system

Abstract

Provide a system. [Solution] means for receiving basic information from a user and generating a profile of the user; A means for selecting and tailoring specific questions based on a user's profile; and A means for generating questions to provide an opportunity for users to think about their problems rather than giving immediate answers; A means to propose individual learning curriculum and career paths based on users' answers and progress, A means to store conversation logs with users and provide support content according to the user's growth and changes, A system including:

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] Conventional AI chatbots' main function was to provide immediate answers to user questions, making it difficult to develop users' independence and problem-solving abilities. Furthermore, they often failed to provide adequate individualized support tailored to the user's characteristics, career path, or learning curriculum, resulting in limited support. Furthermore, there was a need for a system that could flexibly respond to changes in the support required as the user grows. [Means for solving the problem]

[0005] The present invention provides a means for receiving basic information from a user to generate a profile, and for selecting and adjusting specific questions based on that profile. It also has a means for generating questions that do not immediately answer the user's problems but provide an opportunity for them to think. It also includes a means for proposing individual learning curricula and career paths based on the user's answers and progress. It also has a means for saving a conversation log with the user and providing support content that responds to the user's growth and changes, thereby realizing long-term and flexible support.

[0006] "User" refers to any individual or entity that uses this system.

[0007] "Basic information" refers to information about the user's name, age, occupation, and interests.

[0008] "Profile" refers to an individual data set generated based on a user's basic information.

[0009] "Questioning" refers to questions and advice that the system presents to the user.

[0010] "Adjustment" refers to the act of appropriately changing the content and timing of questions based on the user's profile information.

[0011] "Immediate response" refers to providing immediate answers to users' questions or problems.

[0012] "Opportunity to think" means providing users with time and questions to help them find their own solutions.

[0013] "Question generation" refers to the act of the system creating a new question to address the user's problem.

[0014] "Response" refers to the reply or opinion given by the user to the system.

[0015] "Progress" refers to the progress of users' learning, career paths, etc.

[0016] "Individual learning curriculum" refers to an educational program customized to the user's profile and progress.

[0017] "Career path" refers to a planned career path based on the user's occupation or field of expertise.

[0018] "Conversation log" refers to data that records all conversations that take place between a user and the system.

[0019] "Growth" refers to the process by which users' skills and knowledge improve.

[0020] "Support content" refers to advice, educational resources, etc. that the system provides to users.

[0021] "Long-term support" refers to support provided continuously as users continue to interact with the system over a long period of time. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] MODE FOR CARRYING OUT THE INVENTION

[0044] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves a conversation log with the user, realizing long-term and flexible support that provides support content tailored to the user's growth and changes.

[0045] Program processing overview

[0046] Collection of user information

[0047] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0048] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[0049] Conversation Design

[0050] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0051] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[0052] Conversations that encourage autonomy

[0053] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0054] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[0055] Individual curriculum proposals

[0056] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0057] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[0058] Long-term support and growth

[0059] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[0060] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[0061] The above is a specific embodiment of the function of the program of the system of the present invention to collect user information, propose personalized questions and learning curricula, and provide long-term support.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[0065] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[0066] Step 2:

[0067] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[0068] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[0069] Step 3:

[0070] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[0071] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[0072] Step 4:

[0073] The user enters an answer to the question, and the terminal sends the answer to the server.

[0074] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[0075] Step 5:

[0076] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[0077] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[0078] Step 6:

[0079] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[0080] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[0081] Step 7:

[0082] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[0083] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[0084] Step 8:

[0085] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[0086] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[0087] Step 9:

[0088] As users ask new questions or make new requests, the device continues to respond with improved content.

[0089] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[0090] The above is a description of the program processing divided into specific steps.

[0091] Example 1

[0092] 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."

[0093] In conventional systems, educational and vocational support for users was uniform, making it difficult to respond flexibly to individual needs and progress. Furthermore, there was a lack of mechanisms to provide users with opportunities to think for themselves to solve problems, which meant that users' autonomy and growth were not sufficiently promoted. The present invention aims to solve these problems.

[0094] 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.

[0095] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual educational plan or career path based on the user's answers and progress, and means for storing a record of interactions with the user and providing support content according to the user's maturity and changes. This enables flexible educational and career support tailored to the individual needs of the user. It also provides users with opportunities to think for themselves to solve problems, promoting their independence and growth.

[0096] "Basic information" refers to information entered when using the service for the first time, such as the user's name, age, occupation, and areas of interest.

[0097] A "profile" refers to data about a user's attributes and characteristics that is generated based on the user's basic information and stored in a database.

[0098] "Prompts" refer to questions or confirmations that are asked to the user and are tailored appropriately based on the user's profile.

[0099] "Educational Plan" refers to a learning strategy or curriculum that is individually provided based on the user's progress and needs.

[0100] "Career Pathways" refers to specific steps or suggestions to guide users on their career path.

[0101] "Dialogue records" refers to data that the system uses to store the content of conversations with users.

[0102] "Support content" refers to the overall assistance provided to users, such as advice, resources, and questions, as they grow and change.

[0103] MODE FOR CARRYING OUT THE INVENTION

[0104] The present invention relates to a system that receives basic information from a user, creates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual educational plans and career paths based on the user's answers and progress. Furthermore, it stores a record of interactions with the user and provides flexible support content that adapts to the user's maturity and changes.

[0105] Collection of user information

[0106] When using the device for the first time, the user enters basic information (such as name, age, occupation, and areas of interest). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0107] Example: A user enters "I'm Ichiro Yamada, 35 years old, a software developer. I'm interested in machine learning and cloud computing." The device sends this information to a server, which generates and stores a new profile.

[0108] Conversation Design

[0109] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0110] Example: Based on the profile generated by the server, the device displays the question, "Yamada, what machine learning-related projects are you working on now?"

[0111] Conversations that encourage autonomy

[0112] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0113] Example: If a user types, "I'm having trouble organizing data for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you considered?"

[0114] Individual curriculum proposals

[0115] The server analyzes the user's past answers and progress to generate an appropriate educational plan and career path, and the terminal then presents the curriculum received from the server to the user.

[0116] Example: If a user types "I'm having trouble organizing my data," the server generates a suggestion such as "I recommend this online course that focuses on data organization," and the device presents this to the user.

[0117] Long-term support and growth

[0118] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. Based on the analysis results, the server continually refines the support content and question patterns. Each time the user makes a new question or request, the device responds using the refined content.

[0119] Example: If a user enters the following message after a few months: "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as the next step," which the device will then present to the user.

[0120] These steps are achieved through collaboration between the server and the device. The server analyzes the user's profile data, dialogue records, and responses, and utilizes generative AI models and prompts to provide appropriate questions and support. Meanwhile, the device plays a role in advancing the dialogue with the user based on instructions from the server. This system enables educational and vocational support tailored to the individual needs of each user. Furthermore, by giving users the opportunity to think for themselves to solve problems, it promotes their independence and growth.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1: Enter your user information

[0123] The user enters basic information (such as name, age, occupation, and areas of interest) into the device. At this point, the input information is text data such as name and age. The device sends the entered information to the server. For example, if the user enters "I'm Yamada Ichiro, 35 years old, a software developer. I'm interested in machine learning and cloud computing," the device sends this information to the server in JSON format.

[0124] Input: User's basic information (name, age, occupation, interests)

[0125] Output: JSON data of user information sent to the server

[0126] Step 2: Generate a profile

[0127] The server analyzes the received user information and generates a user profile. This profile includes information such as name, age, occupation, and areas of interest. The profile data is stored in a database. For example, the server generates and stores a profile in the following format: {"name": "Yamada Ichiro", "age": 35, "profession": "Software Developer", "interests": ["machine learning", "cloud computing"]}.

[0128] Input: JSON data of user information

[0129] Output: Generated user profile database entries

[0130] Step 3: Design the question

[0131] The device has pre-programmed question patterns. The server selects and tailors appropriate questions based on the user's profile. The server references the profile and generates customized questions such as, "What machine learning-related projects are you currently working on?" The device then displays these questions to the user.

[0132] Input: Generated user profile

[0133] Output: A customized prompt that is displayed to the user.

[0134] Step 4: User input on the problem

[0135] The user responds to the prompt by inputting a specific problem or concern. For example, the user might input, "I'm having trouble organizing data for a machine learning project." This user input is sent from the device to the server.

[0136] Input: User's problem or concern

[0137] Output: The text data of the problem sent to the server

[0138] Step 5: Conversations that encourage autonomy

[0139] The device does not immediately answer the problem entered by the user, but generates support questions to help the user think of a solution on their own. The server generates more in-depth questions and advice based on the user's answers. For example, the device generates and displays support questions such as, "Which part do you feel is particularly problematic? What solutions have you considered for it?" In response to the user's answer, "Data cleansing is difficult," the server generates a question such as, "What specific data cleansing techniques have you tried?"

[0140] Input: Text data of user problems and concerns

[0141] Output: Generate and display supplementary and probing questions

[0142] Step 6: Propose an individual curriculum

[0143] The server analyzes the user's past responses and progress to generate a personalized educational plan and career path. The device then presents the curriculum received from the server to the user. For example, if the user types, "I'm having trouble with data organization," the server generates a suggestion, such as, "I recommend this online course that focuses on data organization," and the device presents it to the user.

[0144] Input: User's past answers and progress data

[0145] Output: Creation and presentation of individualized curriculum and career pathways

[0146] Step 7: Long-term support and growth

[0147] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. The server continues to improve the support content and question patterns based on the analysis results. For example, if a user inputs after a few months, "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[0148] Input: Saved conversation log

[0149] Output: Improved support content, question patterns, and suggested content

[0150] The above are the specific processing steps of the program of this system.

[0151] (Application example 1)

[0152] 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."

[0153] A challenge facing modern educational environments is the lack of personalized learning support tailored to individual learners. In particular, it is difficult to provide dynamic curriculum and content that responds to users' interests and progress, and there is a lack of mechanisms to promote independent learning. This results in many learners being unable to learn efficiently and taking a long time to achieve their goals.

[0154] 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.

[0155] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum or career path based on the user's answers and progress, means for recommending optimal learning content based on the user's interests and learning progress information, and means for saving a conversation log with the user and providing support content according to the user's growth and changes. This makes it possible to provide individualized learning support to users and promote efficient and independent learning.

[0156] "Basic information" refers to personal information such as the user's name, age, occupation, and interests.

[0157] A "profile" is an individual collection of information generated based on a user's basic information.

[0158] "Specific questions" are questions selected based on the user's profile.

[0159] "Thinking questions" are questions that encourage users to think of solutions on their own.

[0160] A "personalized learning curriculum" is a personalized learning plan that is suggested based on the user's progress and responses.

[0161] A "career path" is a suggestion of a career path that is presented based on the user's occupation and interests.

[0162] "Interests" refers to areas or topics in which a user is particularly interested.

[0163] "Study progress information" is information relating to the progress of a user's learning activities.

[0164] The means for recommending "optimal learning content" is a method for recommending the most appropriate learning materials and content based on the user's interests and learning progress.

[0165] A "conversation log" is a record of all conversations between a user and the system.

[0166] "Support content according to growth and change" refers to appropriate assistance and advice provided according to the user's growth and progress.

[0167] Creating a user profile

[0168] When a user first uses the device, they enter basic information. The device collects basic information such as the user's name, age, occupation, and interests, and sends it to the server. The server then creates a user profile based on the received basic information and stores it in a database. This profile serves as the basis for providing questions and curriculum that are individually tailored to the user.

[0169] Specific examples

[0170] A user enters, "I'm Taro Yamada, 25 years old, a programmer, and I'm interested in machine learning and data analysis." The device sends this information to the server, which generates and saves a new profile.

[0171] Dynamic adjustment of specific questions

[0172] The server dynamically tailors specific questions to match the user's interests based on pre-programmed question patterns based on the profile, and the device displays the customized questions to the user.

[0173] Specific examples

[0174] Based on the profile generated by the server, the device displays the question, "Yamada-san, what machine learning projects have you been working on recently?"

[0175] Generate questions to encourage self-direction

[0176] When a user inputs a specific problem or concern, the server does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0177] Specific examples

[0178] If a user types, "I'm having trouble with data preprocessing for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you come up with?"

[0179] Individual curriculum proposals

[0180] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0181] Specific examples

[0182] If a user inputs "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," which the device presents to the user.

[0183] Long-term support and growth

[0184] The server stores the conversation logs and provides support content that responds to the user's growth and changes. The server periodically analyzes the stored conversation logs to confirm the user's progress and needs, and continues to improve the support content based on that.

[0185] Specific examples

[0186] If a user inputs "I understand the basics of data preprocessing, but next I want to learn about model tuning" after a few months, the server will analyze the logs and check the user's progress. It will then generate support content based on the user's progress, such as "I recommend this resource as the next step," and present it to the user on the device.

[0187] Prompt Sentence Examples

[0188] My name is Taro Yamada, I'm 25 years old and I'm a programmer. I'm interested in machine learning and data analysis. I'm currently struggling with data preprocessing for a machine learning project.

[0189] This invention is realized by an application installed on a device such as a smartphone, tablet, or PC, and a program running on the server side. User input information is exchanged with the server via communication methods such as RESTful API or WebSocket. A database management system (DBMS) is used to store data, and a generative AI model is used for natural language processing. This realizes a system that allows users to receive personalized learning support.

[0190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0191] Step 1: Enter user information

[0192] The user uses the device to input basic information such as name, age, occupation, and interests. The device then sends this information to the server. The input is received as text data, and the output is transmitted to the server via an API request.

[0193] Step 2: Generate a profile

[0194] The server generates a user profile based on the received basic information. Profile generation involves mapping the input information to fields based on templates stored in a database. The input is the basic information, and the output is the generated profile data.

[0195] Step 3: Dynamically adjust specific questions

[0196] The server then references the generated profile and selects and tailors specific questions based on the profile, using profile-based filtering and scoring algorithms to determine the most appropriate questions, with the profile data as input and the specific questions as output.

[0197] Step 4: Present the question

[0198] The terminal receives a question from the server and displays it to the user, who then enters a response. The input to this process is the question, and the output is the user's response.

[0199] Step 5: Question Generation

[0200] The server takes the user's answer and generates new questions to provide further insight. This step uses a generative AI model to dynamically create probing questions, with the user's answer as input and the new question as output.

[0201] Step 6: Propose an individual curriculum

[0202] The server analyzes the user's answers and progress and generates a personalized learning curriculum and career path. Machine learning algorithms are used here to provide a learning plan that best suits the user's needs. The input is the user's answers and progress data, and the output is the generated learning curriculum and career path.

[0203] Step 7: Recommend learning content

[0204] The server recommends optimal learning content based on the user's interests and learning progress information. In this step, a scoring model is used to select content taking into account the user's history and preferences. The input is interests and learning progress information, and the output is recommended content.

[0205] Step 8: Store and analyze logs

[0206] The server stores all conversation logs and periodically analyzes them to evaluate user growth and changes. This analysis uses natural language processing and data analysis tools. The input is conversation log data, and the output is the user's growth status and improved support content.

[0207] Step 9: Providing long-term support

[0208] The server provides personalized long-term support to the user based on the analysis results, and the terminal displays this support content to the user. The analysis results are input, and new support content is output.

[0209] 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.

