in response to questions individually input by users.

[1387] "User terminal" refers to a device on which a user inputs questions and selects proposers, and includes PCs, smartphones, tablets, etc.

[1388] The "proposer selection means" is a function or interface that allows a user to select a desired proposer from multiple proposers (such as experts).

[1389] The "application server" is a central processing unit that receives and analyzes the question content and proposer information sent from the user terminal.

[1390] The "means for receiving and analyzing" is a function by which the application server receives data from the user terminal and analyzes its contents.

[1391] The "generative artificial intelligence model server" is a server that operates an AI model to generate advice based on analyzed information.

[1392] The "means for sending a request" is a function by which the application server sends data to the artificial intelligence model server based on the analysis results.

[1393] The "means for generating advice" is a function in which the artificial intelligence model server generates advice for a user's question based on the famous quotes, personal experiences, and past advice of a designated proposer.

[1394] The "means for returning" is a function for transmitting the advice generated by the generating artificial intelligence model server to the application server.

[1395] The "formatting means" is a function that formats the advice received by the application server into a format that is easy to display on the user terminal.

[1396] The "display means" is a function that allows the user terminal to visually present the advice sent from the application server to the user.

[1397] "Famous quotes, personal experiences, and past advice" refers to useful words, stories based on experience, and advice given by the proposer in the past.

[1398] The present invention is a system that uses a user terminal, an application server, and a generative artificial intelligence model server to provide appropriate advice based on the quotes, personal experiences, and past advice of a proposer selected by the user.

[1399] Overall system configuration

[1400] The system consists of three main hardware and software components:

[1401] User devices: Devices such as PCs, smartphones, tablets, etc. These devices operate through a web browser or dedicated applications.

[1402] Application server: This server runs on a cloud service such as Amazon Web Services (AWS) or Google Cloud Platform (GCP) and handles the main processing such as receiving and analyzing data. The backend is built using Python or Node.js.

[1403] Generative AI model server: This server utilizes generative AI models such as OpenAI's GPT-3 and BERT. This server is essential for generating advice.

[1404] Software used and data processing

[1405] 1. User device operation

[1406] A user accesses the system using a terminal, inputs a question, and selects the desired proposer from the provided list. For example, a user inputs a question such as "I'm worried about my career path. What should I do?" and selects "Mr. A" as the proposer.

[1407] 2. Data transmission

[1408] The user terminal sends the entered question and the selected proposer information to the application server as JSON format data.

[1409] json

[1410] {

[1411] "userID": "user123",

[1412] "question": "I'm worried about my career path. What should I do?"

[1413] "advisor": "Mr. A"

[1414] }

[1415] 3. Data analysis and request generation

[1416] The application server analyzes the received data and constructs a request to the generative AI model based on the question and the proposer. Specifically, it generates the following prompt:

[1417] Prompt: "You are a well-known career counselor, Mr. A. The user's question is, 'I'm worried about my career path. What should I do?' Please provide appropriate advice based on Mr. A's past advice and famous quotes."

[1418] This prompt sentence is sent to the generation AI model server.

[1419] 4. Generating Advice

[1420] The generation AI model server generates advice for the user's question based on the received prompt sentence, taking into account the famous quotes, personal experiences, and past advice of the designated proposer. For example, the generated advice might look like this:

[1421] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[1422] 5. Formatting and Submission of Advice

[1423] The application server receives the generated advice, formats it into a format that is easy to display on the user terminal, and then transmits the formatted advice to the user terminal.

[1424] 6. Displaying Advice

[1425] The user device visually displays the received advice to the user, for example, on the device screen as follows:

[1426] "If you're wondering about your career path, it's important to first understand your strengths and find a field where you can utilize them."

[1427] This system allows users to get fast, reliable advice.

[1428] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1429] Step 1:

[1430] The user enters a question and selects a proposer

[1431] A user accesses the system using a terminal, inputs a question, and selects a desired proposer from a provided list.

[1432] Specific behavior:

[1433] A user types into an input field, "I'm having trouble deciding on my career path. What should I do?"

[1434] The user selects "Mr. A" from the drop-down list.

[1435] The user clicks the "Submit" button.

[1436] Input: User's question and selected proposer information

[1437] Output: Data including question content and proposer information

[1438] Step 2:

[1439] The device sends data to the application server

[1440] The device sends the question entered by the user and the information of the selected proposer to the application server. The data sent is in JSON format and includes the user ID, question, and information of the selected proposer.

[1441] Specific behavior:

[1442] The terminal generates JSON data and sends it to the application server as an HTTP POST request.

[1443] Input: Question content entered by the user and selected proposer information

[1444] Output: JSON data sent to the application server

[1445] Step 3:

[1446] The application server analyzes the data and sends a request to the AI ​​model server

[1447] The application server analyzes the received data and constructs and sends a request to the generative AI model based on the question content and proposer information.

