system

Abstract

To provide a system.SOLUTION: A system includes: means for using a generative AI to provide a user with suggestions to help the user reach an answer to a question from the user; means for recording in a log data on the user's behavior reaching the answer; means for recognizing the user's emotions in real time using an emotion engine; and means for adjusting a level of difficulty of the suggestions provided to the user based on the behavioral data recorded in the log and emotion data indicating the recognized user's emotions.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The use of generative AI presents the challenge of reducing users' ability to learn on their own. [Means for solving the problem]

[0005] To solve this problem, we propose a system that utilizes generative AI to provide hints and methods for users to find the answer themselves, rather than providing direct answers to their questions. Furthermore, the system generates hints taking into account the user's learning ability and interests, and tracks the process by which the user finds the answer themselves, optimizing the generation of hints for the next time based on the results. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.,

[0012] hard disk), or magnetic tape.

[0013] 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.

[0014] 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."

[0015] [First embodiment]

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0028] "Example 1"

[0029] As one embodiment of the present invention, a system utilizing generative AI is provided. This system does not provide a direct answer to a user's question, but rather provides hints and methods for finding the answer on one's own. Specifically, if a user asks, "What's the weather like in Tokyo?", the system will provide a hint such as, "Why don't you check the weather forecast website?"

[0030] "Example 2"

[0031] Furthermore, as another embodiment of the present invention, a system is provided in which a generative AI generates hints taking into account the user's learning ability and interests. Specifically, if the system determines that the user is interested in science, it provides hints from a scientific perspective. For example, if the user asks, "Why does it rain?", the system provides a hint such as, "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?"

[0032] "Example 3"

[0033] Furthermore, as another embodiment of the present invention, a system is provided in which a generative AI tracks the process by which a user finds the answer on their own and optimizes the generation of the next hint based on the results. Specifically, the generation of the next hint is optimized based on information such as what information the user searched for based on the previous hint and how long it took to find the answer. For example, if the user quickly found the answer from the previous hint, it is possible to adjust the system to provide a more difficult hint next time.

[0034] The processing flow of each embodiment will be described below.

[0035] "Example 1"

[0036] Step 1: Receive a question from the user. For example, receive a question like "What's the weather like in Tokyo?"

[0037] Step 2: Generative AI generates a hint for the question, in this case "Why not check the weather website?"

[0038] Step 3: Provide the generated hints to the user.

[0039] "Example 2"

[0040] Step 1: Receive a user question and their interests. For example, receive the question "Why does it rain?" and information that the user is interested in science.

[0041] Step 2: The generative AI generates a hint based on the question and the user's interests. In this case, it generates the hint, "Why not investigate how water vapor cools, forming clouds, and then falls as rain?"

[0042] Step 3: Provide the generated hints to the user.

[0043] "Example 3"

[0044] Step 1: Receive a question from the user and collect information such as what information the user searched for based on the previous hint and how long it took them to find the answer.

[0045] Step 2: The generative AI optimizes the next hint generation based on the collected information. For example, if the user quickly finds the answer from the previous hint, it will generate a more difficult hint next time.

[0046] Step 3: Provide optimized tips to users.

[0047] Example 1

[0048] Next, a description will be given of Example 1 of Form 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."

[0049] Conventional generative AI systems often provide direct answers to user questions, leaving few opportunities for users to develop the ability to find answers on their own. Furthermore, they lack the ability to provide hints that take into account the user's learning ability and interests, resulting in reduced user satisfaction and learning effectiveness. Furthermore, they lack the ability to track the user's process of finding the answer on their own and optimize the generation of next hints based on the results, making continuous learning support difficult.

[0050] 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.

[0051] In this invention, the server includes means for receiving a question from a user, means for analyzing the received question, means for generating a prompt sentence to be input to the generative AI model based on the analysis result, means for inputting the prompt sentence to the generative AI model, means for receiving output from the generative AI model, means for formatting the output from the generative AI model as a hint to be provided to the user, and means for sending the formatted hint to the user. This enables the server to develop the user's ability to find answers on their own and to provide hints that take into account their learning ability and interests. Furthermore, by tracking the user's learning process and optimizing the generation of the next hint, continuous learning support can be realized.

[0052] The "means for receiving a question from a user" is a function that allows the system to receive a question entered by a user.

[0053] The "means for analyzing a received question" is a function for analyzing a received question in order to understand the content of the question and perform appropriate processing.

[0054] "Means for generating prompt sentences to be input to the generative AI model" refers to a function that creates prompt sentences to give appropriate instructions to the generative AI model based on the analysis results.

[0055] "Means for inputting prompt sentences to the generative AI model" refers to a function for sending the generated prompt sentences to the generative AI model, which then generates the appropriate output.

[0056] "Means for receiving output from a generative AI model" refers to a function for receiving the output generated by a generative AI model.

[0057] "Means for formatting the output from a generative AI model as a hint to provide to the user" is a function that formats the output from a generative AI model in a form that is easy for the user to understand.

[0058] The "means for sending formatted hints to the user" is a function for delivering formatted hints to the user.

[0059] A "generative AI model" is an artificial intelligence model that generates appropriate hints and answers to user questions.

[0060] A "prompt sentence" is an input sentence that causes a generative AI model to generate a specific output.

[0061] This invention is a system that utilizes a generative AI model to provide users with hints and methods for finding answers on their own, rather than providing direct answers to questions from users. Specific embodiments of this system are described below.

[0062] Hardware and Software Configuration

[0063] server

[0064] The server receives questions from users, analyzes them, inputs prompts to the generative AI model, receives the output from the generative AI model, formats it, and sends it to the user. The server uses the following software and hardware:

[0065] Natural Language Processing Library: Use a natural language processing library, such as SpaCy or NLTK, to parse the question.

[0066] Generative AI model: For example, OpenAI's (registered trademark) GPT-4 (registered trademark) is used as the generative AI model.

[0067] Communication protocol: HTTP / HTTPS protocol is used for communication with user terminals.

[0068] Terminal

[0069] The terminal is responsible for inputting questions by the user and receiving and displaying hints from the server. The terminal uses the following software and hardware:

[0070] User interface: Provide a GUI for inputting questions and displaying hints. For example, use a smartphone app or a web browser.

[0071] Communication protocol: Use HTTP / HTTPS protocol to communicate with the server.

[0072] user

[0073] The user uses a terminal to enter a question and receives hints provided by the server.

[0074] Data processing and calculation

[0075] 1. User inputs a question

[0076] The user types a question into an input field on the device, for example, "What's the weather like in Tokyo?"

[0077] 2. Submit your question

[0078] The device sends the question entered by the user to the server using an HTTP request.

[0079] 3. Question Analysis

[0080] The server analyzes the received question using a natural language processing library, for example, extracting keywords such as "weather in Tokyo."

[0081] 4. Prompt generation

[0082] The server generates a prompt sentence to be input to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as, "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast."

[0083] 5. Input to the generative AI model

[0084] The server inputs the generated prompt sentence into a generative AI model, for example, by sending the prompt sentence to the GPT-4 API.

[0085] 6. Obtaining the output of the generative AI model

[0086] The server receives the output from the generative AI model, for example, "Why not check out a weather website?"

[0087] 7. Hint Formatting

[0088] The server formats the output from the generative AI model as hints to provide to the user.

[0089] 8. Submit a Tip

[0090] The server sends the formatted hint to the device using an HTTP response.

[0091] 9. Displaying Hints

[0092] The device displays the hint received from the server to the user, for example, "Why not check out our weather website?"

[0093] Specific examples

[0094] Example 1: Weather question

[0095] User asks: "What's the weather like in Tokyo?"

[0096] Server prompt: "User is asking about the weather in Tokyo. Please suggest a way to check the forecast."

[0097] Generative AI model output: "Why not check out a weather website?"

[0098] Device says: "Why don't you check the weather website?"

[0099] In this way, users can be helped to find information themselves.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] User question input

[0103] Subject: User

[0104] Specific operation: The user enters a question into the input field of the device and presses the send button. For example, "What's the weather like in Tokyo?"

[0105] Input: User question (e.g. "What's the weather like in Tokyo?")

[0106] Output: Question typed into the terminal

[0107] Step 2:

[0108] Submit a Question

[0109] Subject: Device

[0110] What happens: The device sends the question entered by the user to the server using an HTTP request.

[0111] Input: Question typed into the terminal

[0112] Output: The question sent to the server

[0113] Step 3:

[0114] Question Analysis

[0115] Subject: Server

[0116] Specific operation: The server analyzes the received question using a natural language processing library (e.g., SpaCy or NLTK). For example, it extracts keywords such as "weather in Tokyo."

[0117] Input: The question sent to the server

[0118] Data processing: Use natural language processing libraries to parse the question and extract keywords.

[0119] Output: Parsed question keywords (e.g. "Weather in Tokyo")

[0120] Step 4:

[0121] Generate prompt statement

[0122] Subject: Server

[0123] Specific operation: Based on the analysis results, the server generates a prompt sentence to be input to the generative AI model. For example, it generates a prompt sentence such as, "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast."

[0124] Input: Keywords from the parsed question

[0125] Data processing: Generate prompt sentences based on keywords.

[0126] Output: The generated prompt (e.g., "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast.")

[0127] Step 5:

[0128] Input to generative AI models

[0129] Subject: Server

[0130] Specific operation: The server inputs the generated prompt sentence into the generative AI model. For example, it sends the prompt sentence to the API of the generative AI model.

[0131] Input: Generated prompt statement

[0132] Output: The prompt sent to the generative AI model

[0133] Step 6:

[0134] Obtaining the output of a generative AI model

[0135] Subject: Server

[0136] What it does: The server receives the output from the generative AI model, for example, "Why don't you check the weather website?"

[0137] Input: The prompt sent to the generative AI model

[0138] Data computation: The generative AI model generates output based on the prompt.

[0139] Output: The output from the generative AI model (e.g., "Why not check out a weather website?")

[0140] Step 7:

[0141] Hint formatting

[0142] Subject: Server

[0143] What it does: The server formats the output from the generative AI model as hints to provide to the user.

[0144] Input: Output from a generative AI model

[0145] Data processing: Formatting the output to make it easier for users to understand.

[0146] Output: A formatted hint (e.g., "Why not check out the weather website?")

[0147] Step 8:

[0148] Submit a tip

[0149] Subject: Server

[0150] Specific operation: The server sends the formatted hint to the device using an HTTP response.

[0151] Input: Formatted hint

[0152] Output: Hints sent to the terminal

[0153] Step 9:

[0154] Show Hints

[0155] Subject: Device

[0156] What happens: The device displays the hint received from the server to the user, for example, "Why not check out the weather website?"

[0157] Input: Hint sent to terminal

[0158] Output: The hint displayed to the user

[0159] (Application example 1)

[0160] Next, a description will be given of Application Example 1 of Embodiment 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."

[0161] Conventional generative AI systems often provide direct answers to user questions, leaving few opportunities for users to develop the ability to find answers on their own. Furthermore, in physical stores, it is difficult for users to quickly obtain information about products and stores, resulting in an inconvenient shopping experience. To solve these issues, a system is needed that provides users with hints and methods for finding answers on their own.

[0162] 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.

[0163] In this invention, the server includes means for utilizing generative AI to provide hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for the generative AI to take the user's learning ability and interests into consideration when generating hints for the user's questions, means for the generative AI to track the process by which the user finds the answer on their own and optimize the generation of next hints based on the results, and means for providing hints and methods for finding answers when the user asks a question about a product or a store in a physical store. This enables users to develop their ability to find answers on their own while improving their shopping experience in the physical store.

[0164] "Generative AI" is a type of artificial intelligence that generates new information and answers based on user input.

[0165] A "hint" is information that provides clues or directions to help users find the answer themselves.

[0166] "Learning ability" is the user's ability to understand and apply new information.

[0167] An "interest" is a user's interest or curiosity about a particular piece of information or activity.

[0168] "Tracking" is the process of recording and analyzing user actions and choices.

[0169] "Optimization" refers to adjusting and improving a system or process to achieve a specific purpose.

[0170] A "brick and mortar store" is a store that exists in a physical location and offers goods and services.

[0171] A "guide map" is a diagram showing the layout of a store and the locations of products.

[0172] A "prompt sentence" is an input sentence that instructs a generative AI to generate specific information.

[0173] To implement this invention, it is necessary to build a system that utilizes generative AI. This system does not provide direct answers to questions from users, but rather provides methods and hints for finding answers. A specific embodiment of this system is described below.

[0174] System configuration

[0175] The system consists of the following main components:

[0176] 1. Generative AI model: An artificial intelligence model that generates hints in response to user questions. Specifically, we use OpenAI's generative AI model.

[0177] 2. User device: The device on which the user enters the question, such as a smartphone or tablet.

[0178] 3. Server: A server for hosting the generative AI model and processing user queries.

[0179] Program processing

[0180] The server processes the data as follows:

[0181] 1. Receive user question: A question is sent from the user's device.

[0182] 2. Prompt generation: The server generates a prompt based on the user's question. For example, if the user asks, "Where is this product?", the prompt will be, "When the user asks, 'Where is this product?', please provide hints to help them find the answer, rather than a direct answer."

[0183] 3. Generate hints using a generative AI model: The server sends a prompt to the generative AI model to generate a hint.

[0184] 4. Providing hint to user: The generated hint is sent to the user's terminal and displayed to the user.

[0185] Hardware and software used

[0186] Hardware: smartphones, tablets, servers

[0187] Software: Python (registered trademark), OpenAI API

[0188] Specific examples

[0189] When a user asks "Where is this item?" in a physical store, the system works as follows:

[0190] 1. A question is sent from the user device to the server.

[0191] 2. The server generates a prompt based on the question.

[0192] 3. Prompt: "When a user asks, 'Where is this item?', provide a hint to help them find the answer, rather than a direct answer."

[0193] 4. The server sends a prompt to the generative AI model to generate a hint.

[0194] 5. Generated hint: "Please check the store map. It's located near the entrance."

[0195] 6. The hint is sent to the user's device and displayed to the user.

[0196] In this way, users can develop their ability to find answers on their own while improving their in-store shopping experience.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] The user types a question.

[0200] Users input questions using devices such as smartphones or tablets, and the input questions are sent from the device to the server.

[0201] Input: User question (e.g., "Where is this item?")

[0202] Output: The question data sent to the server

[0203] Step 2:

[0204] The server receives the query.

[0205] The server receives question data sent from the user terminal, analyzes the received question data, and prepares to generate a prompt sentence.

[0206] Input: User question data

[0207] Output: Parsed question data

[0208] Step 3:

[0209] The server generates a prompt.

[0210] The server generates a prompt based on the parsed question data. For example, if the user's question is "Where is this product?", the prompt will be "When the user asks, 'Where is this product?', please provide a hint to help them find the answer, rather than a direct answer."

[0211] Input: Parsed question data

[0212] Output: Generated prompt statement

[0213] Step 4:

[0214] The server sends a prompt to the generative AI model.

[0215] The server sends the generated prompt sentence to the generative AI model, instructing it to generate a hint.

[0216] Input: Generated prompt text

[0217] Output: The prompt sent to the generative AI model

[0218] Step 5:

[0219] A generative AI model generates hints.

[0220] The generative AI model generates hints based on the prompt it receives, such as "Please check the store map. It's located near the entrance."

[0221] Input: A prompt sent to the generative AI model

[0222] Output: Generated hints

[0223] Step 6:

[0224] The server receives the generated hint.

[0225] The server receives the hints generated by the generative AI model and prepares them to be sent to the user's device.

[0226] Input: Generated hint

[0227] Output: Hint data sent to the user's device

[0228] Step 7:

[0229] The user device receives the hint.

[0230] The user terminal receives the hint data sent from the server and displays it to the user.

[0231] Input: Hint data sent from the server

[0232] Output: A hint to be displayed to the user (e.g., "Please check the store map. It's located near the entrance.")

[0233] This way, users can get hints to find the answer themselves.

[0234] Example 2

[0235] Next, a description will be given of Example 2 of Form 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."

[0236] In conventional systems using generative AI, it has become common to provide direct answers to user questions. However, this makes it difficult for users to develop the ability to find answers on their own, and the learning effect is limited. Furthermore, there are few systems that provide hints that take into account the user's interests and learning ability, and there is an issue that learning support optimized for individual users is not being provided sufficiently.

[0237] 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 the user to input a question, a means for the terminal to send the question to the server, a means for the server to receive the question and analyze the user's interests and learning ability, a means for the server to input a prompt sentence to the generative AI model, a means for the generative AI model to generate a hint, a means for the server to receive the generated hint and send it to the terminal, and a means for the terminal to display the hint to the user. This allows the user to obtain appropriate hints according to their interests and learning ability, improving the learning effect.

[0238] "User" refers to an individual who utilizes the system to enter questions and receive hints.

[0239] "Terminal" refers to the device through which the user inputs questions and communicates with the server. Specifically, this includes smartphones and personal computers.

[0240] "Server" refers to a central processing unit that receives questions from users, generates hints using a generative AI model, and sends them to the terminal.

[0241] "Generative AI model" refers to an artificial intelligence model that generates appropriate hints in response to user questions. Specifically, it includes models that use natural language processing technology.

[0242] A "prompt sentence" is a sentence input to a generative AI model that includes the user's question and the analysis results.

[0243] A "hint" is information that provides clues or methods for users to find the answer themselves.

[0244] A "question" refers to a question or problem that a user inputs into the system.

[0245] "Analysis" refers to the processing of data by the server to assess the user's interests and learning ability.

[0246] "Learning ability" refers to the ability of a user to acquire new knowledge or skills.

[0247] "Interests" refer to the interest a user has in a particular field or topic.

[0248] This invention relates to a system that allows a user to input a question and provides appropriate hints using a generative AI model. Specific embodiments of this system are described below.

[0249] First, the user inputs a question using a terminal. The terminal can be a device such as a smartphone or a PC. The question input by the user is sent from the terminal to a server. The terminal then sends the data to the server via the Internet.

[0250] The server receives the questions sent from the device and then analyzes the user's interests and learning ability based on the user's past question history and profile information. This analysis is performed using a database and machine learning algorithms.

[0251] The server generates a prompt based on the user's question and the analysis results. The prompt is a sentence that is input to the generative AI model and includes the user's question and the analysis results. For example, a prompt might be generated that reads, "It has been determined that the user is interested in science. The user's question is, 'Why does it rain?' Please provide appropriate hints from a scientific perspective."

[0252] Next, the server inputs this prompt into a generative AI model. A model using natural language processing technology (such as GPT-4) is used as the generative AI model. The generative AI model generates an appropriate hint for the user's question based on the prompt. For example, a hint such as "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?" is generated.

[0253] The server receives the hints generated from the generative AI model. The server then sends the hints to the user's device. The device receives the hints sent from the server and displays them to the user. The user can check the hints on the device screen.

[0254] As a concrete example, consider the case where a user inputs the question "Why does it rain?" The device sends this question to the server. The server receives the question and determines that the user is interested in science because they have asked many science-related questions in the past. The server inputs the following prompt to the generative AI model: "It has been determined that the user is interested in science. The user's question is 'Why does it rain?' Please provide an appropriate hint from a scientific perspective." The generative AI model generates the hint: "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?" The server sends this hint to the device, and the device displays it to the user. The user can check the hint on the device screen and obtain an answer from a scientific perspective.

[0255] In this way, users can obtain appropriate hints according to their interests and learning abilities, improving their learning effectiveness.

[0256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0257] Step 1:

[0258] The user inputs a question. The user uses a device (smartphone or PC) to input a question to the system. For example, the user might input "Why does it rain?" The input question is stored in the device's memory.

[0259] Step 2:

[0260] The terminal sends a question to the server. The terminal sends a question entered by the user to the server via the Internet. The input data is the user's question text. The output data is the question text sent to the server.

[0261] Step 3:

[0262] The server receives the question and analyzes the user's interests and learning ability. The server receives the question sent from the terminal. The server then accesses a database to obtain the user's past question history and profile information. The input data is the question text and the user's past question history and profile information. The server analyzes this data and evaluates the user's interests and learning ability. The output data is the analysis results regarding the user's interests and learning ability.

[0263] Step 4:

[0264] The server inputs a prompt sentence into the generative AI model. The server generates a prompt sentence based on the user's question and the analysis results. For example, it generates a prompt sentence such as, "It has been determined that the user is interested in science. The user's question is 'Why does it rain?' Please provide appropriate hints from a scientific perspective." The input data is the question text and the analysis results. The output data is the generated prompt sentence.

[0265] Step 5:

[0266] The generative AI model generates a hint. The server inputs the generated prompt sentence into the generative AI model. The generative AI model (for example, a model using natural language processing technology) generates an appropriate hint for the user's question based on the prompt sentence. For example, it generates the hint, "Why not investigate the process by which water vapor cools, forms clouds, and then falls as rain?" The input data is the prompt sentence. The output data is the generated hint.

[0267] Step 6:

[0268] The server receives the generated hint and sends it to the terminal. The server receives the hint generated from the generative AI model. The server then sends this hint to the user's terminal. The input data is the generated hint. The output data is the hint sent to the terminal.

[0269] Step 7:

[0270] The terminal displays the hint to the user. The terminal receives the hint sent from the server and displays it to the user. The user can check the hint on the terminal screen. The input data is the hint sent from the server. The output data is the hint displayed on the terminal screen.

[0271] (Application example 2)

[0272] Next, a description will be given of Application Example 2 of Form 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."

[0273] Conventional generative AI systems often provide direct answers to user questions, making it difficult for users to develop the ability to find answers on their own. They also lack the ability to provide hints that take into account the user's learning ability and interests, resulting in reduced learning efficiency. Furthermore, they lack the ability to analyze the user's past learning history and interests to optimize the generation of next hints, making it difficult to provide continuous learning support.

[0274] 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.