[0210] MODE FOR CARRYING OUT THE INVENTION

[0211] The present invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[0212] Program processing overview

[0213] Collection of user information

[0214] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0215] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[0216] Conversation Design

[0217] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0218] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[0219] Conversations that encourage autonomy

[0220] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0221] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[0222] Individual curriculum proposals

[0223] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0224] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[0225] Long-term support and growth

[0226] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[0227] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[0228] Use of emotion engine

[0229] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on this recognition result, the server adjusts the content of the questions and the learning curriculum. If the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates advice for relaxation and appropriate questions, which are presented to the user via the device.

[0230] Example: If a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress state and notifies the server. The server then suggests "Why don't you try some methods to relax?", which the device displays to the user.

[0231] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[0235] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[0236] Step 2:

[0237] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[0238] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[0239] Step 3:

[0240] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[0241] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[0242] Step 4:

[0243] The user enters an answer to the question, and the device sends the answer to the server.

[0244] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[0245] Step 5:

[0246] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[0247] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[0248] Step 6:

[0249] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[0250] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[0251] Step 7:

[0252] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[0253] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[0254] Step 8:

[0255] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[0256] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[0257] Step 9:

[0258] As users ask new questions or make new requests, the device continues to respond with improved content.

[0259] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[0260] Step 10:

[0261] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. The recognition results are sent to the server.

[0262] Specific behavior: When a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine detects the stress state and sends the result to the server.

[0263] Step 11:

[0264] The server receives the emotion recognition results from the emotion engine and adjusts the questions and learning curriculum accordingly. The device then presents the adjusted content to the user.

[0265] Specific operation: The server generates a question, "Would you like to try some ways to relax?", and the device presents this to the user.

[0266] The above is the processing flow of the system when combined with the emotion engine.

[0267] Example 2

[0268] 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."

[0269] Conventional learning support systems and career development support systems face challenges in that they are unable to flexibly respond to individual users' needs and growth, making it difficult to provide users with appropriate advice immediately. Furthermore, they lack the ability to recognize users' emotions and adjust their responses accordingly, resulting in insufficient support for users' long-term growth and psychological development. This can lead to reduced learning effectiveness and reduced career development efficiency.

[0270] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving basic information from a user and generating a user profile, a means for selecting and adjusting specific questions based on the user profile, a means for generating questions to provide an opportunity for the user to think rather than immediately answering the user's problems, a means for proposing an individual learning curriculum and career path based on the user's answers and progress, and a means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This enables flexible responses according to the individual needs of users and psychological support through emotion recognition.

[0271] "User" refers to any person or organization that uses this system.

[0272] "Basic information" refers to basic information about an individual or organization, such as the user's name, age, occupation, and interests.

[0273] A "profile" refers to a data set that indicates individual characteristics and needs, generated based on basic information about the user.

[0274] "Questions" refers to the questions and conversations asked to users.

[0275] "Not giving an immediate answer" refers to not providing an immediate answer to a user's questions or concerns.

[0276] "Providing an opportunity to think" means providing time and space for users to think about solutions and opinions on their own.

[0277] "Individual learning curriculum" refers to a learning plan customized according to the characteristics and needs of the user.

[0278] A "career path" refers to a path created to support users' professional growth and advancement.

[0279] "Conversation log" refers to a record of conversations between users.

[0280] "Emotion" refers to the user's psychological state or feelings.

[0281] "Emotion recognition" refers to identifying a user's psychological state by analyzing their input data, voice, facial expressions, etc.

[0282] "Adjusting the content of questions and learning curriculum" refers to dynamically changing the questions asked and the content of the learning plan provided based on the user's profile and emotion recognition results.

[0283] MODE FOR CARRYING OUT THE INVENTION

[0284] The present invention is a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[0285] This system mainly uses the following hardware and software:

[0286] Hardware used

[0287] Terminal: A device that receives user input, such as a PC or smartphone.

[0288] Server: A high-performance computer, such as a cloud server, that stores and processes data.

[0289] Software used

[0290] Database management system: Software such as MySQL (registered trademark) and PostgreSQL is used.

[0291] Machine learning models: Emotion recognition and profile generation are performed using libraries such as TENSORFLOW (registered trademark) and PyTorch.

[0292] The server receives basic information from the user from the device and generates a profile based on that information. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a profile based on the received information and stores it in a database.

[0293] Based on this profile, the server selects specific questions and generates appropriate questions, which the device displays to the user, asking, for example, "Mr. Tanaka, what AI-related projects are you currently working on?"

[0294] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think of a solution. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you thought of?"

[0295] Furthermore, the server can suggest personalized learning curriculums and career paths based on the user's answers and progress. It analyzes the user's past answers from the database and generates suggestions such as, "We recommend this online course that focuses on data preprocessing."

[0296] To provide long-term support, the device stores conversation logs with the user, and the server uses these logs to periodically analyze the user's growth and progress. For example, if a user inputs, "I understand the basics of data preprocessing, but next I'd like to learn about model tuning," the server analyzes the log and generates support content tailored to the user's growth, such as, "I recommend this resource as the next step," which the device then presents to the user.

[0297] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if a user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[0298] Example prompts for generative AI models

[0299] Here are some examples of prompts you might input to a generative AI model:

[0300] Example prompt:

[0301] User profile:

[0302] Name: Taro Tanaka

[0303] Age: 30

[0304] Occupation: Engineer

[0305] Interests: AI, data science

[0306] User Question:

[0307] "I'm struggling with data preprocessing for my AI project. What part do you find particularly challenging? What solutions have you come up with?"

[0308] This allows the generative AI model to generate appropriate questions and suggestions and provide them to the user.

[0309] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1:

[0312] Collection of user information

[0313] Input: The user enters basic information (name, age, occupation, interests, etc.) when using the service for the first time.

[0314] Processing: The device sends the entered information to the server, which then creates a user profile based on the information received and stores it in a database.

[0315] Output: The server-generated user profile.

[0316] Specific behavior:

[0317] A user types, "I'm Taro Tanaka, I'm 30 years old, I'm an engineer, and I'm interested in AI and data science."

[0318] The device sends this information to the server via an HTTP request.

[0319] The server receives the information and saves the new profile in the database using an INSERT statement.

[0320] Step 2:

[0321] Conversation Design

[0322] Input: The server is the user's profile.

[0323] Processing: The server dynamically adjusts the prompts based on the user's profile. The device displays the customized prompts to the user.

[0324] Output: The customized question that is displayed to the user.

[0325] Specific behavior:

[0326] The server retrieves the user profile from the database using a SELECT statement.

[0327] The server generates a customized question: "Mr. Tanaka, what AI-related projects are you working on now?"

[0328] The terminal displays this question on the user's screen.

[0329] Step 3:

[0330] Conversations that encourage autonomy

[0331] Input: The user's specific problem or concern.

[0332] Processing: The device does not immediately answer the problem, but generates questions to help the user think of a solution. The server receives the user's answers and generates further questions or advice to dig deeper.

[0333] Output: The follow-up question that is presented to the user.

[0334] Specific behavior:

[0335] A user types, "I'm having trouble with data preprocessing for an AI project."

[0336] The device generates follow-up questions such as, "What areas are you particularly challenged by? What solutions have you considered?"

[0337] The server receives the user's answers and generates further probing questions.

[0338] Step 4:

[0339] Individual curriculum proposals

[0340] Input: The user's past answers and progress.

[0341] Processing: The server analyzes this and generates an appropriate learning curriculum and career path. The device presents the curriculum received from the server to the user.

[0342] Output: A suggested learning curriculum or career path for the user.

[0343] Specific behavior:

[0344] The server retrieves the user's past answers from the database using a SELECT statement and analyzes their progress using a machine learning model.

[0345] The server generates a suggestion: "I recommend this online course that focuses on data preprocessing."

[0346] The terminal displays this to the user.

[0347] Step 5:

[0348] Long-term support and growth

[0349] Input: Log of conversation with the user.

[0350] Processing: The server periodically analyzes the user's progress and needs using the saved logs to improve the support content. The device provides the improved content to the user.

[0351] Output: Improved support is provided to the user.

[0352] Specific behavior:

[0353] The terminal writes the contents of the conversation with the user to a log file.

[0354] The server periodically reads the logs and uses data analysis tools to evaluate progress.

[0355] A user types, "I understand the basics of data preprocessing, but now I want to learn about model tuning."

[0356] The server uses the results of log analysis to generate support content appropriate to the user's growth, such as "We recommend this resource as the next step," and the device presents this to the user.

[0357] Step 6:

[0358] Using the Emotion Engine

[0359] Input: User input data, voice, and facial expressions.

[0360] Processing: The emotion engine recognizes the user's emotions and transmits the results to the server. The server adjusts the questions and learning curriculum based on the results, and the device presents the adjustments to the user.

[0361] Output: Tailored questioning and learning curriculum.

[0362] Specific behavior:

[0363] The user types, "I'm feeling stressed out over the amount of tasks I have lately."

[0364] The emotion engine recognizes the user's stress state and notifies the server.

[0365] The server then adjusts the menu by asking, "Would you like to try some relaxation techniques?"

[0366] The terminal displays this to the user.

[0367] (Application example 2)

[0368] 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."

[0369] Conventional learning support systems have difficulty generating appropriate questions and providing learning curricula based on individual user profiles, and in particular lack a response that reflects the user's emotions, making it difficult to provide effective learning support.Furthermore, there are few systems that provide sufficient support in response to long-term growth and change, making it difficult to stimulate users' motivation to learn independently.

[0370] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0371] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum and career path based on the user's answers and progress, means for saving a conversation log with the user and providing support content according to the user's growth and changes, and means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This makes it possible to realize personalized learning support according to the characteristics and emotions of each user, and to continuously stimulate the user's motivation to learn over the long term.

[0372] "Basic information" refers to information received from a user, such as name, age, occupation, and interests.

[0373] A "profile" is data that describes the characteristics of an individual user, generated based on basic information.

[0374] "Prompts" are questions or conversation starters that are asked to users and are tailored based on their profile.

[0375] A "means for generating questions" is a method or system for creating questions that are designed to provide users with an opportunity to think independently, rather than immediately answering their problems.

[0376] A "learning curriculum" is a learning plan or course that is individually suggested based on the user's answers and progress.

[0377] A "career path" is a specific step or plan suggested based on the user's career goals and career path.

[0378] A "conversation log" is data that stores the history of conversations that take place between a user and the system.

[0379] "Support content" refers to the specific advice and assistance provided to users in response to their growth and changes.

[0380] A "means for recognizing emotions" is a method or system that analyzes emotions from user input data (text, voice, facial expressions, etc.) and obtains the results.

[0381] A "means for adjusting the content of questions" is a method or system that dynamically changes the content of questions based on the user's emotions and profile.

[0382] System Overview

[0383] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. Furthermore, the system generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also includes a function that uses an emotion engine to recognize the user's emotions and adjusts the content of the questions and learning curriculum based on the recognition results.

[0384] Collection of user information

[0385] When using the service for the first time, users enter basic information (such as name, age, occupation, and interests). The device, such as a smartphone or head-mounted display (HMD), then sends the entered information to a server, which then generates a user profile based on the information received and stores it in a database. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server, which then generates and stores a new profile.

[0386] Conversation Design

[0387] The device has pre-programmed question patterns to allow the conversation with the user to proceed naturally. The server dynamically adjusts the questions based on the user's profile. For example, based on the profile generated by the server, the device might display the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[0388] Conversations that encourage autonomy

[0389] When a user inputs a specific problem or concern, the device does not immediately answer the question, but instead generates questions to help the user think of a solution. The server receives the user's answer and generates more in-depth questions or advice. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you considered?"

[0390] Individual curriculum proposals

[0391] The server analyzes the user's past answers and progress to generate an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user. For example, if a user enters "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[0392] Long-term support and growth

[0393] The device saves a conversation log with the user, and the server periodically analyzes the user's progress and needs using the saved log. This allows the server to continue improving the support content and question patterns based on the analysis results. For example, if a user inputs, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," after several months, the server will analyze the log, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[0394] Use of emotion engine

[0395] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates relaxation advice and appropriate questions, which are presented to the user via the device. For example, if the user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[0396] Hardware and software used

[0397] Hardware: Smartphone, Head-Mounted Display (HMD)

[0398] Software: User profile management software, sentiment analysis engine, natural language processing model (GPT-4 (registered trademark), etc.)

[0399] Examples of prompt statements

[0400] Initial information-gathering prompt: "Hello, as a new user, please provide some basic information. Please tell us your name, age, occupation, and interests."

[0401] Progress prompt: "Hey, tell us about the AI ​​project you've been working on recently. What challenges do you see?"

[0402] Curriculum suggestion prompt: "It sounds like you're struggling with data preprocessing. Why not try these online courses?"

[0403] Stress management prompt: "You've been feeling stressed lately because of all the tasks. Why don't you try some activities that will help you relax a bit?"

[0404] This makes it possible to provide personalized learning support tailored to each user's individual characteristics and emotions, and to continuously stimulate users' motivation to learn over the long term.

[0405] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0406] Step 1: Collect basic user information

[0407] The server receives basic information (such as name, age, occupation, and interests) from the device when it is used for the first time. For example, if the user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a user profile based on the received information and stores it in a database. The input is the basic information the user entered into the device, and the output is the generated profile data. This profile data is used in later steps.

[0408] Step 2: Generate questions

[0409] Based on the profile data in the database, the server applies appropriate wording to question templates to generate the most suitable question for the user. For example, based on Taro Tanaka's profile, it generates the question, "Mr. Tanaka, what kind of AI-related project are you working on now?" The input is the user's profile data, and the output is a customized question. The server sends this question to the device, which then displays it to the user.

[0410] Step 3: Receiving responses from users

[0411] The device displays the question sent from the server and receives the user's answer to that question. For example, if a user enters "I'm having trouble with data preprocessing for an AI project," the device sends the answer to the server. The input is the answer entered by the user into the device, and the output is the answer data sent to the server.

[0412] Step 4: Generate questions

[0413] The server analyzes the received response data using a natural language processing model (such as GPT-4) and generates questions that do not immediately answer the user's problem but provide an opportunity for them to think. For example, the server might generate a question such as, "Which part do you feel is particularly challenging? What solutions have you considered?" The input is the user's response data, and the output is a new question to dig deeper. The server sends this question to the device, which then displays it to the user.

[0414] Step 5: Propose a learning curriculum

[0415] The server generates an appropriate learning curriculum and career path based on the user's response data and progress data. For example, if the user inputs "Data preprocessing is difficult," the server generates a curriculum that reads, "I recommend this online course that focuses on data preprocessing." The input is the user's response data and progress data, and the output is a suggested learning curriculum. The server sends this curriculum to the terminal, which then presents it to the user.

[0416] Step 6: Save the conversation log

[0417] The server stores all conversation logs with the user in a database. Conversation history and progress data with the user are recorded sequentially, and the server analyzes this data and uses it to provide support according to the user's growth and changes. The input is the conversation data with the user, and the output is the conversation log stored in the database.

[0418] Step 7: Use the Emotion Engine

[0419] The server uses an emotion analysis engine to analyze emotions from text, voice, and facial expression data entered by the user. For example, if a user enters, "I'm feeling stressed because I have too many tasks to do recently," the server uses the emotion engine to recognize the user's stress level and generates advice and appropriate questions to help them relax. The input is data related to the user's emotions, and the output is advice and questions based on those emotions. The server sends these advice and questions to the device, which then presents them to the user.

[0420] 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.

[0421] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0422] 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.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0435] 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."

[0436] MODE FOR CARRYING OUT THE INVENTION

[0437] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves a conversation log with the user, realizing long-term and flexible support that provides support content tailored to the user's growth and changes.