[1448] Specific behavior:

[1449] The application server analyzes the received JSON data and extracts the question content and proposer information.

[1450] The application server generates a prompt sentence and sends it to the generation AI model server as an HTTP POST request.

[1451] Input: Received JSON data (including question content and proposer information)

[1452] Output: The prompt sent to the generative AI model server

[1453] Step 4:

[1454] Generative AI model server generates advice

[1455] The generation AI model server generates advice for the user's question based on the received prompt sentence and by referring to the designated proposer's famous quotes, personal experiences, and past advice.

[1456] Specific behavior:

[1457] The generative AI model server parses the prompt sentence and generates advice using the AI ​​model.

[1458] The generated advice is sent back to the application server.

[1459] Input: prompt statement

[1460] Output: Generated advice

[1461] Step 5:

[1462] The application server formats the advice and sends it to the user terminal.

[1463] The application server formats the advice received from the generation AI model server and sends it back to the user's device. The advice is formatted in a format that is easy to display on the user's device.

[1464] Specific behavior:

[1465] The application server takes the received advice and formats it into HTML.

[1466] The formatted advice is sent to the user device as an HTTP response.

[1467] Input: Generated advice

[1468] Output: Formatted advice

[1469] Step 6:

[1470] The user device displays the advice.

[1471] The user terminal visually displays the received advice to the user, who then checks the presented advice to obtain an answer to their question.

[1472] Specific behavior:

[1473] The user terminal receives the advice in HTML format and displays it on the screen.

[1474] Input: Formatted advice

[1475] Output: Advice displayed to the user

[1476] In this way, the system executes a series of processes to provide prompt and accurate advice in response to a user's question.

[1477] (Application example 1)

[1478] 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."

[1479] Conventional advice-giving systems have the problem that it is difficult for users to receive appropriate advice based on famous quotes or advice from specific celebrities. Furthermore, when users use different devices, such as smartphones, there is a lack of a way to display advice in a visually easy-to-read format. This results in a poor user experience.

[1480] 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.

[1481] In this invention, the server includes a question and advisor selection means input by a user terminal, a means for an application server to receive and analyze the question and advisor information, a means for the application server to send a request to a generating artificial intelligence model server based on the analysis result, a means for the generating artificial intelligence model server to generate advice based on the request, a means for the generating artificial intelligence model server to return the advice generated by the generating artificial intelligence model server to the application server, a means for the application server to send the returned advice to the user terminal, and a means for the user terminal to display the advice. This enables a user to easily receive advice based on the quotes and advice of a selected celebrity using a mobile device such as a smartphone, and display the advice in a visually easy-to-read format.

[1482] A "user terminal" is a device that a user uses to input questions and select advisors, and specifically, is a mobile device such as a smartphone.

[1483] "Application Server" refers to a central processing system for receiving questions and advisor information sent from user terminals, analyzing the information, and sending requests to the generation artificial intelligence model server.

[1484] The "generative artificial intelligence model server" is a server that references the famous quotes, personal experiences, and advice information of designated advisors to generate advice in response to user questions.

[1485] The "question and advisor selection means" is a means for a user to input a question through a terminal and select a desired advisor.

[1486] The "means for analyzing" refers to a means for analyzing the question and advisor information received by the application server and generating a request to an appropriate AI model.

[1487] The "means for sending a request" is a means by which the application server sends a request to the generation artificial intelligence model server based on the analysis results.

[1488] The "means for generating advice" refers to the means by which the artificial intelligence model server generates appropriate advice in response to a user's question based on a designated advisor.

[1489] The "means for returning advice" is a means for returning advice generated by the generating artificial intelligence model server to the application server.

[1490] The "means for sending advice" refers to the means by which the application server sends the generated advice to the user terminal.

[1491] The "means for displaying advice" refers to a means for visually displaying the advice received by the user terminal to the user.

[1492] The present invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. This system will be described in detail below.

[1493] First, the user inputs a question using a user device such as a smartphone and selects the desired advisor from a provided list. This information is sent from the user device to the application server. The data sent includes the user ID, question content, and information about the selected advisor. The hardware used is a smartphone, and the software used by the user to input information is assumed to be a user interface (UI) application.

[1494] The application server receives the data sent from the user's device and analyzes the question and the selected advisor. Based on the analysis results, the application server constructs and sends a request to the generative AI model server. Here, it is assumed that requests between servers will be processed using a programming language such as Python.