[0275] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for generating hints taking into account the user's learning ability and interests, means for analyzing the user's past learning history and interests, and means for generating hints based on the generated prompt sentences. This enables the user to develop the ability to find answers on their own and improve learning efficiency. Furthermore, continuous learning support can be realized by analyzing the user's past learning history and interests to optimize the generation of next hints.

[0276] "Generative AI" is an artificial intelligence system that generates answers and hints in natural language based on user input.

[0277] "User learning ability" refers to the ability of a user to acquire new knowledge or skills.

[0278] "User interests" refers to the interest a user has in a particular field or topic.

[0279] A "hint" is a clue or suggestion that helps users find the answer themselves.

[0280] A "prompt sentence" is an input sentence that a generative AI uses to generate appropriate hints in response to a user's question.

[0281] "Learning history" refers to a record of a user's past learning content and activities.

[0282] "Optimization" is the adjustment of systems or processes to maximize efficiency and effectiveness in order to achieve a specific purpose.

[0283] A system for implementing this invention utilizes generative AI to provide hints and methods for finding answers on one's own, rather than providing direct answers to questions from users. The system has a function for generating hints that takes into account the user's learning ability and interests, and a function for analyzing the user's past learning history and interests. It also includes a function for generating hints based on generated prompt sentences.

[0284] The server receives the user's question and profile as input and analyzes the user's interests. Specifically, it identifies areas of interest from the user's profile and generates an appropriate prompt for the user's question. Based on the generated prompt, the generative AI generates hints and provides them to the user.

[0285] This system is implemented using OpenAI's API, which uses a generative AI model to generate answers and hints in natural language. The server receives the user's question and profile, generates a prompt, and sends it to OpenAI's API. The hints returned by the API are then provided to the user.

[0286] As a concrete example, if a user asks "Why does it rain?" and the user profile contains "science", the generated prompt would be:

[0287] We've determined that you're interested in science. Please provide some scientific clues to the following questions:

[0288] Question: Why does it rain?

[0289] Tip:

[0290] By inputting this prompt into the OpenAI API, an appropriate hint is generated, such as "Why not investigate the process by which water vapor cools, forms clouds, and then falls as rain?"

[0291] This system allows users to develop the ability to find answers on their own and improve their learning efficiency. It also provides continuous learning support by analyzing the user's past learning history and interests to optimize the generation of next hints.

[0292] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0293] Step 1:

[0294] The user enters a question.

[0295] The user inputs a question using a terminal and sends it to the server. The input data is the user's question and profile information.

[0296] Step 2:

[0297] The server analyzes the user's interests.

[0298] The server analyzes the received user profile information and identifies the user's areas of interest. Specifically, it extracts areas of interest (e.g., science, technology, etc.) contained in the profile information. The input is the user's profile information, and the output is the user's areas of interest.

[0299] Step 3:

[0300] The server generates a prompt.

[0301] The server generates a prompt based on the user's question and interests. Specifically, it creates a prompt using a template based on the user's interests. The input is the user's question and interests, and the output is the generated prompt.

[0302] Step 4:

[0303] The server calls the generative AI model.

[0304] The server sends the generated prompt to the OpenAI API and generates appropriate hints. The input is the generated prompt, and the output is the hint returned by the generative AI model.

[0305] Step 5:

[0306] The server provides the hint to the user.

[0307] The server sends the generated hints to the user's device and displays them to the user. The input is the hint returned from the generative AI model, and the output is the hint displayed on the user's device.

[0308] Step 6:

[0309] The server updates the user's learning history.

[0310] The server tracks the hints received by the user and their subsequent actions, and updates the learning history. Specifically, it records what hints the user received and what actions they took based on them. The input is the user's behavioral data, and the output is the updated learning history.

[0311] Step 7:

[0312] The server will optimize the next hint generation.

[0313] The server optimizes the next hint generation based on the updated learning history. Specifically, it analyzes the past learning history and adjusts the algorithm to provide optimal hints based on the user's learning patterns. The input is the updated learning history, and the output is the optimized hint generation algorithm.

[0314] Example 3

[0315] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0316] Conventional generative AI systems have focused on providing direct answers to users, and lacked the means to support users in the process of finding the answer themselves. Furthermore, hints were not generated taking into account the user's learning ability or interests, making it difficult to provide learning support optimized for each individual user. Furthermore, there was no mechanism to utilize user behavior data to optimize the generation of next hints, making it impossible to improve users' learning efficiency.

[0317] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes: a means for utilizing generative AI to provide hints and methods for finding the answer on one's own, rather than providing a direct answer to a question from a user; a means for tracking user behavior and collecting behavioral data such as search keywords, viewed web pages, and the time it took to find the answer; a means for storing the collected behavioral data in a database and using it to generate the next hint; and a means for the generative AI model to analyze the stored behavioral data and optimize the next hint. This makes it possible to support the process of users finding the answer on their own and provide hints optimized for each user.

[0318] "Generative AI" is an artificial intelligence system that generates answers and hints in natural language based on user input.

[0319] "User" means an individual or entity that uses the system to ask questions and obtain clues and answers.

[0320] A "hint" is information that provides clues or directions to help users find the answer themselves.

[0321] "Behavioral data" refers to information such as search keywords generated when users use the system, the web pages they view, and the time it takes them to find an answer.

[0322] A "database" is a system for storing and managing collected behavioral data.

[0323] A "generative AI model" is an algorithm or program that analyzes collected behavioral data and generates hints for the next time.

[0324] "Optimization" is the process of adjusting the difficulty and content of the next hint based on user behavior data.

[0325] This invention is a system that utilizes generative AI to support users in the process of finding solutions themselves. A specific embodiment of this system is described below.

[0326] Hardware and software used

[0327] Hardware: Servers, user devices (PCs, smartphones, etc.)

[0328] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL®), web browsers (e.g., GOOGLE CHROME®)

[0329] System Overview

[0330] This system tracks user behavior and optimizes the generation of the next hint based on the collected behavioral data. Specifically, it optimizes the generation of the next hint based on information such as what information the user searched for based on the previous hint and how long it took them to find the answer.

[0331] Program processing

[0332] 1. User behavior tracking:

[0333] A user logs in to the system using a terminal.

[0334] The server provides the user with initial hints using a generative AI model.

[0335] The user searches for information based on the hints, and behavioral data such as the search engine used, the URL of the web page viewed, and search keywords are sent from the device to the server.

[0336] The server tracks user behavior data in real time and measures the time it takes to find the answer.

[0337] 2. Data Collection and Storage:

[0338] The server collects user behavior data.

[0339] The server stores the collected data in a database management system (e.g., MySQL).

[0340] The server organizes and analyzes the stored data to use in generating next hints.

[0341] 3. Hint generation optimization:

[0342] The server analyzes the user behavior data stored in the database.

[0343] The generative AI model generates the next hint based on the analysis results.

[0344] The server provides the generated hint to the user.

[0345] Specific examples

[0346] For example, suppose a user receives a hint saying, "Find out the meaning of the following word." If the user searches for the word "example" on Google and finds the answer within a few seconds, the next time they receive a more challenging hint, such as, "Find out the meaning of the following sentence."

[0347] Prompt Sentence Examples

[0348] Below are some examples of prompts for generative AI models:

[0349] The user had 10 seconds to find the answer based on the previous hint. Please generate the next hint. Please adjust the difficulty to increase the difficulty.

[0350] In this way, the system can optimize the user's learning process and provide more effective hints. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0351] Step 1: Track user behavior

[0352] Input: The user logs into the system using a terminal and receives an initial hint.

[0353] Specific operation: The server uses the generative AI model to provide the user with an initial hint, and the user begins searching for information based on the hint.

[0354] Data processing: Behavioral data such as the search engine used by the user, the URL of the web page viewed, and search keywords are sent from the device to the server.

[0355] Output: The server tracks user behavior data in real time and measures the time it takes to find the answer.

[0356] Step 2: Collect and store data

[0357] Input: The server receives user behavior data.

[0358] What it does: The server collects behavioral data such as users' search keywords, the URLs of web pages they visited, and the time it took them to find an answer.

[0359] Data processing: The collected behavioral data is stored in a database management system (e.g., MySQL).

[0360] Output: The server organizes and analyzes the stored data for use in generating next hints.

[0361] Step 3: Optimizing hint generation

[0362] Input: The server receives user behavior data stored in a database.

[0363] Specific operation: The server analyzes the behavioral data and generates the next hint taking into account the user's learning ability and interests.

[0364] Data processing: The generative AI model generates the next hint based on the analysis results.

[0365] Output: The server provides the generated hint to the user.

[0366] Specific examples

[0367] For example, if a user receives a hint saying, "Find out the meaning of the following word," and then searches for the word "example" on Google and finds the answer within a few seconds, the next time the system will offer a more challenging hint, such as, "Find out the meaning of the following sentence."

[0368] Prompt Sentence Examples

[0369] Below are some examples of prompts for generative AI models:

[0370] The user had 10 seconds to find the answer based on the previous hint. Please generate the next hint. Please adjust the difficulty to increase the difficulty.

[0371] (Application example 3)

[0372] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0373] Conventional learning support systems have difficulty tracking a user's learning process individually and optimizing the next learning content and hints based on the results. Furthermore, they have had problems generating hints that do not sufficiently take into account the user's learning ability and interests, making it difficult to provide effective learning support. This can lead to a decrease in the user's learning efficiency and motivation to learn.

[0374] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0375] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user, means for tracking what information the user searches for based on the previous hint and how long it takes to find the answer, and means for optimizing the generation of the next hint based on the tracking results. This makes it possible to individually track the user's learning process and optimize the next learning content and hints based on the results.

[0376] "Generative AI" is an artificial intelligence system that generates information based on user input and provides appropriate hints and answers.

[0377] A "hint" is information that provides clues or directions to help users find the answer themselves.

[0378] "Tracking" is the process of recording what information the user searches for based on the previous hint and how long it takes them to find the answer.

[0379] "Optimization" means adjusting the next hint generation based on the tracking results to maximize the user's learning efficiency.

[0380] "Learning ability" is the user's ability to understand, remember, and apply new information.

[0381] An "interest" is a user's interest or curiosity about a particular topic or activity.

[0382] A "system" is a set of devices and programs that work together with multiple elements such as generative AI, hint provision means, tracking means, and optimization means.

[0383] As an embodiment of this invention, a learning support system is constructed. The system utilizes generative AI and includes a means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user. Furthermore, the system includes a means for tracking what information the user searches for based on the previous hint and how long it takes to find the answer, and a means for optimizing the generation of the next hint based on the tracking results.

[0384] Hardware and software used

[0385] Hardware: Smartphone

[0386] Software: Python, JSON, generative AI models

[0387] System configuration

[0388] 1. Generative AI models: Generate information based on user input and provide appropriate hints and answers.

[0389] 2. Hint methods: provide clues or instructions to help users find the answer themselves.

[0390] 3. Tracking: Record what information the user searches for based on the previous hint and how long it takes them to find the answer.

[0391] 4. Optimization measures: Based on the tracking results, the next hint generation is adjusted to maximize the user's learning efficiency.

[0392] Processing flow

[0393] The server has the ability to adjust the hints and difficulty of the questions provided to the user as they study. It tracks what kind of searches the user performed based on the previous hint and how much time they spent on it, and uses that data to optimize the next hint.

[0394] Specific examples

[0395] For example, if a user receives "Hint 1" and finds the answer in 45 seconds, a more difficult hint will be provided the next time. In this way, the learning process of each user can be tracked individually, and the learning content and hints for the next time can be optimized based on the results.

[0396] Prompt Sentence Examples

[0397] "Write a Python program that tracks what information the user searches for based on the previous hint, how long it takes them to find the answer, and then uses that data to optimize the next hint."

[0398] The above is an embodiment of the present invention.

[0399] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0400] Step 1:

[0401] The user enters a question.

[0402] Input: User question text

[0403] Processing: The device receives the user's question and sends it to the generative AI model.

[0404] Output: The question text is passed to the generative AI model.

[0405] Step 2:

[0406] A generative AI model generates hints.

[0407] Input: Question text

[0408] Processing: The server uses a generative AI model to generate hints based on the question text. The generative AI model generates hints taking into account the user's learning ability and interests.

[0409] Output: Hint text

[0410] Step 3:

[0411] The user finds the answer based on the hints.

[0412] Input: Hint text

[0413] Processing: The user searches for information based on the hints and finds the answer. The device records the user's search query and the search time.

[0414] Output: Search query, search time

[0415] Step 4:

[0416] The device tracks the user's activities.

[0417] Input: search query, search time

[0418] Processing: The device records what information the user searches for based on the hints and how long it takes. This data is sent to the server.

[0419] Output: User activity data (search queries, search times)

[0420] Step 5:

[0421] The server will optimize the next hint generation.

[0422] Input: User activity data

[0423] Processing: The server analyzes the user activity data and optimizes the next hint generation. For example, if the user finds the answer in a short time, the server will generate a more difficult hint next time.

[0424] Output: Optimized hint generation parameters

[0425] Step 6:

[0426] The server provides optimized hints to the user.

[0427] Input: Optimized hint generation parameters

[0428] Processing: The server generates the next hint based on the optimized parameters and provides it to the user.

[0429] Output: Next hint text

[0430] The above are the specific processing steps for carrying out the present invention.

[0431] 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.

[0432] "Example 1"

[0433] In one embodiment of the present invention, the generative AI receives a question from a user and generates hints for that question. It uses an emotion engine to recognize the user's emotions and tailors the generation of hints based on those emotions. For example, if the user expresses joy, it generates more positive hints. On the other hand, if the user expresses confusion or anxiety, it generates more specific and detailed hints.

[0434] "Example 2"

[0435] In another embodiment, the emotion engine tracks changes in the user's emotions and optimizes the next hint generation based on the results. For example, if the user expressed a happy emotion in response to the previous hint, the emotion engine generates a similar hint. On the other hand, if the user expressed a dissatisfied emotion in response to the previous hint, the emotion engine uses a different approach in the next hint generation.

[0436] "Example 3"

[0437] In yet another embodiment, the emotion engine recognizes the user's emotion and generates hints based on the emotion, taking into account the user's learning ability and interests. For example, if the user is excited, the emotion engine generates hints to maintain the excitement. If the user is depressed, the emotion engine generates hints to reduce the depression.

[0438] The processing flow of each embodiment will be described below.

[0439] "Example 1"

[0440] Step 1: The generative AI receives a question from the user.

[0441] Step 2: Recognize the user's emotions using the emotion engine.

[0442] Step 3: Adjust the generation of hints based on the recognized emotions.

[0443] Step 4: Provide the adjusted hints to the user.

[0444] "Example 2"

[0445] Step 1: The emotion engine tracks changes in the user's emotions.

[0446] Step 2: Optimize the next hint generation based on the tracked emotion changes.

[0447] Step 3: Provide optimized tips to users.

[0448] "Example 3"

[0449] Step 1: The emotion engine recognizes the user's emotion.

[0450] Step 2: Generate hints that take into account the recognized emotions and the user's learning ability and interests.

[0451] Step 3: Provide the generated hints to the user.

[0452] Example 1

[0453] Next, a description will be given of Example 1 of Form 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."

[0454] Conventional generative AI systems often provide direct answers to user questions, lacking support for users to find answers on their own. Furthermore, they provide uniform answers without considering the user's feelings, which can lead to a decrease in user satisfaction. Furthermore, the lack of technology to provide appropriate hints based on the user's feelings can leave users feeling confused and anxious.

[0455] 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.

[0456] In this invention, the server includes means for a user to input a question, means for the server to receive the question, means for the server to send the question to an emotion engine, means for the emotion engine to analyze the user's emotion, means for the server to send a prompt sentence to the generative AI model, means for the generative AI model to generate a hint, and means for the server to return the generated hint to the user. This makes it possible to provide appropriate hints according to the user's emotion and support the user in finding the answer themselves.

[0457] "User" refers to a person who accesses the system and enters a question.

[0458] The "server" refers to a computer system that receives questions from users, works with an emotion engine and generative AI models to generate hints, and responds to the user.

[0459] "Emotion engine" refers to software or hardware for analyzing a user's question and identifying the user's emotion.

[0460] A "generative AI model" refers to an artificial intelligence model that generates hints to answer a user's question based on a prompt sentence.

[0461] A "prompt sentence" refers to text data that contains instructions for generating hints for a generative AI model.

[0462] A "hint" is information that provides a method or clue for the user to find the answer on their own.

[0463] "Natural language processing technology" refers to technology for analyzing text data and understanding meaning and emotions.

[0464] This invention is a system that utilizes a generative AI model to provide hints to users' questions. The system includes a series of processes: a user inputs a question, a server receives the question, an emotion engine analyzes the user's emotions, a generative AI model generates a prompt sentence to generate a hint, and finally a response to the user.

[0465] Hardware and software used

[0466] server

[0467] The server receives questions from users, works with the emotion engine and generative AI model to generate hints, and responds to the users. The server is a computer system equipped with a high-performance processor and sufficient memory.

[0468] Terminal

[0469] A terminal is a device that allows users to access the system and input questions. Terminals include PCs, smartphones, tablets, etc.

[0470] Emotion Engine

[0471] The emotion engine is software that analyzes user questions and identifies their emotions. It uses natural language processing technology to analyze emotions from text data.

[0472] Generative AI Models

[0473] A generative AI model is an artificial intelligence model that generates hints for a user's question based on a prompt sentence. The generative AI model is trained using deep learning techniques.

[0474] Data processing and calculation

[0475] When the server receives a question from a user, it sends the question to the emotion engine, which uses natural language processing technology to analyze the question text and identify the user's emotion. The analysis results are sent back to the server, which then sends a prompt to the generative AI model based on the results.

[0476] The generative AI model receives the prompt sentence and generates appropriate hints according to the user's emotions. The generated hints are sent back to the server, which then responds to the user.

[0477] Specific examples

[0478] For example, consider the case where a user uses a terminal to input a question such as "What's the weather like in Tokyo?" The server receives this question and sends it to the emotion engine. The emotion engine analyzes the question to determine that the user is expressing the emotion of happiness, and sends the result back to the server.

[0479] The server sends the following prompt to the generative AI model:

[0480] The user asks "What's the weather in Tokyo?" and expresses joy. Generate a positive hint.

[0481] Based on this prompt, the generative AI model generates a hint: "Why don't you check the weather forecast website?" The server returns this hint to the user, who can then check it on their device.

[0482] In this way, the system provides appropriate hints according to the user's emotions and helps the user find the answer by themselves.

[0483] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0484] Step 1:

[0485] The user inputs a question using a terminal. The user opens the terminal's browser, accesses the system's web page, enters "What's the weather in Tokyo?" in the search bar, and presses the send button. The input data is sent to the server in text format.

[0486] Step 2:

[0487] The server receives the question. The server receives the HTTP request and extracts the text "What's the weather in Tokyo?" from the request body. This text is temporarily stored in memory. The input is the user's question text, and the output is the extracted text data.

[0488] Step 3:

[0489] The server sends a question to the emotion engine. The server uses the REST API to send the text "What's the weather in Tokyo?" to the emotion engine. The API request contains text data. The input is the extracted text data, and the output is the API request to the emotion engine.

[0490] Step 4:

[0491] The emotion engine analyzes the user's emotions. The emotion engine analyzes the received text using a natural language processing algorithm and determines that the user is expressing the emotion of joy. The result is sent back to the server in JSON format. The input is text data, and the output is the JSON data of the analysis results.

[0492] Step 5:

[0493] The server sends a prompt to the generative AI model. Based on the analysis results obtained from the emotion engine, the server sends a prompt to the generative AI model saying, "The user is expressing joy. Please generate a positive hint." The prompt is sent as an API request. The input is the JSON data of the analysis results, and the output is the prompt to the generative AI model.

[0494] Step 6:

[0495] The generative AI model generates a hint. The generative AI model receives the prompt and generates a hint such as "Why not check the weather forecast website?" This hint is sent back to the server in text format. The input is the prompt, and the output is the generated hint text data.

[0496] Step 7:

[0497] The server returns the generated hint to the user. The server sends the hint received from the generative AI model back to the user as an HTTP response. The user can check the hint "Why don't you check the weather forecast website?" in the browser on their device. The input is the text data of the generated hint, and the output is the HTTP response to the user.

[0498] (Application example 1)

[0499] Next, a description will be given of Application Example 1 of Embodiment 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."

[0500] Conventional generative AI systems often provide direct answers to user questions, making it difficult for users to develop the ability to find answers on their own. Furthermore, they provide uniform hints without considering the user's feelings, which means they are unable to provide appropriate support based on the user's situation and emotions. For security-related questions in particular, it is necessary to provide specific and useful hints while easing the user's anxiety.

[0501] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for utilizing generative AI to provide hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for adjusting the generation of hints based on the user's emotions using an emotion engine that recognizes the user's emotions, and means for providing solutions and hints when the user asks a security question. This makes it possible to provide appropriate hints according to the user's emotions and develop the user's ability to find answers on their own.

[0502] "Generative AI" is an artificial intelligence technology that generates new information and answers based on user input.

[0503] An "emotion engine" is a technology that recognizes a user's emotions and adjusts the system's response based on those emotions.

[0504] A "hint" is information that provides clues or methods to help users find the answer themselves.

[0505] "Security" refers to the technologies and methods used to protect information and systems from unauthorized access and attacks.

[0506] A "question" is an inquiry a user makes to the system about information they want to know or a problem they want to solve.

[0507] "Solutions" are information that provides specific solutions or steps to address problems or questions users face.

[0508] "User" refers to any individual or organization that uses the System.

[0509] "Adjustment" refers to changing the system's responses and hints based on the user's emotions and situation.

[0510] The system for implementing this invention consists of a server including a generative AI, an emotion engine, and a user interface, and a terminal used by the user.

[0511] System Program

[0512] Program processing explanation

[0513] 1. Input Processing:

[0514] The user enters the question in text format using a device such as a smartphone or PC.

