System

Abstract

A system is provided.SOLUTION: A system including means for a user to input basic information, means for transmitting the input basic information to a server, means for storing the basic information in a database, means for customizing a chatbot based on a user profile, means for receiving a question of a user and transmitting the question to a generated AI model to generate a response, means for presenting the generated response to the user, means for collecting and analyzing dialogue data with the user, and means for updating a data set to improve response accuracy of the chatbot based on an analysis result.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] In modern society, it is difficult to quickly obtain the information one needs from a vast amount of information, requiring a great deal of time and effort. Demand is also increasing for efficient communication, individualized learning support, and health management advice. Furthermore, the need for personal growth and career development is also on the rise. To address these challenges, there is a need for systems that provide personalized support, efficiently obtain information, and solve problems. [Means for solving the problem]

[0005] The present invention includes a means for a user to input basic information, a means for transmitting the input basic information to a server, and a means for saving the basic information in a database. It also includes a means for customizing a chatbot based on a user profile, receiving a user's question, and sending the question to a generative AI model to generate a response. It also includes a means for presenting the generated response to the user, a means for collecting and analyzing dialogue data with the user, and a means for updating a dataset to improve the chatbot's response accuracy based on the analysis results. This enables personalized and efficient support and information provision, supporting personal growth and career development.

[0006] "User" means an individual or end user who utilizes the system to input information and receive answers and support.

[0007] "Basic information" refers to personal information such as name, age, hobbies, etc. that the user enters during initial setup.

[0008] A "server" is a central processing unit that receives information from users, processes the data, and generates the necessary response.

[0009] A "database" is a storage device that stores information received by the server and allows retrieval and updating as needed.

[0010] A "chatbot" is an automated response program that generates responses to user questions.

[0011] A "generative AI model" is an artificial intelligence technology that generates appropriate responses to user questions.

[0012] A "question" is information that a user inputs into the system or a question that the user wants to know.

[0013] A "response" is an answer or information that the server provides to the user using a generative AI model.

[0014] "Personalization" means providing services and support that are individually customized based on the user's basic information.

[0015] "Dialogue data" is a record of questions and responses exchanged between a user and a system.

[0016] A "dataset" is a set of data used to train or improve a generative AI model. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

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

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

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

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0032] 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.

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

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention aims to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[0039] System Configuration

[0040] This system consists of a user terminal, a server, a database, and a generative AI model.

[0041] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[0042] Server: Receives information from user devices, stores it in a database, and sends questions to the generative AI model to generate responses.

[0043] Database: Stores basic information and interaction data and is used for analysis and updates.

[0044] Generative AI model: An artificial intelligence technique that generates appropriate responses to user questions.

[0045] Program processing overview

[0046] 1. Initial Setup

[0047] The user enters basic information.

[0048] The terminal sends this information to the server.

[0049] The server stores the information in a database and generates a user profile.

[0050] 2. Generating personalized chatbots

[0051] The server customizes the chatbot based on the user profile.

[0052] The server transmits the customization information to the terminal.

[0053] 3. Information Acquisition and Response

[0054] The user enters a question.

[0055] The terminal sends a question to the server.

[0056] The server sends the question to a generative AI model, which generates a response.

[0057] The server sends a response to the terminal, which displays it to the user.

[0058] 4. Automatic collaboration and growth support

[0059] The server collects and analyzes the interaction data.

[0060] The server provides personalized learning resources to support the user's growth.

[0061] 5. Data collection and analysis

[0062] The server collects and analyzes the interaction data.

[0063] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0064] Specific examples

[0065] Example of initial settings

[0066] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0067] The terminal sends this information to the server.

[0068] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0069] Examples of personalized chatbots

[0070] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[0071] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[0072] Specific examples of obtaining and responding to information

[0073] A user asks, "What's a good route for my next cycling trip?"

[0074] The terminal sends this question to the server.

[0075] The server sends a question to the generative AI model and receives a response such as, "The best cycling route is the one along the nearby river."

[0076] The server sends this response to the terminal, which displays it to the user.

[0077] Specific examples of growth support

[0078] User types, "I want to improve my project management skills."

[0079] The server searches for relevant online courses and learning resources and sends them to the device.

[0080] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[0081] Examples of data collection and analysis

[0082] The server analyzes the dialogue history and identifies an increase in questions about a particular topic.

[0083] The server adds new response patterns and datasets to respond to subsequent questions.

[0084] The system of the present invention provides efficient and personalized support to users, enabling them to quickly obtain information and solve problems.

[0085] The processing flow will be explained below.

[0086] Step 1:

[0087] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0088] Step 2:

[0089] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[0090] Step 3:

[0091] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[0092] Step 4:

[0093] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[0094] Step 5:

[0095] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[0096] Step 6:

[0097] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[0098] Step 7:

[0099] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[0100] Step 8:

[0101] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[0102] Step 9:

[0103] The server sends the generated response to the terminal. The server receives the response data and sends it to the user's terminal.

[0104] Step 10:

[0105] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is the one along the nearby river."

[0106] Step 11:

[0107] The server collects and analyzes the interaction data. The server collects the interaction history with the user and analyzes trends and frequently occurring problems.

[0108] Step 12:

[0109] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[0110] Step 13:

[0111] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data to provide appropriate learning resources and career support. For example, a user who "wants to improve their project management skills" will be provided with relevant online courses and practical advice.

[0112] Example 1

[0113] 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."

[0114] The purpose of this invention is to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. It aims to provide personalized learning resources, which have been difficult to achieve with conventional systems, and to smoothly deploy conversational agents that are compatible with multiple platforms. Another objective is to provide an effective means for collecting and analyzing dialogue data and improving the response accuracy of conversational agents.

[0115] 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.

[0116] In this invention, the server includes a means for customizing a conversational agent based on a user profile, a means for receiving a user's questions and sending the questions to a generative AI model to generate a response, and a means for providing personalized learning resources to support the user's growth. This allows for efficient and personalized support for users, enabling them to quickly obtain information and solve problems. It also allows for the collection and analysis of dialogue data, and the improvement of the conversational agent's response accuracy based on the analysis results.

[0117] "Basic information" is data required for initial setup, such as name, age, and hobbies, entered by the user.

[0118] The "server" is a central processing unit that receives, stores, and processes data sent from user devices and works with the generative AI model to generate responses.

[0119] A "database" is a place where information is collected to efficiently store and manage basic user information and conversation data.

[0120] A "user profile" is a data set created based on collected basic information about a user to identify and specify an individual user.

[0121] A "conversational agent" is an artificial intelligence system that uses generative AI models to engage in dialogue with users and provide appropriate responses to their questions.

[0122] A "generative artificial intelligence model" is an artificial intelligence algorithm that learns from given data and generates appropriate responses to user questions.

[0123] "Dialogue data" is a record of the information exchanged between a user and a conversational agent.

[0124] "Learning Resources" are educational materials such as online courses and course materials offered to help users grow.

[0125] "Multiple information platforms" is a general term for various Internet services that can be used in different software and hardware environments.

[0126] "Personalization" is the process of individually optimizing information and services according to the characteristics and needs of each individual user.

[0127] The present invention provides a system that allows users to receive personalized support, quickly and safely obtain information, and solve problems. Specific embodiments of the present invention are described in detail below.

[0128] System Configuration

[0129] This system consists of a user terminal, a server, a database, and a generative AI model.

[0130] User device: The user uses this device to enter basic information, send questions, and receive responses from the server. Examples include a smartphone or PC.

[0131] Server: Receives information from user devices, stores it in a database, sends questions to the generative AI model, and generates responses. Server-side programs such as Python and Node.js are used.

[0132] Database: This stores basic information and interaction data and is used for analysis and updating. Relational databases such as MySQL and PostgreSQL are used.

[0133] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. For example, OpenAI's GPT model is used.

[0134] Program processing overview

[0135] Initial Setup

[0136] The user launches the app and enters basic information. The user's device sends this information to the server. The server receives the information and stores it in a database. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[0137] Generate personalized chatbots

[0138] The server generates a customized chatbot based on the user profile. This setting information is sent to the device, and the device displays "Personalization setting complete." For example, the server generates a specific response pattern based on "Taro Tanaka, 30 years old, cycling."

[0139] Obtaining and responding to information

[0140] The user inputs a question, and the device sends it to the server. For example, the user might input, "What's a good route for my next cycling trip?" The server sends the question to a generative AI model, which generates a response such as, "The best route for cycling is the one along the nearby river." The generated response is then sent to the device, which displays it.

[0141] Automated collaboration and growth support

[0142] The server collects and analyzes interaction data, identifying increased interest in specific topics, and providing personalized learning resources to help users grow. For example, if a user types, "I want to improve my project management skills," the server can provide information about related online courses.

[0143] Data collection and analysis

[0144] The server analyzes the dialogue history and updates the dataset of the generative AI model, adding new response patterns and improving the accuracy of responses to the next question.

[0145] Examples of concrete examples and prompts

[0146] Example explanation:

[0147] User types, "I want to improve my project management skills."

[0148] The server searches for relevant online courses and learning resources and sends them to the device.

[0149] The device displays, "Recommended courses on project management are from XYZ Online School."

[0150] Example prompt sentence:

[0151] When a user asks the AI ​​model a question, they can enter a prompt such as, "Tell me a good route for my next cycling trip."

[0152] This system provides users with efficient and personalized support, enabling them to quickly obtain information and solve problems.

[0153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0154] System program processing flow

[0155] Initial Setup

[0156] Step 1: User enters basic information

[0157] The user launches the app and enters basic information such as name, age, and hobbies.

[0158] Input: Name, age, hobbies, etc.

[0159] Output: Basic information is saved to the device.

[0160] Example: Enter "Name: Taro Tanaka, Age: 30, Hobby: Cycling".

[0161] Step 2: The device sends the information to the server

[0162] The terminal sends the entered basic information to the server.

[0163] Input: Basic information

[0164] Output: Basic information received by the server

[0165] The device sends data to the server using the MQTT protocol.

[0166] Step 3: The server stores the information

[0167] The server stores the received information in a database.

[0168] Input: Basic information

[0169] Output: Basic information stored in the database

[0170] Store the information in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0171] Step 4: Create a user profile

[0172] The server generates a user profile based on the stored information.

[0173] Input: Basic information stored in the database

[0174] Output: Generated user profile

[0175] A user profile is generated and the system optimizes its operation based on it.

[0176] Generate personalized chatbots

[0177] Step 1: The server sends the customization data to the generative AI model

[0178] The server retrieves the user profile and sends the customization data to the generative AI model.

[0179] Input: User profile

[0180] Output: Customized data to send to the generative AI model

[0181] For example, let's say "User data: Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0182] Step 2: The generative AI model generates response patterns

[0183] A generative AI model generates personalized response patterns based on the data it receives.

[0184] Input: Customization data

[0185] Output: The generated response pattern

[0186] Generate specific response patterns that take individual content into consideration.

[0187] Step 3: The server sends the configuration data to the device

[0188] The server transmits the generated setting data to the terminal.

[0189] Input: Generated response pattern

[0190] Output: Sending configuration data

[0191] The server sends a response to the terminal, which receives it.

[0192] Step 4: Your device will display a message saying it's set up

[0193] The device will display "Personalized settings complete" based on the setting data received.

[0194] Input: Setting data

[0195] Output: "Personalization setup complete"

[0196] Notify the user that customization is complete.

[0197] Obtaining and responding to information

[0198] Step 1: User enters question

[0199] The user inputs a question such as "Tell me a good route for my next cycling trip."

[0200] Input: Question

[0201] Output: The question is saved to the terminal.

[0202] Step 2: The device sends a question to the server

[0203] The terminal sends the entered question to the server.

[0204] Input: Question

[0205] Output: The question sent to the server

[0206] Submit a question using the REST API.

[0207] Step 3: The server sends the response to the generative AI model

[0208] The server sends the question to the generative AI model, which generates a response such as, "The best cycling route is the one along the nearby river."

[0209] Input: Question

[0210] Output: The generated response

[0211] Leverage generative artificial intelligence models to generate appropriate responses.

[0212] Step 4: The server sends a response to the device

[0213] The server sends the generated response to the terminal.

[0214] Input: Generated response

[0215] Output: Response sent to the terminal

[0216] Step 5: The terminal displays the response

[0217] The terminal displays the received response to the user.

[0218] Input: Response from the server

[0219] Output: The response that is displayed to the user

[0220] Automated collaboration and growth support

[0221] Step 1: The server collects and analyzes the interaction data

[0222] The server collects and analyzes the interaction data.

[0223] Input: Interaction data

[0224] Output: Analysis results

[0225] Identify growing interest in a particular topic.

[0226] Step 2: The server provides personalized learning resources

[0227] The server provides personalized learning resources based on the user's interests.

[0228] Input: Analysis results

[0229] Output: Personalized learning resources

[0230] Example: "The recommended course on project management is XYZ Online School."

[0231] Data collection and analysis

[0232] Step 1: The server analyzes the conversation history

[0233] The server analyzes the dialogue history and updates the dataset for the generative AI model.

[0234] Input: Dialogue history

[0235] Output: Updated dataset

[0236] Identify frequently asked questions and emerging trends and add new response patterns.

[0237] Step 2: Improving response accuracy

[0238] The server will provide a more accurate response to subsequent questions.

[0239] Input: Updated dataset

[0240] Output: Highly accurate response

[0241] Improve the accuracy of generative AI models and increase user satisfaction.

[0242] (Application example 1)

[0243] 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."

[0244] Conventional electronic payment services have faced the challenge of making it difficult for users to receive prompt, safe, and appropriate support. In particular, it has been difficult to provide personalized support tailored to each user's individual situation, and when questions or problems arise regarding electronic payments, appropriate responses are often not possible. Furthermore, there has been insufficient analysis of dialogue data to improve user convenience, and the accuracy of generative AI models has not been improved.

[0245] 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.

[0246] In this invention, the server includes means for acquiring basic information and electronic payment history of a user and providing personalized support based thereon, means for identifying questions on specific topics from the dialogue history and generating new response patterns, and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This allows users to receive prompt, individually customized support and efficiently resolve questions and problems related to electronic payments.

[0247] "Basic user information" refers to profile information such as name, age, hobbies, and electronic payment history that a user enters when using the system.

[0248] "Server" means a central processing unit for processing information received from user terminals, storing it in a database, sending questions to the generative AI model, and providing analysis and responses.

[0249] A "database" is an information management system that stores basic user information and conversation data over a long period of time and is used for analysis and updating.

[0250] A "generative AI model" is an artificial intelligence technology that generates appropriate responses to user questions, and specifically refers to advanced natural language processing models such as GPT-3.

[0251] A "profile" is a personalized data set that collects and centralizes basic information about a user.

[0252] A "chatbot" is an automated response program that interacts with users and uses generative AI models to provide personalized conversations.

[0253] "Personalization" refers to providing optimal support and responses to individual users based on their basic information and historical data.

[0254] "Electronic payment history" refers to a record of electronic payments made by a user in the past.

[0255] "Dialogue history" is data that records the content of past dialogues between a user and a chatbot.

[0256] A "new response pattern" is a different response method from the conventional one, generated based on collected and analyzed dialogue data.

[0257] "Dataset updating" is the process of updating the training data for a generative AI model based on the results of collecting and analyzing interaction data.

[0258] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems related to electronic payments. Hereinafter, the program processing of the system will be described as an embodiment of the present invention.

[0259] System Configuration

[0260] This system mainly uses the following hardware and software.

[0261] User device: Smartphone

[0262] Server: Cloud server (e.g. AWS, Google Cloud)

[0263] Database: Relational database (e.g. MySQL, PostgreSQL)

[0264] Generative AI model: GPT-3 (OpenAI)

[0265] Program processing overview

[0266] Initial Setup

[0267] When a user first uses the system, they enter basic information (e.g., name, age, electronic payment history) using their smartphone. This information is sent from the smartphone to the server, which then creates a user profile and stores it in a database.

[0268] Generate personalized chatbots

[0269] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile, and then sends the customized information to the smartphone, where the chatbot completes the personalized settings.

[0270] Obtaining and responding to information

[0271] When a user types a question, it is sent from the smartphone to the server, which sends it to the generative AI model, which generates an appropriate response, which is then sent back from the server to the smartphone and displayed to the user.

[0272] For example, if a user inputs, "I want to check my recent payment history," the generative AI model will respond with, "My recent payment history is: Movies: 2,000 yen, Restaurants: 5,000 yen."

[0273] Data collection and analysis

[0274] The server collects and analyzes data on user interactions with the chatbot. Based on the analysis results, it generates new response patterns and updates the dataset of the generative AI model. This process continuously improves the accuracy of the chatbot's responses.

[0275] Specific examples

[0276] If a user types, "I want to improve my project management skills," the server searches for relevant online courses and learning resources and provides a response such as, "Recommended courses on project management are from XYZ Online School."

[0277] Prompt Sentence Examples

[0278] Prompt: "I want to check my recent transaction history."

[0279] Generated AI model response: "Recent payment history: Movies: 2000 yen, Restaurants: 5000 yen"

[0280] As a result, the present invention provides users with fast and personalized support, enabling them to efficiently resolve any questions or problems they may have regarding electronic payments.

[0281] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0282] Step 1: User enters basic information.

[0283] Users launch the smartphone application and enter basic information such as name, age, and electronic payment history, which allows the system to collect initial data on the user.

[0284] Step 2: Send basic information to the server.

[0285] The device sends the entered basic information to the server. The server receives the sent data and saves it as user information. The input data is sent to the server in JSON format.

[0286] Step 3: Save the basic information to the database.

[0287] The server stores the received basic information in a database, including the user's name, age, and electronic payment history, allowing for centralized management of data that can be used for subsequent processing.

[0288] Step 4: Customize the chatbot based on the user profile.

[0289] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile information stored in the database. This profile information is used to configure the chatbot to provide the most appropriate responses to the user.

[0290] Step 5: Send the user profile to the terminal.

[0291] The server sends customized chatbot information to the terminal, which receives the information and incorporates it into a smartphone application, providing the user with a personalized chatbot.

[0292] Step 6: Receive the user's question and send it to the generative AI model to generate a response.

[0293] The user uses their smartphone to input a question. This question is sent from the device to a server, which then sends it to a generative AI model. The generative AI model generates an appropriate response and returns it to the server. This process uses prompt statements (e.g., "I would like to check my recent payment history").

[0294] Step 7: Present the generated response to the user.

[0295] The server receives the response from the generative AI model and sends it to the device, which then displays the received response on the user's smartphone screen, allowing the user to immediately check the response from the system.

[0296] Step 8: Collect and analyze user interaction data.

[0297] The server continuously collects data on user interactions with the chatbot. This data is analyzed to identify whether questions about specific topics are frequently asked. The results of the analysis are used to update the dataset.

[0298] Step 9: Update the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0299] The server uses the collected dialogue data and analysis results to update the dataset of the generative AI model, which improves the accuracy of the chatbot's responses and allows it to provide more appropriate responses.

[0300] 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.

[0301] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems. It also provides more personalized responses by incorporating an emotion engine that recognizes the user's emotions and adjusts responses. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[0302] System Configuration

[0303] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine.