[1495] Based on the received request, the generative artificial intelligence model server generates advice for the user's question using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server. A high-performance natural language processing model such as GPT-4 could be used as the generative AI model. An example of a prompt sentence is, "A user is requesting advice from Mr. B about stress caused by excessive work. Please advise the user on how to deal with stress from Mr. B's perspective."

[1496] The application server then formats the received advice and sends it back to the user's device, where the application on the smartphone visually displays the advice to the user, allowing the user to easily receive reliable advice based on the quotes and experiences of the selected celebrity.

[1497] For example, if a user types in the question "I'm having trouble deciding on my career path. What should I do?" and selects "famous business leader" as their advisor, the following will happen:

[1498] 1. The user selects a question and a "famous business leader" via smartphone.

[1499] 2. The user terminal sends the question data and selected advisor information to the application server.

[1500] 3. The application server analyzes the incoming data and sends a request to an AI model based on "famous business leaders."

[1501] 4. The generation AI model server generates advice using a model that has learned from quotes, personal experiences, and past advice from "famous business leaders."

[1502] 5. The generated AI model server returns the generated advice to the application server.

[1503] 6. The application server formats the advice and sends it to the user terminal.

[1504] 7. The user's device will display advice and provide the user with advice from "famous business leaders."

[1505] This allows the system of the present invention to provide reliable advice to users and improve the user experience.

[1506] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1507] Step 1:

[1508] The user inputs a question and the desired advisor using a user device such as a smartphone. The input data includes the user ID, question content, and information about the selected advisor. This data is then sent to the application server using a communication protocol. The input data (question information, advisor information) from the user device is collected through the interface.

[1509] Step 2:

[1510] The user terminal sends the entered question data and selected advisor information to the application server. This transmission is carried out via a communication protocol such as an HTTP request. The data sent from the user terminal to the application server includes the user ID, question content, and selected advisor information.

[1511] Step 3:

[1512] The application server analyzes the question and advisor information received from the user device. During the analysis, natural language processing (NLP) is used to understand the question in detail and identify the user's intention. The application server analyzes the user ID, question content, and advisor information, and builds data to generate a request to the generation artificial intelligence model server.

[1513] Step 4:

[1514] Based on the analysis results, the application server sends a request to the generative AI model server. This request includes the question content and information about the selected advisor. The data sent is in a format that includes a prompt sentence to generate appropriate advice for the generative AI model. For example, it may include the following: "The user is worried about his / her career path. Please give us some advice from the perspective of the specified advisor."

[1515] Step 5:

[1516] The generative AI model server receives the request and generates advice for the user's question by referencing the database of the specified advisor. Here, a generative AI model (e.g., GPT-4) is used to generate appropriate advice based on the prompt. The generative AI model server receives the question content and advisor information as input, generates advice, and outputs it.

[1517] Step 6:

[1518] The generating AI model server returns the generated advice to the application server. This return is made via an HTTP response containing the generated advice data. The generated advice is sent to the application server, and the advice content is returned either as is or in a formatted form.

[1519] Step 7:

[1520] The application server formats the received advice and sends it to the user's device. In this step, the advice content is formatted so that it is easy for the user to understand visually. The application server sends the formatted advice data to the user's device and provides it as an HTTP response.

[1521] Step 8:

[1522] The user device displays the advice received from the application server. The user device displays the advice content in a visually easy-to-understand format, allowing the user to receive appropriate advice. The display on the user device uses methods such as text display and infographics.

[1523] The above steps create a system that allows users to easily receive reliable advice based on their questions.

[1524] 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.

[1525] ---

[1526] This system uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on famous quotes, personal experiences, and past advice selected by the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[1527] Specifically, the process includes the following:

[1528] First, the user inputs a question using the terminal and selects the desired advisor from the provided list. The user terminal is further equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotion information. This information (question content, selected advisor, emotion information) is sent from the user terminal to the application server.

[1529] The application server receives the data sent from the user terminal and analyzes the question content, advisor information, and emotion information. Based on the analysis results, the application server constructs and sends a request to the generation AI model server, which also includes the user's emotion information.

[1530] Based on the received request, the generative artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice. This generated advice is sent back from the generative artificial intelligence model server to the application server.

[1531] The application server then formats the received advice and sends it back to the user terminal, which displays the received advice to the user.

[1532] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will operate as follows:

[1533] 1. The user selects a question and "Mr. B" through the device, and the emotion engine recognizes the user's emotional state as "anxiety."

[1534] 2. The user terminal sends the question data, selected advisor information, and emotion information to the application server.

[1535] 3. The application server analyzes the received data and sends a request to an AI model based on "Mr. B," including the emotional information "anxiety."

[1536] 4. The artificial intelligence model server generates advice taking into account Mr. B's "anxiety" using a model that has learned from his famous quotes, personal experiences, and past advice.