[0515] Hardware used: Smartphone, PC

[0516] Software used: Text input interface

[0517] 2. Emotion recognition:

[0518] The server receives the user's input text and recognizes the user's emotion using an emotion engine.

[0519] Software used: Emotion recognition API (e.g. IBM Watson(R) Tone Analyzer)

[0520] 3. Hint generation:

[0521] The server uses a generative AI model to generate hints for the user's questions.

[0522] Software used: Generative AI models (e.g., OpenAI GPT-4)

[0523] 4. Adjusting the hints:

[0524] The server adjusts the generated hints based on the results of the emotion engine.

[0525] Software used: Custom logic

[0526] 5. Output Processing:

[0527] Display tailored hints on the user's device.

[0528] Hardware used: Smartphone, PC

[0529] Software used: Text display interface

[0530] Specific examples

[0531] For example, if a user asks, "I've been receiving a lot of phishing emails lately. What should I do about it?" the system will act as follows:

[0532] 1. The user enters a question using their smartphone.

[0533] 2. The server receives the question and uses the emotion engine to recognize the user's emotion. In this case, it recognizes that the user is feeling anxious.

[0534] 3. The generative AI model learns the characteristics of phishing emails and generates hints such as "Don't open suspicious emails."

[0535] 4. Based on the results of the sentiment engine, the server adjusts to provide more detailed hints, such as "Let's take a look at some specific examples of phishing emails."

[0536] 5. The tailored hints are displayed on the user's smartphone.

[0537] Example prompt sentence:

[0538] User Question: I've been getting a lot of phishing emails lately, what should I do?

[0539] User Emotion: Anxiety

[0540] Tip: Learn the signs of phishing emails and avoid opening suspicious emails. Let's look at some examples of phishing emails.

[0541] In this way, it is possible to provide appropriate hints according to the user's emotions and develop the user's ability to find the answer by themselves.

[0542] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0543] Step 1:

[0544] The user inputs a question in text format using a terminal. The input text is sent to the server through the terminal's text input interface. The input data is the user's question.

[0545] Step 2:

[0546] The server passes the received user question text to the emotion engine. The emotion engine analyzes the text data and recognizes the user's emotion. Specifically, it uses an emotion recognition API (e.g., IBM Watson Tone Analyzer) to extract emotional information from the text. The output is the user's emotional state (e.g., anxiety, joy, confusion).

[0547] Step 3:

[0548] The server passes the user's question text and the emotion engine's output to a generative AI model. The generative AI model (e.g., OpenAI GPT-4) generates hints for the user's question based on these input data. The generated hints are information that provides clues and methods for the user to find the answer themselves.

[0549] Step 4:

[0550] The server adjusts the generated hints based on the results of the emotion engine. Specifically, it changes the content and level of detail of the hints depending on the user's emotional state. For example, if the user is feeling anxious, it adjusts the hints to provide more specific and detailed information. The output is the adjusted hint information.

[0551] Step 5:

[0552] The server sends the adjusted hint information to the user's terminal, which displays the received hint information to the user through a text display interface, allowing the user to find the answer by themselves using the displayed hint.

[0553] In this way, it is possible to provide appropriate hints according to the user's feelings and develop the user's ability to find the answer by themselves.

[0554] Example 2

[0555] Next, a description will be given of Example 2 of Form 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."

[0556] Conventional generative AI systems primarily provide direct answers to user questions, but lack the support required for users to find answers on their own. Furthermore, they do not generate hints that take into account the user's learning ability or interests, and they lack the ability to track changes in the user's emotions to optimize the generation of next hints. This reduces the effectiveness of user learning and reduces satisfaction.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0558] In this invention, the server does not provide direct answers to questions from users, but includes means for providing hints and methods for finding answers on the user's own, means for utilizing generative AI to analyze user input and identify interests, means for generating appropriate hints based on the user's interests, and means for tracking changes in the user's emotions and optimizing the generation of the next hint based on the results. This makes it possible to provide hints that take into account the user's learning ability and interests, and to track changes in the user's emotions and optimize the generation of the next hint.

[0559] "User" means any person or entity that uses the System to enter questions or requests.

[0560] "Generative AI" is a system that uses artificial intelligence technology to generate appropriate answers and hints based on user input.

[0561] A "hint" is information or instructions that help users find the answer themselves.

[0562] "Interests" are the interest or curiosity a user has in a particular field or topic.

[0563] "Emotional changes" refer to the fluctuations in emotions that users show in response to hints and information provided by the system.

[0564] "Optimization" refers to adjusting the system's behavior and output to maximize user learning effectiveness and satisfaction.

[0565] A "server" is a computer system that receives input from the user, uses generative AI and an emotion engine to generate appropriate hints, and returns them to the user.

[0566] "Input" is text data of questions or requests that a user makes to the system.

[0567] "Analysis" is the process by which generative AI analyzes user input to identify interests and intent.

[0568] An "emotion engine" is software that analyzes user reactions and feedback and tracks changes in emotions.

[0569] This invention is a system that uses generative AI to provide hints that take into account the user's learning ability and interests. It also includes an emotion engine that tracks changes in the user's emotions and optimizes the generation of the next hint.

[0570] Hardware and software used

[0571] Hardware: Servers, devices (PCs, smartphones, etc.)

[0572] Software: Generative AI models (e.g., GPT-4), emotion engines, database management systems (e.g., MySQL)

[0573] Specific operation of the system

[0574] 1. Accepting user input

[0575] Terminal: The user uses the terminal to type a question or request. For example, the user types, "Why does it rain?"

[0576] Specific operation: The user enters a question into the input form on the device and clicks the "Submit" button.

[0577] 2. Analyze user interests

[0578] Server: The server receives the user's input and passes it to a generative AI model (e.g., GPT-4), which analyzes the input text and identifies the user's interests.

[0579] What happens: The server passes the user's input to a text analysis engine, which extracts the keyword "science."

[0580] 3. Generate hints

[0581] Server: The generative AI model generates appropriate hints based on the user's interests, such as "Why not explore how water vapor cools to form clouds, which then fall as rain?"

[0582] Specific operation: The server passes the prompt "Please generate a hint from a scientific perspective" to the generative AI model and receives the generated hint.

[0583] 4. Track your emotions

[0584] Server: The emotion engine analyzes the user's reaction and tracks the emotional changes. For example, if the user expresses happiness in response to a hint, it stores that information in a database.

[0585] Specific operation: The server passes the user's response (e.g., feedback form input or facial expression recognition data) to the emotion engine, which analyzes the emotion data and stores it in a database.

[0586] 5. Optimize the next hint generation

[0587] Server: The emotion engine optimizes the next hint generation based on the previous emotion data. For example, if the user expressed dissatisfaction with the previous hint, a different approach will be adopted.

[0588] Specific operation: The server receives feedback from the emotion engine and adjusts the next prompt sentence. For example, it passes a prompt sentence such as "Since the user expressed dissatisfaction with the previous hint, please generate a hint from a different perspective" to the generative AI model.

[0589] Examples and prompts

[0590] Examples:

[0591] User: "Why is it raining?"

[0592] Terminal: User types in a question and clicks the submit button.

[0593] Server: Receives user input and passes it to the generative AI model.

[0594] Generative AI model: Generates hints such as, "Why not investigate how water vapor cools, forming clouds, and then falls as rain?"

[0595] Server: Returns the hint to the user.

[0596] User: Expresses delight at the hint.

[0597] Server: The emotion engine analyzes the user's emotions and optimizes the next hint generation.

[0598] Example prompt sentence:

[0599] "If you determine that the user is interested in science, generate hints from a scientific perspective. For example, if the user asks, 'Why does it rain?' you could provide a hint such as, 'Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?'"

[0600] In this way, the system takes into account the user's interests and emotions and provides the most appropriate tips.

[0601] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0602] Step 1:

[0603] Accepting user input

[0604] Terminal: The user uses the terminal to type a question or request. For example, the user types, "Why does it rain?"

[0605] Input: User question text

[0606] Specific operation: The user enters a question into the input form on the device and clicks the "Submit" button.

[0607] Output: The user's question text is sent to the server.

[0608] Step 2:

[0609] Analyze user interests

[0610] Server: The server receives the user's input and passes it to a generative AI model (e.g., GPT-4), which analyzes the input text and identifies the user's interests.

[0611] Input: User question text

[0612] What happens: The server passes the user's input to a text analysis engine, which extracts the keyword "science."

[0613] Output: Data about the user's interests (e.g., science)

[0614] Step 3:

[0615] Generate hints

[0616] Server: The generative AI model generates appropriate hints based on the user's interests, such as "Why not explore how water vapor cools to form clouds, which then fall as rain?"

[0617] Input: Data about user interests (e.g., science)

[0618] Specific operation: The server passes the prompt "Please generate a hint from a scientific perspective" to the generative AI model and receives the generated hint.

[0619] Output: Generated hint (e.g., "Why not explore how water vapor cools, forms clouds, and then falls as rain?")

[0620] Step 4:

[0621] Providing hints to users

[0622] Server: Returns the generated hint to the user.

[0623] Input: Generated hint

[0624] Specific operation: The server sends the generated hint to the user's device.

[0625] Output: The user receives the hint.

[0626] Step 5:

[0627] Track changes in emotions

[0628] Server: The emotion engine analyzes the user's reaction and tracks the emotional changes. For example, if the user expresses happiness in response to a hint, it stores that information in a database.

[0629] Input: User response data (e.g., feedback form entries or facial recognition data)

[0630] Specific operation: The server passes the user's response to the emotion engine, analyzes the emotion data, and stores it in a database.

[0631] Output: User sentiment data

[0632] Step 6:

[0633] Optimize next hint generation

[0634] Server: The emotion engine optimizes the next hint generation based on the previous emotion data. For example, if the user expressed dissatisfaction with the previous hint, a different approach will be adopted.

[0635] Input: Previous emotion data

[0636] Specific operation: The server receives feedback from the emotion engine and adjusts the next prompt sentence. For example, it passes a prompt sentence such as "Since the user expressed dissatisfaction with the previous hint, please generate a hint from a different perspective" to the generative AI model.

[0637] Output: Optimized prompt statement

[0638] In this way, the system takes into account the user's interests and emotions and provides the most appropriate tips.

[0639] (Application example 2)

[0640] Next, a description will be given of Application Example 2 of Form 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."

[0641] Conventional generative AI systems often provide direct answers to user questions, but lack the ability to assist users in the process of finding answers themselves. Furthermore, they do not generate hints that take into account the user's learning ability or interests, making it difficult to optimize individual learning experiences. Furthermore, they lack the ability to track changes in the user's emotions and optimize the generation of next hints based on those emotions. This makes it difficult to improve the user's motivation to learn and their level of understanding.

[0642] 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.

[0643] In this invention, the server includes means for utilizing a generative AI to provide hints and methods for finding the answer on one's own rather than providing direct answers to questions from the user, means for the generative AI to take the user's learning ability and interests into consideration when generating hints for the user's questions, means for the generative AI to track the process by which the user finds the answer on their own and optimize the generation of the next hint based on the results, means for the generative AI to track changes in the user's emotions and optimize the generation of the next hint based on the results, and means for the generative AI to generate hints based on the user's questions and emotions. This makes it possible to individually optimize the user's learning experience and improve their motivation to learn and their level of understanding.

[0644] "Generative AI" is an artificial intelligence system that generates new information or answers based on user input.

[0645] A "user question" is a question or inquiry that a user enters into the system.

[0646] A "direct answer" is a specific, immediate answer to a user's question.

[0647] "Self-help" refers to the steps or approaches users take to solve a problem on their own.

[0648] A "hint" is information or instructions that help users find an answer.

[0649] "User learning ability" refers to the ability of a user to acquire new knowledge or skills.

[0650] "User interests" refers to the interest a user has in a particular field or topic.

[0651] The "process by which the user finds the answer on their own" refers to the series of activities and thoughts that the user goes through to solve the problem.

[0652] "Optimizing the next hint generation" means making the next hint provided more effective based on the user's previous response and behavior.

[0653] "Changes in user emotion" refers to the fluctuations in emotion that a user displays through their interaction with the system.

[0654] "Hints based on user questions and emotions" are advice or instructions that take into account the user's question and their current emotional state.

[0655] A system for implementing this invention utilizes generative AI to provide hints and methods for users to find the answer themselves, rather than providing direct answers to questions from users. The system takes into account the user's learning ability and interests, tracks the process by which the user finds the answer themselves, and optimizes the generation of the next hint based on the results. It also includes a function to track changes in the user's emotions and optimize the generation of the next hint based on the results.

[0656] Hardware and software used

[0657] Hardware: Smartphone

[0658] Software: OpenAI API, Emotion Recognition Engine API

[0659] System configuration

[0660] 1. Receive the user's question: The user enters the question using their smartphone.

[0661] 2. Emotion detection: Use the emotion recognition API to detect emotions from the user's question.

[0662] 3. Hint Generation: Uses OpenAI API to generate hints based on the user's question and sentiment.

[0663] 4. Providing hints: Displaying the generated hints to the user.

[0664] Processing flow

[0665] When the server receives a question from a user, it first detects the user's emotion using an emotion recognition engine API. Then, it uses the OpenAI API to generate hints based on the user's question and the detected emotion. These hints take into account the user's learning ability and interests, helping the user find the answer on their own. The generated hints are displayed on the smartphone screen.

[0666] Specific examples

[0667] For example, if a user asks "Why is the sky blue?" and the emotion engine detects "interest," the generated hint might be "The sky looks blue because sunlight is scattered by molecules in the atmosphere. Blue light is particularly strongly scattered, which is why the sky looks blue."

[0668] Prompt Sentence Examples

[0669] If you determine that the user is interested in science, provide clues from a scientific perspective. Question: Why is the sky blue? Emotion: Interest

[0670] In this way, the user's learning experience can be individually optimized, improving engagement and comprehension.

[0671] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0672] Step 1:

[0673] A user inputs a question using a smartphone. The input question is sent to the system. The input data is the user's question text, and the output data is the question text sent to the system.

[0674] Step 2:

[0675] The server sends the received question text to the emotion recognition engine API to detect the user's emotion. The input data is the question text, and the output data is the detected emotion information. Specifically, the server passes the question text to the API and receives the emotion information returned from the API.

[0676] Step 3:

[0677] The server generates a hint by sending a prompt to the OpenAI API based on the question text and the detected emotion information. The input data is the question text and emotion information, and the output data is the generated hint text. Specifically, the server generates a prompt, sends it to the OpenAI API, and receives the returned hint text.

[0678] Step 4:

[0679] The server sends the generated hint text to the smartphone and displays it to the user. The input data is the generated hint text, and the output data is the hint text to be displayed on the smartphone. Specifically, the server sends the hint text to the smartphone and displays it on the screen.

[0680] Step 5:

[0681] The user checks the hints and inputs a new question if necessary. The input data is the user's new question text, and the output data is the new question text sent to the system. Specifically, the user inputs a new question into their smartphone and sends it to the system.

[0682] This series of processes makes it possible to individually optimize the user's learning experience and improve their motivation and understanding.

[0683] Example 3

[0684] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0685] Conventional generative AI systems have focused on providing direct answers to users, but this approach fails to fully tap into the user's learning ability and interest. Furthermore, since hint generation does not take into account the user's emotions or behavioral data, it is difficult to provide an individually optimized learning experience.

[0686] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0687] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user, means for recording in a log what information the user searched for based on the previous hint and how long it took them to find the answer, means for recognizing the user's emotions in real time using an emotion engine, means for adjusting the difficulty of the next hint based on the collected behavioral data and emotion data, and means for transmitting the generated hints to the user's device. This makes it possible to provide an individually optimized learning experience that takes into account the user's learning ability and interests.

[0688] "Generative AI" is an artificial intelligence technology that automatically generates answers and hints based on user input.

[0689] A "hint" is information or instructions that help users find the answer themselves.

[0690] "User behavior data" refers to information such as the search keywords used by users when using the system and the time it takes to find an answer.

[0691] The "emotion engine" is a technology that recognizes emotions in real time from the user's facial expressions, voice, etc.

[0692] "Behavioral data" refers to data such as operation history and search history when a user uses the system.

[0693] "Emotion Data" is data regarding the user's emotional state as recognized by the emotion engine.

[0694] "Adjusting the difficulty level" refers to changing the difficulty level of the next hint provided based on the user's behavioral and emotional data.

[0695] "Terminal" means a device (e.g., PC, smartphone) used by a user to access the system.

[0696] "Recording in a log" refers to saving user behavior data in a database or similar.

[0697] "Push notification" is a technology that sends information from a server to a user's device in real time.

[0698] This invention is a system that utilizes generative AI to assist users in the process of finding solutions on their own. The system collects user behavioral and emotional data and optimizes the next hint based on that data. It also recognizes the user's emotions in real time and provides hints based on those emotions.

[0699] Hardware and software used

[0700] Hardware: Servers, terminals (PCs, smartphones)

[0701] Software: Generative AI models (e.g., GPT-4), emotion engines

[0702] Data processing and calculation

[0703] 1. Collection of user behavior data

[0704] The server logs what information the user searches for based on the previous hint and how long it takes to find the answer.

[0705] Example: If a user receives a hint about "Python list operations", searches for "Python list append" in a search engine, and finds the answer in 5 minutes, store the search keywords and time in a database.

[0706] 2. Collecting user sentiment data

[0707] The device uses an emotion engine to recognize the user's emotions in real time.

[0708] Example: While the user is reading the hint, the device camera captures the user's facial expressions, and the emotion engine analyzes them to determine their emotional state, such as "excited" or "depressed." The result of the determination is sent to the server.

[0709] 3. Optimizing hint generation

[0710] The server adjusts the difficulty of the next hint based on the collected behavioral and emotional data.

[0711] Example: If the user quickly finds the answer from the previous hint, the server will generate a more difficult hint next time, such as "Python list comprehension." Also, if the user is excited, the server will generate a challenging hint to maintain the excitement, and if the user is depressed, it will generate an easy hint that gives a sense of accomplishment.

[0712] 4. Providing hints to users

[0713] The server sends the generated hint to the user's terminal.

[0714] Example: The server generates a hint and sends it to the user's device via a push notification, which the user receives. For example, a "challenging hint for the next step" might say, "Try to find out how to filter a list using Python list comprehension."

[0715] Examples of prompt statements

[0716] Sample prompt 1: "Adjust the difficulty of the next hint based on how much information the user searches for and how long it takes them to find the answer based on the previous hint."

[0717] Sample prompt 2: "Recognize the user's emotions and generate appropriate hints based on their emotions. If the user is excited, provide a challenging hint. If the user is depressed, provide an easy hint."

[0718] This system makes it possible to provide an individually optimized learning experience by taking into consideration the learning ability and interests of the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0719] Step 1:

[0720] Collecting user behavior data

[0721] Input: The keyword the user searched for based on the previous hint and the time it took to find the answer.

[0722] Specific behavior: If a user receives a hint about "Python list operations", searches for "Python list append" in a search engine, and finds the answer in 5 minutes, the search keywords and time will be saved in the database.

[0723] Output: Log data with search keywords and time.

[0724] Step 2:

[0725] Collecting user emotion data

[0726] Input: User facial and voice data.

[0727] Specific operation: While the user is reading the hint, the device camera captures the user's facial expressions, which the emotion engine analyzes to determine their emotional state, such as "excited" or "depressed." The result of the determination is sent to the server.

[0728] Output: User's emotional state data.

[0729] Step 3:

[0730] Optimizing hint generation

[0731] Input: User behavioral and emotional data.

[0732] Specific operation: The server adjusts the difficulty of the next hint based on the collected behavioral and emotional data. For example, if the user quickly finds the answer from the previous hint, the server will generate a more difficult hint such as "Python list comprehension." Also, if the user is excited, the server will generate a challenging hint to maintain the user's excitement, and if the user is depressed, the server will generate an easy hint that gives the user a sense of accomplishment.

[0733] Output: Optimized hints.

[0734] Step 4:

[0735] Providing hints to users

[0736] Input: Optimized hints.

[0737] Specific operation: The server generates a hint and sends it to the user's device via push notification, which the user receives. For example, a "challenging hint for the next step" might be "Try to find out how to filter a list using Python list comprehension."

[0738] Output: The hint displayed on the user's terminal.

[0739] (Application example 3)

[0740] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0741] Conventional learning support systems have the problem that it is difficult to maintain learning efficiency and motivation because they do not generate hints that take into account the process by which the user finds the answer or their emotions at that time. In addition, because it is not possible to provide optimal hints based on the user's progress and emotions, it is not possible to provide appropriate learning support for each individual user.

[0742] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0743] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for tracking the process by which the user finds the answer on their own and optimizing the generation of next hints based on the results, means for recognizing the user's emotions and generating hints based on the emotions taking into account the user's learning ability and interests, means for recording the user's search queries and time, means for analyzing the user's emotions, and means for generating optimal hints based on the user's past data and emotions. This makes it possible to improve the user's learning efficiency and maintain their motivation to learn.

[0744] "Generative AI" is an artificial intelligence system that generates appropriate information and hints based on user input.

[0745] "User" means an individual or organization that uses this system to learn or search for information.

[0746] The "answer-finding process" is the series of actions and thought processes that a user takes to arrive at the final answer based on the hints and information provided.

[0747] "Hint generation" is the process of providing information or instructions to help the user find the answer.

[0748] "Optimization" means making adjustments to make the next tip more effective based on the user's past behavior and emotions.

[0749] "Emotion recognition" is a technology that analyzes and identifies a user's emotional state from their facial expressions and behavior.

[0750] "Learning ability" is the user's ability to understand, remember, and apply new information.

[0751] "Interests" are the interest or curiosity a user shows in a particular topic or activity.

[0752] A "search query" is a keyword or phrase that a user enters when searching for information.

[0753] "Tracking time" means measuring and storing the amount of time a user spends on a particular activity.

[0754] "Past data" refers to information such as the user's past actions and search history.