[0304] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[0305] Server: A central processing unit that receives information from user terminals, processes the data, and generates the necessary responses.

[0306] Database: Stores basic information, dialogue data, and emotion history, and is used for analysis and updates.

[0307] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions.

[0308] Emotion Engine: A technology for recognizing user emotions and adjusting responses.

[0309] Program processing overview

[0310] 1. Initial Setup

[0311] The user enters basic information.

[0312] The terminal sends this information to the server.

[0313] The server stores the information in a database and generates a user profile.

[0314] 2. Generating personalized chatbots

[0315] The server customizes the chatbot based on the user profile.

[0316] The server transmits the customization information to the terminal.

[0317] 3. Information Acquisition and Response

[0318] The user enters a question.

[0319] The terminal sends a question to the server.

[0320] The server sends the question to a generative AI model, which generates a response.

[0321] The emotion engine recognizes the user's emotions.

[0322] The server receives the emotion engine results and adjusts the response.

[0323] The server sends a response to the terminal, which displays it to the user.

[0324] 4. Automatic collaboration and growth support

[0325] The server collects and analyzes dialogue data and emotion history.

[0326] The server provides personalized learning resources to support the user's growth.

[0327] 5. Data collection and analysis

[0328] The server collects and analyzes dialogue data and emotion history.

[0329] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0330] Specific examples

[0331] Example of initial settings

[0332] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0333] The terminal sends this information to the server.

[0334] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0335] Examples of personalized chatbots

[0336] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[0337] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[0338] Specific examples of obtaining and responding to information

[0339] A user asks, "What's a good route for my next cycling trip?"

[0340] The terminal sends this question to the server.

[0341] The server sends a question to the generative AI model, which generates a response: "What's a good route for your next cycling trip?"

[0342] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[0343] The server then applies this sentiment analysis and generates a tailored response: "The best route for your next bike ride is along the nearby river. Have fun!"

[0344] The server sends this response to the terminal, which displays it to the user.

[0345] Specific examples of growth support

[0346] User types, "I want to improve my project management skills."

[0347] The server searches for relevant online courses and learning resources and sends them to the device.

[0348] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[0349] Examples of data collection and analysis

[0350] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[0351] The server adds new response patterns and datasets to respond to subsequent questions.

[0352] The introduction of the emotion engine allows the system of the present invention to provide more personalized responses according to the user's emotions, thereby improving the user experience and deepening user engagement.

[0353] The processing flow will be explained below.

[0354] Step 1:

[0355] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0356] Step 2:

[0357] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[0358] Step 3:

[0359] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[0360] Step 4:

[0361] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[0362] Step 5:

[0363] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[0364] Step 6:

[0365] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[0366] Step 7:

[0367] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[0368] Step 8:

[0369] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[0370] Step 9:

[0371] The emotion engine recognizes the user's emotions and analyzes the user's current emotions based on the content the user has entered and past conversation history.

[0372] Step 10:

[0373] The server receives the results of the emotion engine and adjusts the response. The server reflects the analysis results of the emotion engine in the generated response. For example, if the user is "excited," the server adds "Have fun!"

[0374] Step 11:

[0375] The server sends the adjusted response to the terminal. The server sends the final response to the user's terminal.

[0376] Step 12:

[0377] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is along the nearby river. Have fun!"

[0378] Step 13:

[0379] The server collects and analyzes dialogue data and emotion history. The server stores the dialogue history and emotion analysis results in a database and analyzes trends and frequently occurring problems.

[0380] Step 14:

[0381] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[0382] Step 15:

[0383] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data and emotion history to provide appropriate learning resources and career support. For example, a user who wants to improve their project management skills will be offered relevant online courses and practical advice.

[0384] Example 2

[0385] 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."

[0386] Conventional chatbot systems were unable to adequately reflect the individual needs and emotions of users and could only provide uniform responses. As a result, the user experience was poor and questions often did not receive appropriate responses. Furthermore, the collection and analysis of dialogue data was insufficient, resulting in slow improvements in response accuracy. This led to issues such as low user satisfaction and engagement.

[0387] 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.

[0388] In this invention, the server includes: a means for a user to input basic information; a means for transmitting the input basic information to the server; a means for saving the basic information in a database; a means for customizing the chatbot based on a user profile; a means for receiving a user's question and transmitting the question to a generative AI model to generate a response; a means for recognizing the user's emotion using an emotion engine and adjusting the response; a means for presenting the generated response to the user; a means for collecting and analyzing interaction data with the user; and a means for updating a dataset to improve the accuracy of the chatbot's responses based on the analysis results. This enables personalized responses that reflect the user's individual needs and emotions, thereby improving the user experience and response accuracy.

[0389] "Basic information" refers to personal information such as the user's name, age, hobbies, etc.

[0390] A "server" is a central processing unit that processes information from a user terminal and generates a response.

[0391] A "database" is a storage device that stores basic information, dialogue data, and emotion history of a user and retrieves them as needed.

[0392] A "user profile" is individual user information generated based on the user's basic information and behavioral history.

[0393] A "chatbot" is an automated dialogue system that interacts with users and provides answers to their questions.

[0394] A "generative AI model" refers to artificial intelligence technology that generates appropriate responses to user questions.

[0395] An "emotion engine" is a technology that recognizes emotions from user input and dialogue and adjusts responses accordingly.

[0396] "Dialogue data" refers to historical information about interactions between a user and a system.

[0397] "Response accuracy" is a measure of the accuracy and appropriateness of responses generated to user questions.

[0398] A "dataset" is a collection of interaction data used to train and update a generative AI model.

[0399] "Personalized learning resources" refers to individually optimized learning content provided based on the user's basic information and needs.

[0400] "Multiple platforms" refers to different hardware or software environments, examples of which include different operating systems or devices.

[0401] The present invention provides a system for allowing users to receive individually customized support, quickly and safely obtain information, and solve problems. As an embodiment of the present invention, the details of the system are described below.

[0402] System Configuration

[0403] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine. The specific hardware and software used are as follows:

[0404] User device: A device where a user enters basic information, sends questions, and receives responses from the server. Examples include smartphones and PCs.

[0405] Server: A central processing unit that receives information from user devices, processes the data, and generates the necessary response. Examples include web servers and application servers.

[0406] Database: This is used to store basic user information, interaction data, and emotion history, and is used for analysis and updating. Specifically, this applies to relational database management systems (RDBMS) and NoSQL databases.

[0407] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. Examples include OpenAI's GPT-4.

[0408] Emotion engine: A technology for recognizing user emotions and tailoring responses. Specifically, it is a machine learning model that includes a sentiment analysis algorithm.

[0409] Program processing overview

[0410] 1. Initial Setup

[0411] The user enters basic information.

[0412] The terminal sends this information to the server.

[0413] The server stores the information in a database and generates a user profile.

[0414] 2. Generating personalized chatbots

[0415] The server customizes the chatbot based on the user profile.

[0416] The server transmits the customization information to the terminal.

[0417] 3. Information Acquisition and Response

[0418] The user enters a question.

[0419] The terminal sends a question to the server.

[0420] The server sends the question to a generative AI model, which generates a response.

[0421] The emotion engine recognizes the user's emotions.

[0422] The server receives the emotion engine results and adjusts the response.

[0423] The server sends a response to the terminal, which displays it to the user.

[0424] 4. Automatic collaboration and growth support

[0425] The server collects and analyzes dialogue data and emotion history.

[0426] The server provides personalized learning resources to support the user's growth.

[0427] 5. Data collection and analysis

[0428] The server collects and analyzes dialogue data and emotion history.

[0429] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0430] Specific examples

[0431] Below are some examples of specific operations and responses:

[0432] Example of initial settings

[0433] The user launches the app and enters their name, age, hobbies, etc., such as "Name: Yamada Taro, Age: 25, Hobbies: Mountain climbing."

[0434] The terminal sends this information to the server.

[0435] The server receives the information and stores it in the database as "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[0436] Examples of personalized chatbots

[0437] The server sets a response pattern based on the information "Yamada Taro, 25 years old, mountain climbing."

[0438] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[0439] Specific examples of obtaining and responding to information

[0440] A user asks, "What's your recommendation for the next mountain I should climb?"

[0441] The terminal sends this question to the server.

[0442] The server sends a question to the generative AI model, which generates a response: "Recommendations for the next mountain to climb."

[0443] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[0444] The server reflects the sentiment analysis results and generates a tailored response such as, "The next recommended mountain to climb is nearby Mount Takao. Have fun!"

[0445] The server sends this response to the terminal, which displays it to the user.

[0446] Specific examples of growth support

[0447] User types, "I want to improve my project management skills."

[0448] The server searches for relevant online courses and learning resources and sends them to the device.

[0449] The device displays to the user, "ABC Online School is a recommended course on project management."

[0450] Examples of data collection and analysis

[0451] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[0452] The server adds new response patterns and datasets to respond to subsequent questions.

[0453] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0454] Step 1:

[0455] Enter and submit basic information

[0456] The user starts the application and enters basic information such as name, age, hobbies, etc. An example of input here is "Name: Taro Yamada, Age: 25, Hobbies: Mountain climbing."

[0457] The device sends the entered basic information to the server. The information sent is in JSON format, such as "{"Name": "Yamada Taro", "Age": 25, "Hobbies": "Mountain climbing"}".

[0458] As an output, the server receives this information.

[0459] Step 2:

[0460] Storing information and creating user profiles

[0461] The server stores the received information in a database. For example, the database stores "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[0462] The server generates a user profile based on the stored information, which is associated with a user ID to protect privacy.

[0463] As an output, a user profile is registered in a database.

[0464] Step 3:

[0465] Generate a customized chatbot

[0466] The server retrieves the user profile from the database and customizes the chatbot, for example, by setting response patterns related to "Taro Yamada, 25 years old, mountain climbing."

[0467] The server transmits the customization information to the terminal.

[0468] The device will display "Personalization settings complete."

[0469] As an output, a customized chatbot is prepared on the terminal.

[0470] Step 4:

[0471] Enter and submit your question

[0472] A user types a question such as "What's your recommendation for the next mountain to climb?"

[0473] The device sends this question to the server. The data sent is "{"Question": "What mountain do you recommend I climb next?"}".

[0474] As an output, the server receives the question.

[0475] Step 5:

[0476] Generating a response

[0477] The server sends the question to a generative AI model (e.g., OpenAI GPT-4), which analyzes the question and generates a response such as "Recommend the next mountain to climb."

[0478] As input, the server provides the question and the user profile to the generative AI model.

[0479] As an output, the generative AI model generates the response, "The next mountain to climb is Mount Takao."

[0480] Step 6:

[0481] Recognizing emotions and regulating responses

[0482] The emotion engine analyzes the user's input text and dialogue history to recognize emotions such as "excited."

[0483] The server reflects the analysis results of the emotion engine and generates a tailored response such as, "Mount Takao is especially recommended at this time of year. Have fun!"

[0484] As input, the emotion engine receives the user's text data.

[0485] The output is a tailored response that blends the results of the emotion engine with the response of the generative AI model.

[0486] Step 7:

[0487] Sending and Displaying Responses

[0488] The server sends the adjusted response to the terminal.

[0489] The device displays a response to the user, specifically, "Mount Takao is especially recommended at this time of year. Have fun!"

[0490] As an output, the user can receive an appropriate response.

[0491] Step 8:

[0492] Collecting dialogue data and emotion history

[0493] The server periodically collects all dialogue history and emotion history and stores them in a database.

[0494] As output, the dialogue data and emotion history are saved.

[0495] Step 9:

[0496] Analyzing data and updating datasets

[0497] The server analyzes the collected conversation data and sentiment history to identify trends in questions about specific topics and changes in sentiment.

[0498] Based on the analysis results, the server updates the dataset of the generative AI model to improve response accuracy.

[0499] It uses collected dialogue data and emotion history as input.

[0500] The output is an updated dataset that improves the accuracy of the chatbot's responses.

[0501] (Application example 2)

[0502] 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."

[0503] Conventional chatbot systems often fail to provide responses that fully reflect the individual needs of users. Furthermore, they lack personalization capabilities, such as responses that take the user's emotions into account and automatic provision of learning resources. Therefore, there is a need for an improved user experience. Particularly in brick-and-mortar stores, there is a need for a system that provides real-time, personalized support to users while they are shopping.

[0504] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information; means for transmitting the input basic information to the server; means for saving the basic information in a database; means for customizing the chatbot based on a user profile; means for receiving a user's question and transmitting the question to a generative AI model to generate a response; means for presenting the generated response to the user; means for using an emotion engine that recognizes the user's emotions and adjusts the response; means for collecting and analyzing dialogue data with the user; and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This makes it possible to provide quick and personalized responses to user questions and generate optimal responses according to the user's emotions.

[0505] The "means for users to input basic information" is an interface that allows users to digitally input personal information such as name, age, hobbies, etc.

[0506] The "means for saving basic information to a database" is a function for storing the information entered by the user in a database so that it can be referenced and analyzed later.

[0507] "Means for customizing chatbots based on user profiles" refers to a function for generating chatbots with individually set response patterns and characteristics based on saved basic information about users.

[0508] "Means for receiving a user's question and sending the question to a generative AI model to generate a response" refers to a system for receiving a question submitted by a user, sending it to a generative AI model, and generating an appropriate response.

[0509] The "means for presenting the generated response to the user" is an interface for displaying the response obtained from the generative AI model to the user.

[0510] The "means for using an emotion engine that recognizes the user's emotion and adjusts the response" is an engine for analyzing the user's emotion and optimizing the response based on the result.

[0511] "Means for collecting and analyzing dialogue data with users" is a function for collecting the content of dialogue exchanged between users and chatbots and analyzing it later.

[0512] "Means for updating the dataset to improve the accuracy of chatbot responses based on the analysis results" refers to a function that uses the analysis results of dialogue data to update the dataset to improve the content and accuracy of chatbot responses.

[0513] This invention is a "smart shopping assistant" system that optimizes the shopping experience in physical stores to suit user needs. When a user inputs a question, the system uses a generative AI model to generate a quick and personalized response, and further uses an emotion engine to provide the optimal response based on the user's emotions.

[0514] System Configuration

[0515] 1. User Device:

[0516] This is an interface that users use to enter basic information (such as name, age, hobbies, etc.) and questions. It is implemented as a smartphone application.

[0517] 2. Server:

[0518] It is a central processing unit that receives basic information and questions sent from the user device and performs various processes including generative AI models and emotion engines. It also stores the data in a database and generates and manages user profiles.

[0519] 3. Database:

[0520] This is a storage device for saving basic user information, dialogue data, emotion history, etc. Relational database management systems such as MySQL and PostgreSQL can be used.

[0521] 4. Generative AI Models:

[0522] It is an artificial intelligence model used to generate appropriate responses to user questions. It generally uses natural language processing techniques such as GPT-3.

[0523] 5. Emotion Engine:

[0524] It is an engine that recognizes emotions from user input and adjusts responses based on the results. For sentiment analysis, it uses sentiment analysis APIs (e.g., Microsoft Azure's text analysis API).

[0525] Program processing overview

[0526] 1. Initial Setup:

[0527] A user starts the app and enters basic information, for example, "Name: Taro Yamada, Age: 28, Hobby: Reading." The device sends this information to the server, which receives it and stores it in a database.

[0528] 2. Generate personalized chatbots:

[0529] The server customizes the chatbot based on the user profile. For example, it sets a response pattern based on the information "Yamada Taro, 28 years old, reading." The customized settings are sent to the device, and the message "Personalization settings complete" is displayed.

[0530] 3. Information Acquisition and Response:

[0531] When a user asks, "Tell me a review of this product," the device sends the question to a server. The server sends the question to a generative AI model, which generates a "review of this product." The emotion engine then analyzes the user's emotions, and if it recognizes, for example, an "excited" state, it adjusts the final response, displaying, "This product has a great review. Enjoy!"

[0532] 4. Data collection and analysis:

[0533] The server collects and analyzes the interaction data and sentiment history, for example identifying popular questions about a particular product and adding new response patterns and datasets.

[0534] Prompt Sentence Examples

[0535] User: Write a review for this product

[0536] Assistant:

[0537] This makes it possible to provide the information the user wants quickly and accurately, and improve the user experience by responding according to their emotions.

[0538] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0539] Step 1:

[0540] The user enters basic information

[0541] A user inputs basic information (such as name, age, and hobbies) through a smartphone app. The input data includes information such as "Name: Yamada Taro, Age: 28, Hobbies: Reading." This is the input data. The device acquires this data and sends it to the server.

[0542] Step 2:

[0543] The server stores basic information in a database

[0544] The server receives the basic information sent by the user from the device. The received data is analyzed and stored in a database in a structured format. For example, the information is stored in the database as "User ID: 001, Name: Yamada Taro, Age: 28, Hobby: Reading." This is the output data.

[0545] Step 3:

[0546] The server customizes the chatbot based on the user profile.

[0547] The server generates a user profile based on the stored basic information. This allows for customized settings based on the user's profile data. For example, based on the information "Yamada Taro, 28 years old, reading," the chatbot prepares relevant response patterns and content. The customized settings are output data.

[0548] Step 4:

[0549] The user enters a question

[0550] The user inputs a question through a smartphone app. For example, they might type, "Please give me a review of this product." This is the input data. The device then sends this question to the server.

[0551] Step 5:

[0552] The server sends the question to the generative AI model to generate a response.

[0553] The server receives the question sent by the user and sends it to the generative AI model. The generative AI model generates a response using the prompt "User: Tell me the review of this product\nAssistant:". For example, it generates "This product has good reviews." This is the output data.

[0554] Step 6:

[0555] The server recognizes the user's emotions and adjusts the response

[0556] Based on the generated response, the server sends the data to the emotion engine. The emotion engine recognizes the emotion from the text entered by the user, analyzing it as "excited," for example. Based on the results, it adjusts the response. For example, the final response might be "This product has good reviews. Enjoy." This is the output data.

[0557] Step 7:

[0558] The server generates a response and presents it to the user.

[0559] The server sends the adjusted response to the terminal, which displays it to the user, which is the output data the user receives.

[0560] Step 8:

[0561] The server collects and analyzes user interaction data

[0562] The server collects conversation data and emotion history between the user and the chatbot. The collected data is analyzed to determine conversation trends and frequently asked questions. This is the analytical data.

[0563] Step 9:

[0564] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0565] Based on the analysis results, the server updates the training dataset of the generative AI model to improve the accuracy of the generated responses, thereby providing accurate and personalized responses to subsequent questions. The updated dataset is the output data.

[0566] 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.

[0567] 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.

[0568] 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.

[0569] [Second embodiment]

[0570] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0571] 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.

[0572] 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).

[0573] 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.

[0574] 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.

[0575] 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).

[0576] 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.

[0577] 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.

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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."

[0582] The present invention aims to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[0583] System Configuration

[0584] This system consists of a user terminal, a server, a database, and a generative AI model.

[0585] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[0586] Server: Receives information from user devices, stores it in a database, and sends questions to the generative AI model to generate responses.