[1537] 5. The generated AI model server returns the generated advice to the application server.

[1538] 6. The application server formats the received advice and sends it to the user terminal.

[1539] 7. The user device displays the advice and provides "Mr. B"'s advice to the user.

[1540] In this way, the system of the present invention can provide reliable advice that takes into account the user's emotional state.

[1541] ---

[1542] The processing flow will be explained below.

[1543] ---

[1544] Step 1:

[1545] The user uses a terminal to enter a question and selects an advisor from a provided list.

[1546] Specifically, the user enters the question "I'm worried about my career path. What should I do?" into the application interface and selects "Mr. B."

[1547] Step 2:

[1548] The emotion engine installed in the user's device recognizes the user's emotions from their facial expressions, tone of voice, content of the text, etc.

[1549] Specifically, the system uses a camera, microphone, and text analysis algorithm to determine that the user's emotion is "anxiety."

[1550] Step 3:

[1551] The user terminal transmits the question content, the selected advisor information, and the emotion information to the application server.

[1552] Specifically, a data packet containing the user ID, question content, information about the selected advisor, and emotion information is generated and sent to the application server.

[1553] Step 4:

[1554] The application server receives the data sent from the user terminal.

[1555] Specifically, it receives the transmitted data packet and begins to analyze its contents.

[1556] Step 5:

[1557] The application server analyzes the received data and extracts the question content, advisor information, and emotion information.

[1558] Specifically, the question content, advisor information, and emotion information are extracted from the data packet, and preparations for the next process are made.

[1559] Step 6:

[1560] The application server constructs and sends a request to the generation artificial intelligence model server based on the extracted data.

[1561] Specifically, a request including the extracted question, advisor information, and emotion information is generated and sent to the generation artificial intelligence model server.

[1562] Step 7:

[1563] A generating artificial intelligence model server receives the request sent from the application server.

[1564] Specifically, the request data is received and the content is analyzed.

[1565] Step 8:

[1566] The generation artificial intelligence model server uses quotes, experiences, and past advice of the advisor specified based on the request to generate advice that takes into account the user's emotional information.

[1567] Specifically, it refers to the learning data of the designated advisor and generates appropriate advice to alleviate the "anxiety."

[1568] Step 9:

[1569] The generating artificial intelligence model server returns the generated advice to the application server.

[1570] Specifically, the generated advice is packaged in a data packet and sent to the application server.

[1571] Step 10:

[1572] The application server formats the received advice for transmission to the user terminal.

[1573] Specifically, the received advice is formatted in a way that is easy for the user to understand, and a data packet is generated.

[1574] Step 11:

[1575] The application server sends the formatted advice to the user terminal.

[1576] Specifically, the generated data packet is transmitted to the user terminal.

[1577] Step 12:

[1578] The user terminal displays the received advice to the user.

[1579] Specifically, advice is output to a display interface so that the user can visually confirm it.

[1580] For example, if a user enters the question, "I'm worried about my career path. What should I do?" and selects "Mr. B" as an advisor, and the system recognizes that the user's emotion is "anxiety," the system will provide advice based on "Mr. B's" famous quotes and experiences, such as, "When you feel anxious, it's important to believe in yourself and keep moving forward."

[1581] ---

[1582] This is a detailed explanation of the system's program processing, broken down into steps, which gives a clear understanding of how each component works together.

[1583] Example 2

[1584] 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."

[1585] In today's world, people face a wide variety of problems and worries, and they need ways to get appropriate advice. However, there are few systems that can provide advice that is optimal for individual situations and emotional states, and efficient solutions do not exist. In particular, advanced technology is required to generate appropriate advice that takes into account the user's emotional state. This makes it difficult for users to instantly receive advice that is most appropriate for their situation.

[1586] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1587] In this invention, the server includes a question and advisor selection means input by the user terminal, a means for recognizing the user's emotional state in real time and generating emotional information, a means for the application server to receive and analyze the question, advisor information, and emotional information, and a means for the application server to send a request to the generation artificial intelligence model server based on the analysis result, thereby making it possible to instantly provide advanced and personalized advice based on the user's emotional state and selected advisor.

[1588] A "user terminal" is a device used by a user to input data, such as a smartphone or PC.

[1589] "Advisor selection means" refers to an interface or function that allows a user to select a desired advisor.

[1590] An "emotion engine" refers to software or hardware that recognizes a user's emotional state in real time and generates emotional information.

[1591] "Application server" refers to a server that receives and analyzes data sent from a user terminal and acts as a relay for communication with other servers.

[1592] "Generative AI model server" refers to a server that generates advice using an AI model based on data and returns it to other servers.

[1593] "Analysis means" refers to the functions and software used to analyze received data and extract and organize necessary information.