[0438] Program processing overview

[0439] Collection of user information

[0440] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0441] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[0442] Conversation Design

[0443] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0444] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[0445] Conversations that encourage autonomy

[0446] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0447] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[0448] Individual curriculum proposals

[0449] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0450] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[0451] Long-term support and growth

[0452] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[0453] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[0454] The above is a specific embodiment of the function of the program of the system of the present invention to collect user information, propose personalized questions and learning curricula, and provide long-term support.

[0455] The processing flow will be explained below.

[0456] Step 1:

[0457] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[0458] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[0459] Step 2:

[0460] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[0461] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[0462] Step 3:

[0463] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[0464] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[0465] Step 4:

[0466] The user enters an answer to the question, and the device sends the answer to the server.

[0467] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[0468] Step 5:

[0469] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[0470] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[0471] Step 6:

[0472] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[0473] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[0474] Step 7:

[0475] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[0476] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[0477] Step 8:

[0478] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[0479] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[0480] Step 9:

[0481] As users ask new questions or make new requests, the device continues to respond with improved content.

[0482] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[0483] The above is a description of the program processing divided into specific steps.

[0484] Example 1

[0485] 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."

[0486] In conventional systems, educational and vocational support for users was uniform, making it difficult to respond flexibly to individual needs and progress. Furthermore, there was a lack of mechanisms to provide users with opportunities to think for themselves to solve problems, which meant that users' autonomy and growth were not sufficiently promoted. The present invention aims to solve these problems.

[0487] 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.

[0488] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual educational plan or career path based on the user's answers and progress, and means for storing a record of interactions with the user and providing support content according to the user's maturity and changes. This enables flexible educational and career support tailored to the individual needs of the user. It also provides users with opportunities to think for themselves to solve problems, promoting their independence and growth.

[0489] "Basic information" refers to information entered when using the service for the first time, such as the user's name, age, occupation, and areas of interest.

[0490] A "profile" refers to data about a user's attributes and characteristics that is generated based on the user's basic information and stored in a database.

[0491] "Prompts" refer to questions or confirmations that are asked to the user and are tailored appropriately based on the user's profile.

[0492] "Educational Plan" refers to a learning strategy or curriculum that is individually provided based on the user's progress and needs.

[0493] "Career Pathways" refers to specific steps or suggestions to guide users on their career path.

[0494] "Dialogue records" refers to data that the system uses to store the content of conversations with users.

[0495] "Support content" refers to the overall assistance provided to users, such as advice, resources, and questions, as they grow and change.

[0496] MODE FOR CARRYING OUT THE INVENTION

[0497] The present invention relates to a system that receives basic information from a user, creates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual educational plans and career paths based on the user's answers and progress. Furthermore, it stores a record of interactions with the user and provides flexible support content that adapts to the user's maturity and changes.

[0498] Collection of user information

[0499] When using the device for the first time, the user enters basic information (such as name, age, occupation, and areas of interest). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0500] Example: A user enters "I'm Ichiro Yamada, 35 years old, a software developer. I'm interested in machine learning and cloud computing." The device sends this information to a server, which generates and stores a new profile.

[0501] Conversation Design

[0502] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0503] Example: Based on the profile generated by the server, the device displays the question, "Yamada, what machine learning-related projects are you working on now?"

[0504] Conversations that encourage autonomy

[0505] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0506] Example: If a user types, "I'm having trouble organizing data for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you considered?"

[0507] Individual curriculum proposals

[0508] The server analyzes the user's past answers and progress to generate an appropriate educational plan and career path, and the terminal then presents the curriculum received from the server to the user.

[0509] Example: If a user types "I'm having trouble organizing my data," the server generates a suggestion such as "I recommend this online course that focuses on data organization," and the device presents this to the user.

[0510] Long-term support and growth

[0511] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. Based on the analysis results, the server continually refines the support content and question patterns. Each time the user makes a new question or request, the device responds using the refined content.

[0512] Example: If a user enters the following message after a few months: "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as the next step," which the device will then present to the user.

[0513] These steps are achieved through collaboration between the server and the device. The server analyzes the user's profile data, dialogue records, and responses, and utilizes generative AI models and prompts to provide appropriate questions and support. Meanwhile, the device plays a role in advancing the dialogue with the user based on instructions from the server. This system enables educational and vocational support tailored to the individual needs of each user. Furthermore, by giving users the opportunity to think for themselves to solve problems, it promotes their independence and growth.

[0514] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0515] Step 1: Enter your user information

[0516] The user enters basic information (such as name, age, occupation, and areas of interest) into the device. At this point, the input information is text data such as name and age. The device sends the entered information to the server. For example, if the user enters "I'm Yamada Ichiro, 35 years old, a software developer. I'm interested in machine learning and cloud computing," the device sends this information to the server in JSON format.

[0517] Input: User's basic information (name, age, occupation, interests)

[0518] Output: JSON data of user information sent to the server

[0519] Step 2: Generate a profile

[0520] The server analyzes the received user information and generates a user profile. This profile includes information such as name, age, occupation, and areas of interest. The profile data is stored in a database. For example, the server generates and stores a profile in the following format: {"name": "Yamada Ichiro", "age": 35, "profession": "Software Developer", "interests": ["machine learning", "cloud computing"]}.

[0521] Input: JSON data of user information

[0522] Output: Generated user profile database entries

[0523] Step 3: Design the question

[0524] The device has pre-programmed question patterns. The server selects and tailors appropriate questions based on the user's profile. The server references the profile and generates customized questions such as, "What machine learning-related projects are you currently working on?" The device then displays these questions to the user.

[0525] Input: Generated user profile

[0526] Output: A customized prompt that is displayed to the user.

[0527] Step 4: User input on the problem

[0528] The user responds to the prompt by inputting a specific problem or concern. For example, the user might input, "I'm having trouble organizing data for a machine learning project." This user input is sent from the device to the server.

[0529] Input: User's problem or concern

[0530] Output: The text data of the problem sent to the server

[0531] Step 5: Conversations that encourage autonomy

[0532] The device does not immediately answer the problem entered by the user, but generates support questions to help the user think of a solution on their own. The server generates more in-depth questions and advice based on the user's answers. For example, the device generates and displays support questions such as, "Which part do you feel is particularly problematic? What solutions have you considered for it?" In response to the user's answer, "Data cleansing is difficult," the server generates a question such as, "What specific data cleansing techniques have you tried?"

[0533] Input: Text data of user problems and concerns

[0534] Output: Generate and display supplementary and probing questions

[0535] Step 6: Propose an individual curriculum

[0536] The server analyzes the user's past responses and progress to generate a personalized educational plan and career path. The device then presents the curriculum received from the server to the user. For example, if the user types, "I'm having trouble with data organization," the server generates a suggestion, such as, "I recommend this online course that focuses on data organization," and the device presents it to the user.

[0537] Input: User's past answers and progress data

[0538] Output: Creation and presentation of individualized curriculum and career pathways

[0539] Step 7: Long-term support and growth

[0540] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. The server continues to improve the support content and question patterns based on the analysis results. For example, if a user inputs after a few months, "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[0541] Input: Saved conversation log

[0542] Output: Improved support content, question patterns, and suggested content

[0543] The above are the specific processing steps of the program of this system.

[0544] (Application example 1)

[0545] 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."

[0546] A challenge facing modern educational environments is the lack of personalized learning support tailored to individual learners. In particular, it is difficult to provide dynamic curriculum and content that responds to users' interests and progress, and there is a lack of mechanisms to promote independent learning. This results in many learners being unable to learn efficiently and taking a long time to achieve their goals.

[0547] 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.

[0548] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum or career path based on the user's answers and progress, means for recommending optimal learning content based on the user's interests and learning progress information, and means for saving a conversation log with the user and providing support content according to the user's growth and changes. This makes it possible to provide individualized learning support to users and promote efficient and independent learning.

[0549] "Basic information" refers to personal information such as the user's name, age, occupation, and interests.

[0550] A "profile" is an individual collection of information generated based on a user's basic information.

[0551] "Specific questions" are questions selected based on the user's profile.

[0552] "Thinking questions" are questions that encourage users to think of solutions on their own.

[0553] A "personalized learning curriculum" is a personalized learning plan that is suggested based on the user's progress and responses.

[0554] A "career path" is a suggestion of a career path that is presented based on the user's occupation and interests.

[0555] "Interests" refers to areas or topics in which a user is particularly interested.

[0556] "Study progress information" is information relating to the progress of a user's learning activities.

[0557] The means for recommending "optimal learning content" is a method for recommending the most appropriate learning materials and content based on the user's interests and learning progress.

[0558] A "conversation log" is a record of all conversations between a user and the system.

[0559] "Support content according to growth and change" refers to appropriate assistance and advice provided according to the user's growth and progress.

[0560] Creating a user profile

[0561] When a user first uses the device, they enter basic information. The device collects basic information such as the user's name, age, occupation, and interests, and sends it to the server. The server then creates a user profile based on the received basic information and stores it in a database. This profile serves as the basis for providing questions and curriculum that are individually tailored to the user.

[0562] Specific examples

[0563] A user enters, "I'm Taro Yamada, 25 years old, a programmer, and I'm interested in machine learning and data analysis." The device sends this information to the server, which generates and saves a new profile.

[0564] Dynamic adjustment of specific questions

[0565] The server dynamically tailors specific questions to match the user's interests based on pre-programmed question patterns based on the profile, and the device displays the customized questions to the user.

[0566] Specific examples

[0567] Based on the profile generated by the server, the device displays the question, "Yamada-san, what machine learning projects have you been working on recently?"

[0568] Generate questions to encourage self-direction

[0569] When a user inputs a specific problem or concern, the server does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0570] Specific examples

[0571] If a user types, "I'm having trouble with data preprocessing for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you come up with?"

[0572] Individual curriculum proposals

[0573] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0574] Specific examples

[0575] If a user inputs "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," which the device presents to the user.

[0576] Long-term support and growth

[0577] The server stores the conversation logs and provides support content that responds to the user's growth and changes. The server periodically analyzes the stored conversation logs to confirm the user's progress and needs, and continues to improve the support content based on that.

[0578] Specific examples

[0579] If a user inputs "I understand the basics of data preprocessing, but next I want to learn about model tuning" after a few months, the server will analyze the logs and check the user's progress. It will then generate support content based on the user's progress, such as "I recommend this resource as the next step," and present it to the user on the device.

[0580] Prompt Sentence Examples

[0581] My name is Taro Yamada, I'm 25 years old and I'm a programmer. I'm interested in machine learning and data analysis. I'm currently struggling with data preprocessing for a machine learning project.

[0582] This invention is realized by an application installed on a device such as a smartphone, tablet, or PC, and a program running on the server side. User input information is exchanged with the server via communication methods such as RESTful API or WebSocket. A database management system (DBMS) is used to store data, and a generative AI model is used for natural language processing. This realizes a system that allows users to receive personalized learning support.

[0583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0584] Step 1: Enter user information

[0585] The user uses the device to input basic information such as name, age, occupation, and interests. The device then sends this information to the server. The input is received as text data, and the output is transmitted to the server via an API request.

[0586] Step 2: Generate a profile

[0587] The server generates a user profile based on the received basic information. Profile generation involves mapping the input information to fields based on templates stored in a database. The input is the basic information, and the output is the generated profile data.

[0588] Step 3: Dynamically adjust specific questions

[0589] The server then references the generated profile and selects and tailors specific questions based on the profile, using profile-based filtering and scoring algorithms to determine the most appropriate questions, with the profile data as input and the specific questions as output.

[0590] Step 4: Present the question

[0591] The terminal receives a question from the server and displays it to the user, who then enters a response. The input to this process is the question, and the output is the user's response.

[0592] Step 5: Question Generation

[0593] The server takes the user's answer and generates new questions to provide further insight. This step uses a generative AI model to dynamically create probing questions, with the user's answer as input and the new question as output.

[0594] Step 6: Propose an individual curriculum

[0595] The server analyzes the user's answers and progress and generates a personalized learning curriculum and career path. Machine learning algorithms are used here to provide a learning plan that best suits the user's needs. The input is the user's answers and progress data, and the output is the generated learning curriculum and career path.

[0596] Step 7: Recommend learning content

[0597] The server recommends optimal learning content based on the user's interests and learning progress information. In this step, a scoring model is used to select content taking into account the user's history and preferences. The input is interests and learning progress information, and the output is recommended content.

[0598] Step 8: Store and analyze logs

[0599] The server stores all conversation logs and periodically analyzes them to evaluate user growth and changes. This analysis uses natural language processing and data analysis tools. The input is conversation log data, and the output is the user's growth status and improved support content.

[0600] Step 9: Providing long-term support

[0601] The server provides personalized long-term support to the user based on the analysis results, and the terminal displays this support content to the user. The analysis results are input, and new support content is output.

[0602] 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.

[0603] MODE FOR CARRYING OUT THE INVENTION

[0604] The present invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[0605] Program processing overview

[0606] Collection of user information

[0607] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0608] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[0609] Conversation Design

[0610] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0611] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[0612] Conversations that encourage autonomy

[0613] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0614] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[0615] Individual curriculum proposals

[0616] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0617] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[0618] Long-term support and growth

[0619] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[0620] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[0621] Use of emotion engine

[0622] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on this recognition result, the server adjusts the content of the questions and the learning curriculum. If the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates advice for relaxation and appropriate questions, which are presented to the user via the device.

[0623] Example: If a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress state and notifies the server. The server then suggests "Why don't you try some methods to relax?", which the device displays to the user.

[0624] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[0625] The processing flow will be explained below.

[0626] Step 1:

[0627] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[0628] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[0629] Step 2:

[0630] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[0631] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[0632] Step 3:

[0633] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[0634] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[0635] Step 4:

[0636] The user enters an answer to the question, and the device sends the answer to the server.

[0637] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[0638] Step 5:

[0639] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[0640] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[0641] Step 6:

[0642] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[0643] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[0644] Step 7:

[0645] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[0646] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[0647] Step 8:

[0648] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[0649] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[0650] Step 9:

[0651] As users ask new questions or make new requests, the device continues to respond with improved content.

[0652] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[0653] Step 10:

[0654] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. The recognition results are sent to the server.

[0655] Specific behavior: When a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine detects the stress state and sends the result to the server.

[0656] Step 11:

[0657] The server receives the emotion recognition results from the emotion engine and adjusts the questions and learning curriculum accordingly. The device then presents the adjusted content to the user.

[0658] Specific operation: The server generates a question, "Would you like to try some ways to relax?", and the device presents this to the user.

[0659] The above is the processing flow of the system when combined with the emotion engine.

[0660] Example 2

[0661] 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."

[0662] Conventional learning support systems and career development support systems face challenges in that they are unable to flexibly respond to individual users' needs and growth, making it difficult to provide users with appropriate advice immediately. Furthermore, they lack the ability to recognize users' emotions and adjust their responses accordingly, resulting in insufficient support for users' long-term growth and psychological development. This can lead to reduced learning effectiveness and reduced career development efficiency.

[0663] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving basic information from a user and generating a user profile, a means for selecting and adjusting specific questions based on the user profile, a means for generating questions to provide an opportunity for the user to think rather than immediately answering the user's problems, a means for proposing an individual learning curriculum and career path based on the user's answers and progress, and a means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This enables flexible responses according to the individual needs of users and psychological support through emotion recognition.

[0664] "User" refers to any person or organization that uses this system.

[0665] "Basic information" refers to basic information about an individual or organization, such as the user's name, age, occupation, and interests.

[0666] A "profile" refers to a data set that indicates individual characteristics and needs, generated based on basic information about the user.