[0587] Database: Stores basic information and interaction data and is used for analysis and updates.

[0588] Generative AI model: An artificial intelligence technique that generates appropriate responses to user questions.

[0589] Program processing overview

[0590] 1. Initial Setup

[0591] The user enters basic information.

[0592] The terminal sends this information to the server.

[0593] The server stores the information in a database and generates a user profile.

[0594] 2. Generating personalized chatbots

[0595] The server customizes the chatbot based on the user profile.

[0596] The server transmits the customization information to the terminal.

[0597] 3. Information Acquisition and Response

[0598] The user enters a question.

[0599] The terminal sends a question to the server.

[0600] The server sends the question to a generative AI model, which generates a response.

[0601] The server sends a response to the terminal, which displays it to the user.

[0602] 4. Automatic collaboration and growth support

[0603] The server collects and analyzes the interaction data.

[0604] The server provides personalized learning resources to support the user's growth.

[0605] 5. Data collection and analysis

[0606] The server collects and analyzes the interaction data.

[0607] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0608] Specific examples

[0609] Example of initial settings

[0610] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0611] The terminal sends this information to the server.

[0612] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0613] Examples of personalized chatbots

[0614] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[0615] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[0616] Specific examples of obtaining and responding to information

[0617] A user asks, "What's a good route for my next cycling trip?"

[0618] The terminal sends this question to the server.

[0619] The server sends a question to the generative AI model and receives a response such as, "The best cycling route is the one along the nearby river."

[0620] The server sends this response to the terminal, which displays it to the user.

[0621] Specific examples of growth support

[0622] User types, "I want to improve my project management skills."

[0623] The server searches for relevant online courses and learning resources and sends them to the device.

[0624] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[0625] Examples of data collection and analysis

[0626] The server analyzes the dialogue history and identifies an increase in questions about a particular topic.

[0627] The server adds new response patterns and datasets to respond to subsequent questions.

[0628] The system of the present invention provides efficient and personalized support to users, enabling them to quickly obtain information and solve problems.

[0629] The processing flow will be explained below.

[0630] Step 1:

[0631] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0632] Step 2:

[0633] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[0634] Step 3:

[0635] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[0636] Step 4:

[0637] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[0638] Step 5:

[0639] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[0640] Step 6:

[0641] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[0642] Step 7:

[0643] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[0644] Step 8:

[0645] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[0646] Step 9:

[0647] The server sends the generated response to the terminal. The server receives the response data and sends it to the user's terminal.

[0648] Step 10:

[0649] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is the one along the nearby river."

[0650] Step 11:

[0651] The server collects and analyzes the interaction data. The server collects the interaction history with the user and analyzes trends and frequently occurring problems.

[0652] Step 12:

[0653] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[0654] Step 13:

[0655] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data to provide appropriate learning resources and career support. For example, a user who "wants to improve their project management skills" will be provided with relevant online courses and practical advice.

[0656] Example 1

[0657] 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."

[0658] The purpose of this invention is to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. It aims to provide personalized learning resources, which have been difficult to achieve with conventional systems, and to smoothly deploy conversational agents that are compatible with multiple platforms. Another objective is to provide an effective means for collecting and analyzing dialogue data and improving the response accuracy of conversational agents.

[0659] 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.

[0660] In this invention, the server includes a means for customizing a conversational agent based on a user profile, a means for receiving a user's questions and sending the questions to a generative AI model to generate a response, and a means for providing personalized learning resources to support the user's growth. This allows for efficient and personalized support for users, enabling them to quickly obtain information and solve problems. It also allows for the collection and analysis of dialogue data, and the improvement of the conversational agent's response accuracy based on the analysis results.

[0661] "Basic information" is data required for initial setup, such as name, age, and hobbies, entered by the user.

[0662] The "server" is a central processing unit that receives, stores, and processes data sent from user devices and works with the generative AI model to generate responses.

[0663] A "database" is a place where information is collected to efficiently store and manage basic user information and conversation data.

[0664] A "user profile" is a data set created based on collected basic information about a user to identify and specify an individual user.

[0665] A "conversational agent" is an artificial intelligence system that uses generative AI models to engage in dialogue with users and provide appropriate responses to their questions.

[0666] A "generative artificial intelligence model" is an artificial intelligence algorithm that learns from given data and generates appropriate responses to user questions.

[0667] "Dialogue data" is a record of the information exchanged between a user and a conversational agent.

[0668] "Learning Resources" are educational materials such as online courses and course materials offered to help users grow.

[0669] "Multiple information platforms" is a general term for various Internet services that can be used in different software and hardware environments.

[0670] "Personalization" is the process of individually optimizing information and services according to the characteristics and needs of each individual user.

[0671] The present invention provides a system that allows users to receive personalized support, quickly and safely obtain information, and solve problems. Specific embodiments of the present invention are described in detail below.

[0672] System Configuration

[0673] This system consists of a user terminal, a server, a database, and a generative AI model.

[0674] User device: The user uses this device to enter basic information, send questions, and receive responses from the server. Examples include a smartphone or PC.

[0675] Server: Receives information from user devices, stores it in a database, sends questions to the generative AI model, and generates responses. Server-side programs such as Python and Node.js are used.

[0676] Database: This stores basic information and interaction data and is used for analysis and updating. Relational databases such as MySQL and PostgreSQL are used.

[0677] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. For example, OpenAI's GPT model is used.

[0678] Program processing overview

[0679] Initial Setup

[0680] The user launches the app and enters basic information. The user's device sends this information to the server. The server receives the information and stores it in a database. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[0681] Generate personalized chatbots

[0682] The server generates a customized chatbot based on the user profile. This setting information is sent to the device, and the device displays "Personalization setting complete." For example, the server generates a specific response pattern based on "Taro Tanaka, 30 years old, cycling."

[0683] Obtaining and responding to information

[0684] The user inputs a question, and the device sends it to the server. For example, the user might input, "What's a good route for my next cycling trip?" The server sends the question to a generative AI model, which generates a response such as, "The best route for cycling is the one along the nearby river." The generated response is then sent to the device, which displays it.

[0685] Automated collaboration and growth support

[0686] The server collects and analyzes interaction data, identifying increased interest in specific topics, and providing personalized learning resources to help users grow. For example, if a user types, "I want to improve my project management skills," the server can provide information about related online courses.

[0687] Data collection and analysis

[0688] The server analyzes the dialogue history and updates the dataset of the generative AI model, adding new response patterns and improving the accuracy of responses to the next question.

[0689] Examples of concrete examples and prompts

[0690] Example explanation:

[0691] User types, "I want to improve my project management skills."

[0692] The server searches for relevant online courses and learning resources and sends them to the device.

[0693] The device displays, "Recommended courses on project management are from XYZ Online School."

[0694] Example prompt sentence:

[0695] When a user asks the AI ​​model a question, they can enter a prompt such as, "Tell me a good route for my next cycling trip."

[0696] This system provides users with efficient and personalized support, enabling them to quickly obtain information and solve problems.

[0697] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0698] System program processing flow

[0699] Initial Setup

[0700] Step 1: User enters basic information

[0701] The user launches the app and enters basic information such as name, age, and hobbies.

[0702] Input: Name, age, hobbies, etc.

[0703] Output: Basic information is saved to the device.

[0704] Example: Enter "Name: Taro Tanaka, Age: 30, Hobby: Cycling".

[0705] Step 2: The device sends the information to the server

[0706] The terminal sends the entered basic information to the server.

[0707] Input: Basic information

[0708] Output: Basic information received by the server

[0709] The device sends data to the server using the MQTT protocol.

[0710] Step 3: The server stores the information

[0711] The server stores the received information in a database.

[0712] Input: Basic information

[0713] Output: Basic information stored in the database

[0714] Store the information in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0715] Step 4: Create a user profile

[0716] The server generates a user profile based on the stored information.

[0717] Input: Basic information stored in the database

[0718] Output: Generated user profile

[0719] A user profile is generated and the system optimizes its operation based on it.

[0720] Generate personalized chatbots

[0721] Step 1: The server sends the customization data to the generative AI model

[0722] The server retrieves the user profile and sends the customization data to the generative AI model.

[0723] Input: User profile

[0724] Output: Customized data to send to the generative AI model

[0725] For example, let's say "User data: Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0726] Step 2: The generative AI model generates response patterns

[0727] A generative AI model generates personalized response patterns based on the data it receives.

[0728] Input: Customization data

[0729] Output: The generated response pattern

[0730] Generate specific response patterns that take individual content into consideration.

[0731] Step 3: The server sends the configuration data to the device

[0732] The server transmits the generated setting data to the terminal.

[0733] Input: Generated response pattern

[0734] Output: Sending configuration data

[0735] The server sends a response to the terminal, which receives it.

[0736] Step 4: Your device will display a message saying it's set up

[0737] The device will display "Personalized settings complete" based on the setting data received.

[0738] Input: Setting data

[0739] Output: "Personalization setup complete"

[0740] Notify the user that customization is complete.

[0741] Obtaining and responding to information

[0742] Step 1: User enters question

[0743] The user inputs a question such as "Tell me a good route for my next cycling trip."

[0744] Input: Question

[0745] Output: The question is saved to the terminal.

[0746] Step 2: The device sends a question to the server

[0747] The terminal sends the entered question to the server.

[0748] Input: Question

[0749] Output: The question sent to the server

[0750] Submit a question using the REST API.

[0751] Step 3: The server sends the response to the generative AI model

[0752] The server sends the question to the generative AI model, which generates a response such as, "The best cycling route is the one along the nearby river."

[0753] Input: Question

[0754] Output: The generated response

[0755] Leverage generative artificial intelligence models to generate appropriate responses.

[0756] Step 4: The server sends a response to the device

[0757] The server sends the generated response to the terminal.

[0758] Input: Generated response

[0759] Output: Response sent to the terminal

[0760] Step 5: The terminal displays the response

[0761] The terminal displays the received response to the user.

[0762] Input: Response from the server

[0763] Output: The response that is displayed to the user

[0764] Automated collaboration and growth support

[0765] Step 1: The server collects and analyzes the interaction data

[0766] The server collects and analyzes the interaction data.

[0767] Input: Interaction data

[0768] Output: Analysis results

[0769] Identify growing interest in a particular topic.

[0770] Step 2: The server provides personalized learning resources

[0771] The server provides personalized learning resources based on the user's interests.

[0772] Input: Analysis results

[0773] Output: Personalized learning resources

[0774] Example: "The recommended course on project management is XYZ Online School."

[0775] Data collection and analysis

[0776] Step 1: The server analyzes the conversation history

[0777] The server analyzes the dialogue history and updates the dataset for the generative AI model.

[0778] Input: Dialogue history

[0779] Output: Updated dataset

[0780] Identify frequently asked questions and emerging trends and add new response patterns.

[0781] Step 2: Improving response accuracy

[0782] The server will provide a more accurate response to subsequent questions.

[0783] Input: Updated dataset

[0784] Output: Highly accurate response

[0785] Improve the accuracy of generative AI models and increase user satisfaction.

[0786] (Application example 1)

[0787] 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."

[0788] Conventional electronic payment services have faced the challenge of making it difficult for users to receive prompt, safe, and appropriate support. In particular, it has been difficult to provide personalized support tailored to each user's individual situation, and when questions or problems arise regarding electronic payments, appropriate responses are often not possible. Furthermore, there has been insufficient analysis of dialogue data to improve user convenience, and the accuracy of generative AI models has not been improved.

[0789] 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.

[0790] In this invention, the server includes means for acquiring basic information and electronic payment history of a user and providing personalized support based thereon, means for identifying questions on specific topics from the dialogue history and generating new response patterns, and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This allows users to receive prompt, individually customized support and efficiently resolve questions and problems related to electronic payments.

[0791] "Basic user information" refers to profile information such as name, age, hobbies, and electronic payment history that a user enters when using the system.

[0792] "Server" means a central processing unit for processing information received from user terminals, storing it in a database, sending questions to the generative AI model, and providing analysis and responses.

[0793] A "database" is an information management system that stores basic user information and conversation data over a long period of time and is used for analysis and updating.

[0794] A "generative AI model" is an artificial intelligence technology that generates appropriate responses to user questions, and specifically refers to advanced natural language processing models such as GPT-3.

[0795] A "profile" is a personalized data set that collects and centralizes basic information about a user.

[0796] A "chatbot" is an automated response program that interacts with users and uses generative AI models to provide personalized conversations.

[0797] "Personalization" refers to providing optimal support and responses to individual users based on their basic information and historical data.

[0798] "Electronic payment history" refers to a record of electronic payments made by a user in the past.

[0799] "Dialogue history" is data that records the content of past dialogues between a user and a chatbot.

[0800] A "new response pattern" is a different response method from the conventional one, generated based on collected and analyzed dialogue data.

[0801] "Dataset updating" is the process of updating the training data for a generative AI model based on the results of collecting and analyzing interaction data.

[0802] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems related to electronic payments. Hereinafter, the program processing of the system will be described as an embodiment of the present invention.

[0803] System Configuration

[0804] This system mainly uses the following hardware and software.

[0805] User device: Smartphone

[0806] Server: Cloud server (e.g. AWS, Google Cloud)

[0807] Database: Relational database (e.g. MySQL, PostgreSQL)

[0808] Generative AI model: GPT-3 (OpenAI)

[0809] Program processing overview

[0810] Initial Setup

[0811] When a user first uses the system, they enter basic information (e.g., name, age, electronic payment history) using their smartphone. This information is sent from the smartphone to the server, which then creates a user profile and stores it in a database.

[0812] Generate personalized chatbots

[0813] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile, and then sends the customized information to the smartphone, where the chatbot completes the personalized settings.

[0814] Obtaining and responding to information

[0815] When a user types a question, it is sent from the smartphone to the server, which sends it to the generative AI model, which generates an appropriate response, which is then sent back from the server to the smartphone and displayed to the user.

[0816] For example, if a user inputs, "I want to check my recent payment history," the generative AI model will respond with, "My recent payment history is: Movies: 2,000 yen, Restaurants: 5,000 yen."

[0817] Data collection and analysis

[0818] The server collects and analyzes data on user interactions with the chatbot. Based on the analysis results, it generates new response patterns and updates the dataset of the generative AI model. This process continuously improves the accuracy of the chatbot's responses.

[0819] Specific examples

[0820] If a user types, "I want to improve my project management skills," the server searches for relevant online courses and learning resources and provides a response such as, "Recommended courses on project management are from XYZ Online School."

[0821] Prompt Sentence Examples

[0822] Prompt: "I want to check my recent transaction history."

[0823] Generated AI model response: "Recent payment history: Movies: 2000 yen, Restaurants: 5000 yen"

[0824] As a result, the present invention provides users with fast and personalized support, enabling them to efficiently resolve any questions or problems they may have regarding electronic payments.

[0825] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0826] Step 1: User enters basic information.

[0827] Users launch the smartphone application and enter basic information such as name, age, and electronic payment history, which allows the system to collect initial data on the user.

[0828] Step 2: Send basic information to the server.

[0829] The device sends the entered basic information to the server. The server receives the sent data and saves it as user information. The input data is sent to the server in JSON format.

[0830] Step 3: Save the basic information to the database.

[0831] The server stores the received basic information in a database, including the user's name, age, and electronic payment history, allowing for centralized management of data that can be used for subsequent processing.

[0832] Step 4: Customize the chatbot based on the user profile.

[0833] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile information stored in the database. This profile information is used to configure the chatbot to provide the most appropriate responses to the user.

[0834] Step 5: Send the user profile to the terminal.

[0835] The server sends customized chatbot information to the terminal, which receives the information and incorporates it into a smartphone application, providing the user with a personalized chatbot.

[0836] Step 6: Receive the user's question and send it to the generative AI model to generate a response.

[0837] The user uses their smartphone to input a question. This question is sent from the device to a server, which then sends it to a generative AI model. The generative AI model generates an appropriate response and returns it to the server. This process uses prompt statements (e.g., "I would like to check my recent payment history").

[0838] Step 7: Present the generated response to the user.

[0839] The server receives the response from the generative AI model and sends it to the device, which then displays the received response on the user's smartphone screen, allowing the user to immediately check the response from the system.

[0840] Step 8: Collect and analyze user interaction data.

[0841] The server continuously collects data on user interactions with the chatbot. This data is analyzed to identify whether questions about specific topics are frequently asked. The results of the analysis are used to update the dataset.

[0842] Step 9: Update the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0843] The server uses the collected dialogue data and analysis results to update the dataset of the generative AI model, which improves the accuracy of the chatbot's responses and allows it to provide more appropriate responses.

[0844] 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.

[0845] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems. It also provides more personalized responses by incorporating an emotion engine that recognizes the user's emotions and adjusts responses. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[0846] System Configuration

[0847] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine.

[0848] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[0849] Server: A central processing unit that receives information from user terminals, processes the data, and generates the necessary responses.

[0850] Database: Stores basic information, dialogue data, and emotion history, and is used for analysis and updates.

[0851] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions.

[0852] Emotion Engine: A technology for recognizing user emotions and adjusting responses.

[0853] Program processing overview

[0854] 1. Initial Setup

[0855] The user enters basic information.

[0856] The terminal sends this information to the server.

[0857] The server stores the information in a database and generates a user profile.

[0858] 2. Generating personalized chatbots

[0859] The server customizes the chatbot based on the user profile.

[0860] The server transmits the customization information to the terminal.

[0861] 3. Information Acquisition and Response

[0862] The user enters a question.

[0863] The terminal sends a question to the server.

[0864] The server sends the question to a generative AI model, which generates a response.

[0865] The emotion engine recognizes the user's emotions.

[0866] The server receives the emotion engine results and adjusts the response.

[0867] The server sends a response to the terminal, which displays it to the user.

[0868] 4. Automatic collaboration and growth support

[0869] The server collects and analyzes dialogue data and emotion history.

[0870] The server provides personalized learning resources to support the user's growth.

[0871] 5. Data collection and analysis

[0872] The server collects and analyzes dialogue data and emotion history.

[0873] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0874] Specific examples

[0875] Example of initial settings

[0876] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0877] The terminal sends this information to the server.

[0878] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[0879] Examples of personalized chatbots

[0880] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[0881] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[0882] Specific examples of obtaining and responding to information

[0883] A user asks, "What's a good route for my next cycling trip?"

[0884] The terminal sends this question to the server.

[0885] The server sends a question to the generative AI model, which generates a response: "What's a good route for your next cycling trip?"

[0886] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[0887] The server then applies this sentiment analysis and generates a tailored response: "The best route for your next bike ride is along the nearby river. Have fun!"

[0888] The server sends this response to the terminal, which displays it to the user.

[0889] Specific examples of growth support

[0890] User types, "I want to improve my project management skills."

[0891] The server searches for relevant online courses and learning resources and sends them to the device.

[0892] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[0893] Examples of data collection and analysis

[0894] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[0895] The server adds new response patterns and datasets to respond to subsequent questions.

[0896] The introduction of the emotion engine allows the system of the present invention to provide more personalized responses according to the user's emotions, thereby improving the user experience and deepening user engagement.