[0755] "Analysis" is the process of examining collected data to find meaning and patterns.

[0756] The system for implementing this invention utilizes generative AI to provide hints and methods for users to find the answer themselves, rather than providing direct answers to questions from users. The system tracks the process by which the user finds the answer themselves and optimizes the generation of hints for the next time based on the results. The system also recognizes the user's emotions and generates hints that take into account the user's learning ability and interests based on those emotions.

[0757] Hardware and software used

[0758] Hardware: Smartphones, cameras

[0759] Software: Python, emotion recognition library, hint generation library

[0760] Data processing and calculation

[0761] 1. Tracking user progress:

[0762] The server records the queries users search and the times they search, allowing it to understand what information users searched for and how long it took them to find the answers.

[0763] 2. Emotion recognition:

[0764] The server uses an emotion recognition library to recognize the user's emotions, for example, by analyzing the user's facial expressions using a camera to identify emotions such as excitement or depression.

[0765] 3. Hint generation:

[0766] The server uses a hint generation library to generate optimal hints based on the user's past data and emotions. For example, if the user found the answer quickly with the previous hint, the server will provide a hint with increased difficulty the next time.

[0767] Specific examples

[0768] Let's say a user is learning "Python Basics." In the previous hint, they were instructed to "research Python variables," and they quickly found the answer. The next time, they will be given a more difficult hint, such as "research the difference between Python lists and dictionaries." Additionally, the camera will analyze the user's facial expressions while they are learning, and if they are excited, they will be given a positive hint, such as "Try a more interesting topic next time!"

[0769] Prompt Sentence Examples

[0770] If the user finds the answer quickly with the previous hint, provide a more difficult hint next time. Also, if the user is excited, generate hints that will maintain that excitement.

[0771] In this way, the user's learning efficiency and motivation can be maximized.

[0772] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0773] Step 1:

[0774] The server records the queries that users search and the time they spend searching. The search queries that users enter while studying and the time they spend on those queries are stored in a database, allowing us to track users' study behavior.

[0775] Input: User's search query, time spent searching

[0776] Output: Search queries stored in the database and time records

[0777] Step 2:

[0778] The server recognizes the user's emotions using an emotion recognition library, capturing the user's facial expressions through a camera and applying emotion recognition algorithms to identify the user's emotional state.

[0779] Input: User's facial expression data

[0780] Output: Perceived user emotional state (e.g. excited, depressed)

[0781] Step 3:

[0782] The server generates optimal hints based on the user's past data and emotions. Using a hint generation library, the server takes into account the user's past search queries, time, and emotional state to generate hints that will be useful for the next learning.

[0783] Input: User's past search queries, time, emotional state

[0784] Output: Optimized hints

[0785] Step 4:

[0786] The server provides the generated hints to the user, and sends a notification to the user's device to display the hints that will be useful for the next study.

[0787] Input: Optimized hints

[0788] Output: Tip displayed on the user's device

[0789] Step 5:

[0790] The user continues learning based on the provided hints, and continues learning by entering a new search query.

[0791] Input: Provided hint

[0792] Output: New search queries and learning progress

[0793] Step 6:

[0794] The server again records the user's search query and time, recognizes emotions, and accumulates data for generating hints next time.

[0795] Input: New search query, time spent searching, user facial expression data

[0796] Output: New search queries stored in the database, along with a timestamp and the perceived emotional state.

[0797] In this way, the server can continuously track the user's learning behavior and emotions and provide optimal hints to maximize the user's learning efficiency and motivation.

[0798] 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.

[0799] 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> ) 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.

[0800] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0801] 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.

[0802] [Second embodiment]

[0803] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0804] 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.

[0805] 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).

[0806] 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.

[0807] 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.

[0808] 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).

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0814] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0815] "Example 1"

[0816] As one embodiment of the present invention, a system utilizing generative AI is provided. This system does not provide a direct answer to a user's question, but rather provides hints and methods for finding the answer on one's own. Specifically, if a user asks, "What's the weather like in Tokyo?", the system will provide a hint such as, "Why don't you check the weather forecast website?"

[0817] "Example 2"

[0818] Furthermore, as another embodiment of the present invention, a system is provided in which a generative AI generates hints taking into account the user's learning ability and interests. Specifically, if the system determines that the user is interested in science, it provides hints from a scientific perspective. For example, if the user asks, "Why does it rain?", the system provides a hint such as, "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?"

[0819] "Example 3"

[0820] Furthermore, as another embodiment of the present invention, a system is provided in which a generative AI tracks the process by which a user finds the answer on their own and optimizes the generation of the next hint based on the results. Specifically, the generation of the next hint is optimized based on information such as what information the user searched for based on the previous hint and how long it took to find the answer. For example, if the user quickly found the answer from the previous hint, it is possible to adjust the system to provide a more difficult hint next time.

[0821] The processing flow of each embodiment will be described below.

[0822] "Example 1"

[0823] Step 1: Receive a question from the user. For example, receive a question like "What's the weather like in Tokyo?"

[0824] Step 2: Generative AI generates a hint for the question, in this case "Why not check the weather website?"

[0825] Step 3: Provide the generated hints to the user.

[0826] "Example 2"

[0827] Step 1: Receive a user question and their interests. For example, receive the question "Why does it rain?" and information that the user is interested in science.

[0828] Step 2: The generative AI generates a hint based on the question and the user's interests. In this case, it generates the hint, "Why not investigate how water vapor cools, forming clouds, and then falls as rain?"

[0829] Step 3: Provide the generated hints to the user.

[0830] "Example 3"

[0831] Step 1: Receive a question from the user and collect information such as what information the user searched for based on the previous hint and how long it took them to find the answer.

[0832] Step 2: The generative AI optimizes the next hint generation based on the collected information. For example, if the user quickly finds the answer from the previous hint, it will generate a more difficult hint next time.

[0833] Step 3: Provide optimized tips to users.

[0834] Example 1

[0835] Next, a description will be given of Example 1 of Form 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."

[0836] Conventional generative AI systems often provide direct answers to user questions, leaving few opportunities for users to develop the ability to find answers on their own. Furthermore, they lack the ability to provide hints that take into account the user's learning ability and interests, resulting in reduced user satisfaction and learning effectiveness. Furthermore, they lack the ability to track the user's process of finding the answer on their own and optimize the generation of next hints based on the results, making continuous learning support difficult.

[0837] 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.

[0838] In this invention, the server includes means for receiving a question from a user, means for analyzing the received question, means for generating a prompt sentence to be input to the generative AI model based on the analysis result, means for inputting the prompt sentence to the generative AI model, means for receiving output from the generative AI model, means for formatting the output from the generative AI model as a hint to be provided to the user, and means for sending the formatted hint to the user. This enables the server to develop the user's ability to find answers on their own and to provide hints that take into account their learning ability and interests. Furthermore, by tracking the user's learning process and optimizing the generation of the next hint, continuous learning support can be realized.

[0839] The "means for receiving a question from a user" is a function that allows the system to receive a question entered by a user.

[0840] The "means for analyzing a received question" is a function for analyzing a received question in order to understand the content of the question and perform appropriate processing.

[0841] "Means for generating prompt sentences to be input to the generative AI model" refers to a function that creates prompt sentences to give appropriate instructions to the generative AI model based on the analysis results.

[0842] "Means for inputting prompt sentences to the generative AI model" refers to a function for sending the generated prompt sentences to the generative AI model, which then generates the appropriate output.

[0843] "Means for receiving output from a generative AI model" refers to a function for receiving the output generated by a generative AI model.

[0844] "Means for formatting the output from a generative AI model as a hint to provide to the user" is a function that formats the output from a generative AI model in a form that is easy for the user to understand.

[0845] The "means for sending formatted hints to the user" is a function for delivering formatted hints to the user.

[0846] A "generative AI model" is an artificial intelligence model that generates appropriate hints and answers to user questions.

[0847] A "prompt sentence" is an input sentence that causes a generative AI model to generate a specific output.

[0848] This invention is a system that utilizes a generative AI model to provide users with hints and methods for finding answers on their own, rather than providing direct answers to questions from users. Specific embodiments of this system are described below.

[0849] Hardware and Software Configuration

[0850] server

[0851] The server receives questions from users, analyzes them, inputs prompts to the generative AI model, receives the output from the generative AI model, formats it, and sends it to the user. The server uses the following software and hardware:

[0852] Natural Language Processing Library: Use a natural language processing library, such as SpaCy or NLTK, to parse the question.

[0853] Generative AI model: For example, OpenAI's GPT-4 is used as the generative AI model.

[0854] Communication protocol: HTTP / HTTPS protocol is used for communication with user terminals.

[0855] Terminal

[0856] The terminal is responsible for inputting questions by the user and receiving and displaying hints from the server. The terminal uses the following software and hardware:

[0857] User interface: Provide a GUI for inputting questions and displaying hints. For example, use a smartphone app or a web browser.

[0858] Communication protocol: Use HTTP / HTTPS protocol to communicate with the server.

[0859] user

[0860] The user uses a terminal to enter a question and receives hints provided by the server.

[0861] Data processing and calculation

[0862] 1. User inputs a question

[0863] The user types a question into an input field on the device, for example, "What's the weather like in Tokyo?"

[0864] 2. Submit your question

[0865] The device sends the question entered by the user to the server using an HTTP request.

[0866] 3. Question Analysis

[0867] The server analyzes the received question using a natural language processing library, for example, extracting keywords such as "weather in Tokyo."

[0868] 4. Prompt generation

[0869] The server generates a prompt sentence to be input to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as, "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast."

[0870] 5. Input to the generative AI model

[0871] The server inputs the generated prompt sentence into a generative AI model, for example, by sending the prompt sentence to the GPT-4 API.

[0872] 6. Obtaining the output of the generative AI model

[0873] The server receives the output from the generative AI model, for example, "Why not check out a weather website?"

[0874] 7. Hint Formatting

[0875] The server formats the output from the generative AI model as hints to provide to the user.

[0876] 8. Submit a Tip

[0877] The server sends the formatted hint to the device using an HTTP response.

[0878] 9. Displaying Hints

[0879] The device displays the hint received from the server to the user, for example, "Why not check out our weather website?"

[0880] Specific examples

[0881] Example 1: Weather question

[0882] User asks: "What's the weather like in Tokyo?"

[0883] Server prompt: "User is asking about the weather in Tokyo. Please suggest a way to check the forecast."

[0884] Generative AI model output: "Why not check out a weather website?"

[0885] Device says: "Why don't you check the weather website?"

[0886] In this way, users can be helped to find information themselves.

[0887] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0888] Step 1:

[0889] User question input

[0890] Subject: User

[0891] Specific operation: The user enters a question into the input field of the device and presses the send button. For example, "What's the weather like in Tokyo?"

[0892] Input: User question (e.g. "What's the weather like in Tokyo?")

[0893] Output: Question typed into the terminal

[0894] Step 2:

[0895] Submit a Question

[0896] Subject: Device

[0897] What happens: The device sends the question entered by the user to the server using an HTTP request.

[0898] Input: Question typed into the terminal

[0899] Output: The question sent to the server

[0900] Step 3:

[0901] Question Analysis

[0902] Subject: Server

[0903] Specific operation: The server analyzes the received question using a natural language processing library (e.g., SpaCy or NLTK). For example, it extracts keywords such as "weather in Tokyo."

[0904] Input: The question sent to the server

[0905] Data processing: Use natural language processing libraries to parse the question and extract keywords.

[0906] Output: Parsed question keywords (e.g. "Weather in Tokyo")

[0907] Step 4:

[0908] Generate prompt statement

[0909] Subject: Server

[0910] Specific operation: Based on the analysis results, the server generates a prompt sentence to be input to the generative AI model. For example, it generates a prompt sentence such as, "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast."

[0911] Input: Keywords from the parsed question

[0912] Data processing: Generate prompt sentences based on keywords.

[0913] Output: The generated prompt (e.g., "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast.")

[0914] Step 5:

[0915] Input to generative AI models

[0916] Subject: Server

[0917] Specific operation: The server inputs the generated prompt sentence into the generative AI model. For example, it sends the prompt sentence to the API of the generative AI model.

[0918] Input: Generated prompt statement

[0919] Output: The prompt sent to the generative AI model

[0920] Step 6:

[0921] Obtaining the output of a generative AI model

[0922] Subject: Server

[0923] What it does: The server receives the output from the generative AI model, for example, "Why don't you check the weather website?"

[0924] Input: The prompt sent to the generative AI model

[0925] Data computation: The generative AI model generates output based on the prompt.

[0926] Output: The output from the generative AI model (e.g., "Why not check out a weather website?")

[0927] Step 7:

[0928] Hint formatting

[0929] Subject: Server

[0930] What it does: The server formats the output from the generative AI model as hints to provide to the user.

[0931] Input: Output from a generative AI model

[0932] Data processing: Formatting the output to make it easier for users to understand.

[0933] Output: A formatted hint (e.g., "Why not check out the weather website?")

[0934] Step 8:

[0935] Submit a tip

[0936] Subject: Server

[0937] Specific operation: The server sends the formatted hint to the device using an HTTP response.

[0938] Input: Formatted hint

[0939] Output: Hints sent to the terminal

[0940] Step 9:

[0941] Show Hints

[0942] Subject: Device

[0943] What happens: The device displays the hint received from the server to the user, for example, "Why not check out the weather website?"

[0944] Input: Hint sent to terminal

[0945] Output: The hint displayed to the user

[0946] (Application example 1)

[0947] Next, a description will be given of Application Example 1 of Form 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."

[0948] Conventional generative AI systems often provide direct answers to user questions, leaving few opportunities for users to develop the ability to find answers on their own. Furthermore, in physical stores, it is difficult for users to quickly obtain information about products and stores, resulting in an inconvenient shopping experience. To solve these issues, a system is needed that provides users with hints and methods for finding answers on their own.

[0949] 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.

[0950] In this invention, the server includes means for utilizing generative AI to provide hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for the generative AI to take the user's learning ability and interests into consideration when generating hints for the user's questions, means for the generative AI to track the process by which the user finds the answer on their own and optimize the generation of next hints based on the results, and means for providing hints and methods for finding answers when the user asks a question about a product or a store in a physical store. This enables users to develop their ability to find answers on their own while improving their shopping experience in the physical store.

[0951] "Generative AI" is a type of artificial intelligence that generates new information and answers based on user input.

[0952] A "hint" is information that provides clues or directions to help users find the answer themselves.

[0953] "Learning ability" is the user's ability to understand and apply new information.

[0954] An "interest" is a user's interest or curiosity about a particular piece of information or activity.

[0955] "Tracking" is the process of recording and analyzing user actions and choices.

[0956] "Optimization" refers to adjusting and improving a system or process to achieve a specific purpose.

[0957] A "brick and mortar store" is a store that exists in a physical location and offers goods and services.

[0958] A "guide map" is a diagram showing the layout of a store and the locations of products.

[0959] A "prompt sentence" is an input sentence that instructs a generative AI to generate specific information.

[0960] To implement this invention, it is necessary to build a system that utilizes generative AI. This system does not provide direct answers to questions from users, but rather provides methods and hints for finding answers. A specific embodiment of this system is described below.

[0961] System configuration

[0962] The system consists of the following main components:

[0963] 1. Generative AI model: An artificial intelligence model that generates hints in response to user questions. Specifically, we use OpenAI's generative AI model.

[0964] 2. User device: The device on which the user enters the question, such as a smartphone or tablet.

[0965] 3. Server: A server for hosting the generative AI model and processing user queries.

[0966] Program processing

[0967] The server processes the data as follows:

[0968] 1. Receive user question: A question is sent from the user's device.

[0969] 2. Prompt generation: The server generates a prompt based on the user's question. For example, if the user asks, "Where is this product?", the prompt will be, "When the user asks, 'Where is this product?', please provide hints to help them find the answer, rather than a direct answer."

[0970] 3. Generate hints using a generative AI model: The server sends a prompt to the generative AI model to generate a hint.

[0971] 4. Providing hint to user: The generated hint is sent to the user's terminal and displayed to the user.

[0972] Hardware and software used

[0973] Hardware: smartphones, tablets, servers

[0974] Software: Python, OpenAI API

[0975] Specific examples

[0976] When a user asks "Where is this item?" in a physical store, the system works as follows:

[0977] 1. A question is sent from the user device to the server.

[0978] 2. The server generates a prompt based on the question.

[0979] 3. Prompt: "When a user asks, 'Where is this item?', provide a hint to help them find the answer, rather than a direct answer."

[0980] 4. The server sends a prompt to the generative AI model to generate a hint.

[0981] 5. Generated hint: "Please check the store map. It's located near the entrance."

[0982] 6. The hint is sent to the user's device and displayed to the user.

[0983] In this way, users can develop their ability to find answers on their own while improving their in-store shopping experience.

[0984] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0985] Step 1:

[0986] The user types a question.

[0987] Users input questions using devices such as smartphones or tablets, and the input questions are sent from the device to the server.

[0988] Input: User question (e.g., "Where is this item?")

[0989] Output: The question data sent to the server

[0990] Step 2:

[0991] The server receives the query.

[0992] The server receives question data sent from the user terminal, analyzes the received question data, and prepares to generate a prompt sentence.

[0993] Input: User question data

[0994] Output: Parsed question data

[0995] Step 3:

[0996] The server generates a prompt.

[0997] The server generates a prompt based on the parsed question data. For example, if the user's question is "Where is this product?", the prompt will be "When the user asks, 'Where is this product?', please provide a hint to help them find the answer, rather than a direct answer."

[0998] Input: Parsed question data

[0999] Output: Generated prompt statement

[1000] Step 4:

[1001] The server sends a prompt to the generative AI model.

[1002] The server sends the generated prompt sentence to the generative AI model, instructing it to generate a hint.

[1003] Input: Generated prompt text

[1004] Output: The prompt sent to the generative AI model

[1005] Step 5:

[1006] A generative AI model generates hints.

[1007] The generative AI model generates hints based on the prompt it receives, such as "Please check the store map. It's located near the entrance."

[1008] Input: A prompt sent to the generative AI model

[1009] Output: Generated hints

[1010] Step 6:

[1011] The server receives the generated hint.

[1012] The server receives the hints generated by the generative AI model and prepares them to be sent to the user's device.

[1013] Input: Generated hint

[1014] Output: Hint data sent to the user's device

[1015] Step 7:

[1016] The user device receives the hint.

[1017] The user terminal receives the hint data sent from the server and displays it to the user.

[1018] Input: Hint data sent from the server

[1019] Output: A hint to be displayed to the user (e.g., "Please check the store map. It's located near the entrance.")

[1020] This way, users can get hints to find the answer themselves.

[1021] Example 2

[1022] Next, a description will be given of Example 2 of Form 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."

[1023] In conventional systems using generative AI, it has become common to provide direct answers to user questions. However, this makes it difficult for users to develop the ability to find answers on their own, and the learning effect is limited. Furthermore, there are few systems that provide hints that take into account the user's interests and learning ability, and there is an issue that learning support optimized for individual users is not being provided sufficiently.

[1024] 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 the user to input a question, a means for the terminal to send the question to the server, a means for the server to receive the question and analyze the user's interests and learning ability, a means for the server to input a prompt sentence to the generative AI model, a means for the generative AI model to generate a hint, a means for the server to receive the generated hint and send it to the terminal, and a means for the terminal to display the hint to the user. This allows the user to obtain appropriate hints according to their interests and learning ability, improving the learning effect.

[1025] "User" refers to an individual who utilizes the system to enter questions and receive hints.

[1026] "Terminal" refers to the device through which the user inputs questions and communicates with the server. Specifically, this includes smartphones and personal computers.

[1027] "Server" refers to a central processing unit that receives questions from users, generates hints using a generative AI model, and sends them to the terminal.

[1028] "Generative AI model" refers to an artificial intelligence model that generates appropriate hints in response to user questions. Specifically, it includes models that use natural language processing technology.

[1029] A "prompt sentence" is a sentence input to a generative AI model that includes the user's question and the analysis results.

[1030] A "hint" is information that provides clues or methods for users to find the answer themselves.

[1031] A "question" refers to a question or problem that a user inputs into the system.

[1032] "Analysis" refers to the processing of data by the server to assess the user's interests and learning ability.

[1033] "Learning ability" refers to the ability of a user to acquire new knowledge or skills.

[1034] "Interests" refer to the interest a user has in a particular field or topic.

[1035] This invention relates to a system that allows a user to input a question and provides appropriate hints using a generative AI model. Specific embodiments of this system are described below.

[1036] First, the user inputs a question using a terminal. The terminal can be a device such as a smartphone or a PC. The question input by the user is sent from the terminal to a server. The terminal then sends the data to the server via the Internet.

[1037] The server receives the questions sent from the device and then analyzes the user's interests and learning ability based on the user's past question history and profile information. This analysis is performed using a database and machine learning algorithms.

[1038] The server generates a prompt based on the user's question and the analysis results. The prompt is a sentence that is input to the generative AI model and includes the user's question and the analysis results. For example, a prompt might be generated that reads, "It has been determined that the user is interested in science. The user's question is, 'Why does it rain?' Please provide appropriate hints from a scientific perspective."

[1039] Next, the server inputs this prompt into a generative AI model. A model using natural language processing technology (such as GPT-4) is used as the generative AI model. The generative AI model generates an appropriate hint for the user's question based on the prompt. For example, a hint such as "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?" is generated.

[1040] The server receives the hints generated from the generative AI model. The server then sends the hints to the user's device. The device receives the hints sent from the server and displays them to the user. The user can check the hints on the device screen.

[1041] As a concrete example, consider the case where a user inputs the question "Why does it rain?" The device sends this question to the server. The server receives the question and determines that the user is interested in science because they have asked many science-related questions in the past. The server inputs the following prompt to the generative AI model: "It has been determined that the user is interested in science. The user's question is 'Why does it rain?' Please provide an appropriate hint from a scientific perspective." The generative AI model generates the hint: "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?" The server sends this hint to the device, and the device displays it to the user. The user can check the hint on the device screen and obtain an answer from a scientific perspective.