[0667] "Questions" refers to the questions and conversations asked to users.

[0668] "Not giving an immediate answer" refers to not providing an immediate answer to a user's questions or concerns.

[0669] "Providing an opportunity to think" means providing time and space for users to think about solutions and opinions on their own.

[0670] "Individual learning curriculum" refers to a learning plan customized according to the characteristics and needs of the user.

[0671] A "career path" refers to a path created to support users' professional growth and advancement.

[0672] "Conversation log" refers to a record of conversations between users.

[0673] "Emotion" refers to the user's psychological state or feelings.

[0674] "Emotion recognition" refers to identifying a user's psychological state by analyzing their input data, voice, facial expressions, etc.

[0675] "Adjusting the content of questions and learning curriculum" refers to dynamically changing the questions asked and the content of the learning plan provided based on the user's profile and emotion recognition results.

[0676] MODE FOR CARRYING OUT THE INVENTION

[0677] The present invention is a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[0678] This system mainly uses the following hardware and software:

[0679] Hardware used

[0680] Terminal: A device that receives user input, such as a PC or smartphone.

[0681] Server: A high-performance computer, such as a cloud server, that stores and processes data.

[0682] Software used

[0683] Database management system: Software such as MySQL or PostgreSQL is used.

[0684] Machine learning models: Emotion recognition and profile generation are performed using libraries such as TensorFlow and PyTorch.

[0685] The server receives basic information from the user from the device and generates a profile based on that information. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a profile based on the received information and stores it in a database.

[0686] Based on this profile, the server selects specific questions and generates appropriate questions, which the device displays to the user, asking, for example, "Mr. Tanaka, what AI-related projects are you currently working on?"

[0687] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think of a solution. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you thought of?"

[0688] Furthermore, the server can suggest personalized learning curriculums and career paths based on the user's answers and progress. It analyzes the user's past answers from the database and generates suggestions such as, "We recommend this online course that focuses on data preprocessing."

[0689] To provide long-term support, the device stores conversation logs with the user, and the server uses these logs to periodically analyze the user's growth and progress. For example, if a user inputs, "I understand the basics of data preprocessing, but next I'd like to learn about model tuning," the server analyzes the log and generates support content tailored to the user's growth, such as, "I recommend this resource as the next step," which the device then presents to the user.

[0690] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if a user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[0691] Example prompts for generative AI models

[0692] Here are some examples of prompts you might input to a generative AI model:

[0693] Example prompt:

[0694] User profile:

[0695] Name: Taro Tanaka

[0696] Age: 30

[0697] Occupation: Engineer

[0698] Interests: AI, data science

[0699] User Question:

[0700] "I'm struggling with data preprocessing for my AI project. What part do you find particularly challenging? What solutions have you come up with?"

[0701] This allows the generative AI model to generate appropriate questions and suggestions and provide them to the user.

[0702] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[0703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0704] Step 1:

[0705] Collection of user information

[0706] Input: The user enters basic information (name, age, occupation, interests, etc.) when using the service for the first time.

[0707] Processing: The device sends the entered information to the server, which then creates a user profile based on the information received and stores it in a database.

[0708] Output: The server-generated user profile.

[0709] Specific behavior:

[0710] A user types, "I'm Taro Tanaka, I'm 30 years old, I'm an engineer, and I'm interested in AI and data science."

[0711] The device sends this information to the server via an HTTP request.

[0712] The server receives the information and saves the new profile in the database using an INSERT statement.

[0713] Step 2:

[0714] Conversation Design

[0715] Input: The server is the user's profile.

[0716] Processing: The server dynamically adjusts the prompts based on the user's profile. The device displays the customized prompts to the user.

[0717] Output: The customized question that is displayed to the user.

[0718] Specific behavior:

[0719] The server retrieves the user profile from the database using a SELECT statement.

[0720] The server generates a customized question: "Mr. Tanaka, what AI-related projects are you working on now?"

[0721] The terminal displays this question on the user's screen.

[0722] Step 3:

[0723] Conversations that encourage autonomy

[0724] Input: The user's specific problem or concern.

[0725] Processing: The device does not immediately answer the problem, but generates questions to help the user think of a solution. The server receives the user's answers and generates further questions or advice to dig deeper.

[0726] Output: The follow-up question that is presented to the user.

[0727] Specific behavior:

[0728] A user types, "I'm having trouble with data preprocessing for an AI project."

[0729] The device generates follow-up questions such as, "What areas are you particularly challenged by? What solutions have you considered?"

[0730] The server receives the user's answers and generates further probing questions.

[0731] Step 4:

[0732] Individual curriculum proposals

[0733] Input: The user's past answers and progress.

[0734] Processing: The server analyzes this and generates an appropriate learning curriculum and career path. The device presents the curriculum received from the server to the user.

[0735] Output: A suggested learning curriculum or career path for the user.

[0736] Specific behavior:

[0737] The server retrieves the user's past answers from the database using a SELECT statement and analyzes their progress using a machine learning model.

[0738] The server generates a suggestion: "I recommend this online course that focuses on data preprocessing."

[0739] The terminal displays this to the user.

[0740] Step 5:

[0741] Long-term support and growth

[0742] Input: Log of conversation with the user.

[0743] Processing: The server periodically analyzes the user's progress and needs using the saved logs to improve the support content. The device provides the improved content to the user.

[0744] Output: Improved support is provided to the user.

[0745] Specific behavior:

[0746] The terminal writes the contents of the conversation with the user to a log file.

[0747] The server periodically reads the logs and uses data analysis tools to evaluate progress.

[0748] A user types, "I understand the basics of data preprocessing, but now I want to learn about model tuning."

[0749] The server uses the log analysis results to generate support content appropriate to the user's growth, such as "We recommend this resource as the next step," and the device presents this to the user.

[0750] Step 6:

[0751] Use of emotion engine

[0752] Input: User input data, voice, and facial expressions.

[0753] Processing: The emotion engine recognizes the user's emotions and transmits the results to the server. The server adjusts the questions and learning curriculum based on the results, and the device presents the adjustments to the user.

[0754] Output: Tailored questioning and learning curriculum.

[0755] Specific behavior:

[0756] The user types, "I'm feeling stressed out over the amount of tasks I have lately."

[0757] The emotion engine recognizes the user's stress state and notifies the server.

[0758] The server then adjusts the menu by asking, "Would you like to try some relaxation techniques?"

[0759] The terminal displays this to the user.

[0760] (Application example 2)

[0761] 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."

[0762] Conventional learning support systems have difficulty generating appropriate questions and providing learning curricula based on individual user profiles, and in particular lack a response that reflects the user's emotions, making it difficult to provide effective learning support.Furthermore, there are few systems that provide sufficient support in response to long-term growth and change, making it difficult to stimulate users' motivation to learn independently.

[0763] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0764] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum and career path based on the user's answers and progress, means for saving a conversation log with the user and providing support content according to the user's growth and changes, and means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This makes it possible to realize personalized learning support according to the characteristics and emotions of each user, and to continuously stimulate the user's motivation to learn over the long term.

[0765] "Basic information" refers to information received from a user, such as name, age, occupation, and interests.

[0766] A "profile" is data that describes the characteristics of an individual user, generated based on basic information.

[0767] "Prompts" are questions or conversation starters that are asked to users and are tailored based on their profile.

[0768] A "means for generating questions" is a method or system for creating questions that are designed to provide users with an opportunity to think independently, rather than immediately answering their problems.

[0769] A "learning curriculum" is a learning plan or course that is individually suggested based on the user's answers and progress.

[0770] A "career path" is a specific step or plan suggested based on the user's career goals and career path.

[0771] A "conversation log" is data that stores the history of conversations that take place between a user and the system.

[0772] "Support content" refers to the specific advice and assistance provided to users in response to their growth and changes.

[0773] A "means for recognizing emotions" is a method or system that analyzes emotions from user input data (text, voice, facial expressions, etc.) and obtains the results.

[0774] A "means for adjusting the content of questions" is a method or system that dynamically changes the content of questions based on the user's emotions and profile.

[0775] System Overview

[0776] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. Furthermore, the system generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also includes a function that uses an emotion engine to recognize the user's emotions and adjusts the content of the questions and learning curriculum based on the recognition results.

[0777] Collection of user information

[0778] When using the service for the first time, users enter basic information (such as name, age, occupation, and interests). The device, such as a smartphone or head-mounted display (HMD), then sends the entered information to a server, which then generates a user profile based on the information received and stores it in a database. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server, which then generates and stores a new profile.

[0779] Conversation Design

[0780] The device has pre-programmed question patterns to allow the conversation with the user to proceed naturally. The server dynamically adjusts the questions based on the user's profile. For example, based on the profile generated by the server, the device might display the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[0781] Conversations that encourage autonomy

[0782] When a user inputs a specific problem or concern, the device does not immediately answer the question, but instead generates questions to help the user think of a solution. The server receives the user's answer and generates more in-depth questions or advice. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you considered?"

[0783] Individual curriculum proposals

[0784] The server analyzes the user's past answers and progress to generate an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user. For example, if a user enters "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[0785] Long-term support and growth

[0786] The device saves a conversation log with the user, and the server periodically analyzes the user's progress and needs using the saved log. This allows the server to continue improving the support content and question patterns based on the analysis results. For example, if a user inputs, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," after several months, the server will analyze the log, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[0787] Use of emotion engine

[0788] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates relaxation advice and appropriate questions, which are presented to the user via the device. For example, if the user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[0789] Hardware and software used

[0790] Hardware: Smartphone, Head-Mounted Display (HMD)

[0791] Software: User profile management software, sentiment analysis engine, natural language processing model (GPT-4, etc.)

[0792] Examples of prompt statements

[0793] Initial information-gathering prompt: "Hello, as a new user, please provide some basic information. Please tell us your name, age, occupation, and interests."

[0794] Progress prompt: "Hey, tell us about the AI ​​project you've been working on recently. What challenges do you see?"

[0795] Curriculum suggestion prompt: "It sounds like you're struggling with data preprocessing. Why not try these online courses?"

[0796] Stress management prompt: "You've been feeling stressed lately because of all the tasks. Why don't you try some activities that will help you relax a bit?"

[0797] This makes it possible to provide personalized learning support tailored to each user's individual characteristics and emotions, and to continuously stimulate users' motivation to learn over the long term.

[0798] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0799] Step 1: Collect basic user information

[0800] The server receives basic information (such as name, age, occupation, and interests) from the device when it is used for the first time. For example, if the user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a user profile based on the received information and stores it in a database. The input is the basic information the user entered into the device, and the output is the generated profile data. This profile data is used in later steps.

[0801] Step 2: Generate questions

[0802] Based on the profile data in the database, the server applies appropriate wording to question templates to generate the most suitable question for the user. For example, based on Taro Tanaka's profile, it generates the question, "Mr. Tanaka, what kind of AI-related project are you working on now?" The input is the user's profile data, and the output is a customized question. The server sends this question to the device, which then displays it to the user.

[0803] Step 3: Receiving responses from users

[0804] The device displays the question sent from the server and receives the user's answer to that question. For example, if a user enters "I'm having trouble with data preprocessing for an AI project," the device sends the answer to the server. The input is the answer entered by the user into the device, and the output is the answer data sent to the server.

[0805] Step 4: Generate questions

[0806] The server analyzes the received response data using a natural language processing model (such as GPT-4) and generates questions that do not immediately answer the user's problem but provide an opportunity for them to think. For example, the server might generate a question such as, "Which part do you feel is particularly challenging? What solutions have you considered?" The input is the user's response data, and the output is a new question to dig deeper. The server sends this question to the device, which then displays it to the user.

[0807] Step 5: Propose a learning curriculum

[0808] The server generates an appropriate learning curriculum and career path based on the user's response data and progress data. For example, if the user inputs "Data preprocessing is difficult," the server generates a curriculum that reads, "I recommend this online course that focuses on data preprocessing." The input is the user's response data and progress data, and the output is a suggested learning curriculum. The server sends this curriculum to the terminal, which then presents it to the user.

[0809] Step 6: Save the conversation log

[0810] The server stores all conversation logs with the user in a database. Conversation history and progress data with the user are recorded sequentially, and the server analyzes this data and uses it to provide support according to the user's growth and changes. The input is the conversation data with the user, and the output is the conversation log stored in the database.

[0811] Step 7: Use the Emotion Engine

[0812] The server uses an emotion analysis engine to analyze emotions from text, voice, and facial expression data entered by the user. For example, if a user enters, "I'm feeling stressed because I have too many tasks to do recently," the server uses the emotion engine to recognize the user's stress level and generates advice and appropriate questions to help them relax. The input is data related to the user's emotions, and the output is advice and questions based on those emotions. The server sends these advice and questions to the device, which then presents them to the user.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] [Third embodiment]

[0817] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0818] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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."

[0829] MODE FOR CARRYING OUT THE INVENTION

[0830] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves a conversation log with the user, realizing long-term and flexible support that provides support content tailored to the user's growth and changes.

[0831] Program processing overview

[0832] Collection of user information

[0833] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0834] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[0835] Conversation Design

[0836] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0837] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[0838] Conversations that encourage autonomy

[0839] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0840] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[0841] Individual curriculum proposals

[0842] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0843] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[0844] Long-term support and growth

[0845] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[0846] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[0847] The above is a specific embodiment of the function of the program of the system of the present invention to collect user information, propose personalized questions and learning curricula, and provide long-term support.

[0848] The processing flow will be explained below.

[0849] Step 1:

[0850] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[0851] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[0852] Step 2:

[0853] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[0854] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[0855] Step 3:

[0856] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[0857] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[0858] Step 4:

[0859] The user enters an answer to the question, and the device sends the answer to the server.

[0860] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[0861] Step 5:

[0862] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[0863] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[0864] Step 6:

[0865] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[0866] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[0867] Step 7:

[0868] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[0869] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[0870] Step 8:

[0871] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[0872] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[0873] Step 9:

[0874] As users ask new questions or make new requests, the device continues to respond with improved content.

[0875] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[0876] The above is a description of the program processing divided into specific steps.

[0877] Example 1

[0878] 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."

[0879] In conventional systems, educational and vocational support for users was uniform, making it difficult to respond flexibly to individual needs and progress. Furthermore, there was a lack of mechanisms to provide users with opportunities to think for themselves to solve problems, which meant that users' autonomy and growth were not sufficiently promoted. The present invention aims to solve these problems.

[0880] 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.

[0881] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual educational plan or career path based on the user's answers and progress, and means for storing a record of interactions with the user and providing support content according to the user's maturity and changes. This enables flexible educational and career support tailored to the individual needs of the user. It also provides users with opportunities to think for themselves to solve problems, promoting their independence and growth.

[0882] "Basic information" refers to information entered when using the service for the first time, such as the user's name, age, occupation, and areas of interest.

[0883] A "profile" refers to data about a user's attributes and characteristics that is generated based on the user's basic information and stored in a database.

[0884] "Prompts" refer to questions or confirmations that are asked to the user and are tailored appropriately based on the user's profile.

[0885] "Educational Plan" refers to a learning strategy or curriculum that is individually provided based on the user's progress and needs.

[0886] "Career Pathways" refers to specific steps or suggestions to guide users on their career path.

[0887] "Dialogue records" refers to data that the system uses to store the content of conversations with users.

[0888] "Support content" refers to the overall assistance provided to users, such as advice, resources, and questions, as they grow and change.

[0889] MODE FOR CARRYING OUT THE INVENTION

[0890] The present invention relates to a system that receives basic information from a user, creates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual educational plans and career paths based on the user's answers and progress. Furthermore, it stores a record of interactions with the user and provides flexible support content that adapts to the user's maturity and changes.