[0897] The processing flow will be explained below.

[0898] Step 1:

[0899] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[0900] Step 2:

[0901] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[0902] Step 3:

[0903] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[0904] Step 4:

[0905] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[0906] Step 5:

[0907] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[0908] Step 6:

[0909] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[0910] Step 7:

[0911] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[0912] Step 8:

[0913] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[0914] Step 9:

[0915] The emotion engine recognizes the user's emotions and analyzes the user's current emotions based on the content the user has entered and past conversation history.

[0916] Step 10:

[0917] The server receives the results of the emotion engine and adjusts the response. The server reflects the analysis results of the emotion engine in the generated response. For example, if the user is "excited," the server adds "Have fun!"

[0918] Step 11:

[0919] The server sends the adjusted response to the terminal. The server sends the final response to the user's terminal.

[0920] Step 12:

[0921] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is along the nearby river. Have fun!"

[0922] Step 13:

[0923] The server collects and analyzes dialogue data and emotion history. The server stores the dialogue history and emotion analysis results in a database and analyzes trends and frequently occurring problems.

[0924] Step 14:

[0925] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[0926] Step 15:

[0927] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data and emotion history to provide appropriate learning resources and career support. For example, a user who wants to improve their project management skills will be offered relevant online courses and practical advice.

[0928] Example 2

[0929] 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."

[0930] Conventional chatbot systems were unable to adequately reflect the individual needs and emotions of users and could only provide uniform responses. As a result, the user experience was poor and questions often did not receive appropriate responses. Furthermore, the collection and analysis of dialogue data was insufficient, resulting in slow improvements in response accuracy. This led to issues such as low user satisfaction and engagement.

[0931] 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.

[0932] In this invention, the server includes: a means for a user to input basic information; a means for transmitting the input basic information to the server; a means for saving the basic information in a database; a means for customizing the chatbot based on a user profile; a means for receiving a user's question and transmitting the question to a generative AI model to generate a response; a means for recognizing the user's emotion using an emotion engine and adjusting the response; a means for presenting the generated response to the user; a means for collecting and analyzing interaction data with the user; and a means for updating a dataset to improve the accuracy of the chatbot's responses based on the analysis results. This enables personalized responses that reflect the user's individual needs and emotions, thereby improving the user experience and response accuracy.

[0933] "Basic information" refers to personal information such as the user's name, age, hobbies, etc.

[0934] A "server" is a central processing unit that processes information from a user terminal and generates a response.

[0935] A "database" is a storage device that stores basic information, dialogue data, and emotion history of a user and retrieves them as needed.

[0936] A "user profile" is individual user information generated based on the user's basic information and behavioral history.

[0937] A "chatbot" is an automated dialogue system that interacts with users and provides answers to their questions.

[0938] A "generative AI model" refers to artificial intelligence technology that generates appropriate responses to user questions.

[0939] An "emotion engine" is a technology that recognizes emotions from user input and dialogue and adjusts responses accordingly.

[0940] "Dialogue data" refers to historical information about interactions between a user and a system.

[0941] "Response accuracy" is a measure of the accuracy and appropriateness of responses generated to user questions.

[0942] A "dataset" is a collection of interaction data used to train and update a generative AI model.

[0943] "Personalized learning resources" refers to individually optimized learning content provided based on the user's basic information and needs.

[0944] "Multiple platforms" refers to different hardware or software environments, examples of which include different operating systems or devices.

[0945] The present invention provides a system for allowing users to receive individually customized support, quickly and safely obtain information, and solve problems. As an embodiment of the present invention, the details of the system are described below.

[0946] System Configuration

[0947] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine. The specific hardware and software used are as follows:

[0948] User device: A device where a user enters basic information, sends questions, and receives responses from the server. Examples include smartphones and PCs.

[0949] Server: A central processing unit that receives information from user devices, processes the data, and generates the necessary response. Examples include web servers and application servers.

[0950] Database: This is used to store basic user information, interaction data, and emotion history, and is used for analysis and updating. Specifically, this applies to relational database management systems (RDBMS) and NoSQL databases.

[0951] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. Examples include OpenAI's GPT-4.

[0952] Emotion engine: A technology for recognizing user emotions and tailoring responses. Specifically, it is a machine learning model that includes a sentiment analysis algorithm.

[0953] Program processing overview

[0954] 1. Initial Setup

[0955] The user enters basic information.

[0956] The terminal sends this information to the server.

[0957] The server stores the information in a database and generates a user profile.

[0958] 2. Generating personalized chatbots

[0959] The server customizes the chatbot based on the user profile.

[0960] The server transmits the customization information to the terminal.

[0961] 3. Information Acquisition and Response

[0962] The user enters a question.

[0963] The terminal sends a question to the server.

[0964] The server sends the question to a generative AI model, which generates a response.

[0965] The emotion engine recognizes the user's emotions.

[0966] The server receives the emotion engine results and adjusts the response.

[0967] The server sends a response to the terminal, which displays it to the user.

[0968] 4. Automatic collaboration and growth support

[0969] The server collects and analyzes dialogue data and emotion history.

[0970] The server provides personalized learning resources to support the user's growth.

[0971] 5. Data collection and analysis

[0972] The server collects and analyzes dialogue data and emotion history.

[0973] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[0974] Specific examples

[0975] Below are some examples of specific operations and responses:

[0976] Example of initial settings

[0977] The user launches the app and enters their name, age, hobbies, etc., such as "Name: Yamada Taro, Age: 25, Hobbies: Mountain climbing."

[0978] The terminal sends this information to the server.

[0979] The server receives the information and stores it in the database as "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[0980] Examples of personalized chatbots

[0981] The server sets a response pattern based on the information "Yamada Taro, 25 years old, mountain climbing."

[0982] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[0983] Specific examples of obtaining and responding to information

[0984] A user asks, "What's your recommendation for the next mountain I should climb?"

[0985] The terminal sends this question to the server.

[0986] The server sends a question to the generative AI model, which generates a response: "Recommendations for the next mountain to climb."

[0987] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[0988] The server reflects the sentiment analysis results and generates a tailored response such as, "The next recommended mountain to climb is nearby Mount Takao. Have fun!"

[0989] The server sends this response to the terminal, which displays it to the user.

[0990] Specific examples of growth support

[0991] User types, "I want to improve my project management skills."

[0992] The server searches for relevant online courses and learning resources and sends them to the device.

[0993] The device displays to the user, "ABC Online School is a recommended course on project management."

[0994] Examples of data collection and analysis

[0995] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[0996] The server adds new response patterns and datasets to respond to subsequent questions.

[0997] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0998] Step 1:

[0999] Enter and submit basic information

[1000] The user starts the application and enters basic information such as name, age, hobbies, etc. An example of input here is "Name: Taro Yamada, Age: 25, Hobbies: Mountain climbing."

[1001] The device sends the entered basic information to the server. The information sent is in JSON format, such as "{"Name": "Yamada Taro", "Age": 25, "Hobbies": "Mountain climbing"}".

[1002] As an output, the server receives this information.

[1003] Step 2:

[1004] Storing information and creating user profiles

[1005] The server stores the received information in a database. For example, the database stores "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[1006] The server generates a user profile based on the stored information, which is associated with a user ID to protect privacy.

[1007] As an output, a user profile is registered in a database.

[1008] Step 3:

[1009] Generate a customized chatbot

[1010] The server retrieves the user profile from the database and customizes the chatbot, for example, by setting response patterns related to "Taro Yamada, 25 years old, mountain climbing."

[1011] The server transmits the customization information to the terminal.

[1012] The device will display "Personalization settings complete."

[1013] As an output, a customized chatbot is prepared on the terminal.

[1014] Step 4:

[1015] Enter and submit your question

[1016] A user types a question such as "What's your recommendation for the next mountain to climb?"

[1017] The device sends this question to the server. The data sent is "{"Question": "What mountain do you recommend I climb next?"}".

[1018] As an output, the server receives the question.

[1019] Step 5:

[1020] Generating a response

[1021] The server sends the question to a generative AI model (e.g., OpenAI GPT-4), which analyzes the question and generates a response such as "Recommend the next mountain to climb."

[1022] As input, the server provides the question and the user profile to the generative AI model.

[1023] As an output, the generative AI model generates the response, "The next mountain to climb is Mount Takao."

[1024] Step 6:

[1025] Recognizing emotions and regulating responses

[1026] The emotion engine analyzes the user's input text and dialogue history to recognize emotions such as "excited."

[1027] The server reflects the analysis results of the emotion engine and generates a tailored response such as, "Mount Takao is especially recommended at this time of year. Have fun!"

[1028] As input, the emotion engine receives the user's text data.

[1029] The output is a tailored response that blends the results of the emotion engine with the response of the generative AI model.

[1030] Step 7:

[1031] Sending and Displaying Responses

[1032] The server sends the adjusted response to the terminal.

[1033] The device displays a response to the user, specifically, "Mount Takao is especially recommended at this time of year. Have fun!"

[1034] As an output, the user can receive an appropriate response.

[1035] Step 8:

[1036] Collecting dialogue data and emotion history

[1037] The server periodically collects all dialogue history and emotion history and stores them in a database.

[1038] As output, the dialogue data and emotion history are saved.

[1039] Step 9:

[1040] Analyzing data and updating datasets

[1041] The server analyzes the collected conversation data and sentiment history to identify trends in questions about specific topics and changes in sentiment.

[1042] Based on the analysis results, the server updates the dataset of the generative AI model to improve response accuracy.

[1043] It uses collected dialogue data and emotion history as input.

[1044] The output is an updated dataset that improves the accuracy of the chatbot's responses.

[1045] (Application example 2)

[1046] 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."

[1047] Conventional chatbot systems often fail to provide responses that fully reflect the individual needs of users. Furthermore, they lack personalization capabilities, such as responses that take the user's emotions into account and automatic provision of learning resources. Therefore, there is a need for an improved user experience. Particularly in brick-and-mortar stores, there is a need for a system that provides real-time, personalized support to users while they are shopping.

[1048] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information; means for transmitting the input basic information to the server; means for saving the basic information in a database; means for customizing the chatbot based on a user profile; means for receiving a user's question and transmitting the question to a generative AI model to generate a response; means for presenting the generated response to the user; means for using an emotion engine that recognizes the user's emotions and adjusts the response; means for collecting and analyzing dialogue data with the user; and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This makes it possible to provide quick and personalized responses to user questions and generate optimal responses according to the user's emotions.

[1049] The "means for users to input basic information" is an interface that allows users to digitally input personal information such as name, age, hobbies, etc.

[1050] The "means for saving basic information to a database" is a function for storing the information entered by the user in a database so that it can be referenced and analyzed later.

[1051] "Means for customizing chatbots based on user profiles" refers to a function for generating chatbots with individually set response patterns and characteristics based on saved basic information about users.

[1052] "Means for receiving a user's question and sending the question to a generative AI model to generate a response" refers to a system for receiving a question submitted by a user, sending it to a generative AI model, and generating an appropriate response.

[1053] The "means for presenting the generated response to the user" is an interface for displaying the response obtained from the generative AI model to the user.

[1054] The "means for using an emotion engine that recognizes the user's emotion and adjusts the response" is an engine for analyzing the user's emotion and optimizing the response based on the result.

[1055] "Means for collecting and analyzing dialogue data with users" is a function for collecting the content of dialogue exchanged between users and chatbots and analyzing it later.

[1056] "Means for updating the dataset to improve the accuracy of chatbot responses based on the analysis results" refers to a function that uses the analysis results of dialogue data to update the dataset to improve the content and accuracy of chatbot responses.

[1057] This invention is a "smart shopping assistant" system that optimizes the shopping experience in physical stores to suit user needs. When a user inputs a question, the system uses a generative AI model to generate a quick and personalized response, and further uses an emotion engine to provide the optimal response based on the user's emotions.

[1058] System Configuration

[1059] 1. User Device:

[1060] This is an interface that users use to enter basic information (such as name, age, hobbies, etc.) and questions. It is implemented as a smartphone application.

[1061] 2. Server:

[1062] It is a central processing unit that receives basic information and questions sent from the user device and performs various processes including generative AI models and emotion engines. It also stores the data in a database and generates and manages user profiles.

[1063] 3. Database:

[1064] This is a storage device for saving basic user information, dialogue data, emotion history, etc. Relational database management systems such as MySQL and PostgreSQL can be used.

[1065] 4. Generative AI Models:

[1066] It is an artificial intelligence model used to generate appropriate responses to user questions. It generally uses natural language processing techniques such as GPT-3.

[1067] 5. Emotion Engine:

[1068] It is an engine that recognizes emotions from user input and adjusts responses based on the results. For sentiment analysis, it uses sentiment analysis APIs (e.g., Microsoft Azure's text analysis API).

[1069] Program processing overview

[1070] 1. Initial Setup:

[1071] A user starts the app and enters basic information, for example, "Name: Taro Yamada, Age: 28, Hobby: Reading." The device sends this information to the server, which receives it and stores it in a database.

[1072] 2. Generate personalized chatbots:

[1073] The server customizes the chatbot based on the user profile. For example, it sets a response pattern based on the information "Yamada Taro, 28 years old, reading." The customized settings are sent to the device, and the message "Personalization settings complete" is displayed.

[1074] 3. Information Acquisition and Response:

[1075] When a user asks, "Tell me a review of this product," the device sends the question to a server. The server sends the question to a generative AI model, which generates a "review of this product." The emotion engine then analyzes the user's emotions, and if it recognizes, for example, an "excited" state, it adjusts the final response, displaying, "This product has a great review. Enjoy!"

[1076] 4. Data collection and analysis:

[1077] The server collects and analyzes the interaction data and sentiment history, for example identifying popular questions about a particular product and adding new response patterns and datasets.

[1078] Prompt Sentence Examples

[1079] User: Write a review for this product

[1080] Assistant:

[1081] This makes it possible to provide the information the user wants quickly and accurately, and improve the user experience by responding according to their emotions.

[1082] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1083] Step 1:

[1084] The user enters basic information

[1085] A user inputs basic information (such as name, age, and hobbies) through a smartphone app. The input data includes information such as "Name: Yamada Taro, Age: 28, Hobbies: Reading." This is the input data. The device acquires this data and sends it to the server.

[1086] Step 2:

[1087] The server stores basic information in a database

[1088] The server receives the basic information sent by the user from the device. The received data is analyzed and stored in a database in a structured format. For example, the information is stored in the database as "User ID: 001, Name: Yamada Taro, Age: 28, Hobby: Reading." This is the output data.

[1089] Step 3:

[1090] The server customizes the chatbot based on the user profile.

[1091] The server generates a user profile based on the stored basic information. This allows for customized settings based on the user's profile data. For example, based on the information "Yamada Taro, 28 years old, reading," the chatbot prepares relevant response patterns and content. The customized settings are output data.

[1092] Step 4:

[1093] The user enters a question

[1094] The user inputs a question through a smartphone app. For example, they might type, "Please give me a review of this product." This is the input data. The device then sends this question to the server.

[1095] Step 5:

[1096] The server sends the question to the generative AI model to generate a response.

[1097] The server receives the question sent by the user and sends it to the generative AI model. The generative AI model generates a response using the prompt "User: Tell me the review of this product\nAssistant:". For example, it generates "This product has good reviews." This is the output data.

[1098] Step 6:

[1099] The server recognizes the user's emotions and adjusts the response

[1100] Based on the generated response, the server sends the data to the emotion engine. The emotion engine recognizes the emotion from the text entered by the user, analyzing it as "excited," for example. Based on the results, it adjusts the response. For example, the final response might be "This product has good reviews. Enjoy." This is the output data.

[1101] Step 7:

[1102] The server generates a response and presents it to the user.

[1103] The server sends the adjusted response to the terminal, which displays it to the user, which is the output data the user receives.

[1104] Step 8:

[1105] The server collects and analyzes user interaction data

[1106] The server collects conversation data and emotion history between the user and the chatbot. The collected data is analyzed to determine conversation trends and frequently asked questions. This is the analytical data.

[1107] Step 9:

[1108] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1109] Based on the analysis results, the server updates the training dataset of the generative AI model to improve the accuracy of the generated responses, thereby providing accurate and personalized responses to subsequent questions. The updated dataset is the output data.

[1110] 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.

[1111] 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.

[1112] 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.

[1113] [Third embodiment]

[1114] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1115] 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.

[1116] 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).

[1117] 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.

[1118] 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.

[1119] 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).

[1120] 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.

[1121] 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.

[1122] 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.

[1123] 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.

[1124] 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.

[1125] 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."

[1126] The present invention aims to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[1127] System Configuration

[1128] This system consists of a user terminal, a server, a database, and a generative AI model.

[1129] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[1130] Server: Receives information from user devices, stores it in a database, and sends questions to the generative AI model to generate responses.

[1131] Database: Stores basic information and interaction data and is used for analysis and updates.

[1132] Generative AI model: An artificial intelligence technique that generates appropriate responses to user questions.

[1133] Program processing overview

[1134] 1. Initial Setup

[1135] The user enters basic information.

[1136] The terminal sends this information to the server.

[1137] The server stores the information in a database and generates a user profile.

[1138] 2. Generating personalized chatbots

[1139] The server customizes the chatbot based on the user profile.

[1140] The server transmits the customization information to the terminal.

[1141] 3. Information Acquisition and Response

[1142] The user enters a question.

[1143] The terminal sends a question to the server.

[1144] The server sends the question to a generative AI model, which generates a response.

[1145] The server sends a response to the terminal, which displays it to the user.

[1146] 4. Automatic collaboration and growth support

[1147] The server collects and analyzes the interaction data.

[1148] The server provides personalized learning resources to support the user's growth.

[1149] 5. Data collection and analysis

[1150] The server collects and analyzes the interaction data.

[1151] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1152] Specific examples

[1153] Example of initial settings

[1154] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1155] The terminal sends this information to the server.

[1156] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1157] Examples of personalized chatbots

[1158] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[1159] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[1160] Specific examples of obtaining and responding to information

[1161] A user asks, "What's a good route for my next cycling trip?"

[1162] The terminal sends this question to the server.

[1163] The server sends a question to the generative AI model and receives a response such as, "The best cycling route is the one along the nearby river."

[1164] The server sends this response to the terminal, which displays it to the user.

[1165] Specific examples of growth support

[1166] User types, "I want to improve my project management skills."

[1167] The server searches for relevant online courses and learning resources and sends them to the device.

[1168] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[1169] Examples of data collection and analysis

[1170] The server analyzes the dialogue history and identifies an increase in questions about a particular topic.

[1171] The server adds new response patterns and datasets to respond to subsequent questions.

[1172] The system of the present invention provides efficient and personalized support to users, enabling them to quickly obtain information and solve problems.

[1173] The processing flow will be explained below.

[1174] Step 1:

[1175] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1176] Step 2:

[1177] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[1178] Step 3:

[1179] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[1180] Step 4:

[1181] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[1182] Step 5:

[1183] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[1184] Step 6:

[1185] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[1186] Step 7:

[1187] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[1188] Step 8:

[1189] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[1190] Step 9:

[1191] The server sends the generated response to the terminal. The server receives the response data and sends it to the user's terminal.