[1042] In this way, users can obtain appropriate hints according to their interests and learning abilities, improving their learning effectiveness.

[1043] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1044] Step 1:

[1045] The user inputs a question. The user uses a device (smartphone or PC) to input a question to the system. For example, the user might input "Why does it rain?" The input question is stored in the device's memory.

[1046] Step 2:

[1047] The terminal sends a question to the server. The terminal sends a question entered by the user to the server via the Internet. The input data is the user's question text. The output data is the question text sent to the server.

[1048] Step 3:

[1049] The server receives the question and analyzes the user's interests and learning ability. The server receives the question sent from the terminal. The server then accesses a database to obtain the user's past question history and profile information. The input data is the question text and the user's past question history and profile information. The server analyzes this data and evaluates the user's interests and learning ability. The output data is the analysis results regarding the user's interests and learning ability.

[1050] Step 4:

[1051] The server inputs a prompt sentence into the generative AI model. The server generates a prompt sentence based on the user's question and the analysis results. For example, it generates a prompt sentence such as, "It has been determined that the user is interested in science. The user's question is 'Why does it rain?' Please provide appropriate hints from a scientific perspective." The input data is the question text and the analysis results. The output data is the generated prompt sentence.

[1052] Step 5:

[1053] The generative AI model generates a hint. The server inputs the generated prompt sentence into the generative AI model. The generative AI model (for example, a model using natural language processing technology) generates an appropriate hint for the user's question based on the prompt sentence. For example, it generates the hint, "Why not investigate the process by which water vapor cools, forms clouds, and then falls as rain?" The input data is the prompt sentence. The output data is the generated hint.

[1054] Step 6:

[1055] The server receives the generated hint and sends it to the terminal. The server receives the hint generated from the generative AI model. The server then sends this hint to the user's terminal. The input data is the generated hint. The output data is the hint sent to the terminal.

[1056] Step 7:

[1057] The terminal displays the hint to the user. The terminal receives the hint sent from the server and displays it to the user. The user can check the hint on the terminal screen. The input data is the hint sent from the server. The output data is the hint displayed on the terminal screen.

[1058] (Application example 2)

[1059] Next, a description will be given of Application Example 2 of Form 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."

[1060] Conventional generative AI systems often provide direct answers to user questions, making it difficult for users to develop the ability to find answers on their own. They also lack the ability to provide hints that take into account the user's learning ability and interests, resulting in reduced learning efficiency. Furthermore, they lack the ability to analyze the user's past learning history and interests to optimize the generation of next hints, making it difficult to provide continuous learning support.

[1061] 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.

[1062] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for generating hints taking into account the user's learning ability and interests, means for analyzing the user's past learning history and interests, and means for generating hints based on the generated prompt sentences. This enables the user to develop the ability to find answers on their own and improve learning efficiency. Furthermore, continuous learning support can be realized by analyzing the user's past learning history and interests to optimize the generation of next hints.

[1063] "Generative AI" is an artificial intelligence system that generates answers and hints in natural language based on user input.

[1064] "User learning ability" refers to the ability of a user to acquire new knowledge or skills.

[1065] "User interests" refers to the interest a user has in a particular field or topic.

[1066] A "hint" is a clue or suggestion that helps users find the answer themselves.

[1067] A "prompt sentence" is an input sentence that a generative AI uses to generate appropriate hints in response to a user's question.

[1068] "Learning history" refers to a record of a user's past learning content and activities.

[1069] "Optimization" is the adjustment of systems or processes to maximize efficiency and effectiveness in order to achieve a specific purpose.

[1070] A system for implementing this invention utilizes generative AI to provide hints and methods for finding answers on one's own, rather than providing direct answers to questions from users. The system has a function for generating hints that takes into account the user's learning ability and interests, and a function for analyzing the user's past learning history and interests. It also includes a function for generating hints based on generated prompt sentences.

[1071] The server receives the user's question and profile as input and analyzes the user's interests. Specifically, it identifies areas of interest from the user's profile and generates an appropriate prompt for the user's question. Based on the generated prompt, the generative AI generates hints and provides them to the user.

[1072] This system is implemented using OpenAI's API, which uses a generative AI model to generate answers and hints in natural language. The server receives the user's question and profile, generates a prompt, and sends it to OpenAI's API. The hints returned by the API are then provided to the user.

[1073] As a concrete example, if a user asks "Why does it rain?" and the user profile contains "science", the generated prompt would be:

[1074] We've determined that you're interested in science. Please provide some scientific clues to the following questions:

[1075] Question: Why does it rain?

[1076] Tip:

[1077] By inputting this prompt into the OpenAI API, an appropriate hint is generated, such as "Why not investigate the process by which water vapor cools, forms clouds, and then falls as rain?"

[1078] This system allows users to develop the ability to find answers on their own and improve their learning efficiency. It also provides continuous learning support by analyzing the user's past learning history and interests to optimize the generation of next hints.

[1079] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1080] Step 1:

[1081] The user enters a question.

[1082] The user inputs a question using a terminal and sends it to the server. The input data is the user's question and profile information.

[1083] Step 2:

[1084] The server analyzes the user's interests.

[1085] The server analyzes the received user profile information and identifies the user's areas of interest. Specifically, it extracts areas of interest (e.g., science, technology, etc.) contained in the profile information. The input is the user's profile information, and the output is the user's areas of interest.

[1086] Step 3:

[1087] The server generates a prompt.

[1088] The server generates a prompt based on the user's question and interests. Specifically, it creates a prompt using a template based on the user's interests. The input is the user's question and interests, and the output is the generated prompt.

[1089] Step 4:

[1090] The server calls the generative AI model.

[1091] The server sends the generated prompt to the OpenAI API and generates appropriate hints. The input is the generated prompt, and the output is the hint returned by the generative AI model.

[1092] Step 5:

[1093] The server provides the hint to the user.

[1094] The server sends the generated hints to the user's device and displays them to the user. The input is the hint returned from the generative AI model, and the output is the hint displayed on the user's device.

[1095] Step 6:

[1096] The server updates the user's learning history.

[1097] The server tracks the hints received by the user and their subsequent actions, and updates the learning history. Specifically, it records what hints the user received and what actions they took based on them. The input is the user's behavioral data, and the output is the updated learning history.

[1098] Step 7:

[1099] The server will optimize the next hint generation.

[1100] The server optimizes the next hint generation based on the updated learning history. Specifically, it analyzes the past learning history and adjusts the algorithm to provide optimal hints based on the user's learning patterns. The input is the updated learning history, and the output is the optimized hint generation algorithm.

[1101] Example 3

[1102] Next, a description will be given of Example 3 of Form Example 3. 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."

[1103] Conventional generative AI systems have focused on providing direct answers to users, and lacked the means to support users in the process of finding the answer themselves. Furthermore, hints were not generated taking into account the user's learning ability or interests, making it difficult to provide learning support optimized for each individual user. Furthermore, there was no mechanism to utilize user behavior data to optimize the generation of next hints, making it impossible to improve users' learning efficiency.

[1104] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes: a means for utilizing generative AI to provide hints and methods for finding the answer on one's own, rather than providing a direct answer to a question from a user; a means for tracking user behavior and collecting behavioral data such as search keywords, viewed web pages, and the time it took to find the answer; a means for storing the collected behavioral data in a database and using it to generate the next hint; and a means for the generative AI model to analyze the stored behavioral data and optimize the next hint. This makes it possible to support the process of users finding the answer on their own and provide hints optimized for each user.

[1105] "Generative AI" is an artificial intelligence system that generates answers and hints in natural language based on user input.

[1106] "User" means an individual or entity that uses the system to ask questions and obtain clues and answers.

[1107] A "hint" is information that provides clues or directions to help users find the answer themselves.

[1108] "Behavioral data" refers to information such as search keywords generated when users use the system, the web pages they view, and the time it takes them to find an answer.

[1109] A "database" is a system for storing and managing collected behavioral data.

[1110] A "generative AI model" is an algorithm or program that analyzes collected behavioral data and generates hints for the next time.

[1111] "Optimization" is the process of adjusting the difficulty and content of the next hint based on user behavior data.

[1112] This invention is a system that utilizes generative AI to support users in the process of finding solutions themselves. A specific embodiment of this system is described below.

[1113] Hardware and software used

[1114] Hardware: Servers, user devices (PCs, smartphones, etc.)

[1115] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), web browsers (e.g., Google Chrome)

[1116] System Overview

[1117] This system tracks user behavior and optimizes the generation of the next hint based on the collected behavioral data. Specifically, it optimizes the generation of the next hint based on information such as what information the user searched for based on the previous hint and how long it took them to find the answer.

[1118] Program processing

[1119] 1. User behavior tracking:

[1120] A user logs in to the system using a terminal.

[1121] The server provides the user with initial hints using a generative AI model.

[1122] The user searches for information based on the hints, and behavioral data such as the search engine used, the URL of the web page viewed, and search keywords are sent from the device to the server.

[1123] The server tracks user behavior data in real time and measures the time it takes to find the answer.

[1124] 2. Data Collection and Storage:

[1125] The server collects user behavior data.

[1126] The server stores the collected data in a database management system (e.g., MySQL).

[1127] The server organizes and analyzes the stored data to use in generating next hints.

[1128] 3. Hint generation optimization:

[1129] The server analyzes the user behavior data stored in the database.

[1130] The generative AI model generates the next hint based on the analysis results.

[1131] The server provides the generated hint to the user.

[1132] Specific examples

[1133] For example, if a user receives a hint saying, "Find out the meaning of the following word," and then searches for the word "example" on Google and finds the answer within a few seconds, the next time the system will offer a more challenging hint, such as, "Find out the meaning of the following sentence."

[1134] Prompt Sentence Examples

[1135] Below are some examples of prompts for generative AI models:

[1136] The user had 10 seconds to find the answer based on the previous hint. Please generate the next hint. Please adjust the difficulty to increase the difficulty.

[1137] In this way, the system can optimize the user's learning process and provide more effective hints. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1138] Step 1: Track user behavior

[1139] Input: The user logs into the system using a terminal and receives an initial hint.

[1140] Specific operation: The server uses the generative AI model to provide the user with an initial hint, and the user begins searching for information based on the hint.

[1141] Data processing: Behavioral data such as the search engine used by the user, the URL of the web page viewed, and search keywords are sent from the device to the server.

[1142] Output: The server tracks user behavior data in real time and measures the time it takes to find the answer.

[1143] Step 2: Collect and store data

[1144] Input: The server receives user behavior data.

[1145] What it does: The server collects behavioral data such as users' search keywords, the URLs of web pages they visited, and the time it took them to find an answer.

[1146] Data processing: The collected behavioral data is stored in a database management system (e.g., MySQL).

[1147] Output: The server organizes and analyzes the stored data for use in generating next hints.

[1148] Step 3: Optimizing hint generation

[1149] Input: The server receives user behavior data stored in a database.

[1150] Specific operation: The server analyzes the behavioral data and generates the next hint taking into account the user's learning ability and interests.

[1151] Data processing: The generative AI model generates the next hint based on the analysis results.

[1152] Output: The server provides the generated hint to the user.

[1153] Specific examples

[1154] For example, if a user receives a hint saying, "Find out the meaning of the following word," and then searches for the word "example" on Google and finds the answer within a few seconds, the next time the system will offer a more challenging hint, such as, "Find out the meaning of the following sentence."

[1155] Prompt Sentence Examples

[1156] Below are some examples of prompts for generative AI models:

[1157] The user had 10 seconds to find the answer based on the previous hint. Please generate the next hint. Please adjust the difficulty to increase the difficulty.

[1158] (Application example 3)

[1159] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1160] Conventional learning support systems have difficulty tracking a user's learning process individually and optimizing the next learning content and hints based on the results. Furthermore, they have had problems generating hints that do not sufficiently take into account the user's learning ability and interests, making it difficult to provide effective learning support. This can lead to a decrease in the user's learning efficiency and motivation to learn.

[1161] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1162] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user, means for tracking what information the user searches for based on the previous hint and how long it takes to find the answer, and means for optimizing the generation of the next hint based on the tracking results. This makes it possible to individually track the user's learning process and optimize the next learning content and hints based on the results.

[1163] "Generative AI" is an artificial intelligence system that generates information based on user input and provides appropriate hints and answers.

[1164] A "hint" is information that provides clues or directions to help users find the answer themselves.

[1165] "Tracking" is the process of recording what information the user searches for based on the previous hint and how long it takes them to find the answer.

[1166] "Optimization" means adjusting the next hint generation based on the tracking results to maximize the user's learning efficiency.

[1167] "Learning ability" is the user's ability to understand, remember, and apply new information.

[1168] An "interest" is a user's interest or curiosity about a particular topic or activity.

[1169] A "system" is a set of devices and programs that work together with multiple elements such as generative AI, hint provision means, tracking means, and optimization means.

[1170] As an embodiment of this invention, a learning support system is constructed. The system utilizes generative AI and includes a means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user. Furthermore, the system includes a means for tracking what information the user searches for based on the previous hint and how long it takes to find the answer, and a means for optimizing the generation of the next hint based on the tracking results.

[1171] Hardware and software used

[1172] Hardware: Smartphone

[1173] Software: Python, JSON, generative AI models

[1174] System configuration

[1175] 1. Generative AI models: Generate information based on user input and provide appropriate hints and answers.

[1176] 2. Hint methods: provide clues or instructions to help users find the answer themselves.

[1177] 3. Tracking: Record what information the user searches for based on the previous hint and how long it takes them to find the answer.

[1178] 4. Optimization measures: Based on the tracking results, the next hint generation is adjusted to maximize the user's learning efficiency.

[1179] Processing flow

[1180] The server has the ability to adjust the hints and difficulty of the questions provided to the user as they study. It tracks what kind of searches the user performed based on the previous hint and how much time they spent on it, and uses that data to optimize the next hint.

[1181] Specific examples

[1182] For example, if a user receives "Hint 1" and finds the answer in 45 seconds, a more difficult hint will be provided the next time. In this way, the learning process of each user can be tracked individually, and the learning content and hints for the next time can be optimized based on the results.

[1183] Prompt Sentence Examples

[1184] "Write a Python program that tracks what information the user searches for based on the previous hint, how long it takes them to find the answer, and then uses that data to optimize the next hint."

[1185] The above is an embodiment of the present invention.

[1186] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1187] Step 1:

[1188] The user enters a question.

[1189] Input: User question text

[1190] Processing: The device receives the user's question and sends it to the generative AI model.

[1191] Output: The question text is passed to the generative AI model.

[1192] Step 2:

[1193] A generative AI model generates hints.

[1194] Input: Question text

[1195] Processing: The server uses a generative AI model to generate hints based on the question text. The generative AI model generates hints taking into account the user's learning ability and interests.

[1196] Output: Hint text

[1197] Step 3:

[1198] The user finds the answer based on the hints.

[1199] Input: Hint text

[1200] Processing: The user searches for information based on the hints and finds the answer. The device records the user's search query and the search time.

[1201] Output: Search query, search time

[1202] Step 4:

[1203] The device tracks the user's activities.

[1204] Input: search query, search time

[1205] Processing: The device records what information the user searches for based on the hints and how long it takes. This data is sent to the server.

[1206] Output: User activity data (search queries, search times)

[1207] Step 5:

[1208] The server will optimize the next hint generation.

[1209] Input: User activity data

[1210] Processing: The server analyzes the user activity data and optimizes the next hint generation. For example, if the user finds the answer in a short time, the server will generate a more difficult hint next time.

[1211] Output: Optimized hint generation parameters

[1212] Step 6:

[1213] The server provides optimized hints to the user.

[1214] Input: Optimized hint generation parameters

[1215] Processing: The server generates the next hint based on the optimized parameters and provides it to the user.

[1216] Output: Next hint text

[1217] The above are the specific processing steps for carrying out the present invention.

[1218] 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.

[1219] "Example 1"

[1220] In one embodiment of the present invention, the generative AI receives a question from a user and generates hints for that question. It uses an emotion engine to recognize the user's emotions and tailors the generation of hints based on those emotions. For example, if the user expresses joy, it generates more positive hints. On the other hand, if the user expresses confusion or anxiety, it generates more specific and detailed hints.

[1221] "Example 2"

[1222] In another embodiment, the emotion engine tracks changes in the user's emotions and optimizes the next hint generation based on the results. For example, if the user expressed a happy emotion in response to the previous hint, the emotion engine generates a similar hint. On the other hand, if the user expressed a dissatisfied emotion in response to the previous hint, the emotion engine uses a different approach in the next hint generation.

[1223] "Example 3"

[1224] In yet another embodiment, the emotion engine recognizes the user's emotion and generates hints based on the emotion, taking into account the user's learning ability and interests. For example, if the user is excited, the emotion engine generates hints to maintain the excitement. If the user is depressed, the emotion engine generates hints to reduce the depression.

[1225] The processing flow of each embodiment will be described below.

[1226] "Example 1"

[1227] Step 1: The generative AI receives a question from the user.

[1228] Step 2: Recognize the user's emotions using the emotion engine.

[1229] Step 3: Adjust the generation of hints based on the recognized emotions.

[1230] Step 4: Provide the adjusted hints to the user.

[1231] "Example 2"

[1232] Step 1: The emotion engine tracks changes in the user's emotions.

[1233] Step 2: Optimize the next hint generation based on the tracked emotion changes.

[1234] Step 3: Provide optimized tips to users.

[1235] "Example 3"

[1236] Step 1: The emotion engine recognizes the user's emotion.

[1237] Step 2: Generate hints that take into account the recognized emotions and the user's learning ability and interests.

[1238] Step 3: Provide the generated hints to the user.

[1239] Example 1

[1240] Next, a description will be given of Example 1 of Form 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."

[1241] Conventional generative AI systems often provide direct answers to user questions, lacking support for users to find answers on their own. Furthermore, they provide uniform answers without considering the user's feelings, which can lead to a decrease in user satisfaction. Furthermore, the lack of technology to provide appropriate hints based on the user's feelings can leave users feeling confused and anxious.

[1242] 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.

[1243] In this invention, the server includes means for a user to input a question, means for the server to receive the question, means for the server to send the question to an emotion engine, means for the emotion engine to analyze the user's emotion, means for the server to send a prompt sentence to the generative AI model, means for the generative AI model to generate a hint, and means for the server to return the generated hint to the user. This makes it possible to provide appropriate hints according to the user's emotion and support the user in finding the answer themselves.

[1244] "User" refers to a person who accesses the system and enters a question.

[1245] The "server" refers to a computer system that receives questions from users, works with an emotion engine and generative AI models to generate hints, and responds to the user.

[1246] "Emotion engine" refers to software or hardware for analyzing a user's question and identifying the user's emotion.

[1247] A "generative AI model" refers to an artificial intelligence model that generates hints to answer a user's question based on a prompt sentence.

[1248] A "prompt sentence" refers to text data that contains instructions for generating hints for a generative AI model.

[1249] A "hint" is information that provides a method or clue for the user to find the answer on their own.

[1250] "Natural language processing technology" refers to technology for analyzing text data and understanding meaning and emotions.

[1251] This invention is a system that utilizes a generative AI model to provide hints to users' questions. The system includes a series of processes: a user inputs a question, a server receives the question, an emotion engine analyzes the user's emotions, a generative AI model generates a prompt sentence to generate a hint, and finally a response to the user.

[1252] Hardware and software used

[1253] server

[1254] The server receives questions from users, works with the emotion engine and generative AI model to generate hints, and responds to the users. The server is a computer system equipped with a high-performance processor and sufficient memory.

[1255] Terminal

[1256] A terminal is a device that allows users to access the system and input questions. Terminals include PCs, smartphones, tablets, etc.

[1257] Emotion Engine

[1258] The emotion engine is software that analyzes user questions and identifies their emotions. It uses natural language processing technology to analyze emotions from text data.

[1259] Generative AI Models

[1260] A generative AI model is an artificial intelligence model that generates hints for a user's question based on a prompt sentence. The generative AI model is trained using deep learning techniques.

[1261] Data processing and calculation

[1262] When the server receives a question from a user, it sends the question to the emotion engine, which uses natural language processing technology to analyze the question text and identify the user's emotion. The analysis results are sent back to the server, which then sends a prompt to the generative AI model based on the results.

[1263] The generative AI model receives the prompt sentence and generates appropriate hints according to the user's emotions. The generated hints are sent back to the server, which then responds to the user.

[1264] Specific examples

[1265] For example, consider the case where a user uses a terminal to input a question such as "What's the weather like in Tokyo?" The server receives this question and sends it to the emotion engine. The emotion engine analyzes the question to determine that the user is expressing the emotion of happiness, and sends the result back to the server.

[1266] The server sends the following prompt to the generative AI model:

[1267] The user asks "What's the weather in Tokyo?" and expresses joy. Generate a positive hint.

[1268] Based on this prompt, the generative AI model generates a hint: "Why don't you check the weather forecast website?" The server returns this hint to the user, who can then check it on their device.

[1269] In this way, the system provides appropriate hints according to the user's emotions and helps the user find the answer by themselves.

[1270] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1271] Step 1:

[1272] The user inputs a question using a terminal. The user opens the terminal's browser, accesses the system's web page, enters "What's the weather in Tokyo?" in the search bar, and presses the send button. The input data is sent to the server in text format.

[1273] Step 2:

[1274] The server receives the question. The server receives the HTTP request and extracts the text "What's the weather in Tokyo?" from the request body. This text is temporarily stored in memory. The input is the user's question text, and the output is the extracted text data.

[1275] Step 3:

[1276] The server sends a question to the emotion engine. The server uses the REST API to send the text "What's the weather in Tokyo?" to the emotion engine. The API request contains text data. The input is the extracted text data, and the output is the API request to the emotion engine.