[0891] Collection of user information

[0892] When using the device for the first time, the user enters basic information (such as name, age, occupation, and areas of interest). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[0893] Example: A user enters "I'm Ichiro Yamada, 35 years old, a software developer. I'm interested in machine learning and cloud computing." The device sends this information to a server, which generates and stores a new profile.

[0894] Conversation Design

[0895] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[0896] Example: Based on the profile generated by the server, the device displays the question, "Yamada, what machine learning-related projects are you working on now?"

[0897] Conversations that encourage autonomy

[0898] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0899] Example: If a user types, "I'm having trouble organizing data for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you considered?"

[0900] Individual curriculum proposals

[0901] The server analyzes the user's past answers and progress to generate an appropriate educational plan and career path, and the terminal then presents the curriculum received from the server to the user.

[0902] Example: If a user types "I'm having trouble organizing my data," the server generates a suggestion such as "I recommend this online course that focuses on data organization," and the device presents this to the user.

[0903] Long-term support and growth

[0904] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. Based on the analysis results, the server continually refines the support content and question patterns. Each time the user makes a new question or request, the device responds using the refined content.

[0905] Example: If a user enters the following message after a few months: "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as the next step," which the device will then present to the user.

[0906] These steps are achieved through collaboration between the server and the device. The server analyzes the user's profile data, dialogue records, and responses, and utilizes generative AI models and prompts to provide appropriate questions and support. Meanwhile, the device plays a role in advancing the dialogue with the user based on instructions from the server. This system enables educational and vocational support tailored to the individual needs of each user. Furthermore, by giving users the opportunity to think for themselves to solve problems, it promotes their independence and growth.

[0907] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0908] Step 1: Enter your user information

[0909] The user enters basic information (such as name, age, occupation, and areas of interest) into the device. At this point, the input information is text data such as name and age. The device sends the entered information to the server. For example, if the user enters "I'm Yamada Ichiro, 35 years old, a software developer. I'm interested in machine learning and cloud computing," the device sends this information to the server in JSON format.

[0910] Input: User's basic information (name, age, occupation, interests)

[0911] Output: JSON data of user information sent to the server

[0912] Step 2: Generate a profile

[0913] The server analyzes the received user information and generates a user profile. This profile includes information such as name, age, occupation, and areas of interest. The profile data is stored in a database. For example, the server generates and stores a profile in the following format: {"name": "Yamada Ichiro", "age": 35, "profession": "Software Developer", "interests": ["machine learning", "cloud computing"]}.

[0914] Input: JSON data of user information

[0915] Output: Generated user profile database entries

[0916] Step 3: Design the question

[0917] The device has pre-programmed question patterns. The server selects and tailors appropriate questions based on the user's profile. The server references the profile and generates customized questions such as, "What machine learning-related projects are you currently working on?" The device then displays these questions to the user.

[0918] Input: Generated user profile

[0919] Output: A customized prompt that is displayed to the user.

[0920] Step 4: User input on the problem

[0921] The user responds to the prompt by inputting a specific problem or concern. For example, the user might input, "I'm having trouble organizing data for a machine learning project." This user input is sent from the device to the server.

[0922] Input: User's problem or concern

[0923] Output: The text data of the problem sent to the server

[0924] Step 5: Conversations that encourage autonomy

[0925] The device does not immediately answer the problem entered by the user, but generates support questions to help the user think of a solution on their own. The server generates more in-depth questions and advice based on the user's answers. For example, the device generates and displays support questions such as, "Which part do you feel is particularly problematic? What solutions have you considered for it?" In response to the user's answer, "Data cleansing is difficult," the server generates a question such as, "What specific data cleansing techniques have you tried?"

[0926] Input: Text data of user problems and concerns

[0927] Output: Generate and display supplementary and probing questions

[0928] Step 6: Propose an individual curriculum

[0929] The server analyzes the user's past responses and progress to generate a personalized educational plan and career path. The device then presents the curriculum received from the server to the user. For example, if the user types, "I'm having trouble with data organization," the server generates a suggestion, such as, "I recommend this online course that focuses on data organization," and the device presents it to the user.

[0930] Input: User's past answers and progress data

[0931] Output: Creation and presentation of individualized curriculum and career pathways

[0932] Step 7: Long-term support and growth

[0933] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. The server continues to improve the support content and question patterns based on the analysis results. For example, if a user inputs after a few months, "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[0934] Input: Saved conversation log

[0935] Output: Improved support content, question patterns, and suggested content

[0936] The above are the specific processing steps of the program of this system.

[0937] (Application example 1)

[0938] 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."

[0939] A challenge facing modern educational environments is the lack of personalized learning support tailored to individual learners. In particular, it is difficult to provide dynamic curriculum and content that responds to users' interests and progress, and there is a lack of mechanisms to promote independent learning. This results in many learners being unable to learn efficiently and taking a long time to achieve their goals.

[0940] 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.

[0941] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum or career path based on the user's answers and progress, means for recommending optimal learning content based on the user's interests and learning progress information, and means for saving a conversation log with the user and providing support content according to the user's growth and changes. This makes it possible to provide individualized learning support to users and promote efficient and independent learning.

[0942] "Basic information" refers to personal information such as the user's name, age, occupation, and interests.

[0943] A "profile" is an individual collection of information generated based on a user's basic information.

[0944] "Specific questions" are questions selected based on the user's profile.

[0945] "Thinking questions" are questions that encourage users to think of solutions on their own.

[0946] A "personalized learning curriculum" is a personalized learning plan that is suggested based on the user's progress and responses.

[0947] A "career path" is a suggestion of a career path that is presented based on the user's occupation and interests.

[0948] "Interests" refers to areas or topics in which a user is particularly interested.

[0949] "Study progress information" is information relating to the progress of a user's learning activities.

[0950] The means for recommending "optimal learning content" is a method for recommending the most appropriate learning materials and content based on the user's interests and learning progress.

[0951] A "conversation log" is a record of all conversations between a user and the system.

[0952] "Support content according to growth and change" refers to appropriate assistance and advice provided according to the user's growth and progress.

[0953] Creating a user profile

[0954] When a user first uses the device, they enter basic information. The device collects basic information such as the user's name, age, occupation, and interests, and sends it to the server. The server then creates a user profile based on the received basic information and stores it in a database. This profile serves as the basis for providing questions and curriculum that are individually tailored to the user.

[0955] Specific examples

[0956] A user enters, "I'm Taro Yamada, 25 years old, a programmer, and I'm interested in machine learning and data analysis." The device sends this information to the server, which generates and saves a new profile.

[0957] Dynamic adjustment of specific questions

[0958] The server dynamically tailors specific questions to match the user's interests based on pre-programmed question patterns based on the profile, and the device displays the customized questions to the user.

[0959] Specific examples

[0960] Based on the profile generated by the server, the device displays the question, "Yamada-san, what machine learning projects have you been working on recently?"

[0961] Generate questions to encourage self-direction

[0962] When a user inputs a specific problem or concern, the server does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[0963] Specific examples

[0964] If a user types, "I'm having trouble with data preprocessing for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you come up with?"

[0965] Individual curriculum proposals

[0966] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[0967] Specific examples

[0968] If a user inputs "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," which the device presents to the user.

[0969] Long-term support and growth

[0970] The server stores the conversation logs and provides support content that responds to the user's growth and changes. The server periodically analyzes the stored conversation logs to confirm the user's progress and needs, and continues to improve the support content based on that.

[0971] Specific examples

[0972] If a user inputs "I understand the basics of data preprocessing, but next I want to learn about model tuning" after a few months, the server will analyze the logs and check the user's progress. It will then generate support content based on the user's progress, such as "I recommend this resource as the next step," and present it to the user on the device.

[0973] Prompt Sentence Examples

[0974] My name is Taro Yamada, I'm 25 years old and I'm a programmer. I'm interested in machine learning and data analysis. I'm currently struggling with data preprocessing for a machine learning project.

[0975] This invention is realized by an application installed on a device such as a smartphone, tablet, or PC, and a program running on the server side. User input information is exchanged with the server via communication methods such as RESTful API or WebSocket. A database management system (DBMS) is used to store data, and a generative AI model is used for natural language processing. This realizes a system that allows users to receive personalized learning support.

[0976] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0977] Step 1: Enter user information

[0978] The user uses the device to input basic information such as name, age, occupation, and interests. The device then sends this information to the server. The input is received as text data, and the output is transmitted to the server via an API request.

[0979] Step 2: Generate a profile

[0980] The server generates a user profile based on the received basic information. Profile generation involves mapping the input information to fields based on templates stored in a database. The input is the basic information, and the output is the generated profile data.

[0981] Step 3: Dynamically adjust specific questions

[0982] The server then references the generated profile and selects and tailors specific questions based on the profile, using profile-based filtering and scoring algorithms to determine the most appropriate questions, with the profile data as input and the specific questions as output.

[0983] Step 4: Present the question

[0984] The terminal receives a question from the server and displays it to the user, who then enters a response. The input to this process is the question, and the output is the user's response.

[0985] Step 5: Question Generation

[0986] The server takes the user's answer and generates new questions to provide further insight. This step uses a generative AI model to dynamically create probing questions, with the user's answer as input and the new question as output.

[0987] Step 6: Propose an individual curriculum

[0988] The server analyzes the user's answers and progress and generates a personalized learning curriculum and career path. Machine learning algorithms are used here to provide a learning plan that best suits the user's needs. The input is the user's answers and progress data, and the output is the generated learning curriculum and career path.

[0989] Step 7: Recommend learning content

[0990] The server recommends optimal learning content based on the user's interests and learning progress information. In this step, a scoring model is used to select content taking into account the user's history and preferences. The input is interests and learning progress information, and the output is recommended content.

[0991] Step 8: Store and analyze logs

[0992] The server stores all conversation logs and periodically analyzes them to evaluate user growth and changes. This analysis uses natural language processing and data analysis tools. The input is conversation log data, and the output is the user's growth status and improved support content.

[0993] Step 9: Providing long-term support

[0994] The server provides personalized long-term support to the user based on the analysis results, and the terminal displays this support content to the user. The analysis results are input, and new support content is output.

[0995] 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.

[0996] MODE FOR CARRYING OUT THE INVENTION

[0997] The present invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[0998] Program processing overview

[0999] Collection of user information

[1000] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[1001] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[1002] Conversation Design

[1003] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[1004] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[1005] Conversations that encourage autonomy

[1006] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[1007] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[1008] Individual curriculum proposals

[1009] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[1010] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[1011] Long-term support and growth

[1012] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[1013] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[1014] Use of emotion engine

[1015] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on this recognition result, the server adjusts the content of the questions and the learning curriculum. If the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates advice for relaxation and appropriate questions, which are presented to the user via the device.

[1016] Example: If a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress state and notifies the server. The server then suggests "Why don't you try some methods to relax?", which the device displays to the user.

[1017] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[1018] The processing flow will be explained below.

[1019] Step 1:

[1020] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[1021] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[1022] Step 2:

[1023] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[1024] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[1025] Step 3:

[1026] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[1027] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[1028] Step 4:

[1029] The user enters an answer to the question, and the device sends the answer to the server.

[1030] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[1031] Step 5:

[1032] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[1033] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[1034] Step 6:

[1035] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[1036] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[1037] Step 7:

[1038] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[1039] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[1040] Step 8:

[1041] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[1042] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[1043] Step 9:

[1044] As users ask new questions or make new requests, the device continues to respond with improved content.

[1045] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[1046] Step 10:

[1047] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. The recognition results are sent to the server.

[1048] Specific behavior: When a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine detects the stress state and sends the result to the server.

[1049] Step 11:

[1050] The server receives the emotion recognition results from the emotion engine and adjusts the questions and learning curriculum accordingly. The device then presents the adjusted content to the user.

[1051] Specific operation: The server generates a question, "Would you like to try some ways to relax?", and the device presents this to the user.

[1052] The above is the processing flow of the system when combined with the emotion engine.

[1053] Example 2

[1054] 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."

[1055] Conventional learning support systems and career development support systems face challenges in that they are unable to flexibly respond to individual users' needs and growth, making it difficult to provide users with appropriate advice immediately. Furthermore, they lack the ability to recognize users' emotions and adjust their responses accordingly, resulting in insufficient support for users' long-term growth and psychological development. This can lead to reduced learning effectiveness and reduced career development efficiency.

[1056] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving basic information from a user and generating a user profile, a means for selecting and adjusting specific questions based on the user profile, a means for generating questions to provide an opportunity for the user to think rather than immediately answering the user's problems, a means for proposing an individual learning curriculum and career path based on the user's answers and progress, and a means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This enables flexible responses according to the individual needs of users and psychological support through emotion recognition.

[1057] "User" refers to any person or organization that uses this system.

[1058] "Basic information" refers to basic information about an individual or organization, such as the user's name, age, occupation, and interests.

[1059] A "profile" refers to a data set that indicates individual characteristics and needs, generated based on basic information about the user.

[1060] "Questions" refers to the questions and conversations asked to users.

[1061] "Not giving an immediate answer" refers to not providing an immediate answer to a user's questions or concerns.

[1062] "Providing an opportunity to think" means providing time and space for users to think about solutions and opinions on their own.

[1063] "Individual learning curriculum" refers to a learning plan customized according to the characteristics and needs of the user.

[1064] A "career path" refers to a path created to support users' professional growth and advancement.

[1065] "Conversation log" refers to a record of conversations between users.

[1066] "Emotion" refers to the user's psychological state or feelings.

[1067] "Emotion recognition" refers to identifying a user's psychological state by analyzing their input data, voice, facial expressions, etc.

[1068] "Adjusting the content of questions and learning curriculum" refers to dynamically changing the questions asked and the content of the learning plan provided based on the user's profile and emotion recognition results.

[1069] MODE FOR CARRYING OUT THE INVENTION

[1070] The present invention is a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[1071] This system mainly uses the following hardware and software:

[1072] Hardware used

[1073] Terminal: A device that receives user input, such as a PC or smartphone.

[1074] Server: A high-performance computer, such as a cloud server, that stores and processes data.

[1075] Software used

[1076] Database management system: Software such as MySQL or PostgreSQL is used.

[1077] Machine learning models: Emotion recognition and profile generation are performed using libraries such as TensorFlow and PyTorch.

[1078] The server receives basic information from the user from the device and generates a profile based on that information. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a profile based on the received information and stores it in a database.

[1079] Based on this profile, the server selects specific questions and generates appropriate questions, which the device displays to the user, asking, for example, "Mr. Tanaka, what AI-related projects are you currently working on?"

[1080] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think of a solution. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you thought of?"

[1081] Furthermore, the server can suggest personalized learning curriculums and career paths based on the user's answers and progress. It analyzes the user's past answers from the database and generates suggestions such as, "We recommend this online course that focuses on data preprocessing."

[1082] To provide long-term support, the device stores conversation logs with the user, and the server uses these logs to periodically analyze the user's growth and progress. For example, if a user inputs, "I understand the basics of data preprocessing, but next I'd like to learn about model tuning," the server analyzes the log and generates support content tailored to the user's growth, such as, "I recommend this resource as the next step," which the device then presents to the user.

[1083] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if a user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[1084] Example prompts for generative AI models

[1085] Here are some examples of prompts you might input to a generative AI model:

[1086] Example prompt:

[1087] User profile:

[1088] Name: Taro Tanaka

[1089] Age: 30

[1090] Occupation: Engineer

[1091] Interests: AI, data science

[1092] User Question:

[1093] "I'm struggling with data preprocessing for my AI project. What part do you find particularly challenging? What solutions have you come up with?"