[1192] Step 10:

[1193] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is the one along the nearby river."

[1194] Step 11:

[1195] The server collects and analyzes the interaction data. The server collects the interaction history with the user and analyzes trends and frequently occurring problems.

[1196] Step 12:

[1197] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[1198] Step 13:

[1199] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data to provide appropriate learning resources and career support. For example, a user who "wants to improve their project management skills" will be provided with relevant online courses and practical advice.

[1200] Example 1

[1201] 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."

[1202] The purpose of this invention is to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. It aims to provide personalized learning resources, which have been difficult to achieve with conventional systems, and to smoothly deploy conversational agents that are compatible with multiple platforms. Another objective is to provide an effective means for collecting and analyzing dialogue data and improving the response accuracy of conversational agents.

[1203] 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.

[1204] In this invention, the server includes a means for customizing a conversational agent based on a user profile, a means for receiving a user's questions and sending the questions to a generative AI model to generate a response, and a means for providing personalized learning resources to support the user's growth. This allows for efficient and personalized support for users, enabling them to quickly obtain information and solve problems. It also allows for the collection and analysis of dialogue data, and the improvement of the conversational agent's response accuracy based on the analysis results.

[1205] "Basic information" is data required for initial setup, such as name, age, and hobbies, entered by the user.

[1206] The "server" is a central processing unit that receives, stores, and processes data sent from user devices and works with the generative AI model to generate responses.

[1207] A "database" is a place where information is collected to efficiently store and manage basic user information and conversation data.

[1208] A "user profile" is a data set created based on collected basic information about a user to identify and specify an individual user.

[1209] A "conversational agent" is an artificial intelligence system that uses generative AI models to engage in dialogue with users and provide appropriate responses to their questions.

[1210] A "generative artificial intelligence model" is an artificial intelligence algorithm that learns from given data and generates appropriate responses to user questions.

[1211] "Dialogue data" is a record of the information exchanged between a user and a conversational agent.

[1212] "Learning Resources" are educational materials such as online courses and course materials offered to help users grow.

[1213] "Multiple information platforms" is a general term for various Internet services that can be used in different software and hardware environments.

[1214] "Personalization" is the process of individually optimizing information and services according to the characteristics and needs of each individual user.

[1215] The present invention provides a system that allows users to receive personalized support, quickly and safely obtain information, and solve problems. Specific embodiments of the present invention are described in detail below.

[1216] System Configuration

[1217] This system consists of a user terminal, a server, a database, and a generative AI model.

[1218] User device: The user uses this device to enter basic information, send questions, and receive responses from the server. Examples include a smartphone or PC.

[1219] Server: Receives information from user devices, stores it in a database, sends questions to the generative AI model, and generates responses. Server-side programs such as Python and Node.js are used.

[1220] Database: This stores basic information and interaction data and is used for analysis and updating. Relational databases such as MySQL and PostgreSQL are used.

[1221] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. For example, OpenAI's GPT model is used.

[1222] Program processing overview

[1223] Initial Setup

[1224] The user launches the app and enters basic information. The user's device sends this information to the server. The server receives the information and stores it in a database. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[1225] Generate personalized chatbots

[1226] The server generates a customized chatbot based on the user profile. This setting information is sent to the device, and the device displays "Personalization setting complete." For example, the server generates a specific response pattern based on "Taro Tanaka, 30 years old, cycling."

[1227] Obtaining and responding to information

[1228] The user inputs a question, and the device sends it to the server. For example, the user might input, "What's a good route for my next cycling trip?" The server sends the question to a generative AI model, which generates a response such as, "The best route for cycling is the one along the nearby river." The generated response is then sent to the device, which displays it.

[1229] Automated collaboration and growth support

[1230] The server collects and analyzes interaction data, identifying increased interest in specific topics, and providing personalized learning resources to help users grow. For example, if a user types, "I want to improve my project management skills," the server can provide information about related online courses.

[1231] Data collection and analysis

[1232] The server analyzes the dialogue history and updates the dataset of the generative AI model, adding new response patterns and improving the accuracy of responses to the next question.

[1233] Examples of concrete examples and prompts

[1234] Example explanation:

[1235] User types, "I want to improve my project management skills."

[1236] The server searches for relevant online courses and learning resources and sends them to the device.

[1237] The device displays, "Recommended courses on project management are from XYZ Online School."

[1238] Example prompt sentence:

[1239] When a user asks the AI ​​model a question, they can enter a prompt such as, "Tell me a good route for my next cycling trip."

[1240] This system provides users with efficient and personalized support, enabling them to quickly obtain information and solve problems.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] System program processing flow

[1243] Initial Setup

[1244] Step 1: User enters basic information

[1245] The user launches the app and enters basic information such as name, age, and hobbies.

[1246] Input: Name, age, hobbies, etc.

[1247] Output: Basic information is saved to the device.

[1248] Example: Enter "Name: Taro Tanaka, Age: 30, Hobby: Cycling".

[1249] Step 2: The device sends the information to the server

[1250] The terminal sends the entered basic information to the server.

[1251] Input: Basic information

[1252] Output: Basic information received by the server

[1253] The device sends data to the server using the MQTT protocol.

[1254] Step 3: The server stores the information

[1255] The server stores the received information in a database.

[1256] Input: Basic information

[1257] Output: Basic information stored in the database

[1258] Store the information in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1259] Step 4: Create a user profile

[1260] The server generates a user profile based on the stored information.

[1261] Input: Basic information stored in the database

[1262] Output: Generated user profile

[1263] A user profile is generated and the system optimizes its operation based on it.

[1264] Generate personalized chatbots

[1265] Step 1: The server sends the customization data to the generative AI model

[1266] The server retrieves the user profile and sends the customization data to the generative AI model.

[1267] Input: User profile

[1268] Output: Customized data to send to the generative AI model

[1269] For example, let's say "User data: Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1270] Step 2: The generative AI model generates response patterns

[1271] A generative AI model generates personalized response patterns based on the data it receives.

[1272] Input: Customization data

[1273] Output: The generated response pattern

[1274] Generate specific response patterns that take individual content into consideration.

[1275] Step 3: The server sends the configuration data to the device

[1276] The server transmits the generated setting data to the terminal.

[1277] Input: Generated response pattern

[1278] Output: Sending configuration data

[1279] The server sends a response to the terminal, which receives it.

[1280] Step 4: Your device will display a message saying it's set up

[1281] The device will display "Personalized settings complete" based on the setting data received.

[1282] Input: Setting data

[1283] Output: "Personalization setup complete"

[1284] Notify the user that customization is complete.

[1285] Obtaining and responding to information

[1286] Step 1: User enters question

[1287] The user inputs a question such as "Tell me a good route for my next cycling trip."

[1288] Input: Question

[1289] Output: The question is saved to the terminal.

[1290] Step 2: The device sends a question to the server

[1291] The terminal sends the entered question to the server.

[1292] Input: Question

[1293] Output: The question sent to the server

[1294] Submit a question using the REST API.

[1295] Step 3: The server sends the response to the generative AI model

[1296] The server sends the question to the generative AI model, which generates a response such as, "The best cycling route is the one along the nearby river."

[1297] Input: Question

[1298] Output: The generated response

[1299] Leverage generative artificial intelligence models to generate appropriate responses.

[1300] Step 4: The server sends a response to the device

[1301] The server sends the generated response to the terminal.

[1302] Input: Generated response

[1303] Output: Response sent to the terminal

[1304] Step 5: The terminal displays the response

[1305] The terminal displays the received response to the user.

[1306] Input: Response from the server

[1307] Output: The response that is displayed to the user

[1308] Automated collaboration and growth support

[1309] Step 1: The server collects and analyzes the interaction data

[1310] The server collects and analyzes the interaction data.

[1311] Input: Interaction data

[1312] Output: Analysis results

[1313] Identify growing interest in a particular topic.

[1314] Step 2: The server provides personalized learning resources

[1315] The server provides personalized learning resources based on the user's interests.

[1316] Input: Analysis results

[1317] Output: Personalized learning resources

[1318] Example: "The recommended course on project management is XYZ Online School."

[1319] Data collection and analysis

[1320] Step 1: The server analyzes the conversation history

[1321] The server analyzes the dialogue history and updates the dataset for the generative AI model.

[1322] Input: Dialogue history

[1323] Output: Updated dataset

[1324] Identify frequently asked questions and emerging trends and add new response patterns.

[1325] Step 2: Improving response accuracy

[1326] The server will provide a more accurate response to subsequent questions.

[1327] Input: Updated dataset

[1328] Output: Highly accurate response

[1329] Improve the accuracy of generative AI models and increase user satisfaction.

[1330] (Application example 1)

[1331] 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."

[1332] Conventional electronic payment services have faced the challenge of making it difficult for users to receive prompt, safe, and appropriate support. In particular, it has been difficult to provide personalized support tailored to each user's individual situation, and when questions or problems arise regarding electronic payments, appropriate responses are often not possible. Furthermore, there has been insufficient analysis of dialogue data to improve user convenience, and the accuracy of generative AI models has not been improved.

[1333] 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.

[1334] In this invention, the server includes means for acquiring basic information and electronic payment history of a user and providing personalized support based thereon, means for identifying questions on specific topics from the dialogue history and generating new response patterns, and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This allows users to receive prompt, individually customized support and efficiently resolve questions and problems related to electronic payments.

[1335] "Basic user information" refers to profile information such as name, age, hobbies, and electronic payment history that a user enters when using the system.

[1336] "Server" means a central processing unit for processing information received from user terminals, storing it in a database, sending questions to the generative AI model, and providing analysis and responses.

[1337] A "database" is an information management system that stores basic user information and conversation data over a long period of time and is used for analysis and updating.

[1338] A "generative AI model" is an artificial intelligence technology that generates appropriate responses to user questions, and specifically refers to advanced natural language processing models such as GPT-3.

[1339] A "profile" is a personalized data set that collects and centralizes basic information about a user.

[1340] A "chatbot" is an automated response program that interacts with users and uses generative AI models to provide personalized conversations.

[1341] "Personalization" refers to providing optimal support and responses to individual users based on their basic information and historical data.

[1342] "Electronic payment history" refers to a record of electronic payments made by a user in the past.

[1343] "Dialogue history" is data that records the content of past dialogues between a user and a chatbot.

[1344] A "new response pattern" is a different response method from the conventional one, generated based on collected and analyzed dialogue data.

[1345] "Dataset updating" is the process of updating the training data for a generative AI model based on the results of collecting and analyzing interaction data.

[1346] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems related to electronic payments. Hereinafter, the program processing of the system will be described as an embodiment of the present invention.

[1347] System Configuration

[1348] This system mainly uses the following hardware and software.

[1349] User device: Smartphone

[1350] Server: Cloud server (e.g. AWS, Google Cloud)

[1351] Database: Relational database (e.g. MySQL, PostgreSQL)

[1352] Generative AI model: GPT-3 (OpenAI)

[1353] Program processing overview

[1354] Initial Setup

[1355] When a user first uses the system, they enter basic information (e.g., name, age, electronic payment history) using their smartphone. This information is sent from the smartphone to the server, which then creates a user profile and stores it in a database.

[1356] Generate personalized chatbots

[1357] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile, and then sends the customized information to the smartphone, where the chatbot completes the personalized settings.

[1358] Obtaining and responding to information

[1359] When a user types a question, it is sent from the smartphone to the server, which sends it to the generative AI model, which generates an appropriate response, which is then sent back from the server to the smartphone and displayed to the user.

[1360] For example, if a user inputs, "I want to check my recent payment history," the generative AI model will respond with, "My recent payment history is: Movies: 2,000 yen, Restaurants: 5,000 yen."

[1361] Data collection and analysis

[1362] The server collects and analyzes data on user interactions with the chatbot. Based on the analysis results, it generates new response patterns and updates the dataset of the generative AI model. This process continuously improves the accuracy of the chatbot's responses.

[1363] Specific examples

[1364] If a user types, "I want to improve my project management skills," the server searches for relevant online courses and learning resources and provides a response such as, "Recommended courses on project management are from XYZ Online School."

[1365] Prompt Sentence Examples

[1366] Prompt: "I want to check my recent transaction history."

[1367] Generated AI model response: "Recent payment history: Movies: 2000 yen, Restaurants: 5000 yen"

[1368] As a result, the present invention provides users with fast and personalized support, enabling them to efficiently resolve any questions or problems they may have regarding electronic payments.

[1369] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1370] Step 1: User enters basic information.

[1371] Users launch the smartphone application and enter basic information such as name, age, and electronic payment history, which allows the system to collect initial data on the user.

[1372] Step 2: Send basic information to the server.

[1373] The device sends the entered basic information to the server. The server receives the sent data and saves it as user information. The input data is sent to the server in JSON format.

[1374] Step 3: Save the basic information to the database.

[1375] The server stores the received basic information in a database, including the user's name, age, and electronic payment history, allowing for centralized management of data that can be used for subsequent processing.

[1376] Step 4: Customize the chatbot based on the user profile.

[1377] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile information stored in the database. This profile information is used to configure the chatbot to provide the most appropriate responses to the user.

[1378] Step 5: Send the user profile to the terminal.

[1379] The server sends customized chatbot information to the terminal, which receives the information and incorporates it into a smartphone application, providing the user with a personalized chatbot.

[1380] Step 6: Receive the user's question and send it to the generative AI model to generate a response.

[1381] The user uses their smartphone to input a question. This question is sent from the device to a server, which then sends it to a generative AI model. The generative AI model generates an appropriate response and returns it to the server. This process uses prompt statements (e.g., "I would like to check my recent payment history").

[1382] Step 7: Present the generated response to the user.

[1383] The server receives the response from the generative AI model and sends it to the device, which then displays the received response on the user's smartphone screen, allowing the user to immediately check the response from the system.

[1384] Step 8: Collect and analyze user interaction data.

[1385] The server continuously collects data on user interactions with the chatbot. This data is analyzed to identify whether questions about specific topics are frequently asked. The results of the analysis are used to update the dataset.

[1386] Step 9: Update the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1387] The server uses the collected dialogue data and analysis results to update the dataset of the generative AI model, which improves the accuracy of the chatbot's responses and allows it to provide more appropriate responses.

[1388] 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.

[1389] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems. It also provides more personalized responses by incorporating an emotion engine that recognizes the user's emotions and adjusts responses. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[1390] System Configuration

[1391] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine.

[1392] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[1393] Server: A central processing unit that receives information from user terminals, processes the data, and generates the necessary responses.

[1394] Database: Stores basic information, dialogue data, and emotion history, and is used for analysis and updates.

[1395] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions.

[1396] Emotion Engine: A technology for recognizing user emotions and adjusting responses.

[1397] Program processing overview

[1398] 1. Initial Setup

[1399] The user enters basic information.

[1400] The terminal sends this information to the server.

[1401] The server stores the information in a database and generates a user profile.

[1402] 2. Generating personalized chatbots

[1403] The server customizes the chatbot based on the user profile.

[1404] The server transmits the customization information to the terminal.

[1405] 3. Information Acquisition and Response

[1406] The user enters a question.

[1407] The terminal sends a question to the server.

[1408] The server sends the question to a generative AI model, which generates a response.

[1409] The emotion engine recognizes the user's emotions.

[1410] The server receives the emotion engine results and adjusts the response.

[1411] The server sends a response to the terminal, which displays it to the user.

[1412] 4. Automatic collaboration and growth support

[1413] The server collects and analyzes dialogue data and emotion history.

[1414] The server provides personalized learning resources to support the user's growth.

[1415] 5. Data collection and analysis

[1416] The server collects and analyzes dialogue data and emotion history.

[1417] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1418] Specific examples

[1419] Example of initial settings

[1420] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1421] The terminal sends this information to the server.

[1422] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1423] Examples of personalized chatbots

[1424] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[1425] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[1426] Specific examples of obtaining and responding to information

[1427] A user asks, "What's a good route for my next cycling trip?"

[1428] The terminal sends this question to the server.

[1429] The server sends a question to the generative AI model, which generates a response: "What's a good route for your next cycling trip?"

[1430] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[1431] The server then applies this sentiment analysis and generates a tailored response: "The best route for your next bike ride is along the nearby river. Have fun!"

[1432] The server sends this response to the terminal, which displays it to the user.

[1433] Specific examples of growth support

[1434] User types, "I want to improve my project management skills."

[1435] The server searches for relevant online courses and learning resources and sends them to the device.

[1436] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[1437] Examples of data collection and analysis

[1438] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[1439] The server adds new response patterns and datasets to respond to subsequent questions.

[1440] The introduction of the emotion engine allows the system of the present invention to provide more personalized responses according to the user's emotions, thereby improving the user experience and deepening user engagement.

[1441] The processing flow will be explained below.

[1442] Step 1:

[1443] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1444] Step 2:

[1445] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[1446] Step 3:

[1447] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[1448] Step 4:

[1449] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[1450] Step 5:

[1451] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[1452] Step 6:

[1453] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[1454] Step 7:

[1455] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[1456] Step 8:

[1457] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[1458] Step 9:

[1459] The emotion engine recognizes the user's emotions and analyzes the user's current emotions based on the content the user has entered and past conversation history.

[1460] Step 10:

[1461] The server receives the results of the emotion engine and adjusts the response. The server reflects the analysis results of the emotion engine in the generated response. For example, if the user is "excited," the server adds "Have fun!"

[1462] Step 11:

[1463] The server sends the adjusted response to the terminal. The server sends the final response to the user's terminal.

[1464] Step 12:

[1465] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is along the nearby river. Have fun!"

[1466] Step 13:

[1467] The server collects and analyzes dialogue data and emotion history. The server stores the dialogue history and emotion analysis results in a database and analyzes trends and frequently occurring problems.

[1468] Step 14:

[1469] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[1470] Step 15:

[1471] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data and emotion history to provide appropriate learning resources and career support. For example, a user who wants to improve their project management skills will be offered relevant online courses and practical advice.

[1472] Example 2

[1473] 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."

[1474] Conventional chatbot systems were unable to adequately reflect the individual needs and emotions of users and could only provide uniform responses. As a result, the user experience was poor and questions often did not receive appropriate responses. Furthermore, the collection and analysis of dialogue data was insufficient, resulting in slow improvements in response accuracy. This led to issues such as low user satisfaction and engagement.

[1475] 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.

[1476] In this invention, the server includes: a means for a user to input basic information; a means for transmitting the input basic information to the server; a means for saving the basic information in a database; a means for customizing the chatbot based on a user profile; a means for receiving a user's question and transmitting the question to a generative AI model to generate a response; a means for recognizing the user's emotion using an emotion engine and adjusting the response; a means for presenting the generated response to the user; a means for collecting and analyzing interaction data with the user; and a means for updating a dataset to improve the accuracy of the chatbot's responses based on the analysis results. This enables personalized responses that reflect the user's individual needs and emotions, thereby improving the user experience and response accuracy.

[1477] "Basic information" refers to personal information such as the user's name, age, hobbies, etc.

[1478] A "server" is a central processing unit that processes information from a user terminal and generates a response.