[1594] "Means for sending requests" refers to the functions and processes for sending requests to other servers based on the analyzed data.

[1595] A "famous quote" is a highly valued and widely known expression or statement spoken by a famous person or expert.

[1596] "Testimonials" refer to information that describes events that individuals have experienced and the insights they have gained from them.

[1597] "Prior advice" refers to advice or suggestions that an advisor has previously provided in a particular situation.

[1598] MODE FOR CARRYING OUT THE INVENTION

[1599] This invention is a system that uses a user terminal, an application server, and a generative AI model server to provide appropriate advice based on the quotes, personal experiences, and past advice of an advisor selected by the user. In addition, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that takes into account the user's emotional state.

[1600] Hardware and software used

[1601] User device: Devices such as smartphones and computers

[1602] Emotion engine: Software that recognizes the user's emotional state in real time, such as "Amazon Rekognition" and "Microsoft Azure Emotion API"

[1603] Application server: A server that runs on a cloud service (e.g., AWS, GCP)

[1604] Generative AI model server: A server that generates advice using AI models, such as "OpenAI GPT" generative AI models

[1605] Specific operation of the system

[1606] 1. Enter your question and select an advisor

[1607] Users use a terminal to enter their question and select their preferred advisor from a list provided.

[1608] Example: A user types into the device, "I'm having trouble deciding on my career path. What should I do?" and selects "Mr. B."

[1609] 2. Collecting emotional information

[1610] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[1611] Example: An emotion engine analyzes a user's facial and voice data and recognizes that the user is "anxious."

[1612] 3. Data transmission

[1613] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[1614] Specifically, the device sends the following data:

[1615] Q: I'm having trouble deciding on my career path. What should I do?

[1616] Advisor: Mr. B

[1617] Emotion: Anxiety

[1618] 4. Data Analysis

[1619] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[1620] Based on the results of this analysis, the necessary data is sent as a request to the generative artificial intelligence model server that holds the AI ​​model.

[1621] 5. Generating Advice

[1622] Based on the received request, the generation artificial intelligence model server generates advice that takes into account the user's emotional information, using the specified advisor's famous quotes, personal experiences, and past advice.

[1623] Example: Based on past quotes and advice from "Mr. B," the model generates advice such as, "To overcome your anxiety, it is important to first set small goals."

[1624] 6. Advice Format

[1625] The application server formats the received advice and sends it back to the user terminal.

[1626] 7. Displaying Advice

[1627] The user terminal displays the received advice to the user.

[1628] For example, the following advice will be displayed on the terminal screen:

[1629] To overcome your anxiety, it's important to start by setting small goals.

[1630] Mr. B

[1631] Prompt Sentence Examples

[1632] An example of a prompt to input to the generative AI model is as follows:

[1633] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[1634] In this way, the system can provide highly accurate advice based on the user's emotional state as well as the information of the selected advisor.

[1635] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1636] Program processing flow and specific explanation

[1637] Step 1: Enter your question and choose an advisor

[1638] Users enter their questions using a device such as a smartphone or computer and select the advisor of their choice from a list provided.

[1639] Input: Text data question: "I'm worried about my career path. What should I do?", selected advisor: "Mr. B"

[1640] Output: Question and advisor information

[1641] Specific operation: The user enters a question into a text box on the terminal interface and selects an advisor using a drop-down list or button.

[1642] Step 2: Collecting emotional information

[1643] The device uses an emotion engine to recognize the user's emotional state in real time and generate emotion information.

[1644] Input: User's face and voice data

[1645] Output: Emotional information (e.g., "anxiety")

[1646] What it does: An emotion engine (e.g., Microsoft Azure Emotion API) analyzes data from the user's camera and microphone and identifies the user as "anxious."

[1647] Step 3: Sending data

[1648] The terminal transmits the question content, the selected advisor, and the generated emotion information to the application server.

[1649] Input: Question content, advisor information, emotional information

[1650] Output: Sends data to the application server as an HTTP POST request

[1651] Specific operation: The data including the question "I'm worried about my career path. What should I do?", advisor "Mr. B", and emotion "anxiety" is sent to the application server in JSON format.

[1652] Step 4: Analyze the data

[1653] The application server receives the data sent from the terminal and analyzes the question content, advisor information, and emotion information.

[1654] Input: Data sent from the device (question content, advisor information, emotional information)

[1655] Output: Structured information of the parsed data

[1656] What happens: The application server parses the received JSON data and extracts information from the question, advisor, and sentiment fields.

[1657] Step 5: Building the Request

[1658] The application server constructs a request based on the analyzed data to be sent to the generation artificial intelligence model server.