[1277] Step 4:

[1278] The emotion engine analyzes the user's emotions. The emotion engine analyzes the received text using a natural language processing algorithm and determines that the user is expressing the emotion of joy. The result is sent back to the server in JSON format. The input is text data, and the output is the JSON data of the analysis results.

[1279] Step 5:

[1280] The server sends a prompt to the generative AI model. Based on the analysis results obtained from the emotion engine, the server sends a prompt to the generative AI model saying, "The user is expressing joy. Please generate a positive hint." The prompt is sent as an API request. The input is the JSON data of the analysis results, and the output is the prompt to the generative AI model.

[1281] Step 6:

[1282] The generative AI model generates a hint. The generative AI model receives the prompt and generates a hint such as "Why not check the weather forecast website?" This hint is sent back to the server in text format. The input is the prompt, and the output is the generated hint text data.

[1283] Step 7:

[1284] The server returns the generated hint to the user. The server sends the hint received from the generative AI model back to the user as an HTTP response. The user can check the hint "Why don't you check the weather forecast website?" in the browser on their device. The input is the text data of the generated hint, and the output is the HTTP response to the user.

[1285] (Application example 1)

[1286] Next, a description will be given of Application Example 1 of Form 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."

[1287] Conventional generative AI systems often provide direct answers to user questions, making it difficult for users to develop the ability to find answers on their own. Furthermore, they provide uniform hints without considering the user's feelings, which means they are unable to provide appropriate support based on the user's situation and emotions. For security-related questions in particular, it is necessary to provide specific and useful hints while easing the user's anxiety.

[1288] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for utilizing generative AI to provide hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for adjusting the generation of hints based on the user's emotions using an emotion engine that recognizes the user's emotions, and means for providing solutions and hints when the user asks a security question. This makes it possible to provide appropriate hints according to the user's emotions and develop the user's ability to find answers on their own.

[1289] "Generative AI" is an artificial intelligence technology that generates new information and answers based on user input.

[1290] An "emotion engine" is a technology that recognizes a user's emotions and adjusts the system's response based on those emotions.

[1291] A "hint" is information that provides clues or methods to help users find the answer themselves.

[1292] "Security" refers to the technologies and methods used to protect information and systems from unauthorized access and attacks.

[1293] A "question" is an inquiry a user makes to the system about information they want to know or a problem they want to solve.

[1294] "Solutions" are information that provides specific solutions or steps to address problems or questions users face.

[1295] "User" refers to any individual or organization that uses the System.

[1296] "Adjustment" refers to changing the system's responses and hints based on the user's emotions and situation.

[1297] The system for implementing this invention consists of a server including a generative AI, an emotion engine, and a user interface, and a terminal used by the user.

[1298] System Program

[1299] Program processing explanation

[1300] 1. Input Processing:

[1301] The user enters the question in text format using a device such as a smartphone or PC.

[1302] Hardware used: Smartphone, PC

[1303] Software used: Text input interface

[1304] 2. Emotion recognition:

[1305] The server receives the user's input text and recognizes the user's emotion using an emotion engine.

[1306] Software used: Emotion recognition API (e.g. IBM Watson Tone Analyzer)

[1307] 3. Hint generation:

[1308] The server uses a generative AI model to generate hints for the user's questions.

[1309] Software used: Generative AI models (e.g., OpenAI GPT-4)

[1310] 4. Adjusting the hints:

[1311] The server adjusts the generated hints based on the results of the emotion engine.

[1312] Software used: Custom logic

[1313] 5. Output Processing:

[1314] Display tailored hints on the user's device.

[1315] Hardware used: Smartphone, PC

[1316] Software used: Text display interface

[1317] Specific examples

[1318] For example, if a user asks, "I've been receiving a lot of phishing emails lately. What should I do about it?" the system will act as follows:

[1319] 1. The user enters a question using their smartphone.

[1320] 2. The server receives the question and uses the emotion engine to recognize the user's emotion. In this case, it recognizes that the user is feeling anxious.

[1321] 3. The generative AI model learns the characteristics of phishing emails and generates hints such as "Don't open suspicious emails."

[1322] 4. Based on the results of the sentiment engine, the server adjusts to provide more detailed hints, such as "Let's take a look at some specific examples of phishing emails."

[1323] 5. The tailored hints are displayed on the user's smartphone.

[1324] Example prompt sentence:

[1325] User Question: I've been getting a lot of phishing emails lately, what should I do?

[1326] User Emotion: Anxiety

[1327] Tip: Learn the signs of phishing emails and avoid opening suspicious emails. Let's look at some examples of phishing emails.

[1328] In this way, it is possible to provide appropriate hints according to the user's emotions and develop the user's ability to find the answer by themselves.

[1329] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1330] Step 1:

[1331] The user inputs a question in text format using a terminal. The input text is sent to the server through the terminal's text input interface. The input data is the user's question.

[1332] Step 2:

[1333] The server passes the received user question text to the emotion engine. The emotion engine analyzes the text data and recognizes the user's emotion. Specifically, it uses an emotion recognition API (e.g., IBM Watson Tone Analyzer) to extract emotional information from the text. The output is the user's emotional state (e.g., anxiety, joy, confusion).

[1334] Step 3:

[1335] The server passes the user's question text and the emotion engine's output to a generative AI model. The generative AI model (e.g., OpenAI GPT-4) generates hints for the user's question based on these input data. The generated hints are information that provides clues and methods for the user to find the answer themselves.

[1336] Step 4:

[1337] The server adjusts the generated hints based on the results of the emotion engine. Specifically, it changes the content and level of detail of the hints depending on the user's emotional state. For example, if the user is feeling anxious, it adjusts the hints to provide more specific and detailed information. The output is the adjusted hint information.

[1338] Step 5:

[1339] The server sends the adjusted hint information to the user's terminal, which displays the received hint information to the user through a text display interface, allowing the user to find the answer by themselves using the displayed hint.

[1340] In this way, it is possible to provide appropriate hints according to the user's feelings and develop the user's ability to find the answer by themselves.

[1341] Example 2

[1342] Next, a description will be given of Example 2 of Form 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."

[1343] Conventional generative AI systems primarily provide direct answers to user questions, but lack the support required for users to find answers on their own. Furthermore, they do not generate hints that take into account the user's learning ability or interests, and they lack the ability to track changes in the user's emotions to optimize the generation of next hints. This reduces the effectiveness of user learning and reduces satisfaction.

[1344] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1345] In this invention, the server does not provide direct answers to questions from users, but includes means for providing hints and methods for finding answers on the user's own, means for utilizing generative AI to analyze user input and identify interests, means for generating appropriate hints based on the user's interests, and means for tracking changes in the user's emotions and optimizing the generation of the next hint based on the results. This makes it possible to provide hints that take into account the user's learning ability and interests, and to track changes in the user's emotions and optimize the generation of the next hint.

[1346] "User" means any person or entity that uses the System to enter questions or requests.

[1347] "Generative AI" is a system that uses artificial intelligence technology to generate appropriate answers and hints based on user input.

[1348] A "hint" is information or instructions that help users find the answer themselves.

[1349] "Interests" are the interest or curiosity a user has in a particular field or topic.

[1350] "Emotional changes" refer to the fluctuations in emotions that users show in response to hints and information provided by the system.

[1351] "Optimization" refers to adjusting the system's behavior and output to maximize user learning effectiveness and satisfaction.

[1352] A "server" is a computer system that receives input from the user, uses generative AI and an emotion engine to generate appropriate hints, and returns them to the user.

[1353] "Input" is text data of questions or requests that a user makes to the system.

[1354] "Analysis" is the process by which generative AI analyzes user input to identify interests and intent.

[1355] An "emotion engine" is software that analyzes user reactions and feedback and tracks changes in emotions.

[1356] This invention is a system that uses generative AI to provide hints that take into account the user's learning ability and interests. It also includes an emotion engine that tracks changes in the user's emotions and optimizes the generation of the next hint.

[1357] Hardware and software used

[1358] Hardware: Servers, devices (PCs, smartphones, etc.)

[1359] Software: Generative AI models (e.g., GPT-4), emotion engines, database management systems (e.g., MySQL)

[1360] Specific operation of the system

[1361] 1. Accepting user input

[1362] Terminal: The user uses the terminal to type a question or request. For example, the user types, "Why does it rain?"

[1363] Specific operation: The user enters a question into the input form on the device and clicks the "Submit" button.

[1364] 2. Analyze user interests

[1365] Server: The server receives the user's input and passes it to a generative AI model (e.g., GPT-4), which analyzes the input text and identifies the user's interests.

[1366] What happens: The server passes the user's input to a text analysis engine, which extracts the keyword "science."

[1367] 3. Generate hints

[1368] Server: The generative AI model generates appropriate hints based on the user's interests, such as "Why not explore how water vapor cools to form clouds, which then fall as rain?"

[1369] Specific operation: The server passes the prompt "Please generate a hint from a scientific perspective" to the generative AI model and receives the generated hint.

[1370] 4. Track your emotions

[1371] Server: The emotion engine analyzes the user's reaction and tracks the emotional changes. For example, if the user expresses happiness in response to a hint, it stores that information in a database.

[1372] Specific operation: The server passes the user's response (e.g., feedback form input or facial expression recognition data) to the emotion engine, which analyzes the emotion data and stores it in a database.

[1373] 5. Optimize the next hint generation

[1374] Server: The emotion engine optimizes the next hint generation based on the previous emotion data. For example, if the user expressed dissatisfaction with the previous hint, a different approach will be adopted.

[1375] Specific operation: The server receives feedback from the emotion engine and adjusts the next prompt sentence. For example, it passes a prompt sentence such as "Since the user expressed dissatisfaction with the previous hint, please generate a hint from a different perspective" to the generative AI model.

[1376] Examples and prompts

[1377] Examples:

[1378] User: "Why is it raining?"

[1379] Terminal: User types in a question and clicks the submit button.

[1380] Server: Receives user input and passes it to the generative AI model.

[1381] Generative AI model: Generates hints such as, "Why not investigate how water vapor cools, forming clouds, and then falls as rain?"

[1382] Server: Returns the hint to the user.

[1383] User: Expresses delight at the hint.

[1384] Server: The emotion engine analyzes the user's emotions and optimizes the next hint generation.

[1385] Example prompt sentence:

[1386] "If you determine that the user is interested in science, generate hints from a scientific perspective. For example, if the user asks, 'Why does it rain?' you could provide a hint such as, 'Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?'"

[1387] In this way, the system takes into account the user's interests and emotions and provides the most appropriate tips.

[1388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1389] Step 1:

[1390] Accepting user input

[1391] Terminal: The user uses the terminal to type a question or request. For example, the user types, "Why does it rain?"

[1392] Input: User question text

[1393] Specific operation: The user enters a question into the input form on the device and clicks the "Submit" button.

[1394] Output: The user's question text is sent to the server.

[1395] Step 2:

[1396] Analyze user interests

[1397] Server: The server receives the user's input and passes it to a generative AI model (e.g., GPT-4), which analyzes the input text and identifies the user's interests.

[1398] Input: User question text

[1399] What happens: The server passes the user's input to a text analysis engine, which extracts the keyword "science."

[1400] Output: Data about the user's interests (e.g., science)

[1401] Step 3:

[1402] Generate hints

[1403] Server: The generative AI model generates appropriate hints based on the user's interests, such as "Why not explore how water vapor cools to form clouds, which then fall as rain?"

[1404] Input: Data about user interests (e.g., science)

[1405] Specific operation: The server passes the prompt "Please generate a hint from a scientific perspective" to the generative AI model and receives the generated hint.

[1406] Output: Generated hint (e.g., "Why not explore how water vapor cools, forms clouds, and then falls as rain?")

[1407] Step 4:

[1408] Providing hints to users

[1409] Server: Returns the generated hint to the user.

[1410] Input: Generated hint

[1411] Specific operation: The server sends the generated hint to the user's device.

[1412] Output: The user receives the hint.

[1413] Step 5:

[1414] Track changes in emotions

[1415] Server: The emotion engine analyzes the user's reaction and tracks the emotional changes. For example, if the user expresses happiness in response to a hint, it stores that information in a database.

[1416] Input: User response data (e.g., feedback form entries or facial recognition data)

[1417] Specific operation: The server passes the user's response to the emotion engine, analyzes the emotion data, and stores it in a database.

[1418] Output: User sentiment data

[1419] Step 6:

[1420] Optimize next hint generation

[1421] Server: The emotion engine optimizes the next hint generation based on the previous emotion data. For example, if the user expressed dissatisfaction with the previous hint, a different approach will be adopted.

[1422] Input: Previous emotion data

[1423] Specific operation: The server receives feedback from the emotion engine and adjusts the next prompt sentence. For example, it passes a prompt sentence such as "Since the user expressed dissatisfaction with the previous hint, please generate a hint from a different perspective" to the generative AI model.

[1424] Output: Optimized prompt statement

[1425] In this way, the system takes into account the user's interests and emotions and provides the most appropriate tips.

[1426] (Application example 2)

[1427] Next, a description will be given of Application Example 2 of Form 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."

[1428] Conventional generative AI systems often provide direct answers to user questions, but lack the ability to assist users in the process of finding answers themselves. Furthermore, they do not generate hints that take into account the user's learning ability or interests, making it difficult to optimize individual learning experiences. Furthermore, they lack the ability to track changes in the user's emotions and optimize the generation of next hints based on those emotions. This makes it difficult to improve the user's motivation to learn and their level of understanding.

[1429] 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.

[1430] In this invention, the server includes means for utilizing a generative AI to provide hints and methods for finding the answer on one's own rather than providing direct answers to questions from the user, means for the generative AI to take the user's learning ability and interests into consideration when generating hints for the user's questions, means for the generative AI to track the process by which the user finds the answer on their own and optimize the generation of the next hint based on the results, means for the generative AI to track changes in the user's emotions and optimize the generation of the next hint based on the results, and means for the generative AI to generate hints based on the user's questions and emotions. This makes it possible to individually optimize the user's learning experience and improve their motivation to learn and their level of understanding.

[1431] "Generative AI" is an artificial intelligence system that generates new information or answers based on user input.

[1432] A "user question" is a question or inquiry that a user enters into the system.

[1433] A "direct answer" is a specific, immediate answer to a user's question.

[1434] "Self-help" refers to the steps or approaches users take to solve a problem on their own.

[1435] A "hint" is information or instructions that help users find an answer.

[1436] "User learning ability" refers to the ability of a user to acquire new knowledge or skills.

[1437] "User interests" refers to the interest a user has in a particular field or topic.

[1438] The "process by which the user finds the answer on their own" refers to the series of activities and thoughts that the user goes through to solve the problem.

[1439] "Optimizing the next hint generation" means making the next hint provided more effective based on the user's previous response and behavior.

[1440] "Changes in user emotion" refers to the fluctuations in emotion that a user displays through their interaction with the system.

[1441] "Hints based on user questions and emotions" are advice or instructions that take into account the user's question and their current emotional state.

[1442] A system for implementing this invention utilizes generative AI to provide hints and methods for users to find the answer themselves, rather than providing direct answers to questions from users. The system takes into account the user's learning ability and interests, tracks the process by which the user finds the answer themselves, and optimizes the generation of the next hint based on the results. It also includes a function to track changes in the user's emotions and optimize the generation of the next hint based on the results.

[1443] Hardware and software used

[1444] Hardware: Smartphone

[1445] Software: OpenAI API, Emotion Recognition Engine API

[1446] System configuration

[1447] 1. Receive the user's question: The user enters the question using their smartphone.

[1448] 2. Emotion detection: Use the emotion recognition API to detect emotions from the user's question.

[1449] 3. Hint Generation: Uses OpenAI API to generate hints based on the user's question and sentiment.

[1450] 4. Providing hints: Displaying the generated hints to the user.

[1451] Processing flow

[1452] When the server receives a question from a user, it first detects the user's emotion using an emotion recognition engine API. Then, it uses the OpenAI API to generate hints based on the user's question and the detected emotion. These hints take into account the user's learning ability and interests, helping the user find the answer on their own. The generated hints are displayed on the smartphone screen.

[1453] Specific examples

[1454] For example, if a user asks "Why is the sky blue?" and the emotion engine detects "interest," the generated hint might be "The sky looks blue because sunlight is scattered by molecules in the atmosphere. Blue light is particularly strongly scattered, which is why the sky looks blue."

[1455] Prompt Sentence Examples

[1456] If you determine that the user is interested in science, provide clues from a scientific perspective. Question: Why is the sky blue? Emotion: Interest

[1457] In this way, the user's learning experience can be individually optimized, improving engagement and comprehension.

[1458] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1459] Step 1:

[1460] A user inputs a question using a smartphone. The input question is sent to the system. The input data is the user's question text, and the output data is the question text sent to the system.

[1461] Step 2:

[1462] The server sends the received question text to the emotion recognition engine API to detect the user's emotion. The input data is the question text, and the output data is the detected emotion information. Specifically, the server passes the question text to the API and receives the emotion information returned from the API.

[1463] Step 3:

[1464] The server generates a hint by sending a prompt to the OpenAI API based on the question text and the detected emotion information. The input data is the question text and emotion information, and the output data is the generated hint text. Specifically, the server generates a prompt, sends it to the OpenAI API, and receives the returned hint text.

[1465] Step 4:

[1466] The server sends the generated hint text to the smartphone and displays it to the user. The input data is the generated hint text, and the output data is the hint text to be displayed on the smartphone. Specifically, the server sends the hint text to the smartphone and displays it on the screen.

[1467] Step 5:

[1468] The user checks the hints and inputs a new question if necessary. The input data is the user's new question text, and the output data is the new question text sent to the system. Specifically, the user inputs a new question into their smartphone and sends it to the system.

[1469] This series of processes makes it possible to individually optimize the user's learning experience and improve their motivation and understanding.

[1470] Example 3

[1471] Next, a description will be given of Example 3 of Form Example 3. 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."

[1472] Conventional generative AI systems have focused on providing direct answers to users, but this approach fails to fully tap into the user's learning ability and interest. Furthermore, since hint generation does not take into account the user's emotions or behavioral data, it is difficult to provide an individually optimized learning experience.

[1473] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1474] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user, means for recording in a log what information the user searched for based on the previous hint and how long it took them to find the answer, means for recognizing the user's emotions in real time using an emotion engine, means for adjusting the difficulty of the next hint based on the collected behavioral data and emotion data, and means for transmitting the generated hints to the user's device. This makes it possible to provide an individually optimized learning experience that takes into account the user's learning ability and interests.

[1475] "Generative AI" is an artificial intelligence technology that automatically generates answers and hints based on user input.

[1476] A "hint" is information or instructions that help users find the answer themselves.

[1477] "User behavior data" refers to information such as the search keywords used by users when using the system and the time it takes to find an answer.

[1478] The "emotion engine" is a technology that recognizes emotions in real time from the user's facial expressions, voice, etc.

[1479] "Behavioral data" refers to data such as operation history and search history when a user uses the system.

[1480] "Emotion Data" is data regarding the user's emotional state as recognized by the emotion engine.

[1481] "Adjusting the difficulty level" refers to changing the difficulty level of the next hint provided based on the user's behavioral and emotional data.

[1482] "Terminal" means a device (e.g., PC, smartphone) used by a user to access the system.

[1483] "Recording in a log" refers to saving user behavior data in a database or similar.

[1484] "Push notification" is a technology that sends information from a server to a user's device in real time.

[1485] This invention is a system that utilizes generative AI to assist users in the process of finding solutions on their own. The system collects user behavioral and emotional data and optimizes the next hint based on that data. It also recognizes the user's emotions in real time and provides hints based on those emotions.

[1486] Hardware and software used

[1487] Hardware: Servers, terminals (PCs, smartphones)

[1488] Software: Generative AI models (e.g., GPT-4), emotion engines

[1489] Data processing and calculation

[1490] 1. Collection of user behavior data

[1491] The server logs what information the user searches for based on the previous hint and how long it takes to find the answer.

[1492] Example: If a user receives a hint about "Python list operations", searches for "Python list append" in a search engine, and finds the answer in 5 minutes, store the search keywords and time in a database.

[1493] 2. Collecting user sentiment data

[1494] The device uses an emotion engine to recognize the user's emotions in real time.

[1495] Example: While the user is reading the hint, the device camera captures the user's facial expressions, and the emotion engine analyzes them to determine their emotional state, such as "excited" or "depressed." The result of the determination is sent to the server.

[1496] 3. Optimizing hint generation

[1497] The server adjusts the difficulty of the next hint based on the collected behavioral and emotional data.

[1498] Example: If the user quickly finds the answer from the previous hint, the server will generate a more difficult hint next time, such as "Python list comprehension." Also, if the user is excited, the server will generate a challenging hint to maintain the excitement, and if the user is depressed, it will generate an easy hint that gives a sense of accomplishment.

[1499] 4. Providing hints to users

[1500] The server sends the generated hint to the user's terminal.

[1501] Example: The server generates a hint and sends it to the user's device via a push notification, which the user receives. For example, a "challenging hint for the next step" might say, "Try to find out how to filter a list using Python list comprehension."

[1502] Examples of prompt statements

[1503] Sample prompt 1: "Adjust the difficulty of the next hint based on how much information the user searches for and how long it takes them to find the answer based on the previous hint."

[1504] Sample prompt 2: "Recognize the user's emotions and generate appropriate hints based on their emotions. If the user is excited, provide a challenging hint. If the user is depressed, provide an easy hint."

[1505] This system makes it possible to provide an individually optimized learning experience by taking into consideration the learning ability and interests of the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1506] Step 1:

[1507] Collecting user behavior data

[1508] Input: The keyword the user searched for based on the previous hint and the time it took to find the answer.

[1509] Specific behavior: If a user receives a hint about "Python list operations", searches for "Python list append" in a search engine, and finds the answer in 5 minutes, the search keywords and time will be saved in the database.