[1479] A "database" is a storage device that stores basic information, dialogue data, and emotion history of a user and retrieves them as needed.

[1480] A "user profile" is individual user information generated based on the user's basic information and behavioral history.

[1481] A "chatbot" is an automated dialogue system that interacts with users and provides answers to their questions.

[1482] A "generative AI model" refers to artificial intelligence technology that generates appropriate responses to user questions.

[1483] An "emotion engine" is a technology that recognizes emotions from user input and dialogue and adjusts responses accordingly.

[1484] "Dialogue data" refers to historical information about interactions between a user and a system.

[1485] "Response accuracy" is a measure of the accuracy and appropriateness of responses generated to user questions.

[1486] A "dataset" is a collection of interaction data used to train and update a generative AI model.

[1487] "Personalized learning resources" refers to individually optimized learning content provided based on the user's basic information and needs.

[1488] "Multiple platforms" refers to different hardware or software environments, examples of which include different operating systems or devices.

[1489] The present invention provides a system for allowing users to receive individually customized support, quickly and safely obtain information, and solve problems. As an embodiment of the present invention, the details of the system are described below.

[1490] System Configuration

[1491] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine. The specific hardware and software used are as follows:

[1492] User device: A device where a user enters basic information, sends questions, and receives responses from the server. Examples include smartphones and PCs.

[1493] Server: A central processing unit that receives information from user devices, processes the data, and generates the necessary response. Examples include web servers and application servers.

[1494] Database: This is used to store basic user information, interaction data, and emotion history, and is used for analysis and updating. Specifically, this applies to relational database management systems (RDBMS) and NoSQL databases.

[1495] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. Examples include OpenAI's GPT-4.

[1496] Emotion engine: A technology for recognizing user emotions and tailoring responses. Specifically, it is a machine learning model that includes a sentiment analysis algorithm.

[1497] Program processing overview

[1498] 1. Initial Setup

[1499] The user enters basic information.

[1500] The terminal sends this information to the server.

[1501] The server stores the information in a database and generates a user profile.

[1502] 2. Generating personalized chatbots

[1503] The server customizes the chatbot based on the user profile.

[1504] The server transmits the customization information to the terminal.

[1505] 3. Information Acquisition and Response

[1506] The user enters a question.

[1507] The terminal sends a question to the server.

[1508] The server sends the question to a generative AI model, which generates a response.

[1509] The emotion engine recognizes the user's emotions.

[1510] The server receives the emotion engine results and adjusts the response.

[1511] The server sends a response to the terminal, which displays it to the user.

[1512] 4. Automatic collaboration and growth support

[1513] The server collects and analyzes dialogue data and emotion history.

[1514] The server provides personalized learning resources to support the user's growth.

[1515] 5. Data collection and analysis

[1516] The server collects and analyzes dialogue data and emotion history.

[1517] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1518] Specific examples

[1519] Below are some examples of specific operations and responses:

[1520] Example of initial settings

[1521] The user launches the app and enters their name, age, hobbies, etc., such as "Name: Yamada Taro, Age: 25, Hobbies: Mountain climbing."

[1522] The terminal sends this information to the server.

[1523] The server receives the information and stores it in the database as "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[1524] Examples of personalized chatbots

[1525] The server sets a response pattern based on the information "Yamada Taro, 25 years old, mountain climbing."

[1526] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[1527] Specific examples of obtaining and responding to information

[1528] A user asks, "What's your recommendation for the next mountain I should climb?"

[1529] The terminal sends this question to the server.

[1530] The server sends a question to the generative AI model, which generates a response: "Recommendations for the next mountain to climb."

[1531] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[1532] The server reflects the sentiment analysis results and generates a tailored response such as, "The next recommended mountain to climb is nearby Mount Takao. Have fun!"

[1533] The server sends this response to the terminal, which displays it to the user.

[1534] Specific examples of growth support

[1535] User types, "I want to improve my project management skills."

[1536] The server searches for relevant online courses and learning resources and sends them to the device.

[1537] The device displays to the user, "ABC Online School is a recommended course on project management."

[1538] Examples of data collection and analysis

[1539] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[1540] The server adds new response patterns and datasets to respond to subsequent questions.

[1541] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1542] Step 1:

[1543] Enter and submit basic information

[1544] The user starts the application and enters basic information such as name, age, hobbies, etc. An example of input here is "Name: Taro Yamada, Age: 25, Hobbies: Mountain climbing."

[1545] The device sends the entered basic information to the server. The information sent is in JSON format, such as "{"Name": "Yamada Taro", "Age": 25, "Hobbies": "Mountain climbing"}".

[1546] As an output, the server receives this information.

[1547] Step 2:

[1548] Storing information and creating user profiles

[1549] The server stores the received information in a database. For example, the database stores "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[1550] The server generates a user profile based on the stored information, which is associated with a user ID to protect privacy.

[1551] As an output, a user profile is registered in a database.

[1552] Step 3:

[1553] Generate a customized chatbot

[1554] The server retrieves the user profile from the database and customizes the chatbot, for example, by setting response patterns related to "Taro Yamada, 25 years old, mountain climbing."

[1555] The server transmits the customization information to the terminal.

[1556] The device will display "Personalization settings complete."

[1557] As an output, a customized chatbot is prepared on the terminal.

[1558] Step 4:

[1559] Enter and submit your question

[1560] A user types a question such as "What's your recommendation for the next mountain to climb?"

[1561] The device sends this question to the server. The data sent is "{"Question": "What mountain do you recommend I climb next?"}".

[1562] As an output, the server receives the question.

[1563] Step 5:

[1564] Generating a response

[1565] The server sends the question to a generative AI model (e.g., OpenAI GPT-4), which analyzes the question and generates a response such as "Recommend the next mountain to climb."

[1566] As input, the server provides the question and the user profile to the generative AI model.

[1567] As an output, the generative AI model generates the response, "The next mountain to climb is Mount Takao."

[1568] Step 6:

[1569] Recognizing emotions and regulating responses

[1570] The emotion engine analyzes the user's input text and dialogue history to recognize emotions such as "excited."

[1571] The server reflects the analysis results of the emotion engine and generates a tailored response such as, "Mount Takao is especially recommended at this time of year. Have fun!"

[1572] As input, the emotion engine receives the user's text data.

[1573] The output is a tailored response that blends the results of the emotion engine with the response of the generative AI model.

[1574] Step 7:

[1575] Sending and Displaying Responses

[1576] The server sends the adjusted response to the terminal.

[1577] The device displays a response to the user, specifically, "Mount Takao is especially recommended at this time of year. Have fun!"

[1578] As an output, the user can receive an appropriate response.

[1579] Step 8:

[1580] Collecting dialogue data and emotion history

[1581] The server periodically collects all dialogue history and emotion history and stores them in a database.

[1582] As output, the dialogue data and emotion history are saved.

[1583] Step 9:

[1584] Analyzing data and updating datasets

[1585] The server analyzes the collected conversation data and sentiment history to identify trends in questions about specific topics and changes in sentiment.

[1586] Based on the analysis results, the server updates the dataset of the generative AI model to improve response accuracy.

[1587] It uses collected dialogue data and emotion history as input.

[1588] The output is an updated dataset that improves the accuracy of the chatbot's responses.

[1589] (Application example 2)

[1590] 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."

[1591] Conventional chatbot systems often fail to provide responses that fully reflect the individual needs of users. Furthermore, they lack personalization capabilities, such as responses that take the user's emotions into account and automatic provision of learning resources. Therefore, there is a need for an improved user experience. Particularly in brick-and-mortar stores, there is a need for a system that provides real-time, personalized support to users while they are shopping.

[1592] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information; means for transmitting the input basic information to the server; means for saving the basic information in a database; means for customizing the chatbot based on a user profile; means for receiving a user's question and transmitting the question to a generative AI model to generate a response; means for presenting the generated response to the user; means for using an emotion engine that recognizes the user's emotions and adjusts the response; means for collecting and analyzing dialogue data with the user; and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This makes it possible to provide quick and personalized responses to user questions and generate optimal responses according to the user's emotions.

[1593] The "means for users to input basic information" is an interface that allows users to digitally input personal information such as name, age, hobbies, etc.

[1594] The "means for saving basic information to a database" is a function for storing the information entered by the user in a database so that it can be referenced and analyzed later.

[1595] "Means for customizing chatbots based on user profiles" refers to a function for generating chatbots with individually set response patterns and characteristics based on saved basic information about users.

[1596] "Means for receiving a user's question and sending the question to a generative AI model to generate a response" refers to a system for receiving a question submitted by a user, sending it to a generative AI model, and generating an appropriate response.

[1597] The "means for presenting the generated response to the user" is an interface for displaying the response obtained from the generative AI model to the user.

[1598] The "means for using an emotion engine that recognizes the user's emotion and adjusts the response" is an engine for analyzing the user's emotion and optimizing the response based on the result.

[1599] "Means for collecting and analyzing dialogue data with users" is a function for collecting the content of dialogue exchanged between users and chatbots and analyzing it later.

[1600] "Means for updating the dataset to improve the accuracy of chatbot responses based on the analysis results" refers to a function that uses the analysis results of dialogue data to update the dataset to improve the content and accuracy of chatbot responses.

[1601] This invention is a "smart shopping assistant" system that optimizes the shopping experience in physical stores to suit user needs. When a user inputs a question, the system uses a generative AI model to generate a quick and personalized response, and further uses an emotion engine to provide the optimal response based on the user's emotions.

[1602] System Configuration

[1603] 1. User Device:

[1604] This is an interface that users use to enter basic information (such as name, age, hobbies, etc.) and questions. It is implemented as a smartphone application.

[1605] 2. Server:

[1606] It is a central processing unit that receives basic information and questions sent from the user device and performs various processes including generative AI models and emotion engines. It also stores the data in a database and generates and manages user profiles.

[1607] 3. Database:

[1608] This is a storage device for saving basic user information, dialogue data, emotion history, etc. Relational database management systems such as MySQL and PostgreSQL can be used.

[1609] 4. Generative AI Models:

[1610] It is an artificial intelligence model used to generate appropriate responses to user questions. It generally uses natural language processing techniques such as GPT-3.

[1611] 5. Emotion Engine:

[1612] It is an engine that recognizes emotions from user input and adjusts responses based on the results. For sentiment analysis, it uses sentiment analysis APIs (e.g., Microsoft Azure's text analysis API).

[1613] Program processing overview

[1614] 1. Initial Setup:

[1615] A user starts the app and enters basic information, for example, "Name: Taro Yamada, Age: 28, Hobby: Reading." The device sends this information to the server, which receives it and stores it in a database.

[1616] 2. Generate personalized chatbots:

[1617] The server customizes the chatbot based on the user profile. For example, it sets a response pattern based on the information "Yamada Taro, 28 years old, reading." The customized settings are sent to the device, and the message "Personalization settings complete" is displayed.

[1618] 3. Information Acquisition and Response:

[1619] When a user asks, "Tell me a review of this product," the device sends the question to a server. The server sends the question to a generative AI model, which generates a "review of this product." The emotion engine then analyzes the user's emotions, and if it recognizes, for example, an "excited" state, it adjusts the final response, displaying, "This product has a great review. Enjoy!"

[1620] 4. Data collection and analysis:

[1621] The server collects and analyzes the interaction data and sentiment history, for example identifying popular questions about a particular product and adding new response patterns and datasets.

[1622] Prompt Sentence Examples

[1623] User: Write a review for this product

[1624] Assistant:

[1625] This makes it possible to provide the information the user wants quickly and accurately, and improve the user experience by responding according to their emotions.

[1626] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1627] Step 1:

[1628] The user enters basic information

[1629] A user inputs basic information (such as name, age, and hobbies) through a smartphone app. The input data includes information such as "Name: Yamada Taro, Age: 28, Hobbies: Reading." This is the input data. The device acquires this data and sends it to the server.

[1630] Step 2:

[1631] The server stores basic information in a database

[1632] The server receives the basic information sent by the user from the device. The received data is analyzed and stored in a database in a structured format. For example, the information is stored in the database as "User ID: 001, Name: Yamada Taro, Age: 28, Hobby: Reading." This is the output data.

[1633] Step 3:

[1634] The server customizes the chatbot based on the user profile.

[1635] The server generates a user profile based on the stored basic information. This allows for customized settings based on the user's profile data. For example, based on the information "Yamada Taro, 28 years old, reading," the chatbot prepares relevant response patterns and content. The customized settings are output data.

[1636] Step 4:

[1637] The user enters a question

[1638] The user inputs a question through a smartphone app. For example, they might type, "Please give me a review of this product." This is the input data. The device then sends this question to the server.

[1639] Step 5:

[1640] The server sends the question to the generative AI model to generate a response.

[1641] The server receives the question sent by the user and sends it to the generative AI model. The generative AI model generates a response using the prompt "User: Tell me the review of this product\nAssistant:". For example, it generates "This product has good reviews." This is the output data.

[1642] Step 6:

[1643] The server recognizes the user's emotions and adjusts the response

[1644] Based on the generated response, the server sends the data to the emotion engine. The emotion engine recognizes the emotion from the text entered by the user, analyzing it as "excited," for example. Based on the results, it adjusts the response. For example, the final response might be "This product has good reviews. Enjoy." This is the output data.

[1645] Step 7:

[1646] The server generates a response and presents it to the user.

[1647] The server sends the adjusted response to the terminal, which displays it to the user, which is the output data the user receives.

[1648] Step 8:

[1649] The server collects and analyzes user interaction data

[1650] The server collects conversation data and emotion history between the user and the chatbot. The collected data is analyzed to determine conversation trends and frequently asked questions. This is the analytical data.

[1651] Step 9:

[1652] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1653] Based on the analysis results, the server updates the training dataset of the generative AI model to improve the accuracy of the generated responses, thereby providing accurate and personalized responses to subsequent questions. The updated dataset is the output data.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] [Fourth embodiment]

[1658] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1659] 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.

[1660] 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).

[1661] 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.

[1662] 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.

[1663] 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).

[1664] 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.

[1665] 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.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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."

[1671] The present invention aims to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[1672] System Configuration

[1673] This system consists of a user terminal, a server, a database, and a generative AI model.

[1674] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[1675] Server: Receives information from user devices, stores it in a database, and sends questions to the generative AI model to generate responses.

[1676] Database: Stores basic information and interaction data and is used for analysis and updates.

[1677] Generative AI model: An artificial intelligence technique that generates appropriate responses to user questions.

[1678] Program processing overview

[1679] 1. Initial Setup

[1680] The user enters basic information.

[1681] The terminal sends this information to the server.

[1682] The server stores the information in a database and generates a user profile.

[1683] 2. Generating personalized chatbots

[1684] The server customizes the chatbot based on the user profile.

[1685] The server transmits the customization information to the terminal.

[1686] 3. Information Acquisition and Response

[1687] The user enters a question.

[1688] The terminal sends a question to the server.

[1689] The server sends the question to a generative AI model, which generates a response.

[1690] The server sends a response to the terminal, which displays it to the user.

[1691] 4. Automatic collaboration and growth support

[1692] The server collects and analyzes the interaction data.

[1693] The server provides personalized learning resources to support the user's growth.

[1694] 5. Data collection and analysis

[1695] The server collects and analyzes the interaction data.

[1696] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1697] Specific examples

[1698] Example of initial settings

[1699] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1700] The terminal sends this information to the server.

[1701] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1702] Examples of personalized chatbots

[1703] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[1704] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[1705] Specific examples of obtaining and responding to information

[1706] A user asks, "What's a good route for my next cycling trip?"

[1707] The terminal sends this question to the server.

[1708] The server sends a question to the generative AI model and receives a response such as, "The best cycling route is the one along the nearby river."

[1709] The server sends this response to the terminal, which displays it to the user.

[1710] Specific examples of growth support

[1711] User types, "I want to improve my project management skills."

[1712] The server searches for relevant online courses and learning resources and sends them to the device.

[1713] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[1714] Examples of data collection and analysis

[1715] The server analyzes the dialogue history and identifies an increase in questions about a particular topic.

[1716] The server adds new response patterns and datasets to respond to subsequent questions.

[1717] The system of the present invention provides efficient and personalized support to users, enabling them to quickly obtain information and solve problems.

[1718] The processing flow will be explained below.

[1719] Step 1:

[1720] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1721] Step 2:

[1722] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[1723] Step 3:

[1724] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[1725] Step 4:

[1726] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[1727] Step 5:

[1728] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[1729] Step 6:

[1730] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[1731] Step 7:

[1732] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[1733] Step 8:

[1734] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[1735] Step 9:

[1736] The server sends the generated response to the terminal. The server receives the response data and sends it to the user's terminal.

[1737] Step 10:

[1738] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is the one along the nearby river."

[1739] Step 11:

[1740] The server collects and analyzes the interaction data. The server collects the interaction history with the user and analyzes trends and frequently occurring problems.

[1741] Step 12:

[1742] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[1743] Step 13:

[1744] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data to provide appropriate learning resources and career support. For example, a user who "wants to improve their project management skills" will be provided with relevant online courses and practical advice.

[1745] Example 1

[1746] 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."

[1747] The purpose of this invention is to enable users to receive individually customized support, quickly and safely obtain information, and solve problems. It aims to provide personalized learning resources, which have been difficult to achieve with conventional systems, and to smoothly deploy conversational agents that are compatible with multiple platforms. Another objective is to provide an effective means for collecting and analyzing dialogue data and improving the response accuracy of conversational agents.

[1748] 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.

[1749] In this invention, the server includes a means for customizing a conversational agent based on a user profile, a means for receiving a user's questions and sending the questions to a generative AI model to generate a response, and a means for providing personalized learning resources to support the user's growth. This allows for efficient and personalized support for users, enabling them to quickly obtain information and solve problems. It also allows for the collection and analysis of dialogue data, and the improvement of the conversational agent's response accuracy based on the analysis results.

[1750] "Basic information" is data required for initial setup, such as name, age, and hobbies, entered by the user.

[1751] The "server" is a central processing unit that receives, stores, and processes data sent from user devices and works with the generative AI model to generate responses.

[1752] A "database" is a place where information is collected to efficiently store and manage basic user information and conversation data.

[1753] A "user profile" is a data set created based on collected basic information about a user to identify and specify an individual user.

[1754] A "conversational agent" is an artificial intelligence system that uses generative AI models to engage in dialogue with users and provide appropriate responses to their questions.

[1755] A "generative artificial intelligence model" is an artificial intelligence algorithm that learns from given data and generates appropriate responses to user questions.

[1756] "Dialogue data" is a record of the information exchanged between a user and a conversational agent.

[1757] "Learning Resources" are educational materials such as online courses and course materials offered to help users grow.

[1758] "Multiple information platforms" is a general term for various Internet services that can be used in different software and hardware environments.

[1759] "Personalization" is the process of individually optimizing information and services according to the characteristics and needs of each individual user.

[1760] The present invention provides a system that allows users to receive personalized support, quickly and safely obtain information, and solve problems. Specific embodiments of the present invention are described in detail below.