[1659] Input: Analyzed data (question content, advisor information, emotional information)

[1660] Output: Prompt sentence to the generative AI model

[1661] Specific behavior: Generates a prompt like this:

[1662] "The user is worried and anxious about their career path. Please refer to Mr. B's quotes and experiences to provide advice for this situation."

[1663] Step 6: Generating Advice

[1664] The generation artificial intelligence model server receives a request from the application server and generates advice based on the specified advisor's famous words, personal experiences, and past advice.

[1665] Input: Prompt sentence for generative AI model

[1666] Output: Generated advice

[1667] How it works: A generative AI model (e.g., OpenAI GPT-3) analyzes the prompt and generates advice based on quotes and personal experiences related to "Mr. B," such as "To overcome your anxiety, it's important to first set small goals."

[1668] Step 7: Formatting the advice

[1669] The application server formats the received advice into an appropriate format and sends it back to the user terminal.

[1670] Input: Advice returned from the generative AI model server

[1671] Output: Formatted advice

[1672] Specific behavior: The advice is formatted and sent as an HTTP response in a user-friendly format.

[1673] Step 8: Viewing Advice

[1674] The user terminal displays the advice received from the application server to the user.

[1675] Input: formatted advice

[1676] Output: Advice displayed to the user

[1677] What happens: The following message will be displayed on the device screen:

[1678] To overcome your anxiety, it's important to start by setting small goals.

[1679] Mr. B

[1680] Through the above processing steps, the system is able to provide highly accurate advice that takes into account the user's questions and emotions.

[1681] (Application example 2)

[1682] 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."

[1683] Previously, there were systems that provided expert advice when users purchased products online, but they had the problem of not being able to provide individualized support that took into account the user's emotional state. Providing appropriate advice in response to changes in emotions would improve the user's purchasing experience, but such a system had not yet been realized.

[1684] 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.

[1685] In this invention, the server includes: a question and advisor selection means input by a user terminal; a means for an application server to receive and analyze the question and advisor information; a means for the application server to send a request to a generative artificial intelligence model server based on the analysis result; a means for the generative artificial intelligence model server to generate advice based on the request; a means for the generative artificial intelligence model server to return the advice generated by the generative artificial intelligence model server to the application server; a means for the application server to send the returned advice to the user terminal; a means for the user terminal to display the advice; a means for the user terminal to have an emotion engine installed, to recognize the user's emotional state in real time and generate emotion information; a means for the application server to include the emotion information in the request; and a means for the generative artificial intelligence model server to generate advice taking the emotion information into consideration. This enables individual advice that takes the user's emotional state into consideration.

[1686] The "user terminal" is a device where users can input questions and select advisors. It also has an emotion engine and is capable of recognizing the user's emotional state in real time.

[1687] An "application server" is a device that analyzes questions and advisor information received from a user terminal and sends a request to the artificial intelligence model generation server based on the analysis results.

[1688] The "generative artificial intelligence model server" is a device that generates advice based on a request from the application server and returns the generated advice to the application server.

[1689] An "emotion engine" is a function or software that recognizes a user's emotional state in real time and generates emotional information.

[1690] An "advisor" is a celebrity or expert selected by the user who provides advice based on their famous quotes, experiences, and past advice.

[1691] A "question" is a consultation or question entered by a user.

[1692] "Advice" refers to answers or suggestions generated by the generative artificial intelligence model server taking into account the user's question and emotional state.

[1693] "Emotion information" is data that represents the user's emotional state, recognized and generated by the emotion engine.

[1694] A "request" is request data including question content, advisor information, and emotion information, sent from the application server to the generation artificial intelligence model server.

[1695] "Analysis" is the process by which the application server processes the question and advisor information received from the user and generates a request to the appropriate generative artificial intelligence model server.

[1696] The present invention is a system that provides advice that takes into account emotional states using a user terminal, an application server, and a generative artificial intelligence model server. The system of the present invention allows users to receive advice from specific celebrities or experts, and uses an emotion engine to provide personalized support based on the user's emotional state.

[1697] The user terminal provides an interface for users to input questions and select advisors. In addition, it is equipped with an emotion engine that recognizes the user's emotional state in real time and generates emotional information. The data obtained from the user terminal (question content, selected advisor, emotional information) is sent to the application server.

[1698] The application server receives the data sent from the user terminal, analyzes the question content and advisor information, and based on the analysis result, constructs an appropriate request to the generative artificial intelligence model server and sends the request including the emotion information.

[1699] The generative AI model server generates advice based on the received request. This server uses a generative AI model that has learned quotes, personal experiences, and past advice from multiple celebrities and experts, and generates optimal advice taking into account the user's emotional information. The generated advice is then sent back from the generative AI model server to the application server.

[1700] The application server formats the returned advice into an appropriate format and sends it to the user terminal, which displays the received advice and provides it to the user.