[1510] Output: Log data with search keywords and time.

[1511] Step 2:

[1512] Collecting user emotion data

[1513] Input: User facial and voice data.

[1514] Specific operation: While the user is reading the hint, the device camera captures the user's facial expressions, which the emotion engine analyzes to determine their emotional state, such as "excited" or "depressed." The result of the determination is sent to the server.

[1515] Output: User's emotional state data.

[1516] Step 3:

[1517] Optimizing hint generation

[1518] Input: User behavioral and emotional data.

[1519] Specific operation: The server adjusts the difficulty of the next hint based on the collected behavioral and emotional data. For example, if the user quickly finds the answer from the previous hint, the server will generate a more difficult hint such as "Python list comprehension." Also, if the user is excited, the server will generate a challenging hint to maintain the user's excitement, and if the user is depressed, the server will generate an easy hint that gives the user a sense of accomplishment.

[1520] Output: Optimized hints.

[1521] Step 4:

[1522] Providing hints to users

[1523] Input: Optimized hints.

[1524] Specific operation: The server generates a hint and sends it to the user's device via push notification, which the user receives. For example, a "challenging hint for the next step" might be "Try to find out how to filter a list using Python list comprehension."

[1525] Output: The hint displayed on the user's terminal.

[1526] (Application example 3)

[1527] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1528] Conventional learning support systems have the problem that it is difficult to maintain learning efficiency and motivation because they do not generate hints that take into account the process by which the user finds the answer or their emotions at that time. In addition, because it is not possible to provide optimal hints based on the user's progress and emotions, it is not possible to provide appropriate learning support for each individual user.

[1529] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1530] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for tracking the process by which the user finds the answer on their own and optimizing the generation of next hints based on the results, means for recognizing the user's emotions and generating hints based on the emotions taking into account the user's learning ability and interests, means for recording the user's search queries and time, means for analyzing the user's emotions, and means for generating optimal hints based on the user's past data and emotions. This makes it possible to improve the user's learning efficiency and maintain their motivation to learn.

[1531] "Generative AI" is an artificial intelligence system that generates appropriate information and hints based on user input.

[1532] "User" means an individual or organization that uses this system to learn or search for information.

[1533] The "answer-finding process" is the series of actions and thought processes that a user takes to arrive at the final answer based on the hints and information provided.

[1534] "Hint generation" is the process of providing information or instructions to help the user find the answer.

[1535] "Optimization" means making adjustments to make the next tip more effective based on the user's past behavior and emotions.

[1536] "Emotion recognition" is a technology that analyzes and identifies a user's emotional state from their facial expressions and behavior.

[1537] "Learning ability" is the user's ability to understand, remember, and apply new information.

[1538] "Interests" are the interest or curiosity a user shows in a particular topic or activity.

[1539] A "search query" is a keyword or phrase that a user enters when searching for information.

[1540] "Tracking time" means measuring and storing the amount of time a user spends on a particular activity.

[1541] "Past data" refers to information such as the user's past actions and search history.

[1542] "Analysis" is the process of examining collected data to find meaning and patterns.

[1543] The system for implementing this invention utilizes generative AI to provide hints and methods for users to find the answer themselves, rather than providing direct answers to questions from users. The system tracks the process by which the user finds the answer themselves and optimizes the generation of hints for the next time based on the results. The system also recognizes the user's emotions and generates hints that take into account the user's learning ability and interests based on those emotions.

[1544] Hardware and software used

[1545] Hardware: Smartphones, cameras

[1546] Software: Python, emotion recognition library, hint generation library

[1547] Data processing and calculation

[1548] 1. Tracking user progress:

[1549] The server records the queries users search and the times they search, allowing it to understand what information users searched for and how long it took them to find the answers.

[1550] 2. Emotion recognition:

[1551] The server uses an emotion recognition library to recognize the user's emotions, for example, by analyzing the user's facial expressions using a camera to identify emotions such as excitement or depression.

[1552] 3. Hint generation:

[1553] The server uses a hint generation library to generate optimal hints based on the user's past data and emotions. For example, if the user found the answer quickly with the previous hint, the server will provide a hint with increased difficulty the next time.

[1554] Specific examples

[1555] Let's say a user is learning "Python Basics." In the previous hint, they were instructed to "research Python variables," and they quickly found the answer. The next time, they will be given a more difficult hint, such as "research the difference between Python lists and dictionaries." Additionally, the camera will analyze the user's facial expressions while they are learning, and if they are excited, they will be given a positive hint, such as "Try a more interesting topic next time!"

[1556] Prompt Sentence Examples

[1557] If the user finds the answer quickly with the previous hint, provide a more difficult hint next time. Also, if the user is excited, generate hints that will maintain that excitement.

[1558] In this way, the user's learning efficiency and motivation can be maximized.

[1559] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1560] Step 1:

[1561] The server records the queries that users search and the time they spend searching. The search queries that users enter while studying and the time they spend on those queries are stored in a database, allowing us to track users' study behavior.

[1562] Input: User's search query, time spent searching

[1563] Output: Search queries stored in the database and time records

[1564] Step 2:

[1565] The server recognizes the user's emotions using an emotion recognition library, capturing the user's facial expressions through a camera and applying emotion recognition algorithms to identify the user's emotional state.

[1566] Input: User's facial expression data

[1567] Output: Perceived user emotional state (e.g. excited, depressed)

[1568] Step 3:

[1569] The server generates optimal hints based on the user's past data and emotions. Using a hint generation library, the server takes into account the user's past search queries, time, and emotional state to generate hints that will be useful for the next learning.

[1570] Input: User's past search queries, time, emotional state

[1571] Output: Optimized hints

[1572] Step 4:

[1573] The server provides the generated hints to the user, and sends a notification to the user's device to display the hints that will be useful for the next study.

[1574] Input: Optimized hints

[1575] Output: Tip displayed on the user's device

[1576] Step 5:

[1577] The user continues learning based on the provided hints, and continues learning by entering a new search query.

[1578] Input: Provided hint

[1579] Output: New search queries and learning progress

[1580] Step 6:

[1581] The server again records the user's search query and time, recognizes emotions, and accumulates data for generating hints next time.

[1582] Input: New search query, time spent searching, user facial expression data

[1583] Output: New search queries stored in the database, along with a timestamp and the perceived emotional state.

[1584] In this way, the server can continuously track the user's learning behavior and emotions and provide optimal hints to maximize the user's learning efficiency and motivation.

[1585] 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.

[1586] 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> ) 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.

[1587] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1588] 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.

[1589] [Third embodiment]

[1590] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1591] 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.

[1592] 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).

[1593] 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.

[1594] 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.

[1595] 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).

[1596] 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.

[1597] 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.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1602] "Example 1"

[1603] As one embodiment of the present invention, a system utilizing generative AI is provided. This system does not provide a direct answer to a user's question, but rather provides hints and methods for finding the answer on one's own. Specifically, if a user asks, "What's the weather like in Tokyo?", the system will provide a hint such as, "Why don't you check the weather forecast website?"

[1604] "Example 2"

[1605] Furthermore, as another embodiment of the present invention, a system is provided in which a generative AI generates hints taking into account the user's learning ability and interests. Specifically, if the system determines that the user is interested in science, it provides hints from a scientific perspective. For example, if the user asks, "Why does it rain?", the system provides a hint such as, "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?"

[1606] "Example 3"

[1607] Furthermore, as another embodiment of the present invention, a system is provided in which a generative AI tracks the process by which a user finds the answer on their own and optimizes the generation of the next hint based on the results. Specifically, the generation of the next hint is optimized based on information such as what information the user searched for based on the previous hint and how long it took to find the answer. For example, if the user quickly found the answer from the previous hint, it is possible to adjust the system to provide a more difficult hint next time.

[1608] The processing flow of each embodiment will be described below.

[1609] "Example 1"

[1610] Step 1: Receive a question from the user. For example, receive a question like "What's the weather like in Tokyo?"

[1611] Step 2: Generative AI generates a hint for the question, in this case "Why not check the weather website?"

[1612] Step 3: Provide the generated hints to the user.

[1613] "Example 2"

[1614] Step 1: Receive a user question and their interests. For example, receive the question "Why does it rain?" and information that the user is interested in science.

[1615] Step 2: The generative AI generates a hint based on the question and the user's interests. In this case, it generates the hint, "Why not investigate how water vapor cools, forming clouds, and then falls as rain?"

[1616] Step 3: Provide the generated hints to the user.

[1617] "Example 3"

[1618] Step 1: Receive a question from the user and collect information such as what information the user searched for based on the previous hint and how long it took them to find the answer.

[1619] Step 2: The generative AI optimizes the next hint generation based on the collected information. For example, if the user quickly finds the answer from the previous hint, it will generate a more difficult hint next time.

[1620] Step 3: Provide optimized tips to users.

[1621] Example 1

[1622] Next, a description will be given of Example 1 of Form 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."

[1623] Conventional generative AI systems often provide direct answers to user questions, leaving few opportunities for users to develop the ability to find answers on their own. Furthermore, they lack the ability to provide hints that take into account the user's learning ability and interests, resulting in reduced user satisfaction and learning effectiveness. Furthermore, they lack the ability to track the user's process of finding the answer on their own and optimize the generation of next hints based on the results, making continuous learning support difficult.

[1624] 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.

[1625] In this invention, the server includes means for receiving a question from a user, means for analyzing the received question, means for generating a prompt sentence to be input to the generative AI model based on the analysis result, means for inputting the prompt sentence to the generative AI model, means for receiving output from the generative AI model, means for formatting the output from the generative AI model as a hint to be provided to the user, and means for sending the formatted hint to the user. This enables the server to develop the user's ability to find answers on their own and to provide hints that take into account their learning ability and interests. Furthermore, by tracking the user's learning process and optimizing the generation of the next hint, continuous learning support can be realized.

[1626] The "means for receiving a question from a user" is a function that allows the system to receive a question entered by a user.

[1627] The "means for analyzing a received question" is a function for analyzing a received question in order to understand the content of the question and perform appropriate processing.

[1628] "Means for generating prompt sentences to be input to the generative AI model" refers to a function that creates prompt sentences to give appropriate instructions to the generative AI model based on the analysis results.

[1629] "Means for inputting prompt sentences to the generative AI model" refers to a function for sending the generated prompt sentences to the generative AI model, which then generates the appropriate output.

[1630] "Means for receiving output from a generative AI model" refers to a function for receiving the output generated by a generative AI model.

[1631] "Means for formatting the output from a generative AI model as a hint to provide to the user" is a function that formats the output from a generative AI model in a form that is easy for the user to understand.

[1632] The "means for sending formatted hints to the user" is a function for delivering formatted hints to the user.

[1633] A "generative AI model" is an artificial intelligence model that generates appropriate hints and answers to user questions.

[1634] A "prompt sentence" is an input sentence that causes a generative AI model to generate a specific output.

[1635] This invention is a system that utilizes a generative AI model to provide users with hints and methods for finding answers on their own, rather than providing direct answers to questions from users. Specific embodiments of this system are described below.

[1636] Hardware and Software Configuration

[1637] server

[1638] The server receives questions from users, analyzes them, inputs prompts to the generative AI model, receives the output from the generative AI model, formats it, and sends it to the user. The server uses the following software and hardware:

[1639] Natural Language Processing Library: Use a natural language processing library, such as SpaCy or NLTK, to parse the question.

[1640] Generative AI model: For example, OpenAI's GPT-4 is used as the generative AI model.

[1641] Communication protocol: HTTP / HTTPS protocol is used for communication with user terminals.

[1642] Terminal

[1643] The terminal is responsible for inputting questions by the user and receiving and displaying hints from the server. The terminal uses the following software and hardware:

[1644] User interface: Provide a GUI for inputting questions and displaying hints. For example, use a smartphone app or a web browser.

[1645] Communication protocol: Use HTTP / HTTPS protocol to communicate with the server.

[1646] user

[1647] The user uses a terminal to enter a question and receives hints provided by the server.

[1648] Data processing and calculation

[1649] 1. User inputs a question

[1650] The user types a question into an input field on the device, for example, "What's the weather like in Tokyo?"

[1651] 2. Submit your question

[1652] The device sends the question entered by the user to the server using an HTTP request.

[1653] 3. Question Analysis

[1654] The server analyzes the received question using a natural language processing library, for example, extracting keywords such as "weather in Tokyo."

[1655] 4. Prompt generation

[1656] The server generates a prompt sentence to be input to the generative AI model based on the analysis results. For example, it generates a prompt sentence such as, "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast."

[1657] 5. Input to the generative AI model

[1658] The server inputs the generated prompt sentence into a generative AI model, for example, by sending the prompt sentence to the GPT-4 API.

[1659] 6. Obtaining the output of the generative AI model

[1660] The server receives the output from the generative AI model, for example, "Why not check out a weather website?"

[1661] 7. Hint Formatting

[1662] The server formats the output from the generative AI model as hints to provide to the user.

[1663] 8. Submit a Tip

[1664] The server sends the formatted hint to the device using an HTTP response.

[1665] 9. Displaying Hints

[1666] The device displays the hint received from the server to the user, for example, "Why not check out our weather website?"

[1667] Specific examples

[1668] Example 1: Weather question

[1669] User asks: "What's the weather like in Tokyo?"

[1670] Server prompt: "User is asking about the weather in Tokyo. Please suggest a way to check the forecast."

[1671] Generative AI model output: "Why not check out a weather website?"

[1672] Device says: "Why don't you check the weather website?"

[1673] In this way, users can be helped to find information themselves.

[1674] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1675] Step 1:

[1676] User question input

[1677] Subject: User

[1678] Specific operation: The user enters a question into the input field of the device and presses the send button. For example, "What's the weather like in Tokyo?"

[1679] Input: User question (e.g. "What's the weather like in Tokyo?")

[1680] Output: Question typed into the terminal

[1681] Step 2:

[1682] Submit a Question

[1683] Subject: Device

[1684] What happens: The device sends the question entered by the user to the server using an HTTP request.

[1685] Input: Question typed into the terminal

[1686] Output: The question sent to the server

[1687] Step 3:

[1688] Question Analysis

[1689] Subject: Server

[1690] Specific operation: The server analyzes the received question using a natural language processing library (e.g., SpaCy or NLTK). For example, it extracts keywords such as "weather in Tokyo."

[1691] Input: The question sent to the server

[1692] Data processing: Use natural language processing libraries to parse the question and extract keywords.

[1693] Output: Parsed question keywords (e.g. "Weather in Tokyo")

[1694] Step 4:

[1695] Generate prompt statement

[1696] Subject: Server

[1697] Specific operation: Based on the analysis results, the server generates a prompt sentence to be input to the generative AI model. For example, it generates a prompt sentence such as, "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast."

[1698] Input: Keywords from the parsed question

[1699] Data processing: Generate prompt sentences based on keywords.

[1700] Output: The generated prompt (e.g., "The user is asking about the weather in Tokyo. Please suggest a way to check the weather forecast.")

[1701] Step 5:

[1702] Input to generative AI models

[1703] Subject: Server

[1704] Specific operation: The server inputs the generated prompt sentence into the generative AI model. For example, it sends the prompt sentence to the API of the generative AI model.

[1705] Input: Generated prompt statement

[1706] Output: The prompt sent to the generative AI model

[1707] Step 6:

[1708] Obtaining the output of a generative AI model

[1709] Subject: Server

[1710] What it does: The server receives the output from the generative AI model, for example, "Why don't you check the weather website?"

[1711] Input: The prompt sent to the generative AI model

[1712] Data computation: The generative AI model generates output based on the prompt.

[1713] Output: The output from the generative AI model (e.g., "Why not check out a weather website?")

[1714] Step 7:

[1715] Hint formatting

[1716] Subject: Server

[1717] What it does: The server formats the output from the generative AI model as hints to provide to the user.

[1718] Input: Output from a generative AI model

[1719] Data processing: Formatting the output to make it easier for users to understand.

[1720] Output: A formatted hint (e.g., "Why not check out the weather website?")

[1721] Step 8:

[1722] Submit a tip

[1723] Subject: Server

[1724] Specific operation: The server sends the formatted hint to the device using an HTTP response.

[1725] Input: Formatted hint

[1726] Output: Hints sent to the terminal

[1727] Step 9:

[1728] Show Hints

[1729] Subject: Device

[1730] What happens: The device displays the hint received from the server to the user, for example, "Why not check out the weather website?"

[1731] Input: Hint sent to terminal

[1732] Output: The hint displayed to the user

[1733] (Application example 1)

[1734] Next, a description will be given of Application Example 1 of Form 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."

[1735] Conventional generative AI systems often provide direct answers to user questions, leaving few opportunities for users to develop the ability to find answers on their own. Furthermore, in physical stores, it is difficult for users to quickly obtain information about products and stores, resulting in an inconvenient shopping experience. To solve these issues, a system is needed that provides users with hints and methods for finding answers on their own.

[1736] 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.

[1737] In this invention, the server includes means for utilizing generative AI to provide hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for the generative AI to take the user's learning ability and interests into consideration when generating hints for the user's questions, means for the generative AI to track the process by which the user finds the answer on their own and optimize the generation of next hints based on the results, and means for providing hints and methods for finding answers when the user asks a question about a product or a store in a physical store. This enables users to develop their ability to find answers on their own while improving their shopping experience in the physical store.

[1738] "Generative AI" is a type of artificial intelligence that generates new information and answers based on user input.

[1739] A "hint" is information that provides clues or directions to help users find the answer themselves.

[1740] "Learning ability" is the user's ability to understand and apply new information.

[1741] An "interest" is a user's interest or curiosity about a particular piece of information or activity.

[1742] "Tracking" is the process of recording and analyzing user actions and choices.

[1743] "Optimization" refers to adjusting and improving a system or process to achieve a specific purpose.

[1744] A "brick and mortar store" is a store that exists in a physical location and offers goods and services.

[1745] A "guide map" is a diagram showing the layout of a store and the locations of products.

[1746] A "prompt sentence" is an input sentence that instructs a generative AI to generate specific information.

[1747] To implement this invention, it is necessary to build a system that utilizes generative AI. This system does not provide direct answers to questions from users, but rather provides methods and hints for finding answers. A specific embodiment of this system is described below.

[1748] System configuration

[1749] The system consists of the following main components:

[1750] 1. Generative AI model: An artificial intelligence model that generates hints in response to user questions. Specifically, we use OpenAI's generative AI model.

[1751] 2. User device: The device on which the user enters the question, such as a smartphone or tablet.

[1752] 3. Server: A server for hosting the generative AI model and processing user queries.

[1753] Program processing

[1754] The server processes the data as follows:

[1755] 1. Receive user question: A question is sent from the user's device.

[1756] 2. Prompt generation: The server generates a prompt based on the user's question. For example, if the user asks, "Where is this product?", the prompt will be, "When the user asks, 'Where is this product?', please provide hints to help them find the answer, rather than a direct answer."

[1757] 3. Generate hints using a generative AI model: The server sends a prompt to the generative AI model to generate a hint.

[1758] 4. Providing hint to user: The generated hint is sent to the user's terminal and displayed to the user.

[1759] Hardware and software used

[1760] Hardware: smartphones, tablets, servers

[1761] Software: Python, OpenAI API

[1762] Specific examples

[1763] When a user asks "Where is this item?" in a physical store, the system works as follows:

[1764] 1. A question is sent from the user device to the server.

[1765] 2. The server generates a prompt based on the question.

[1766] 3. Prompt: "When a user asks, 'Where is this item?', provide a hint to help them find the answer, rather than a direct answer."

[1767] 4. The server sends a prompt to the generative AI model to generate a hint.

[1768] 5. Generated hint: "Please check the store map. It's located near the entrance."

[1769] 6. The hint is sent to the user's device and displayed to the user.

[1770] In this way, users can develop their ability to find answers on their own while improving their in-store shopping experience.

[1771] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1772] Step 1:

[1773] The user types a question.

[1774] Users input questions using devices such as smartphones or tablets, and the input questions are sent from the device to the server.

[1775] Input: User question (e.g., "Where is this item?")

[1776] Output: The question data sent to the server

[1777] Step 2:

[1778] The server receives the query.

[1779] The server receives question data sent from the user terminal, analyzes the received question data, and prepares to generate a prompt sentence.

[1780] Input: User question data

[1781] Output: Parsed question data

[1782] Step 3:

[1783] The server generates a prompt.

[1784] The server generates a prompt based on the parsed question data. For example, if the user's question is "Where is this product?", the prompt will be "When the user asks, 'Where is this product?', please provide a hint to help them find the answer, rather than a direct answer."

[1785] Input: Parsed question data

[1786] Output: Generated prompt statement

[1787] Step 4:

[1788] The server sends a prompt to the generative AI model.

[1789] The server sends the generated prompt sentence to the generative AI model, instructing it to generate a hint.

[1790] Input: Generated prompt text

[1791] Output: The prompt sent to the generative AI model

[1792] Step 5:

[1793] A generative AI model generates hints.

[1794] The generative AI model generates hints based on the prompt it receives, such as "Please check the store map. It's located near the entrance."

[1795] Input: A prompt sent to the generative AI model

[1796] Output: Generated hints

[1797] Step 6:

[1798] The server receives the generated hint.

[1799] The server receives the hints generated by the generative AI model and prepares them to be sent to the user's device.

[1800] Input: Generated hint

[1801] Output: Hint data sent to the user's device

[1802] Step 7:

[1803] The user device receives the hint.

[1804] The user terminal receives the hint data sent from the server and displays it to the user.

[1805] Input: Hint data sent from the server

[1806] Output: A hint to be displayed to the user (e.g., "Please check the store map. It's located near the entrance.")

[1807] This way, users can get hints to find the answer themselves.

[1808] Example 2

[1809] Next, a description will be given of Example 2 of Form 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."