[1094] This allows the generative AI model to generate appropriate questions and suggestions and provide them to the user.

[1095] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[1096] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1097] Step 1:

[1098] Collection of user information

[1099] Input: The user enters basic information (name, age, occupation, interests, etc.) when using the service for the first time.

[1100] Processing: The device sends the entered information to the server, which then creates a user profile based on the information received and stores it in a database.

[1101] Output: The server-generated user profile.

[1102] Specific behavior:

[1103] A user types, "I'm Taro Tanaka, I'm 30 years old, I'm an engineer, and I'm interested in AI and data science."

[1104] The device sends this information to the server via an HTTP request.

[1105] The server receives the information and saves the new profile in the database using an INSERT statement.

[1106] Step 2:

[1107] Conversation Design

[1108] Input: The server is the user's profile.

[1109] Processing: The server dynamically adjusts the prompts based on the user's profile. The device displays the customized prompts to the user.

[1110] Output: The customized question that is displayed to the user.

[1111] Specific behavior:

[1112] The server retrieves the user profile from the database using a SELECT statement.

[1113] The server generates a customized question: "Mr. Tanaka, what AI-related projects are you working on now?"

[1114] The terminal displays this question on the user's screen.

[1115] Step 3:

[1116] Conversations that encourage autonomy

[1117] Input: The user's specific problem or concern.

[1118] Processing: The device does not immediately answer the problem, but generates questions to help the user think of a solution. The server receives the user's answers and generates further questions or advice to dig deeper.

[1119] Output: The follow-up question that is presented to the user.

[1120] Specific behavior:

[1121] A user types, "I'm having trouble with data preprocessing for an AI project."

[1122] The device generates follow-up questions such as, "What areas are you particularly challenged by? What solutions have you considered?"

[1123] The server receives the user's answers and generates further probing questions.

[1124] Step 4:

[1125] Individual curriculum proposals

[1126] Input: The user's past answers and progress.

[1127] Processing: The server analyzes this and generates an appropriate learning curriculum and career path. The device presents the curriculum received from the server to the user.

[1128] Output: A suggested learning curriculum or career path for the user.

[1129] Specific behavior:

[1130] The server retrieves the user's past answers from the database using a SELECT statement and analyzes their progress using a machine learning model.

[1131] The server generates a suggestion: "I recommend this online course that focuses on data preprocessing."

[1132] The terminal displays this to the user.

[1133] Step 5:

[1134] Long-term support and growth

[1135] Input: Log of conversation with the user.

[1136] Processing: The server periodically analyzes the user's progress and needs using the saved logs to improve the support content. The device provides the improved content to the user.

[1137] Output: Improved support is provided to the user.

[1138] Specific behavior:

[1139] The terminal writes the contents of the conversation with the user to a log file.

[1140] The server periodically reads the logs and uses data analysis tools to evaluate progress.

[1141] A user types, "I understand the basics of data preprocessing, but now I want to learn about model tuning."

[1142] The server uses the log analysis results to generate support content appropriate to the user's growth, such as "We recommend this resource as the next step," and the device presents this to the user.

[1143] Step 6:

[1144] Use of emotion engine

[1145] Input: User input data, voice, and facial expressions.

[1146] Processing: The emotion engine recognizes the user's emotions and transmits the results to the server. The server adjusts the questions and learning curriculum based on the results, and the device presents the adjustments to the user.

[1147] Output: Tailored questioning and learning curriculum.

[1148] Specific behavior:

[1149] The user types, "I'm feeling stressed out over the amount of tasks I have lately."

[1150] The emotion engine recognizes the user's stress state and notifies the server.

[1151] The server then adjusts the menu by asking, "Would you like to try some relaxation techniques?"

[1152] The terminal displays this to the user.

[1153] (Application example 2)

[1154] 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."

[1155] Conventional learning support systems have difficulty generating appropriate questions and providing learning curricula based on individual user profiles, and in particular lack a response that reflects the user's emotions, making it difficult to provide effective learning support.Furthermore, there are few systems that provide sufficient support in response to long-term growth and change, making it difficult to stimulate users' motivation to learn independently.

[1156] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1157] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum and career path based on the user's answers and progress, means for saving a conversation log with the user and providing support content according to the user's growth and changes, and means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This makes it possible to realize personalized learning support according to the characteristics and emotions of each user, and to continuously stimulate the user's motivation to learn over the long term.

[1158] "Basic information" refers to information received from a user, such as name, age, occupation, and interests.

[1159] A "profile" is data that describes the characteristics of an individual user, generated based on basic information.

[1160] "Prompts" are questions or conversation starters that are asked to users and are tailored based on their profile.

[1161] A "means for generating questions" is a method or system for creating questions that are designed to provide users with an opportunity to think independently, rather than immediately answering their problems.

[1162] A "learning curriculum" is a learning plan or course that is individually suggested based on the user's answers and progress.

[1163] A "career path" is a specific step or plan suggested based on the user's career goals and career path.

[1164] A "conversation log" is data that stores the history of conversations that take place between a user and the system.

[1165] "Support content" refers to the specific advice and assistance provided to users in response to their growth and changes.

[1166] A "means for recognizing emotions" is a method or system that analyzes emotions from user input data (text, voice, facial expressions, etc.) and obtains the results.

[1167] A "means for adjusting the content of questions" is a method or system that dynamically changes the content of questions based on the user's emotions and profile.

[1168] System Overview

[1169] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. Furthermore, the system generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also includes a function that uses an emotion engine to recognize the user's emotions and adjusts the content of the questions and learning curriculum based on the recognition results.

[1170] Collection of user information

[1171] When using the service for the first time, users enter basic information (such as name, age, occupation, and interests). The device, such as a smartphone or head-mounted display (HMD), then sends the entered information to a server, which then generates a user profile based on the information received and stores it in a database. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server, which then generates and stores a new profile.

[1172] Conversation Design

[1173] The device has pre-programmed question patterns to allow the conversation with the user to proceed naturally. The server dynamically adjusts the questions based on the user's profile. For example, based on the profile generated by the server, the device might display the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[1174] Conversations that encourage autonomy

[1175] When a user inputs a specific problem or concern, the device does not immediately answer the question, but instead generates questions to help the user think of a solution. The server receives the user's answer and generates more in-depth questions or advice. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you considered?"

[1176] Individual curriculum proposals

[1177] The server analyzes the user's past answers and progress to generate an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user. For example, if a user enters "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[1178] Long-term support and growth

[1179] The device saves a conversation log with the user, and the server periodically analyzes the user's progress and needs using the saved log. This allows the server to continue improving the support content and question patterns based on the analysis results. For example, if a user inputs, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," after several months, the server will analyze the log, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[1180] Use of emotion engine

[1181] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates relaxation advice and appropriate questions, which are presented to the user via the device. For example, if the user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[1182] Hardware and software used

[1183] Hardware: Smartphone, Head-Mounted Display (HMD)

[1184] Software: User profile management software, sentiment analysis engine, natural language processing model (GPT-4, etc.)

[1185] Examples of prompt statements

[1186] Initial information-gathering prompt: "Hello, as a new user, please provide some basic information. Please tell us your name, age, occupation, and interests."

[1187] Progress prompt: "Hey, tell us about the AI ​​project you've been working on recently. What challenges do you see?"

[1188] Curriculum suggestion prompt: "It sounds like you're struggling with data preprocessing. Why not try these online courses?"

[1189] Stress management prompt: "You've been feeling stressed lately because of all the tasks. Why don't you try some activities that will help you relax a bit?"

[1190] This makes it possible to provide personalized learning support tailored to each user's individual characteristics and emotions, and to continuously stimulate users' motivation to learn over the long term.

[1191] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1192] Step 1: Collect basic user information

[1193] The server receives basic information (such as name, age, occupation, and interests) from the device when it is used for the first time. For example, if the user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a user profile based on the received information and stores it in a database. The input is the basic information the user entered into the device, and the output is the generated profile data. This profile data is used in later steps.

[1194] Step 2: Generate questions

[1195] Based on the profile data in the database, the server applies appropriate wording to question templates to generate the most suitable question for the user. For example, based on Taro Tanaka's profile, it generates the question, "Mr. Tanaka, what kind of AI-related project are you working on now?" The input is the user's profile data, and the output is a customized question. The server sends this question to the device, which then displays it to the user.

[1196] Step 3: Receiving responses from users

[1197] The device displays the question sent from the server and receives the user's answer to that question. For example, if a user enters "I'm having trouble with data preprocessing for an AI project," the device sends the answer to the server. The input is the answer entered by the user into the device, and the output is the answer data sent to the server.

[1198] Step 4: Generate questions

[1199] The server analyzes the received response data using a natural language processing model (such as GPT-4) and generates questions that do not immediately answer the user's problem but provide an opportunity for them to think. For example, the server might generate a question such as, "Which part do you feel is particularly challenging? What solutions have you considered?" The input is the user's response data, and the output is a new question to dig deeper. The server sends this question to the device, which then displays it to the user.

[1200] Step 5: Propose a learning curriculum

[1201] The server generates an appropriate learning curriculum and career path based on the user's response data and progress data. For example, if the user inputs "Data preprocessing is difficult," the server generates a curriculum that reads, "I recommend this online course that focuses on data preprocessing." The input is the user's response data and progress data, and the output is a suggested learning curriculum. The server sends this curriculum to the terminal, which then presents it to the user.

[1202] Step 6: Save the conversation log

[1203] The server stores all conversation logs with the user in a database. Conversation history and progress data with the user are recorded sequentially, and the server analyzes this data and uses it to provide support according to the user's growth and changes. The input is the conversation data with the user, and the output is the conversation log stored in the database.

[1204] Step 7: Use the Emotion Engine

[1205] The server uses an emotion analysis engine to analyze emotions from text, voice, and facial expression data entered by the user. For example, if a user enters, "I'm feeling stressed because I have too many tasks to do recently," the server uses the emotion engine to recognize the user's stress level and generates advice and appropriate questions to help them relax. The input is data related to the user's emotions, and the output is advice and questions based on those emotions. The server sends these advice and questions to the device, which then presents them to the user.

[1206] 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.

[1207] 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.

[1208] 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.

[1209] [Fourth embodiment]

[1210] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1211] 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.

[1212] 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).

[1213] 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.

[1214] 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.

[1215] 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).

[1216] 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.

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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."

[1223] MODE FOR CARRYING OUT THE INVENTION

[1224] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves a conversation log with the user, realizing long-term and flexible support that provides support content tailored to the user's growth and changes.

[1225] Program processing overview

[1226] Collection of user information

[1227] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[1228] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[1229] Conversation Design

[1230] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[1231] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[1232] Conversations that encourage autonomy

[1233] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[1234] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[1235] Individual curriculum proposals

[1236] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[1237] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[1238] Long-term support and growth

[1239] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[1240] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[1241] The above is a specific embodiment of the function of the program of the system of the present invention to collect user information, propose personalized questions and learning curricula, and provide long-term support.

[1242] The processing flow will be explained below.

[1243] Step 1:

[1244] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[1245] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[1246] Step 2:

[1247] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[1248] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[1249] Step 3:

[1250] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[1251] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[1252] Step 4:

[1253] The user enters an answer to the question, and the device sends the answer to the server.

[1254] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[1255] Step 5:

[1256] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[1257] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[1258] Step 6:

[1259] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[1260] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[1261] Step 7:

[1262] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[1263] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[1264] Step 8:

[1265] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[1266] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[1267] Step 9:

[1268] As users ask new questions or make new requests, the device continues to respond with improved content.

[1269] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[1270] The above is a description of the program processing divided into specific steps.

[1271] Example 1

[1272] 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."

[1273] In conventional systems, educational and vocational support for users was uniform, making it difficult to respond flexibly to individual needs and progress. Furthermore, there was a lack of mechanisms to provide users with opportunities to think for themselves to solve problems, which meant that users' autonomy and growth were not sufficiently promoted. The present invention aims to solve these problems.

[1274] 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.

[1275] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual educational plan or career path based on the user's answers and progress, and means for storing a record of interactions with the user and providing support content according to the user's maturity and changes. This enables flexible educational and career support tailored to the individual needs of the user. It also provides users with opportunities to think for themselves to solve problems, promoting their independence and growth.

[1276] "Basic information" refers to information entered when using the service for the first time, such as the user's name, age, occupation, and areas of interest.

[1277] A "profile" refers to data about a user's attributes and characteristics that is generated based on the user's basic information and stored in a database.

[1278] "Prompts" refer to questions or confirmations that are asked to the user and are tailored appropriately based on the user's profile.

[1279] "Educational Plan" refers to a learning strategy or curriculum that is individually provided based on the user's progress and needs.

[1280] "Career Pathways" refers to specific steps or suggestions to guide users on their career path.

[1281] "Dialogue records" refers to data that the system uses to store the content of conversations with users.

[1282] "Support content" refers to the overall assistance provided to users, such as advice, resources, and questions, as they grow and change.

[1283] MODE FOR CARRYING OUT THE INVENTION

[1284] The present invention relates to a system that receives basic information from a user, creates a profile, and selects and adjusts specific questions based on the profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual educational plans and career paths based on the user's answers and progress. Furthermore, it stores a record of interactions with the user and provides flexible support content that adapts to the user's maturity and changes.

[1285] Collection of user information

[1286] When using the device for the first time, the user enters basic information (such as name, age, occupation, and areas of interest). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[1287] Example: A user enters "I'm Ichiro Yamada, 35 years old, a software developer. I'm interested in machine learning and cloud computing." The device sends this information to a server, which generates and stores a new profile.

[1288] Conversation Design

[1289] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[1290] Example: Based on the profile generated by the server, the device displays the question, "Yamada, what machine learning-related projects are you working on now?"

[1291] Conversations that encourage autonomy

[1292] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[1293] Example: If a user types, "I'm having trouble organizing data for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you considered?"

[1294] Individual curriculum proposals

[1295] The server analyzes the user's past answers and progress to generate an appropriate educational plan and career path, and the terminal then presents the curriculum received from the server to the user.

[1296] Example: If a user types "I'm having trouble organizing my data," the server generates a suggestion such as "I recommend this online course that focuses on data organization," and the device presents this to the user.

[1297] Long-term support and growth

[1298] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. Based on the analysis results, the server continually refines the support content and question patterns. Each time the user makes a new question or request, the device responds using the refined content.

[1299] Example: If a user enters the following message after a few months: "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as the next step," which the device will then present to the user.

[1300] These steps are achieved through collaboration between the server and the device. The server analyzes the user's profile data, dialogue records, and responses, and utilizes generative AI models and prompts to provide appropriate questions and support. Meanwhile, the device plays a role in advancing the dialogue with the user based on instructions from the server. This system enables educational and vocational support tailored to the individual needs of each user. Furthermore, by giving users the opportunity to think for themselves to solve problems, it promotes their independence and growth.

[1301] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1302] Step 1: Enter your user information

[1303] The user enters basic information (such as name, age, occupation, and areas of interest) into the device. At this point, the input information is text data such as name and age. The device sends the entered information to the server. For example, if the user enters "I'm Yamada Ichiro, 35 years old, a software developer. I'm interested in machine learning and cloud computing," the device sends this information to the server in JSON format.