[1761] System Configuration

[1762] This system consists of a user terminal, a server, a database, and a generative AI model.

[1763] User device: The user uses this device to enter basic information, send questions, and receive responses from the server. Examples include a smartphone or PC.

[1764] Server: Receives information from user devices, stores it in a database, sends questions to the generative AI model, and generates responses. Server-side programs such as Python and Node.js are used.

[1765] Database: This stores basic information and interaction data and is used for analysis and updating. Relational databases such as MySQL and PostgreSQL are used.

[1766] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. For example, OpenAI's GPT model is used.

[1767] Program processing overview

[1768] Initial Setup

[1769] The user launches the app and enters basic information. The user's device sends this information to the server. The server receives the information and stores it in a database. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[1770] Generate personalized chatbots

[1771] The server generates a customized chatbot based on the user profile. This setting information is sent to the device, and the device displays "Personalization setting complete." For example, the server generates a specific response pattern based on "Taro Tanaka, 30 years old, cycling."

[1772] Obtaining and responding to information

[1773] The user inputs a question, and the device sends it to the server. For example, the user might input, "What's a good route for my next cycling trip?" The server sends the question to a generative AI model, which generates a response such as, "The best route for cycling is the one along the nearby river." The generated response is then sent to the device, which displays it.

[1774] Automated collaboration and growth support

[1775] The server collects and analyzes interaction data, identifying increased interest in specific topics, and providing personalized learning resources to help users grow. For example, if a user types, "I want to improve my project management skills," the server can provide information about related online courses.

[1776] Data collection and analysis

[1777] The server analyzes the dialogue history and updates the dataset of the generative AI model, adding new response patterns and improving the accuracy of responses to the next question.

[1778] Examples of concrete examples and prompts

[1779] Example explanation:

[1780] User types, "I want to improve my project management skills."

[1781] The server searches for relevant online courses and learning resources and sends them to the device.

[1782] The device displays, "Recommended courses on project management are from XYZ Online School."

[1783] Example prompt sentence:

[1784] When a user asks the AI ​​model a question, they can enter a prompt such as, "Tell me a good route for my next cycling trip."

[1785] This system provides users with efficient and personalized support, enabling them to quickly obtain information and solve problems.

[1786] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1787] System program processing flow

[1788] Initial Setup

[1789] Step 1: User enters basic information

[1790] The user launches the app and enters basic information such as name, age, and hobbies.

[1791] Input: Name, age, hobbies, etc.

[1792] Output: Basic information is saved to the device.

[1793] Example: Enter "Name: Taro Tanaka, Age: 30, Hobby: Cycling".

[1794] Step 2: The device sends the information to the server

[1795] The terminal sends the entered basic information to the server.

[1796] Input: Basic information

[1797] Output: Basic information received by the server

[1798] The device sends data to the server using the MQTT protocol.

[1799] Step 3: The server stores the information

[1800] The server stores the received information in a database.

[1801] Input: Basic information

[1802] Output: Basic information stored in the database

[1803] Store the information in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1804] Step 4: Create a user profile

[1805] The server generates a user profile based on the stored information.

[1806] Input: Basic information stored in the database

[1807] Output: Generated user profile

[1808] A user profile is generated and the system optimizes its operation based on it.

[1809] Generate personalized chatbots

[1810] Step 1: The server sends the customization data to the generative AI model

[1811] The server retrieves the user profile and sends the customization data to the generative AI model.

[1812] Input: User profile

[1813] Output: Customized data to send to the generative AI model

[1814] For example, let's say "User data: Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1815] Step 2: The generative AI model generates response patterns

[1816] A generative AI model generates personalized response patterns based on the data it receives.

[1817] Input: Customization data

[1818] Output: The generated response pattern

[1819] Generate specific response patterns that take individual content into consideration.

[1820] Step 3: The server sends the configuration data to the device

[1821] The server transmits the generated setting data to the terminal.

[1822] Input: Generated response pattern

[1823] Output: Sending configuration data

[1824] The server sends a response to the terminal, which receives it.

[1825] Step 4: Your device will display a message saying it's set up

[1826] The device will display "Personalized settings complete" based on the setting data received.

[1827] Input: Setting data

[1828] Output: "Personalization setup complete"

[1829] Notify the user that customization is complete.

[1830] Obtaining and responding to information

[1831] Step 1: User enters question

[1832] The user inputs a question such as "Tell me a good route for my next cycling trip."

[1833] Input: Question

[1834] Output: The question is saved to the terminal.

[1835] Step 2: The device sends a question to the server

[1836] The terminal sends the entered question to the server.

[1837] Input: Question

[1838] Output: The question sent to the server

[1839] Submit a question using the REST API.

[1840] Step 3: The server sends the response to the generative AI model

[1841] The server sends the question to the generative AI model, which generates a response such as, "The best cycling route is the one along the nearby river."

[1842] Input: Question

[1843] Output: The generated response

[1844] Leverage generative artificial intelligence models to generate appropriate responses.

[1845] Step 4: The server sends a response to the device

[1846] The server sends the generated response to the terminal.

[1847] Input: Generated response

[1848] Output: Response sent to the terminal

[1849] Step 5: The terminal displays the response

[1850] The terminal displays the received response to the user.

[1851] Input: Response from the server

[1852] Output: The response that is displayed to the user

[1853] Automated collaboration and growth support

[1854] Step 1: The server collects and analyzes the interaction data

[1855] The server collects and analyzes the interaction data.

[1856] Input: Interaction data

[1857] Output: Analysis results

[1858] Identify growing interest in a particular topic.

[1859] Step 2: The server provides personalized learning resources

[1860] The server provides personalized learning resources based on the user's interests.

[1861] Input: Analysis results

[1862] Output: Personalized learning resources

[1863] Example: "The recommended course on project management is XYZ Online School."

[1864] Data collection and analysis

[1865] Step 1: The server analyzes the conversation history

[1866] The server analyzes the dialogue history and updates the dataset for the generative AI model.

[1867] Input: Dialogue history

[1868] Output: Updated dataset

[1869] Identify frequently asked questions and emerging trends and add new response patterns.

[1870] Step 2: Improving response accuracy

[1871] The server will provide a more accurate response to subsequent questions.

[1872] Input: Updated dataset

[1873] Output: Highly accurate response

[1874] Improve the accuracy of generative AI models and increase user satisfaction.

[1875] (Application example 1)

[1876] 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."

[1877] Conventional electronic payment services have faced the challenge of making it difficult for users to receive prompt, safe, and appropriate support. In particular, it has been difficult to provide personalized support tailored to each user's individual situation, and when questions or problems arise regarding electronic payments, appropriate responses are often not possible. Furthermore, there has been insufficient analysis of dialogue data to improve user convenience, and the accuracy of generative AI models has not been improved.

[1878] 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.

[1879] In this invention, the server includes means for acquiring basic information and electronic payment history of a user and providing personalized support based thereon, means for identifying questions on specific topics from the dialogue history and generating new response patterns, and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This allows users to receive prompt, individually customized support and efficiently resolve questions and problems related to electronic payments.

[1880] "Basic user information" refers to profile information such as name, age, hobbies, and electronic payment history that a user enters when using the system.

[1881] "Server" means a central processing unit for processing information received from user terminals, storing it in a database, sending questions to the generative AI model, and providing analysis and responses.

[1882] A "database" is an information management system that stores basic user information and conversation data over a long period of time and is used for analysis and updating.

[1883] A "generative AI model" is an artificial intelligence technology that generates appropriate responses to user questions, and specifically refers to advanced natural language processing models such as GPT-3.

[1884] A "profile" is a personalized data set that collects and centralizes basic information about a user.

[1885] A "chatbot" is an automated response program that interacts with users and uses generative AI models to provide personalized conversations.

[1886] "Personalization" refers to providing optimal support and responses to individual users based on their basic information and historical data.

[1887] "Electronic payment history" refers to a record of electronic payments made by a user in the past.

[1888] "Dialogue history" is data that records the content of past dialogues between a user and a chatbot.

[1889] A "new response pattern" is a different response method from the conventional one, generated based on collected and analyzed dialogue data.

[1890] "Dataset updating" is the process of updating the training data for a generative AI model based on the results of collecting and analyzing interaction data.

[1891] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems related to electronic payments. Hereinafter, the program processing of the system will be described as an embodiment of the present invention.

[1892] System Configuration

[1893] This system mainly uses the following hardware and software.

[1894] User device: Smartphone

[1895] Server: Cloud server (e.g. AWS, Google Cloud)

[1896] Database: Relational database (e.g. MySQL, PostgreSQL)

[1897] Generative AI model: GPT-3 (OpenAI)

[1898] Program processing overview

[1899] Initial Setup

[1900] When a user first uses the system, they enter basic information (e.g., name, age, electronic payment history) using their smartphone. This information is sent from the smartphone to the server, which then creates a user profile and stores it in a database.

[1901] Generate personalized chatbots

[1902] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile, and then sends the customized information to the smartphone, where the chatbot completes the personalized settings.

[1903] Obtaining and responding to information

[1904] When a user types a question, it is sent from the smartphone to the server, which sends it to the generative AI model, which generates an appropriate response, which is then sent back from the server to the smartphone and displayed to the user.

[1905] For example, if a user inputs, "I want to check my recent payment history," the generative AI model will respond with, "My recent payment history is: Movies: 2,000 yen, Restaurants: 5,000 yen."

[1906] Data collection and analysis

[1907] The server collects and analyzes data on user interactions with the chatbot. Based on the analysis results, it generates new response patterns and updates the dataset of the generative AI model. This process continuously improves the accuracy of the chatbot's responses.

[1908] Specific examples

[1909] If a user types, "I want to improve my project management skills," the server searches for relevant online courses and learning resources and provides a response such as, "Recommended courses on project management are from XYZ Online School."

[1910] Prompt Sentence Examples

[1911] Prompt: "I want to check my recent transaction history."

[1912] Generated AI model response: "Recent payment history: Movies: 2000 yen, Restaurants: 5000 yen"

[1913] As a result, the present invention provides users with fast and personalized support, enabling them to efficiently resolve any questions or problems they may have regarding electronic payments.

[1914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1915] Step 1: User enters basic information.

[1916] Users launch the smartphone application and enter basic information such as name, age, and electronic payment history, which allows the system to collect initial data on the user.

[1917] Step 2: Send basic information to the server.

[1918] The device sends the entered basic information to the server. The server receives the sent data and saves it as user information. The input data is sent to the server in JSON format.

[1919] Step 3: Save the basic information to the database.

[1920] The server stores the received basic information in a database, including the user's name, age, and electronic payment history, allowing for centralized management of data that can be used for subsequent processing.

[1921] Step 4: Customize the chatbot based on the user profile.

[1922] The server customizes the chatbot using a generative AI model (GPT-3) based on the user profile information stored in the database. This profile information is used to configure the chatbot to provide the most appropriate responses to the user.

[1923] Step 5: Send the user profile to the terminal.

[1924] The server sends customized chatbot information to the terminal, which receives the information and incorporates it into a smartphone application, providing the user with a personalized chatbot.

[1925] Step 6: Receive the user's question and send it to the generative AI model to generate a response.

[1926] The user uses their smartphone to input a question. This question is sent from the device to a server, which then sends it to a generative AI model. The generative AI model generates an appropriate response and returns it to the server. This process uses prompt statements (e.g., "I would like to check my recent payment history").

[1927] Step 7: Present the generated response to the user.

[1928] The server receives the response from the generative AI model and sends it to the device, which then displays the received response on the user's smartphone screen, allowing the user to immediately check the response from the system.

[1929] Step 8: Collect and analyze user interaction data.

[1930] The server continuously collects data on user interactions with the chatbot. This data is analyzed to identify whether questions about specific topics are frequently asked. The results of the analysis are used to update the dataset.

[1931] Step 9: Update the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1932] The server uses the collected dialogue data and analysis results to update the dataset of the generative AI model, which improves the accuracy of the chatbot's responses and allows it to provide more appropriate responses.

[1933] 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.

[1934] The present invention provides a system that allows users to receive individually customized support, quickly and safely obtain information, and solve problems. It also provides more personalized responses by incorporating an emotion engine that recognizes the user's emotions and adjusts responses. Below, as an embodiment of the present invention, the program processing of the system will be described with specific examples.

[1935] System Configuration

[1936] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine.

[1937] User terminal: The user uses this terminal to enter basic information, send questions, and receive responses from the server.

[1938] Server: A central processing unit that receives information from user terminals, processes the data, and generates the necessary responses.

[1939] Database: Stores basic information, dialogue data, and emotion history, and is used for analysis and updates.

[1940] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions.

[1941] Emotion Engine: A technology for recognizing user emotions and adjusting responses.

[1942] Program processing overview

[1943] 1. Initial Setup

[1944] The user enters basic information.

[1945] The terminal sends this information to the server.

[1946] The server stores the information in a database and generates a user profile.

[1947] 2. Generating personalized chatbots

[1948] The server customizes the chatbot based on the user profile.

[1949] The server transmits the customization information to the terminal.

[1950] 3. Information Acquisition and Response

[1951] The user enters a question.

[1952] The terminal sends a question to the server.

[1953] The server sends the question to a generative AI model, which generates a response.

[1954] The emotion engine recognizes the user's emotions.

[1955] The server receives the emotion engine results and adjusts the response.

[1956] The server sends a response to the terminal, which displays it to the user.

[1957] 4. Automatic collaboration and growth support

[1958] The server collects and analyzes dialogue data and emotion history.

[1959] The server provides personalized learning resources to support the user's growth.

[1960] 5. Data collection and analysis

[1961] The server collects and analyzes dialogue data and emotion history.

[1962] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[1963] Specific examples

[1964] Example of initial settings

[1965] The user starts the app and enters their name, age, hobbies, etc. For example, "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1966] The terminal sends this information to the server.

[1967] The server receives the information and stores it in the database as "User ID: 001, Name: Tanaka Taro, Age: 30, Hobby: Cycling."

[1968] Examples of personalized chatbots

[1969] The server sets a response pattern based on the information "Taro Tanaka, 30 years old, cycling."

[1970] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[1971] Specific examples of obtaining and responding to information

[1972] A user asks, "What's a good route for my next cycling trip?"

[1973] The terminal sends this question to the server.

[1974] The server sends a question to the generative AI model, which generates a response: "What's a good route for your next cycling trip?"

[1975] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[1976] The server then applies this sentiment analysis and generates a tailored response: "The best route for your next bike ride is along the nearby river. Have fun!"

[1977] The server sends this response to the terminal, which displays it to the user.

[1978] Specific examples of growth support

[1979] User types, "I want to improve my project management skills."

[1980] The server searches for relevant online courses and learning resources and sends them to the device.

[1981] The device displays to the user, "Recommended courses on project management are from XYZ Online School."

[1982] Examples of data collection and analysis

[1983] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[1984] The server adds new response patterns and datasets to respond to subsequent questions.

[1985] The introduction of the emotion engine allows the system of the present invention to provide more personalized responses according to the user's emotions, thereby improving the user experience and deepening user engagement.

[1986] The processing flow will be explained below.

[1987] Step 1:

[1988] The user enters basic information. The user launches the application and enters personal information such as name, age, and hobbies. For example, the user enters "Name: Taro Tanaka, Age: 30, Hobbies: Cycling."

[1989] Step 2:

[1990] The terminal sends the basic information entered by the user to the server, which then formats and transmits the input data to the server using a secure communication method.

[1991] Step 3:

[1992] The server stores the received basic information in a database. The server analyzes the data and stores it in the database as "User ID: 001, Name: Taro Tanaka, Age: 30, Hobby: Cycling."

[1993] Step 4:

[1994] The server customizes the chatbot based on the user profile, setting appropriate response patterns and parameters for the generative AI model based on the user's interests and tendencies.

[1995] Step 5:

[1996] The server sends the customization information to the terminal. The server completes the configuration and sends the customization data based on the user profile to the terminal.

[1997] Step 6:

[1998] The user inputs a question. The user inputs the information or question they want to know into the terminal, for example, "Tell me a good route for my next cycling trip."

[1999] Step 7:

[2000] The terminal sends the user's question to the server, which then transfers the question data to the server and prepares it for processing.

[2001] Step 8:

[2002] The server sends the question to the generative AI model, which generates a response. The server then forwards the question to the generative AI model via an API, which then generates a response: "What's a good route for your next cycling trip?"

[2003] Step 9:

[2004] The emotion engine recognizes the user's emotions and analyzes the user's current emotions based on the content the user has entered and past conversation history.

[2005] Step 10:

[2006] The server receives the results of the emotion engine and adjusts the response. The server reflects the analysis results of the emotion engine in the generated response. For example, if the user is "excited," the server adds "Have fun!"

[2007] Step 11:

[2008] The server sends the adjusted response to the terminal. The server sends the final response to the user's terminal.

[2009] Step 12:

[2010] The device displays the response to the user. The device displays the response received from the server to the user, saying, "The best cycling route is along the nearby river. Have fun!"

[2011] Step 13:

[2012] The server collects and analyzes dialogue data and emotion history. The server stores the dialogue history and emotion analysis results in a database and analyzes trends and frequently occurring problems.

[2013] Step 14:

[2014] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses, and generates a new dataset to use as training data to improve the generative AI model.

[2015] Step 15:

[2016] The server provides personalized learning resources to support the user's growth. The server utilizes conversation data and emotion history to provide appropriate learning resources and career support. For example, a user who wants to improve their project management skills will be offered relevant online courses and practical advice.

[2017] Example 2

[2018] 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."

[2019] Conventional chatbot systems were unable to adequately reflect the individual needs and emotions of users and could only provide uniform responses. As a result, the user experience was poor and questions often did not receive appropriate responses. Furthermore, the collection and analysis of dialogue data was insufficient, resulting in slow improvements in response accuracy. This led to issues such as low user satisfaction and engagement.

[2020] 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.

[2021] In this invention, the server includes: a means for a user to input basic information; a means for transmitting the input basic information to the server; a means for saving the basic information in a database; a means for customizing the chatbot based on a user profile; a means for receiving a user's question and transmitting the question to a generative AI model to generate a response; a means for recognizing the user's emotion using an emotion engine and adjusting the response; a means for presenting the generated response to the user; a means for collecting and analyzing interaction data with the user; and a means for updating a dataset to improve the accuracy of the chatbot's responses based on the analysis results. This enables personalized responses that reflect the user's individual needs and emotions, thereby improving the user experience and response accuracy.

[2022] "Basic information" refers to personal information such as the user's name, age, hobbies, etc.

[2023] A "server" is a central processing unit that processes information from a user terminal and generates a response.

[2024] A "database" is a storage device that stores basic information, dialogue data, and emotion history of a user and retrieves them as needed.

[2025] A "user profile" is individual user information generated based on the user's basic information and behavioral history.

[2026] A "chatbot" is an automated dialogue system that interacts with users and provides answers to their questions.

[2027] A "generative AI model" refers to artificial intelligence technology that generates appropriate responses to user questions.

[2028] An "emotion engine" is a technology that recognizes emotions from user input and dialogue and adjusts responses accordingly.