[1701] For example, if a user inputs the question "I'm having trouble deciding what to buy. What should I do?" and selects "Mr. A" as the advisor, the system will operate as follows: If the emotion engine recognizes that the user's emotion is "anxiety," the system will generate advice that takes "anxiety" into consideration. This allows the user to receive appropriate advice according to their individual emotions.

[1702] Example prompt sentence:

[1703] Input Question: "I'm having trouble making a purchasing decision. What should I do?"

[1704] Selection Advisor: "Mr. A"

[1705] Recognized emotion: "Anxiety"

[1706] Actual advice:

[1707] "It's natural to feel anxious. In Mr. A's words, it's important to gather enough information and take the time to process your emotions."

[1708] In this way, by understanding the user's emotions and responding appropriately, the system can increase user satisfaction.The present invention enables emotion-based personalized responses in online shopping and other virtual experiences.

[1709] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1710] Step 1:

[1711] The user terminal inputs a question and selects an advisor. The user inputs the consultation content and question through the application interface and selects the desired advisor from the provided list. This generates information about the user's question and the selected advisor.

[1712] Input: Question, Selected Advisor

[1713] Output: Questions, selected advisor information

[1714] Step 2:

[1715] The user device uses an emotion engine to recognize the user's emotional state and generate emotion information. The emotion engine analyzes the user's emotions in real time and outputs the resulting emotion information.

[1716] Input: User's facial expressions and voice information

[1717] Output: Emotional information (e.g., anxiety, joy, excitement, etc.)

[1718] Step 3:

[1719] The user terminal transmits the question content, selected advisor information, and emotion information to the application server, which then aggregates the necessary data.

[1720] Input: Question, selected advisor information, sentiment information

[1721] Output: Sending data to the application server

[1722] Step 4:

[1723] The application server analyzes the received data and constructs an appropriate request to the generative AI model server. The server analyzes the question content and advisor information, and generates a request including emotion information based on the results.

[1724] Input: Question, selected advisor information, sentiment information

[1725] Output: Request to the generative AI model server

[1726] Step 5:

[1727] The generative AI model server receives the request and generates advice based on the specified advisor's quotes, experiences, and advice. The generative AI model uses the learned data and takes emotional information into account to generate appropriate advice.

[1728] Input: Question, selected advisor information, sentiment information

[1729] Output: Advice

[1730] Step 6:

[1731] The generating artificial intelligence model server sends the generated advice back to the application server, which then prepares the generated advice to be provided to the user.

[1732] Input: Advice

[1733] Output: Advice returned to the application server

[1734] Step 7:

[1735] The application server formats the received advice and sends it to the user's terminal, where it is formatted in a format that can be displayed.

[1736] Input: Advice

[1737] Output: Formatted advice, sent to user terminal

[1738] Step 8:

[1739] The user's device will display the received advice, allowing the user to refer to the displayed advice and obtain the necessary information.

[1740] Input: Formatted advice

[1741] Output: Advice displayed to the user

[1742] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1743] 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.

[1744] 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 robot 414.

[1745] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1746] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1747] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1748] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1749] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1750] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1751] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1752] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1753] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1754] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1755] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1756] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1757] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1758] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1759] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1760] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1761] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1762] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1763] The following is further disclosed regarding the above embodiment.

[1764] ---

[1765] (Claim 1)

[1766] A question and advisor selection means input by a user terminal;

[1767] means for an application server to receive and analyze the question and advisor information;

[1768] A means for the application server to send a request to a generation artificial intelligence model server based on the analysis result;

[1769] means for the generating artificial intelligence model server to generate advice based on the request;

[1770] means for returning the advice generated by the generating artificial intelligence model server to the application server;

[1771] means for the application server to send the returned advice to a user terminal;

[1772] means for displaying the advice on the user terminal;

[1773] A system including:

[1774] (Claim 2)

[1775] The system of claim 1, wherein the generative artificial intelligence model server includes a model that has learned famous quotes, personal experiences, and past advice from multiple famous people.

[1776] (Claim 3)

[1777] 2. The system according to claim 1, wherein the artificial intelligence model server provides advice based on the question asked by the user terminal and the quotes, personal experiences, and past advice of the advisor selected by the advisor selection means.

[1778] ---

[1779] "Example 1"

[1780] (Claim 1)

[1781] A question and proposer selection means input by a user terminal;

[1782] means for an application server to receive and analyze the question and proposer information;

[1783] A means for the application server to send a request to a generation artificial intelligence model server based on the analysis result;

[1784] means for the generating artificial intelligence model server to generate advice based on the request;

[1785] means for returning the advice generated by the generating artificial intelligence model server to the application server;

[1786] means for the application server to send the returned advice to a user terminal;

[1787] means for displaying the advice on the user terminal;

[1788] A system including:

[1789] (Claim 2)

[1790] The system of claim 1, wherein the generative artificial intelligence model server includes a model that has learned quotes, personal experiences, and past advice from multiple experts.