[1304] Input: User's basic information (name, age, occupation, interests)

[1305] Output: JSON data of user information sent to the server

[1306] Step 2: Generate a profile

[1307] The server analyzes the received user information and generates a user profile. This profile includes information such as name, age, occupation, and areas of interest. The profile data is stored in a database. For example, the server generates and stores a profile in the following format: {"name": "Yamada Ichiro", "age": 35, "profession": "Software Developer", "interests": ["machine learning", "cloud computing"]}.

[1308] Input: JSON data of user information

[1309] Output: Generated user profile database entries

[1310] Step 3: Design the question

[1311] The device has pre-programmed question patterns. The server selects and tailors appropriate questions based on the user's profile. The server references the profile and generates customized questions such as, "What machine learning-related projects are you currently working on?" The device then displays these questions to the user.

[1312] Input: Generated user profile

[1313] Output: A customized prompt that is displayed to the user.

[1314] Step 4: User input on the problem

[1315] The user responds to the prompt by inputting a specific problem or concern. For example, the user might input, "I'm having trouble organizing data for a machine learning project." This user input is sent from the device to the server.

[1316] Input: User's problem or concern

[1317] Output: The text data of the problem sent to the server

[1318] Step 5: Conversations that encourage autonomy

[1319] The device does not immediately answer the problem entered by the user, but generates support questions to help the user think of a solution on their own. The server generates more in-depth questions and advice based on the user's answers. For example, the device generates and displays support questions such as, "Which part do you feel is particularly problematic? What solutions have you considered for it?" In response to the user's answer, "Data cleansing is difficult," the server generates a question such as, "What specific data cleansing techniques have you tried?"

[1320] Input: Text data of user problems and concerns

[1321] Output: Generate and display supplementary and probing questions

[1322] Step 6: Propose an individual curriculum

[1323] The server analyzes the user's past responses and progress to generate a personalized educational plan and career path. The device then presents the curriculum received from the server to the user. For example, if the user types, "I'm having trouble with data organization," the server generates a suggestion, such as, "I recommend this online course that focuses on data organization," and the device presents it to the user.

[1324] Input: User's past answers and progress data

[1325] Output: Creation and presentation of individualized curriculum and career pathways

[1326] Step 7: Long-term support and growth

[1327] The device stores a record of the user's interactions, and the server periodically analyzes the user's progress and needs using the stored records. The server continues to improve the support content and question patterns based on the analysis results. For example, if a user inputs after a few months, "I understand the basics of data organization, but next I would like to learn about model optimization," the server will analyze the record, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[1328] Input: Saved conversation log

[1329] Output: Improved support content, question patterns, and suggested content

[1330] The above are the specific processing steps of the program of this system.

[1331] (Application example 1)

[1332] 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."

[1333] A challenge facing modern educational environments is the lack of personalized learning support tailored to individual learners. In particular, it is difficult to provide dynamic curriculum and content that responds to users' interests and progress, and there is a lack of mechanisms to promote independent learning. This results in many learners being unable to learn efficiently and taking a long time to achieve their goals.

[1334] 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.

[1335] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum or career path based on the user's answers and progress, means for recommending optimal learning content based on the user's interests and learning progress information, and means for saving a conversation log with the user and providing support content according to the user's growth and changes. This makes it possible to provide individualized learning support to users and promote efficient and independent learning.

[1336] "Basic information" refers to personal information such as the user's name, age, occupation, and interests.

[1337] A "profile" is an individual collection of information generated based on a user's basic information.

[1338] "Specific questions" are questions selected based on the user's profile.

[1339] "Thinking questions" are questions that encourage users to think of solutions on their own.

[1340] A "personalized learning curriculum" is a personalized learning plan that is suggested based on the user's progress and responses.

[1341] A "career path" is a suggestion of a career path that is presented based on the user's occupation and interests.

[1342] "Interests" refers to areas or topics in which a user is particularly interested.

[1343] "Study progress information" is information relating to the progress of a user's learning activities.

[1344] The means for recommending "optimal learning content" is a method for recommending the most appropriate learning materials and content based on the user's interests and learning progress.

[1345] A "conversation log" is a record of all conversations between a user and the system.

[1346] "Support content according to growth and change" refers to appropriate assistance and advice provided according to the user's growth and progress.

[1347] Creating a user profile

[1348] When a user first uses the device, they enter basic information. The device collects basic information such as the user's name, age, occupation, and interests, and sends it to the server. The server then creates a user profile based on the received basic information and stores it in a database. This profile serves as the basis for providing questions and curriculum that are individually tailored to the user.

[1349] Specific examples

[1350] A user enters, "I'm Taro Yamada, 25 years old, a programmer, and I'm interested in machine learning and data analysis." The device sends this information to the server, which generates and saves a new profile.

[1351] Dynamic adjustment of specific questions

[1352] The server dynamically tailors specific questions to match the user's interests based on pre-programmed question patterns based on the profile, and the device displays the customized questions to the user.

[1353] Specific examples

[1354] Based on the profile generated by the server, the device displays the question, "Yamada-san, what machine learning projects have you been working on recently?"

[1355] Generate questions to encourage self-direction

[1356] When a user inputs a specific problem or concern, the server does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[1357] Specific examples

[1358] If a user types, "I'm having trouble with data preprocessing for my machine learning project," the device responds with, "Which part are you particularly struggling with? What solutions have you come up with?"

[1359] Individual curriculum proposals

[1360] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[1361] Specific examples

[1362] If a user inputs "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," which the device presents to the user.

[1363] Long-term support and growth

[1364] The server stores the conversation logs and provides support content that responds to the user's growth and changes. The server periodically analyzes the stored conversation logs to confirm the user's progress and needs, and continues to improve the support content based on that.

[1365] Specific examples

[1366] If a user inputs "I understand the basics of data preprocessing, but next I want to learn about model tuning" after a few months, the server will analyze the logs and check the user's progress. It will then generate support content based on the user's progress, such as "I recommend this resource as the next step," and present it to the user on the device.

[1367] Prompt Sentence Examples

[1368] My name is Taro Yamada, I'm 25 years old and I'm a programmer. I'm interested in machine learning and data analysis. I'm currently struggling with data preprocessing for a machine learning project.

[1369] This invention is realized by an application installed on a device such as a smartphone, tablet, or PC, and a program running on the server side. User input information is exchanged with the server via communication methods such as RESTful API or WebSocket. A database management system (DBMS) is used to store data, and a generative AI model is used for natural language processing. This realizes a system that allows users to receive personalized learning support.

[1370] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1371] Step 1: Enter user information

[1372] The user uses the device to input basic information such as name, age, occupation, and interests. The device then sends this information to the server. The input is received as text data, and the output is transmitted to the server via an API request.

[1373] Step 2: Generate a profile

[1374] The server generates a user profile based on the received basic information. Profile generation involves mapping the input information to fields based on templates stored in a database. The input is the basic information, and the output is the generated profile data.

[1375] Step 3: Dynamically adjust specific questions

[1376] The server then references the generated profile and selects and tailors specific questions based on the profile, using profile-based filtering and scoring algorithms to determine the most appropriate questions, with the profile data as input and the specific questions as output.

[1377] Step 4: Present the question

[1378] The terminal receives a question from the server and displays it to the user, who then enters a response. The input to this process is the question, and the output is the user's response.

[1379] Step 5: Question Generation

[1380] The server takes the user's answer and generates new questions to provide further insight. This step uses a generative AI model to dynamically create probing questions, with the user's answer as input and the new question as output.

[1381] Step 6: Propose an individual curriculum

[1382] The server analyzes the user's answers and progress and generates a personalized learning curriculum and career path. Machine learning algorithms are used here to provide a learning plan that best suits the user's needs. The input is the user's answers and progress data, and the output is the generated learning curriculum and career path.

[1383] Step 7: Recommend learning content

[1384] The server recommends optimal learning content based on the user's interests and learning progress information. In this step, a scoring model is used to select content taking into account the user's history and preferences. The input is interests and learning progress information, and the output is recommended content.

[1385] Step 8: Store and analyze logs

[1386] The server stores all conversation logs and periodically analyzes them to evaluate user growth and changes. This analysis uses natural language processing and data analysis tools. The input is conversation log data, and the output is the user's growth status and improved support content.

[1387] Step 9: Providing long-term support

[1388] The server provides personalized long-term support to the user based on the analysis results, and the terminal displays this support content to the user. The analysis results are input, and new support content is output.

[1389] 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.

[1390] MODE FOR CARRYING OUT THE INVENTION

[1391] The present invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[1392] Program processing overview

[1393] Collection of user information

[1394] When using the device for the first time, the user enters basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server. The server then creates a user profile based on the received information and stores it in a database.

[1395] Example: A user enters "I'm Taro Tanaka, 30 years old, an engineer, and I'm interested in AI and data science." The device sends this information to the server, which generates and saves a new profile.

[1396] Conversation Design

[1397] The device has pre-programmed question patterns to naturally progress the conversation with the user. The server dynamically adjusts the questions based on the user's profile. The device displays customized questions to the user.

[1398] Example: Based on the profile generated by the server, the device displays the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[1399] Conversations that encourage autonomy

[1400] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think about a solution. The server receives the user's answers and generates more in-depth questions and advice.

[1401] Example: If a user types, "I'm having trouble with data preprocessing for my AI project," the device responds with, "Which part are you particularly struggling with? What solutions have you thought of?"

[1402] Individual curriculum proposals

[1403] The server analyzes the user's past answers and progress, and generates an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user.

[1404] Example: If a user types "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents this to the user.

[1405] Long-term support and growth

[1406] The device stores a conversation log with the user, and the server periodically analyzes the user's progress and needs using the stored log. Based on the analysis results, the server continually improves the support content and question patterns. Each time the user makes a new question or request, the device responds using the improved content.

[1407] Example: If a user inputs, after a few months, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," the server will analyze the logs, check the user's progress, and generate support content based on the user's progress, such as "I recommend these resources as your next step," which the device will present to the user.

[1408] Use of emotion engine

[1409] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on this recognition result, the server adjusts the content of the questions and the learning curriculum. If the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates advice for relaxation and appropriate questions, which are presented to the user via the device.

[1410] Example: If a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress state and notifies the server. The server then suggests "Why don't you try some methods to relax?", which the device displays to the user.

[1411] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[1412] The processing flow will be explained below.

[1413] Step 1:

[1414] When a user first uses the device, they enter basic information (such as name, age, occupation, and interests). The device then sends the entered information to the server.

[1415] Specific operation: The user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," and the device sends this information to the server.

[1416] Step 2:

[1417] The server generates a user profile based on the received information and stores it in a database. The terminal displays a message to the user indicating that the profile has been created.

[1418] Specific operation: The server generates a profile for Taro Tanaka and saves it in the database. The device displays a message to the user saying "Profile has been generated."

[1419] Step 3:

[1420] The device initiates an initial conversation with the user. The server generates appropriate questions based on the profile information and sends them to the device.

[1421] Specific operation: Based on Taro Tanaka's profile, the server generates a question, "Mr. Tanaka, what AI-related project are you working on now?" and sends it to the device. The device then displays this question to the user.

[1422] Step 4:

[1423] The user enters an answer to the question, and the device sends the answer to the server.

[1424] Specific operation: The user types "I am developing a natural language processing model," and the device sends this response to the server.

[1425] Step 5:

[1426] The server receives the user's answer and generates a question to give the user an opportunity to think without answering immediately. The terminal displays this question to the user.

[1427] Specific operation: The server generates an additional question, "What part of the project do you find most difficult right now?", and sends it to the device. The device then displays this question to the user.

[1428] Step 6:

[1429] The user enters answers to the follow-up questions, and the device sends these answers to the server.

[1430] Specific behavior: The user types "Cleaning the data is the most difficult," and the device sends this answer to the server.

[1431] Step 7:

[1432] The server generates an individual learning curriculum and career path based on the user's answers and progress information, and the device presents this information to the user.

[1433] Specific behavior: The server finds an online course on data cleaning and suggests, "We recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[1434] Step 8:

[1435] The device stores a conversation log with the user, and the server analyzes the log and periodically updates the user's progress and needs.

[1436] Specific operation: The device stores a conversation log with the user, and the server analyzes this to adjust future support plans.

[1437] Step 9:

[1438] As users ask new questions or make new requests, the device continues to respond with improved content.

[1439] Specific operation: A few months later, when the user types, "I would like to learn about model tuning," the server checks the user's progress and generates support content based on the user's progress, such as, "We recommend these resources as the next step," which the device then presents to the user.

[1440] Step 10:

[1441] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. The recognition results are sent to the server.

[1442] Specific behavior: When a user types "I'm feeling stressed because I have too many tasks to do recently," the emotion engine detects the stress state and sends the result to the server.

[1443] Step 11:

[1444] The server receives the emotion recognition results from the emotion engine and adjusts the questions and learning curriculum accordingly. The device then presents the adjusted content to the user.

[1445] Specific operation: The server generates a question, "Would you like to try some ways to relax?", and the device presents this to the user.

[1446] The above is the processing flow of the system when combined with the emotion engine.

[1447] Example 2

[1448] 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."

[1449] Conventional learning support systems and career development support systems face challenges in that they are unable to flexibly respond to individual users' needs and growth, making it difficult to provide users with appropriate advice immediately. Furthermore, they lack the ability to recognize users' emotions and adjust their responses accordingly, resulting in insufficient support for users' long-term growth and psychological development. This can lead to reduced learning effectiveness and reduced career development efficiency.

[1450] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving basic information from a user and generating a user profile, a means for selecting and adjusting specific questions based on the user profile, a means for generating questions to provide an opportunity for the user to think rather than immediately answering the user's problems, a means for proposing an individual learning curriculum and career path based on the user's answers and progress, and a means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This enables flexible responses according to the individual needs of users and psychological support through emotion recognition.

[1451] "User" refers to any person or organization that uses this system.

[1452] "Basic information" refers to basic information about an individual or organization, such as the user's name, age, occupation, and interests.

[1453] A "profile" refers to a data set that indicates individual characteristics and needs, generated based on basic information about the user.

[1454] "Questions" refers to the questions and conversations asked to users.

[1455] "Not giving an immediate answer" refers to not providing an immediate answer to a user's questions or concerns.

[1456] "Providing an opportunity to think" means providing time and space for users to think about solutions and opinions on their own.

[1457] "Individual learning curriculum" refers to a learning plan customized according to the characteristics and needs of the user.

[1458] A "career path" refers to a path created to support users' professional growth and advancement.

[1459] "Conversation log" refers to a record of conversations between users.

[1460] "Emotion" refers to the user's psychological state or feelings.

[1461] "Emotion recognition" refers to identifying a user's psychological state by analyzing their input data, voice, facial expressions, etc.

[1462] "Adjusting the content of questions and learning curriculum" refers to dynamically changing the questions asked and the content of the learning plan provided based on the user's profile and emotion recognition results.

[1463] MODE FOR CARRYING OUT THE INVENTION

[1464] The present invention is a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. It also generates questions that provide an opportunity for the user to think about their problems rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also saves conversation logs with the user, realizing long-term and flexible support by providing support content tailored to the user's growth and changes. The present invention also includes a function that combines an emotion engine to recognize the user's emotions and adjusts the content of questions and learning curricula based on the recognition results.

[1465] This system mainly uses the following hardware and software:

[1466] Hardware used

[1467] Terminal: A device that receives user input, such as a PC or smartphone.

[1468] Server: A high-performance computer, such as a cloud server, that stores and processes data.

[1469] Software used

[1470] Database management system: Software such as MySQL or PostgreSQL is used.

[1471] Machine learning models: Emotion recognition and profile generation are performed using libraries such as TensorFlow and PyTorch.