[2029] "Dialogue data" refers to historical information about interactions between a user and a system.

[2030] "Response accuracy" is a measure of the accuracy and appropriateness of responses generated to user questions.

[2031] A "dataset" is a collection of interaction data used to train and update a generative AI model.

[2032] "Personalized learning resources" refers to individually optimized learning content provided based on the user's basic information and needs.

[2033] "Multiple platforms" refers to different hardware or software environments, examples of which include different operating systems or devices.

[2034] The present invention provides a system for allowing users to receive individually customized support, quickly and safely obtain information, and solve problems. As an embodiment of the present invention, the details of the system are described below.

[2035] System Configuration

[2036] This system consists of a user terminal, a server, a database, a generative AI model, and an emotion engine. The specific hardware and software used are as follows:

[2037] User device: A device where a user enters basic information, sends questions, and receives responses from the server. Examples include smartphones and PCs.

[2038] Server: A central processing unit that receives information from user devices, processes the data, and generates the necessary response. Examples include web servers and application servers.

[2039] Database: This is used to store basic user information, interaction data, and emotion history, and is used for analysis and updating. Specifically, this applies to relational database management systems (RDBMS) and NoSQL databases.

[2040] Generative AI model: An artificial intelligence technology that generates appropriate responses to user questions. Examples include OpenAI's GPT-4.

[2041] Emotion engine: A technology for recognizing user emotions and tailoring responses. Specifically, it is a machine learning model that includes a sentiment analysis algorithm.

[2042] Program processing overview

[2043] 1. Initial Setup

[2044] The user enters basic information.

[2045] The terminal sends this information to the server.

[2046] The server stores the information in a database and generates a user profile.

[2047] 2. Generating personalized chatbots

[2048] The server customizes the chatbot based on the user profile.

[2049] The server transmits the customization information to the terminal.

[2050] 3. Information Acquisition and Response

[2051] The user enters a question.

[2052] The terminal sends a question to the server.

[2053] The server sends the question to a generative AI model, which generates a response.

[2054] The emotion engine recognizes the user's emotions.

[2055] The server receives the emotion engine results and adjusts the response.

[2056] The server sends a response to the terminal, which displays it to the user.

[2057] 4. Automatic collaboration and growth support

[2058] The server collects and analyzes dialogue data and emotion history.

[2059] The server provides personalized learning resources to support the user's growth.

[2060] 5. Data collection and analysis

[2061] The server collects and analyzes dialogue data and emotion history.

[2062] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[2063] Specific examples

[2064] Below are some examples of specific operations and responses:

[2065] Example of initial settings

[2066] The user launches the app and enters their name, age, hobbies, etc., such as "Name: Yamada Taro, Age: 25, Hobbies: Mountain climbing."

[2067] The terminal sends this information to the server.

[2068] The server receives the information and stores it in the database as "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[2069] Examples of personalized chatbots

[2070] The server sets a response pattern based on the information "Yamada Taro, 25 years old, mountain climbing."

[2071] The server sends the customized settings to the device, and the device displays "Personalized settings complete."

[2072] Specific examples of obtaining and responding to information

[2073] A user asks, "What's your recommendation for the next mountain I should climb?"

[2074] The terminal sends this question to the server.

[2075] The server sends a question to the generative AI model, which generates a response: "Recommendations for the next mountain to climb."

[2076] The emotion engine analyzes the user's emotions and recognizes, for example, that the user is "excited."

[2077] The server reflects the sentiment analysis results and generates a tailored response such as, "The next recommended mountain to climb is nearby Mount Takao. Have fun!"

[2078] The server sends this response to the terminal, which displays it to the user.

[2079] Specific examples of growth support

[2080] User types, "I want to improve my project management skills."

[2081] The server searches for relevant online courses and learning resources and sends them to the device.

[2082] The device displays to the user, "ABC Online School is a recommended course on project management."

[2083] Examples of data collection and analysis

[2084] The server analyzes the dialogue history and sentiment history to identify an increase in questions about a particular topic.

[2085] The server adds new response patterns and datasets to respond to subsequent questions.

[2086] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2087] Step 1:

[2088] Enter and submit basic information

[2089] The user starts the application and enters basic information such as name, age, hobbies, etc. An example of input here is "Name: Taro Yamada, Age: 25, Hobbies: Mountain climbing."

[2090] The device sends the entered basic information to the server. The information sent is in JSON format, such as "{"Name": "Yamada Taro", "Age": 25, "Hobbies": "Mountain climbing"}".

[2091] As an output, the server receives this information.

[2092] Step 2:

[2093] Storing information and creating user profiles

[2094] The server stores the received information in a database. For example, the database stores "User ID: 002, Name: Yamada Taro, Age: 25, Hobby: Mountain climbing."

[2095] The server generates a user profile based on the stored information, which is associated with a user ID to protect privacy.

[2096] As an output, a user profile is registered in a database.

[2097] Step 3:

[2098] Generate a customized chatbot

[2099] The server retrieves the user profile from the database and customizes the chatbot, for example, by setting response patterns related to "Taro Yamada, 25 years old, mountain climbing."

[2100] The server transmits the customization information to the terminal.

[2101] The device will display "Personalization settings complete."

[2102] As an output, a customized chatbot is prepared on the terminal.

[2103] Step 4:

[2104] Enter and submit your question

[2105] A user types a question such as "What's your recommendation for the next mountain to climb?"

[2106] The device sends this question to the server. The data sent is "{"Question": "What mountain do you recommend I climb next?"}".

[2107] As an output, the server receives the question.

[2108] Step 5:

[2109] Generating a response

[2110] The server sends the question to a generative AI model (e.g., OpenAI GPT-4), which analyzes the question and generates a response such as "Recommend the next mountain to climb."

[2111] As input, the server provides the question and the user profile to the generative AI model.

[2112] As an output, the generative AI model generates the response, "The next mountain to climb is Mount Takao."

[2113] Step 6:

[2114] Recognizing emotions and regulating responses

[2115] The emotion engine analyzes the user's input text and dialogue history to recognize emotions such as "excited."

[2116] The server reflects the analysis results of the emotion engine and generates a tailored response such as, "Mount Takao is especially recommended at this time of year. Have fun!"

[2117] As input, the emotion engine receives the user's text data.

[2118] The output is a tailored response that blends the results of the emotion engine with the response of the generative AI model.

[2119] Step 7:

[2120] Sending and Displaying Responses

[2121] The server sends the adjusted response to the terminal.

[2122] The device displays a response to the user, specifically, "Mount Takao is especially recommended at this time of year. Have fun!"

[2123] As an output, the user can receive an appropriate response.

[2124] Step 8:

[2125] Collecting dialogue data and emotion history

[2126] The server periodically collects all dialogue history and emotion history and stores them in a database.

[2127] As output, the dialogue data and emotion history are saved.

[2128] Step 9:

[2129] Analyzing data and updating datasets

[2130] The server analyzes the collected conversation data and sentiment history to identify trends in questions about specific topics and changes in sentiment.

[2131] Based on the analysis results, the server updates the dataset of the generative AI model to improve response accuracy.

[2132] It uses collected dialogue data and emotion history as input.

[2133] The output is an updated dataset that improves the accuracy of the chatbot's responses.

[2134] (Application example 2)

[2135] 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."

[2136] Conventional chatbot systems often fail to provide responses that fully reflect the individual needs of users. Furthermore, they lack personalization capabilities, such as responses that take the user's emotions into account and automatic provision of learning resources. Therefore, there is a need for an improved user experience. Particularly in brick-and-mortar stores, there is a need for a system that provides real-time, personalized support to users while they are shopping.

[2137] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input basic information; means for transmitting the input basic information to the server; means for saving the basic information in a database; means for customizing the chatbot based on a user profile; means for receiving a user's question and transmitting the question to a generative AI model to generate a response; means for presenting the generated response to the user; means for using an emotion engine that recognizes the user's emotions and adjusts the response; means for collecting and analyzing dialogue data with the user; and means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results. This makes it possible to provide quick and personalized responses to user questions and generate optimal responses according to the user's emotions.

[2138] The "means for users to input basic information" is an interface that allows users to digitally input personal information such as name, age, hobbies, etc.

[2139] The "means for saving basic information to a database" is a function for storing the information entered by the user in a database so that it can be referenced and analyzed later.

[2140] "Means for customizing chatbots based on user profiles" refers to a function for generating chatbots with individually set response patterns and characteristics based on saved basic information about users.

[2141] "Means for receiving a user's question and sending the question to a generative AI model to generate a response" refers to a system for receiving a question submitted by a user, sending it to a generative AI model, and generating an appropriate response.

[2142] The "means for presenting the generated response to the user" is an interface for displaying the response obtained from the generative AI model to the user.

[2143] The "means for using an emotion engine that recognizes the user's emotion and adjusts the response" is an engine for analyzing the user's emotion and optimizing the response based on the result.

[2144] "Means for collecting and analyzing dialogue data with users" is a function for collecting the content of dialogue exchanged between users and chatbots and analyzing it later.

[2145] "Means for updating the dataset to improve the accuracy of chatbot responses based on the analysis results" refers to a function that uses the analysis results of dialogue data to update the dataset to improve the content and accuracy of chatbot responses.

[2146] This invention is a "smart shopping assistant" system that optimizes the shopping experience in physical stores to suit user needs. When a user inputs a question, the system uses a generative AI model to generate a quick and personalized response, and further uses an emotion engine to provide the optimal response based on the user's emotions.

[2147] System Configuration

[2148] 1. User Device:

[2149] This is an interface that users use to enter basic information (such as name, age, hobbies, etc.) and questions. It is implemented as a smartphone application.

[2150] 2. Server:

[2151] It is a central processing unit that receives basic information and questions sent from the user device and performs various processes including generative AI models and emotion engines. It also stores the data in a database and generates and manages user profiles.

[2152] 3. Database:

[2153] This is a storage device for saving basic user information, dialogue data, emotion history, etc. Relational database management systems such as MySQL and PostgreSQL can be used.

[2154] 4. Generative AI Models:

[2155] It is an artificial intelligence model used to generate appropriate responses to user questions. It generally uses natural language processing techniques such as GPT-3.

[2156] 5. Emotion Engine:

[2157] It is an engine that recognizes emotions from user input and adjusts responses based on the results. For sentiment analysis, it uses sentiment analysis APIs (e.g., Microsoft Azure's text analysis API).

[2158] Program processing overview

[2159] 1. Initial Setup:

[2160] A user starts the app and enters basic information, for example, "Name: Taro Yamada, Age: 28, Hobby: Reading." The device sends this information to the server, which receives it and stores it in a database.

[2161] 2. Generate personalized chatbots:

[2162] The server customizes the chatbot based on the user profile. For example, it sets a response pattern based on the information "Yamada Taro, 28 years old, reading." The customized settings are sent to the device, and the message "Personalization settings complete" is displayed.

[2163] 3. Information Acquisition and Response:

[2164] When a user asks, "Tell me a review of this product," the device sends the question to a server. The server sends the question to a generative AI model, which generates a "review of this product." The emotion engine then analyzes the user's emotions, and if it recognizes, for example, an "excited" state, it adjusts the final response, displaying, "This product has a great review. Enjoy!"

[2165] 4. Data collection and analysis:

[2166] The server collects and analyzes the interaction data and sentiment history, for example identifying popular questions about a particular product and adding new response patterns and datasets.

[2167] Prompt Sentence Examples

[2168] User: Write a review for this product

[2169] Assistant:

[2170] This makes it possible to provide the information the user wants quickly and accurately, and improve the user experience by responding according to their emotions.

[2171] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2172] Step 1:

[2173] The user enters basic information

[2174] A user inputs basic information (such as name, age, and hobbies) through a smartphone app. The input data includes information such as "Name: Yamada Taro, Age: 28, Hobbies: Reading." This is the input data. The device acquires this data and sends it to the server.

[2175] Step 2:

[2176] The server stores basic information in a database

[2177] The server receives the basic information sent by the user from the device. The received data is analyzed and stored in a database in a structured format. For example, the information is stored in the database as "User ID: 001, Name: Yamada Taro, Age: 28, Hobby: Reading." This is the output data.

[2178] Step 3:

[2179] The server customizes the chatbot based on the user profile.

[2180] The server generates a user profile based on the stored basic information. This allows for customized settings based on the user's profile data. For example, based on the information "Yamada Taro, 28 years old, reading," the chatbot prepares relevant response patterns and content. The customized settings are output data.

[2181] Step 4:

[2182] The user enters a question

[2183] The user inputs a question through a smartphone app. For example, they might type, "Please give me a review of this product." This is the input data. The device then sends this question to the server.

[2184] Step 5:

[2185] The server sends the question to the generative AI model to generate a response.

[2186] The server receives the question sent by the user and sends it to the generative AI model. The generative AI model generates a response using the prompt "User: Tell me the review of this product\nAssistant:". For example, it generates "This product has good reviews." This is the output data.

[2187] Step 6:

[2188] The server recognizes the user's emotions and adjusts the response

[2189] Based on the generated response, the server sends the data to the emotion engine. The emotion engine recognizes the emotion from the text entered by the user, analyzing it as "excited," for example. Based on the results, it adjusts the response. For example, the final response might be "This product has good reviews. Enjoy." This is the output data.

[2190] Step 7:

[2191] The server generates a response and presents it to the user.

[2192] The server sends the adjusted response to the terminal, which displays it to the user, which is the output data the user receives.

[2193] Step 8:

[2194] The server collects and analyzes user interaction data

[2195] The server collects conversation data and emotion history between the user and the chatbot. The collected data is analyzed to determine conversation trends and frequently asked questions. This is the analytical data.

[2196] Step 9:

[2197] The server updates the dataset based on the analysis results to improve the accuracy of the chatbot's responses.

[2198] Based on the analysis results, the server updates the training dataset of the generative AI model to improve the accuracy of the generated responses, thereby providing accurate and personalized responses to subsequent questions. The updated dataset is the output data.

[2199] 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.

[2200] 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.

[2201] 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.

[2202] 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.

[2203] 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.

[2204] 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.

[2205] 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).

[2206] 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.

[2207] 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."

[2208] 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.

[2209] 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).

[2210] 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.

[2211] 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.

[2212] 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.

[2213] 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.

[2214] 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.

[2215] 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.

[2216] 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.

[2217] 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.

[2218] 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.

[2219] 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.

[2220] The following is further disclosed regarding the above embodiment.

[2221] (Claim 1)

[2222] a means for a user to input basic information;

[2223] means for transmitting the input basic information to a server;

[2224] A means of storing basic information in a database;

[2225] A means for customizing the chatbot based on a user profile; and

[2226] means for receiving a user question and sending the question to a generative AI model to generate a response;

[2227] means for presenting the generated response to a user;

[2228] means for collecting and analyzing user interaction data;

[2229] A means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results; and

[2230] A system including:

[2231] (Claim 2)

[2232] 10. The system of claim 1, further comprising means for automatically providing personalized learning resources based on basic information of a user.

[2233] (Claim 3)

[2234] 10. The system of claim 1, further comprising means for deploying the chatbot across multiple platforms.

[2235] "Example 1"

[2236] (Claim 1)

[2237] a means for a user to input basic information;

[2238] means for transmitting the input basic information to a server;

[2239] A means of storing basic information in a database;

[2240] means for customizing the conversational agent based on a user profile;

[2241] means for receiving a user question and sending the question to a generative artificial intelligence model to generate a response;

[2242] means for presenting the generated response to a user;

[2243] means for collecting and analyzing user interaction data;

[2244] a means for updating the dataset to improve the response accuracy of the conversational agent based on the analysis results;

[2245] A means to provide personalized learning resources to help users grow; and

[2246] A system including:

[2247] (Claim 2)

[2248] 2. The system according to claim 1, further comprising means for automatically providing optimized learning resources based on basic information of a user.

[2249] (Claim 3)

[2250] 10. The system of claim 1, further comprising means for deploying conversational agents corresponding to a plurality of information platforms.

[2251] "Application Example 1"

[2252] (Claim 1)

[2253] a means for a user to input basic information;

[2254] means for transmitting the input basic information to a server;

[2255] A means of storing basic information in a database;

[2256] A means for customizing the chatbot based on a user profile; and

[2257] means for receiving a user question and sending the question to a generative AI model to generate a response;

[2258] means for presenting the generated response to a user;

[2259] means for collecting and analyzing user interaction data;

[2260] A means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results; and

[2261] A means for identifying questions on a specific topic from the dialogue history and generating new response patterns;

[2262] A means for obtaining a user's electronic payment history and providing personalized support based thereon;

[2263] A system including:

[2264] (Claim 2)

[2265] 10. The system of claim 1, further comprising means for automatically providing personalized learning resources based on a user's basic information and electronic payment history.

[2266] (Claim 3)

[2267] The system according to claim 1, further comprising means for deploying a chatbot compatible with multiple platforms and supporting users in cooperation across multiple devices.

[2268] "Example 2: Combining Emotion Engines"

[2269] (Claim 1)

[2270] a means for a user to input basic information;

[2271] means for transmitting the input basic information to a server;

[2272] A means of storing basic information in a database;

[2273] A means for customizing the chatbot based on a user profile; and

[2274] means for receiving a user question and sending the question to a generative AI model to generate a response;

[2275] means for recognizing a user's emotions and adjusting a response using an emotion engine;

[2276] means for presenting the generated response to a user;

[2277] means for collecting and analyzing user interaction data;

[2278] A means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results; and

[2279] A system including:

[2280] (Claim 2)

[2281] 10. The system of claim 1, further comprising means for automatically providing personalized learning resources based on basic information of a user.

[2282] (Claim 3)

[2283] 10. The system of claim 1, further comprising means for deploying the chatbot across multiple platforms.

[2284] "Application example 2 when combining emotion engines"

[2285] (Claim 1)

[2286] a means for a user to input basic information;

[2287] means for transmitting the input basic information to a server;

[2288] A means of storing basic information in a database;

[2289] A means for customizing the chatbot based on a user profile; and

[2290] means for receiving a user question and sending the question to a generative AI model to generate a response;

[2291] means for presenting the generated response to a user;

[2292] a means for using an emotion engine to recognize the user's emotions and adjust responses;

[2293] means for collecting and analyzing user interaction data;

[2294] A means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results; and

[2295] A system including:

[2296] (Claim 2)

[2297] 10. The system of claim 1, further comprising means for automatically providing personalized learning resources based on basic information of a user.

[2298] (Claim 3)

[2299] 10. The system of claim 1, wherein the system is implemented on a smartphone. [Explanation of symbols]

[2300] 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 means for a user to input basic information; means for transmitting the input basic information to a server; A means of storing basic information in a database; A means for customizing the chatbot based on a user profile; and means for receiving a user question and sending the question to a generative AI model to generate a response; means for presenting the generated response to a user; means for collecting and analyzing user interaction data; A means for updating the dataset to improve the accuracy of the chatbot's responses based on the analysis results; and A system including:

2. 10. The system of claim 1, further comprising means for automatically providing personalized learning resources based on basic information of the user.

3. 10. The system of claim 1, further comprising means for deploying the chatbot across multiple platforms.

Images