[1791] (Claim 3)

[1792] 2. The system according to claim 1, wherein the generation artificial intelligence model server provides advice based on the question asked by the user terminal and the famous quotes, personal experiences, and past advice of the proposer selected by the proposer selection means.

[1793] "Application Example 1" (Claim 1)

[1794] A question and advisor selection means input by a user terminal;

[1795] means for an application server to receive and analyze the question and advisor information;

[1796] A means for the application server to send a request to a generation artificial intelligence model server based on the analysis result;

[1797] means for the generating artificial intelligence model server to generate advice based on the request;

[1798] means for returning the advice generated by the generating artificial intelligence model server to the application server;

[1799] means for the application server to send the returned advice to a user terminal;

[1800] means for displaying the advice on the user terminal;

[1801] A system including:

[1802] (Claim 2)

[1803] The system of claim 1, wherein the generative artificial intelligence model server includes a model that has learned famous quotes, personal experiences, and past advice from multiple famous people.

[1804] (Claim 3)

[1805] 2. The system according to claim 1, wherein the artificial intelligence model server provides advice based on the question asked by the user terminal and the quotes, personal experiences, and past advice of the advisor selected by the advisor selection means.

[1806] (Claim 4)

[1807] 2. The system of claim 1, wherein the user terminal is a smartphone and includes means for visually displaying advice.

[1808] "Example 2: Combining Emotion Engines"

[1809] (Claim 1)

[1810] A question and advisor selection means input by a user terminal;

[1811] a means for the user terminal to recognize the user's emotional state in real time and generate emotional information;

[1812] an application server receiving and analyzing the questions, advisor information, and emotion information;

[1813] A means for the application server to send a request to a generation artificial intelligence model server based on the analysis result;

[1814] means for the generating artificial intelligence model server to generate advice based on the request;

[1815] means for returning the advice generated by the generating artificial intelligence model server to the application server;

[1816] means for the application server to send the returned advice to a user terminal;

[1817] means for displaying the advice on the user terminal;

[1818] A system including:

[1819] (Claim 2)

[1820] 2. The system of claim 1, wherein the generative artificial intelligence model server includes a model trained on the words, personal experiences, and past advice of multiple celebrities.

[1821] (Claim 3)

[1822] 2. The system according to claim 1, wherein the artificial intelligence model server provides advice based on the words, experiences and past advice of the advisor selected by the user terminal through the question and advisor selection means.

[1823] "Application example 2 when combining emotion engines"

[1824] (Claim 1)

[1825] A question and advisor selection means input by a user terminal;

[1826] means for an application server to receive and analyze the question and advisor information;

[1827] A means for the application server to send a request to a generation artificial intelligence model server based on the analysis result;

[1828] means for the generating artificial intelligence model server to generate advice based on the request;

[1829] means for returning the advice generated by the generating artificial intelligence model server to the application server;

[1830] means for the application server to send the returned advice to a user terminal;

[1831] means for displaying the advice on the user terminal;

[1832] A user device is equipped with an emotion engine, and is a means for recognizing the user's emotional state in real time and generating emotion information;

[1833] means for the application server to include the emotion information in the request;

[1834] A means for generating advice by the artificial intelligence model server taking into account the emotion information;

[1835] A system including:

[1836] (Claim 2)

[1837] The system of claim 1, wherein the generative artificial intelligence model server includes a model that has learned famous quotes, personal experiences, and past advice from multiple famous people.

[1838] (Claim 3)

[1839] 2. The system according to claim 1, wherein the artificial intelligence model server provides advice based on the question asked by the user terminal and the quotes, personal experiences, and past advice of the advisor selected by the advisor selection means. [Explanation of symbols]

[1840] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A question and advisor selection means input by a user terminal; means for an application server to receive and analyze the question and advisor information; A means for the application server to send a request to a generation artificial intelligence model server based on the analysis result; means for the generating artificial intelligence model server to generate advice based on the request; means for returning the advice generated by the generating artificial intelligence model server to the application server; means for the application server to send the returned advice to a user terminal; means for displaying the advice on the user terminal; A system including:

2. 2. The system of claim 1, wherein the generative artificial intelligence model server includes a model that has learned famous quotes, personal experiences, and past advice from a plurality of famous people.

3. 2. The system according to claim 1, wherein the artificial intelligence model server provides advice based on the questions asked by the user terminal and the quotes, personal experiences, and past advice of the advisor selected by the advisor selection means.

Images