[1472] The server receives basic information from the user from the device and generates a profile based on that information. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a profile based on the received information and stores it in a database.

[1473] Based on this profile, the server selects specific questions and generates appropriate questions, which the device displays to the user, asking, for example, "Mr. Tanaka, what AI-related projects are you currently working on?"

[1474] When a user inputs a specific problem or concern, the device does not immediately answer the problem, but instead generates questions to help the user think of a solution. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you thought of?"

[1475] Furthermore, the server can suggest personalized learning curriculums and career paths based on the user's answers and progress. It analyzes the user's past answers from the database and generates suggestions such as, "We recommend this online course that focuses on data preprocessing."

[1476] To provide long-term support, the device stores conversation logs with the user, and the server uses these logs to periodically analyze the user's growth and progress. For example, if a user inputs, "I understand the basics of data preprocessing, but next I'd like to learn about model tuning," the server analyzes the log and generates support content tailored to the user's growth, such as, "I recommend this resource as the next step," which the device then presents to the user.

[1477] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if a user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[1478] Example prompts for generative AI models

[1479] Here are some examples of prompts you might input to a generative AI model:

[1480] Example prompt:

[1481] User profile:

[1482] Name: Taro Tanaka

[1483] Age: 30

[1484] Occupation: Engineer

[1485] Interests: AI, data science

[1486] User Question:

[1487] "I'm struggling with data preprocessing for my AI project. What part do you find particularly challenging? What solutions have you come up with?"

[1488] This allows the generative AI model to generate appropriate questions and suggestions and provide them to the user.

[1489] The above is a specific embodiment of the function in which the program of the system of the present invention collects user information, proposes personalized questions and learning curricula, and further makes adjustments according to the user's emotions using an emotion engine.

[1490] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1491] Step 1:

[1492] Collection of user information

[1493] Input: The user enters basic information (name, age, occupation, interests, etc.) when using the service for the first time.

[1494] Processing: The device sends the entered information to the server, which then creates a user profile based on the information received and stores it in a database.

[1495] Output: The server-generated user profile.

[1496] Specific behavior:

[1497] A user types, "I'm Taro Tanaka, I'm 30 years old, I'm an engineer, and I'm interested in AI and data science."

[1498] The device sends this information to the server via an HTTP request.

[1499] The server receives the information and saves the new profile in the database using an INSERT statement.

[1500] Step 2:

[1501] Conversation Design

[1502] Input: The server is the user's profile.

[1503] Processing: The server dynamically adjusts the prompts based on the user's profile. The device displays the customized prompts to the user.

[1504] Output: The customized question that is displayed to the user.

[1505] Specific behavior:

[1506] The server retrieves the user profile from the database using a SELECT statement.

[1507] The server generates a customized question: "Mr. Tanaka, what AI-related projects are you working on now?"

[1508] The terminal displays this question on the user's screen.

[1509] Step 3:

[1510] Conversations that encourage autonomy

[1511] Input: The user's specific problem or concern.

[1512] Processing: The device does not immediately answer the problem, but generates questions to help the user think of a solution. The server receives the user's answers and generates further questions or advice to dig deeper.

[1513] Output: The follow-up question that is presented to the user.

[1514] Specific behavior:

[1515] A user types, "I'm having trouble with data preprocessing for an AI project."

[1516] The device generates follow-up questions such as, "What areas are you particularly challenged by? What solutions have you considered?"

[1517] The server receives the user's answers and generates further probing questions.

[1518] Step 4:

[1519] Individual curriculum proposals

[1520] Input: The user's past answers and progress.

[1521] Processing: The server analyzes this and generates an appropriate learning curriculum and career path. The device presents the curriculum received from the server to the user.

[1522] Output: A suggested learning curriculum or career path for the user.

[1523] Specific behavior:

[1524] The server retrieves the user's past answers from the database using a SELECT statement and analyzes their progress using a machine learning model.

[1525] The server generates a suggestion: "I recommend this online course that focuses on data preprocessing."

[1526] The terminal displays this to the user.

[1527] Step 5:

[1528] Long-term support and growth

[1529] Input: Log of conversation with the user.

[1530] Processing: The server periodically analyzes the user's progress and needs using the saved logs to improve the support content. The device provides the improved content to the user.

[1531] Output: Improved support is provided to the user.

[1532] Specific behavior:

[1533] The terminal writes the contents of the conversation with the user to a log file.

[1534] The server periodically reads the logs and uses data analysis tools to evaluate progress.

[1535] A user types, "I understand the basics of data preprocessing, but now I want to learn about model tuning."

[1536] The server uses the log analysis results to generate support content appropriate to the user's growth, such as "We recommend this resource as the next step," and the device presents this to the user.

[1537] Step 6:

[1538] Use of emotion engine

[1539] Input: User input data, voice, and facial expressions.

[1540] Processing: The emotion engine recognizes the user's emotions and transmits the results to the server. The server adjusts the questions and learning curriculum based on the results, and the device presents the adjustments to the user.

[1541] Output: Tailored questioning and learning curriculum.

[1542] Specific behavior:

[1543] The user types, "I'm feeling stressed out over the amount of tasks I have lately."

[1544] The emotion engine recognizes the user's stress state and notifies the server.

[1545] The server then adjusts the menu by asking, "Would you like to try some relaxation techniques?"

[1546] The terminal displays this to the user.

[1547] (Application example 2)

[1548] 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."

[1549] Conventional learning support systems have difficulty generating appropriate questions and providing learning curricula based on individual user profiles, and in particular lack a response that reflects the user's emotions, making it difficult to provide effective learning support.Furthermore, there are few systems that provide sufficient support in response to long-term growth and change, making it difficult to stimulate users' motivation to learn independently.

[1550] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1551] In this invention, the server includes means for receiving basic information from a user and generating a user profile, means for selecting and adjusting specific questions based on the user profile, means for generating questions that do not immediately answer problems from the user but provide an opportunity for the user to think, means for proposing an individual learning curriculum and career path based on the user's answers and progress, means for saving a conversation log with the user and providing support content according to the user's growth and changes, and means for recognizing the user's emotions and adjusting the content of the questions and the learning curriculum based on the recognition results. This makes it possible to realize personalized learning support according to the characteristics and emotions of each user, and to continuously stimulate the user's motivation to learn over the long term.

[1552] "Basic information" refers to information received from a user, such as name, age, occupation, and interests.

[1553] A "profile" is data that describes the characteristics of an individual user, generated based on basic information.

[1554] "Prompts" are questions or conversation starters that are asked to users and are tailored based on their profile.

[1555] A "means for generating questions" is a method or system for creating questions that are designed to provide users with an opportunity to think independently, rather than immediately answering their problems.

[1556] A "learning curriculum" is a learning plan or course that is individually suggested based on the user's answers and progress.

[1557] A "career path" is a specific step or plan suggested based on the user's career goals and career path.

[1558] A "conversation log" is data that stores the history of conversations that take place between a user and the system.

[1559] "Support content" refers to the specific advice and assistance provided to users in response to their growth and changes.

[1560] A "means for recognizing emotions" is a method or system that analyzes emotions from user input data (text, voice, facial expressions, etc.) and obtains the results.

[1561] A "means for adjusting the content of questions" is a method or system that dynamically changes the content of questions based on the user's emotions and profile.

[1562] System Overview

[1563] This invention relates to a system that receives basic information from a user, generates a profile, and selects and adjusts specific questions based on that profile. Furthermore, the system generates questions that provide an opportunity for the user to think about their problems, rather than providing an immediate answer, and suggests individual learning curricula and career paths based on the user's answers and progress. It also includes a function that uses an emotion engine to recognize the user's emotions and adjusts the content of the questions and learning curriculum based on the recognition results.

[1564] Collection of user information

[1565] When using the service for the first time, users enter basic information (such as name, age, occupation, and interests). The device, such as a smartphone or head-mounted display (HMD), then sends the entered information to a server, which then generates a user profile based on the information received and stores it in a database. For example, if a user enters, "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server, which then generates and stores a new profile.

[1566] Conversation Design

[1567] The device has pre-programmed question patterns to allow the conversation with the user to proceed naturally. The server dynamically adjusts the questions based on the user's profile. For example, based on the profile generated by the server, the device might display the question, "Mr. Tanaka, what AI-related projects are you working on now?"

[1568] Conversations that encourage autonomy

[1569] When a user inputs a specific problem or concern, the device does not immediately answer the question, but instead generates questions to help the user think of a solution. The server receives the user's answer and generates more in-depth questions or advice. For example, if a user inputs, "I'm having trouble with data preprocessing for an AI project," the device will respond with, "Which part do you find particularly challenging? What solutions have you considered?"

[1570] Individual curriculum proposals

[1571] The server analyzes the user's past answers and progress to generate an appropriate learning curriculum and career path. The device then presents the curriculum received from the server to the user. For example, if a user enters "Data preprocessing is difficult," the server generates a suggestion such as "I recommend this online course that focuses on data preprocessing," and the device presents it to the user.

[1572] Long-term support and growth

[1573] The device saves a conversation log with the user, and the server periodically analyzes the user's progress and needs using the saved log. This allows the server to continue improving the support content and question patterns based on the analysis results. For example, if a user inputs, "I understand the basics of data preprocessing, but next I would like to learn about model tuning," after several months, the server will analyze the log, check the user's progress, and generate support content based on their progress, such as "I recommend this resource as your next step," which the device will present to the user.

[1574] Use of emotion engine

[1575] The emotion engine recognizes emotions from the user's input data, voice, facial expressions, etc. Based on the results of this recognition, the server adjusts the questions and learning curriculum. For example, if the user is feeling anxious or stressed, the emotion engine detects this and notifies the server. The server then generates relaxation advice and appropriate questions, which are presented to the user via the device. For example, if the user inputs, "I'm feeling stressed because I have too many tasks to do recently," the emotion engine recognizes the user's stress level and notifies the server. The server then suggests, "Why not try some methods to relax?" and the device displays this to the user.

[1576] Hardware and software used

[1577] Hardware: Smartphone, Head-Mounted Display (HMD)

[1578] Software: User profile management software, sentiment analysis engine, natural language processing model (GPT-4, etc.)

[1579] Examples of prompt statements

[1580] Initial information-gathering prompt: "Hello, as a new user, please provide some basic information. Please tell us your name, age, occupation, and interests."

[1581] Progress prompt: "Hey, tell us about the AI ​​project you've been working on recently. What challenges do you see?"

[1582] Curriculum suggestion prompt: "It sounds like you're struggling with data preprocessing. Why not try these online courses?"

[1583] Stress management prompt: "You've been feeling stressed lately because of all the tasks. Why don't you try some activities that will help you relax a bit?"

[1584] This makes it possible to provide personalized learning support tailored to each user's individual characteristics and emotions, and to continuously stimulate users' motivation to learn over the long term.

[1585] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1586] Step 1: Collect basic user information

[1587] The server receives basic information (such as name, age, occupation, and interests) from the device when it is used for the first time. For example, if the user enters "I'm Taro Tanaka, 30 years old, an engineer. I'm interested in AI and data science," the device sends this information to the server. The server generates a user profile based on the received information and stores it in a database. The input is the basic information the user entered into the device, and the output is the generated profile data. This profile data is used in later steps.

[1588] Step 2: Generate questions

[1589] Based on the profile data in the database, the server applies appropriate wording to question templates to generate the most suitable question for the user. For example, based on Taro Tanaka's profile, it generates the question, "Mr. Tanaka, what kind of AI-related project are you working on now?" The input is the user's profile data, and the output is a customized question. The server sends this question to the device, which then displays it to the user.

[1590] Step 3: Receiving responses from users

[1591] The device displays the question sent from the server and receives the user's answer to that question. For example, if a user enters "I'm having trouble with data preprocessing for an AI project," the device sends the answer to the server. The input is the answer entered by the user into the device, and the output is the answer data sent to the server.

[1592] Step 4: Generate questions

[1593] The server analyzes the received response data using a natural language processing model (such as GPT-4) and generates questions that do not immediately answer the user's problem but provide an opportunity for them to think. For example, the server might generate a question such as, "Which part do you feel is particularly challenging? What solutions have you considered?" The input is the user's response data, and the output is a new question to dig deeper. The server sends this question to the device, which then displays it to the user.

[1594] Step 5: Propose a learning curriculum

[1595] The server generates an appropriate learning curriculum and career path based on the user's response data and progress data. For example, if the user inputs "Data preprocessing is difficult," the server generates a curriculum that reads, "I recommend this online course that focuses on data preprocessing." The input is the user's response data and progress data, and the output is a suggested learning curriculum. The server sends this curriculum to the terminal, which then presents it to the user.

[1596] Step 6: Save the conversation log

[1597] The server stores all conversation logs with the user in a database. Conversation history and progress data with the user are recorded sequentially, and the server analyzes this data and uses it to provide support according to the user's growth and changes. The input is the conversation data with the user, and the output is the conversation log stored in the database.

[1598] Step 7: Use the Emotion Engine

[1599] The server uses an emotion analysis engine to analyze emotions from text, voice, and facial expression data entered by the user. For example, if a user enters, "I'm feeling stressed because I have too many tasks to do recently," the server uses the emotion engine to recognize the user's stress level and generates advice and appropriate questions to help them relax. The input is data related to the user's emotions, and the output is advice and questions based on those emotions. The server sends these advice and questions to the device, which then presents them to the user.

[1600] 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.

[1601] 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.

[1602] 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 robot 414.

[1603] 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.

[1604] FIG. 9 illustrates 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 behaviors 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.

[1605] 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.

[1606] 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).

[1607] 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.

[1608] 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."

[1609] 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.

[1610] 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).

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] The following is further disclosed regarding the above embodiment.

[1622] (Claim 1)

[1623] means for receiving basic information from a user and generating a profile of the user;

[1624] A means for selecting and tailoring specific questions based on a user's profile; and

[1625] A means for generating questions to provide an opportunity for users to think about their problems rather than giving immediate answers;

[1626] A means to propose individual learning curriculum and career paths based on users' answers and progress,

[1627] A means to store conversation logs with users and provide support content according to the user's growth and changes,

[1628] A system including:

[1629] (Claim 2)

[1630] 10. The system of claim 1, wherein the system dynamically adjusts the questions based on a user profile.

[1631] (Claim 3)

[1632] 10. The system of claim 1, wherein the conversation log is analyzed to improve support content according to the user's growth and progress.

[1633] "Example 1"

[1634] (Claim 1)

[1635] means for receiving basic information from a user and generating a profile of the user;

[1636] A means for selecting and tailoring specific questions based on a user's profile; and

[1637] A means for generating questions to provide an opportunity for users to think about their problems rather than giving immediate answers;

[1638] A means of suggesting individual educational plans and career paths based on users' responses and progress;

[1639] A means of storing records of interactions with users and providing support content according to the user's maturity and changes;

[1640] A system including:

[1641] (Claim 2)

[1642] 10. The system of claim 1, wherein the system dynamically adjusts the questions based on a u...

Claims

1. means for receiving basic information from a user and generating a profile of the user; A means for selecting and tailoring specific questions based on a user's profile; and A means for generating questions to provide an opportunity for users to think about their problems rather than giving immediate answers; A means to propose individual learning curriculum and career paths based on users' answers and progress, A means to store conversation logs with users and provide support content according to the user's growth and changes, A system including:

2. 10. The system of claim 1, wherein the system dynamically adjusts the questions based on a user profile.

3. The system of claim 1 , wherein the conversation log is analyzed to improve support content according to the user's growth and progress.

Images