[1810] In conventional systems using generative AI, it has become common to provide direct answers to user questions. However, this makes it difficult for users to develop the ability to find answers on their own, and the learning effect is limited. Furthermore, there are few systems that provide hints that take into account the user's interests and learning ability, and there is an issue that learning support optimized for individual users is not being provided sufficiently.

[1811] 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 the user to input a question, a means for the terminal to send the question to the server, a means for the server to receive the question and analyze the user's interests and learning ability, a means for the server to input a prompt sentence to the generative AI model, a means for the generative AI model to generate a hint, a means for the server to receive the generated hint and send it to the terminal, and a means for the terminal to display the hint to the user. This allows the user to obtain appropriate hints according to their interests and learning ability, improving the learning effect.

[1812] "User" refers to an individual who utilizes the system to enter questions and receive hints.

[1813] "Terminal" refers to the device through which the user inputs questions and communicates with the server. Specifically, this includes smartphones and personal computers.

[1814] "Server" refers to a central processing unit that receives questions from users, generates hints using a generative AI model, and sends them to the terminal.

[1815] "Generative AI model" refers to an artificial intelligence model that generates appropriate hints in response to user questions. Specifically, it includes models that use natural language processing technology.

[1816] A "prompt sentence" is a sentence input to a generative AI model that includes the user's question and the analysis results.

[1817] A "hint" is information that provides clues or methods for users to find the answer themselves.

[1818] A "question" refers to a question or problem that a user inputs into the system.

[1819] "Analysis" refers to the processing of data by the server to assess the user's interests and learning ability.

[1820] "Learning ability" refers to the ability of a user to acquire new knowledge or skills.

[1821] "Interests" refer to the interest a user has in a particular field or topic.

[1822] This invention relates to a system that allows a user to input a question and provides appropriate hints using a generative AI model. Specific embodiments of this system are described below.

[1823] First, the user inputs a question using a terminal. The terminal can be a device such as a smartphone or a PC. The question input by the user is sent from the terminal to a server. The terminal then sends the data to the server via the Internet.

[1824] The server receives the questions sent from the device and then analyzes the user's interests and learning ability based on the user's past question history and profile information. This analysis is performed using a database and machine learning algorithms.

[1825] The server generates a prompt based on the user's question and the analysis results. The prompt is a sentence that is input to the generative AI model and includes the user's question and the analysis results. For example, a prompt might be generated that reads, "It has been determined that the user is interested in science. The user's question is, 'Why does it rain?' Please provide appropriate hints from a scientific perspective."

[1826] Next, the server inputs this prompt into a generative AI model. A model using natural language processing technology (such as GPT-4) is used as the generative AI model. The generative AI model generates an appropriate hint for the user's question based on the prompt. For example, a hint such as "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?" is generated.

[1827] The server receives the hints generated from the generative AI model. The server then sends the hints to the user's device. The device receives the hints sent from the server and displays them to the user. The user can check the hints on the device screen.

[1828] As a concrete example, consider the case where a user inputs the question "Why does it rain?" The device sends this question to the server. The server receives the question and determines that the user is interested in science because they have asked many science-related questions in the past. The server inputs the following prompt to the generative AI model: "It has been determined that the user is interested in science. The user's question is 'Why does it rain?' Please provide an appropriate hint from a scientific perspective." The generative AI model generates the hint: "Why don't you investigate the process by which water vapor cools, forms clouds, and then falls as rain?" The server sends this hint to the device, and the device displays it to the user. The user can check the hint on the device screen and obtain an answer from a scientific perspective.

[1829] In this way, users can obtain appropriate hints according to their interests and learning abilities, improving their learning effectiveness.

[1830] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1831] Step 1:

[1832] The user inputs a question. The user uses a device (smartphone or PC) to input a question to the system. For example, the user might input "Why does it rain?" The input question is stored in the device's memory.

[1833] Step 2:

[1834] The terminal sends a question to the server. The terminal sends a question entered by the user to the server via the Internet. The input data is the user's question text. The output data is the question text sent to the server.

[1835] Step 3:

[1836] The server receives the question and analyzes the user's interests and learning ability. The server receives the question sent from the terminal. The server then accesses a database to obtain the user's past question history and profile information. The input data is the question text and the user's past question history and profile information. The server analyzes this data and evaluates the user's interests and learning ability. The output data is the analysis results regarding the user's interests and learning ability.

[1837] Step 4:

[1838] The server inputs a prompt sentence into the generative AI model. The server generates a prompt sentence based on the user's question and the analysis results. For example, it generates a prompt sentence such as, "It has been determined that the user is interested in science. The user's question is 'Why does it rain?' Please provide appropriate hints from a scientific perspective." The input data is the question text and the analysis results. The output data is the generated prompt sentence.

[1839] Step 5:

[1840] The generative AI model generates a hint. The server inputs the generated prompt sentence into the generative AI model. The generative AI model (for example, a model using natural language processing technology) generates an appropriate hint for the user's question based on the prompt sentence. For example, it generates the hint, "Why not investigate the process by which water vapor cools, forms clouds, and then falls as rain?" The input data is the prompt sentence. The output data is the generated hint.

[1841] Step 6:

[1842] The server receives the generated hint and sends it to the terminal. The server receives the hint generated from the generative AI model. The server then sends this hint to the user's terminal. The input data is the generated hint. The output data is the hint sent to the terminal.

[1843] Step 7:

[1844] The terminal displays the hint to the user. The terminal receives the hint sent from the server and displays it to the user. The user can check the hint on the terminal screen. The input data is the hint sent from the server. The output data is the hint displayed on the terminal screen.

[1845] (Application example 2)

[1846] Next, a description will be given of Application Example 2 of Form 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."

[1847] Conventional generative AI systems often provide direct answers to user questions, making it difficult for users to develop the ability to find answers on their own. They also lack the ability to provide hints that take into account the user's learning ability and interests, resulting in reduced learning efficiency. Furthermore, they lack the ability to analyze the user's past learning history and interests to optimize the generation of next hints, making it difficult to provide continuous learning support.

[1848] 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.

[1849] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for generating hints taking into account the user's learning ability and interests, means for analyzing the user's past learning history and interests, and means for generating hints based on the generated prompt sentences. This enables the user to develop the ability to find answers on their own and improve learning efficiency. Furthermore, continuous learning support can be realized by analyzing the user's past learning history and interests to optimize the generation of next hints.

[1850] "Generative AI" is an artificial intelligence system that generates answers and hints in natural language based on user input.

[1851] "User learning ability" refers to the ability of a user to acquire new knowledge or skills.

[1852] "User interests" refers to the interest a user has in a particular field or topic.

[1853] A "hint" is a clue or suggestion that helps users find the answer themselves.

[1854] A "prompt sentence" is an input sentence that a generative AI uses to generate appropriate hints in response to a user's question.

[1855] "Learning history" refers to a record of a user's past learning content and activities.

[1856] "Optimization" is the adjustment of systems or processes to maximize efficiency and effectiveness in order to achieve a specific purpose.

[1857] A system for implementing this invention utilizes generative AI to provide hints and methods for finding answers on one's own, rather than providing direct answers to questions from users. The system has a function for generating hints that takes into account the user's learning ability and interests, and a function for analyzing the user's past learning history and interests. It also includes a function for generating hints based on generated prompt sentences.

[1858] The server receives the user's question and profile as input and analyzes the user's interests. Specifically, it identifies areas of interest from the user's profile and generates an appropriate prompt for the user's question. Based on the generated prompt, the generative AI generates hints and provides them to the user.

[1859] This system is implemented using OpenAI's API, which uses a generative AI model to generate answers and hints in natural language. The server receives the user's question and profile, generates a prompt, and sends it to OpenAI's API. The hints returned by the API are then provided to the user.

[1860] As a concrete example, if a user asks "Why does it rain?" and the user profile contains "science", the generated prompt would be:

[1861] We've determined that you're interested in science. Please provide some scientific clues to the following questions:

[1862] Question: Why does it rain?

[1863] Tip:

[1864] By inputting this prompt into the OpenAI API, an appropriate hint is generated, such as "Why not investigate the process by which water vapor cools, forms clouds, and then falls as rain?"

[1865] This system allows users to develop the ability to find answers on their own and improve their learning efficiency. It also provides continuous learning support by analyzing the user's past learning history and interests to optimize the generation of next hints.

[1866] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1867] Step 1:

[1868] The user enters a question.

[1869] The user inputs a question using a terminal and sends it to the server. The input data is the user's question and profile information.

[1870] Step 2:

[1871] The server analyzes the user's interests.

[1872] The server analyzes the received user profile information and identifies the user's areas of interest. Specifically, it extracts areas of interest (e.g., science, technology, etc.) contained in the profile information. The input is the user's profile information, and the output is the user's areas of interest.

[1873] Step 3:

[1874] The server generates a prompt.

[1875] The server generates a prompt based on the user's question and interests. Specifically, it creates a prompt using a template based on the user's interests. The input is the user's question and interests, and the output is the generated prompt.

[1876] Step 4:

[1877] The server calls the generative AI model.

[1878] The server sends the generated prompt to the OpenAI API and generates appropriate hints. The input is the generated prompt, and the output is the hint returned by the generative AI model.

[1879] Step 5:

[1880] The server provides the hint to the user.

[1881] The server sends the generated hints to the user's device and displays them to the user. The input is the hint returned from the generative AI model, and the output is the hint displayed on the user's device.

[1882] Step 6:

[1883] The server updates the user's learning history.

[1884] The server tracks the hints received by the user and their subsequent actions, and updates the learning history. Specifically, it records what hints the user received and what actions they took based on them. The input is the user's behavioral data, and the output is the updated learning history.

[1885] Step 7:

[1886] The server will optimize the next hint generation.

[1887] The server optimizes the next hint generation based on the updated learning history. Specifically, it analyzes the past learning history and adjusts the algorithm to provide optimal hints based on the user's learning patterns. The input is the updated learning history, and the output is the optimized hint generation algorithm.

[1888] Example 3

[1889] Next, a third embodiment of the third embodiment will be described. 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."

[1890] Conventional generative AI systems have focused on providing direct answers to users, and lacked the means to support users in the process of finding the answer themselves. Furthermore, hints were not generated taking into account the user's learning ability or interests, making it difficult to provide learning support optimized for each individual user. Furthermore, there was no mechanism to utilize user behavior data to optimize the generation of next hints, making it impossible to improve users' learning efficiency.

[1891] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes: a means for utilizing generative AI to provide hints and methods for finding the answer on one's own, rather than providing a direct answer to a question from a user; a means for tracking user behavior and collecting behavioral data such as search keywords, viewed web pages, and the time it took to find the answer; a means for storing the collected behavioral data in a database and using it to generate the next hint; and a means for the generative AI model to analyze the stored behavioral data and optimize the next hint. This makes it possible to support the process of users finding the answer on their own and provide hints optimized for each user.

[1892] "Generative AI" is an artificial intelligence system that generates answers and hints in natural language based on user input.

[1893] "User" means an individual or entity that uses the system to ask questions and obtain clues and answers.

[1894] A "hint" is information that provides clues or directions to help users find the answer themselves.

[1895] "Behavioral data" refers to information such as search keywords generated when users use the system, the web pages they view, and the time it takes them to find an answer.

[1896] A "database" is a system for storing and managing collected behavioral data.

[1897] A "generative AI model" is an algorithm or program that analyzes collected behavioral data and generates hints for the next time.

[1898] "Optimization" is the process of adjusting the difficulty and content of the next hint based on user behavior data.

[1899] This invention is a system that utilizes generative AI to support users in the process of finding solutions themselves. A specific embodiment of this system is described below.

[1900] Hardware and software used

[1901] Hardware: Servers, user devices (PCs, smartphones, etc.)

[1902] Software: Generative AI models (e.g., GPT-4), database management systems (e.g., MySQL), web browsers (e.g., Google Chrome)

[1903] System Overview

[1904] This system tracks user behavior and optimizes the generation of the next hint based on the collected behavioral data. Specifically, it optimizes the generation of the next hint based on information such as what information the user searched for based on the previous hint and how long it took them to find the answer.

[1905] Program processing

[1906] 1. User behavior tracking:

[1907] A user logs in to the system using a terminal.

[1908] The server provides the user with initial hints using a generative AI model.

[1909] The user searches for information based on the hints, and behavioral data such as the search engine used, the URL of the web page viewed, and search keywords are sent from the device to the server.

[1910] The server tracks user behavior data in real time and measures the time it takes to find the answer.

[1911] 2. Data Collection and Storage:

[1912] The server collects user behavior data.

[1913] The server stores the collected data in a database management system (e.g., MySQL).

[1914] The server organizes and analyzes the stored data to use in generating next hints.

[1915] 3. Hint generation optimization:

[1916] The server analyzes the user behavior data stored in the database.

[1917] The generative AI model generates the next hint based on the analysis results.

[1918] The server provides the generated hint to the user.

[1919] Specific examples

[1920] For example, if a user receives a hint saying, "Find out the meaning of the following word," and then searches for the word "example" on Google and finds the answer within a few seconds, the next time the system will offer a more challenging hint, such as, "Find out the meaning of the following sentence."

[1921] Prompt Sentence Examples

[1922] Below are some examples of prompts for generative AI models:

[1923] The user had 10 seconds to find the answer based on the previous hint. Please generate the next hint. Please adjust the difficulty to increase the difficulty.

[1924] In this way, the system can optimize the user's learning process and provide more effective hints. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1925] Step 1: Track user behavior

[1926] Input: The user logs into the system using a terminal and receives an initial hint.

[1927] Specific operation: The server uses the generative AI model to provide the user with an initial hint, and the user begins searching for information based on the hint.

[1928] Data processing: Behavioral data such as the search engine used by the user, the URL of the web page viewed, and search keywords are sent from the device to the server.

[1929] Output: The server tracks user behavior data in real time and measures the time it takes to find the answer.

[1930] Step 2: Collect and store data

[1931] Input: The server receives user behavior data.

[1932] What it does: The server collects behavioral data such as users' search keywords, the URLs of web pages they visited, and the time it took them to find an answer.

[1933] Data processing: The collected behavioral data is stored in a database management system (e.g., MySQL).

[1934] Output: The server organizes and analyzes the stored data for use in generating next hints.

[1935] Step 3: Optimizing hint generation

[1936] Input: The server receives user behavior data stored in a database.

[1937] Specific operation: The server analyzes the behavioral data and generates the next hint taking into account the user's learning ability and interests.

[1938] Data processing: The generative AI model generates the next hint based on the analysis results.

[1939] Output: The server provides the generated hint to the user.

[1940] Specific examples

[1941] For example, if a user receives a hint saying, "Find out the meaning of the following word," and then searches for the word "example" on Google and finds the answer within a few seconds, the next time the system will offer a more challenging hint, such as, "Find out the meaning of the following sentence."

[1942] Prompt Sentence Examples

[1943] Below are some examples of prompts for generative AI models:

[1944] The user had 10 seconds to find the answer based on the previous hint. Please generate the next hint. Please adjust the difficulty to increase the difficulty.

[1945] (Application example 3)

[1946] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1947] Conventional learning support systems have difficulty tracking a user's learning process individually and optimizing the next learning content and hints based on the results. Furthermore, they have had problems generating hints that do not sufficiently take into account the user's learning ability and interests, making it difficult to provide effective learning support. This can lead to a decrease in the user's learning efficiency and motivation to learn.

[1948] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1949] In this invention, the server utilizes generative AI and includes means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user, means for tracking what information the user searches for based on the previous hint and how long it takes to find the answer, and means for optimizing the generation of the next hint based on the tracking results. This makes it possible to individually track the user's learning process and optimize the next learning content and hints based on the results.

[1950] "Generative AI" is an artificial intelligence system that generates information based on user input and provides appropriate hints and answers.

[1951] A "hint" is information that provides clues or directions to help users find the answer themselves.

[1952] "Tracking" is the process of recording what information the user searches for based on the previous hint and how long it takes them to find the answer.

[1953] "Optimization" means adjusting the next hint generation based on the tracking results to maximize the user's learning efficiency.

[1954] "Learning ability" is the user's ability to understand, remember, and apply new information.

[1955] An "interest" is a user's interest or curiosity about a particular topic or activity.

[1956] A "system" is a set of devices and programs that work together with multiple elements such as generative AI, hint provision means, tracking means, and optimization means.

[1957] As an embodiment of this invention, a learning support system is constructed. The system utilizes generative AI and includes a means for providing hints and methods for finding answers on the user's own, rather than providing direct answers to questions from the user. Furthermore, the system includes a means for tracking what information the user searches for based on the previous hint and how long it takes to find the answer, and a means for optimizing the generation of the next hint based on the tracking results.

[1958] Hardware and software used

[1959] Hardware: Smartphone

[1960] Software: Python, JSON, generative AI models

[1961] System configuration

[1962] 1. Generative AI models: Generate information based on user input and provide appropriate hints and answers.

[1963] 2. Hint methods: provide clues or instructions to help users find the answer themselves.

[1964] 3. Tracking: Record what information the user searches for based on the previous hint and how long it takes them to find the answer.

[1965] 4. Optimization measures: Based on the tracking results, the next hint generation is adjusted to maximize the user's learning efficiency.

[1966] Processing flow

[1967] The server has the ability to adjust the hints and difficulty of the questions provided to the user as they study. It tracks what kind of searches the user performed based on the previous hint and how much time they spent on it, and uses that data to optimize the next hint.

[1968] Specific examples

[1969] For example, if a user receives "Hint 1" and finds the answer in 45 seconds, a more difficult hint will be provided the next time. In this way, the learning process of each user can be tracked individually, and the learning content and hints for the next time can be optimized based on the results.

[1970] Prompt Sentence Examples

[1971] "Write a Python program that tracks what information the user searches for based on the previous hint, how long it takes them to find the answer, and then uses that data to optimize the next hint."

[1972] The above is an embodiment of the present invention.

[1973] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1974] Step 1:

[1975] The user enters a question.

[1976] Input: User question text

[1977] Processing: The device receives the user's question and sends it to the generative AI model.

[1978] Output: The question text is passed to the generative AI model.

[1979] Step 2:

[1980] A generative AI model generates hints.

[1981] Input: Question text

[1982] Processing: The server uses a generative AI model to generate hints based on the question text. The generative AI model generates hints taking into account the user's learning ability and interests.

[1983] Output: Hint text

[1984] Step 3:

[1985] The user finds the answer based on the hints.

[1986] Input: Hint text

[1987] Processing: The user searches for information based on the hints and finds the answer. The device records the user's search query and the search time.

[1988] Output: Search query, search time

[1989] Step 4:

[1990] The device tracks the user's activities.

[1991] Input: search query, search time

[1992] Processing: The device records what information the user searches for based on the hints and how long it takes. This data is sent to the server.

[1993] Output: User activity data (search queries, search times)

[1994] Step 5:

[1995] The server will optimize the next hint generation.

[1996] Input: User activity data

[1997] Processing: The server analyzes the user activity data and optimizes the next hint generation. For example, if the user finds the answer in a short time, the server will generate a more difficult hint next time.

[1998] Output: Optimized hint generation parameters

[1999] Step 6:

[2000] The server provides optimized hints to the user.

[2001] Input: Optimized hint generation parameters

[2002] Processing: The server generates the next hint based on the optimized parameters and provides it to the user.

[2003] Output: Next hint text

[2004] The above are the specific processing steps for carrying out the present invention.

[2005] 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.

[2006] "Example 1"

[2007] In one embodiment of the present invention, the generative AI receives a question from a user and generates hints for that question. It uses an emotion engine to recognize the user's emotions and tailors the generation of hints based on those emotions. For example, if the user expresses joy, it generates more positive hints. On the other hand, if the user expresses confusion or anxiety, it generates more specific and detailed hints.

[2008] "Example 2"

[2009] In another embodiment, the emotion engine tracks changes in the user's emotions and optimizes the next hint generation based on the results. For example, if the user expressed a happy emotion in response to the previous hint, the emotion engine generates a similar hint. On the other hand, if the user expressed a dissatisfied emotion in response to the previous hint, the emotion engine uses a different approach in the next hint generation.

[2010] "Example 3"

[2011] In yet another embodiment, the emotion engine recognizes the user's emotion and generates hints based on the emotion, taking into account the user's learning ability and interests. For example, if the user is excited, the emotion engine generates hints to maintain the excitement. If the user is depressed, the emotion engine generates hints to reduce the depression.

[2012] The processing flow of each embodiment will be described below.

[2013] "Example 1"

[2014] Step 1: The generative AI receives a question from the user.

[2015] Step 2: Recognize the user's emotions using the emotion engine.

[2016] Step 3: Adjust the generation of hints based on the recognized emotions.

[2017] Step 4: Provide the adjusted hints to the user.

[2018] "Example 2"

[2019] Step 1: The emotion engine tracks changes in the user's emotions.

[2020] Step 2: Optimize the next hint generation based on the tracked emotion changes.

[2021] Step 3: Provide optimized tips to users.

[2022] "Example 3"

[2023] Step 1: The emotion engine recognizes the user's emotion.

[2024] Step 2: Generate hints that take into account the recognized emotions and the user's learning ability and interests.

[2025] Step 3: Provide the generated hints to the user.

[2026] Example 1

[2027] Next, a description will be given of Example 1 of Form 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."

[2028] Conventional generative AI systems often provide direct answers to user questions, lacking support for users to find answers on their own. Furthermore, they provide uniform answers without considering the user's feelings, which can lead to a decrease in user satisfaction. Furthermore, the lack of technology to provide appropriate hints based on the user's feelings can leave users feeling confused and anxious.

[2029] 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.

[2030] In this invention, the server includes means for a user to input a question, means for the server to receive the question, means for the server to send the question to an emotion engine, means for the emotion engine to analyze the user's emotion, means for the server to send a prompt sentence to the generative AI model, means for the generative AI model to generate a hint, and means for the server to return the generated hint to the user. This makes it possible to provide appropriate hints according to the user's emotion and support the user in finding the answer themselves.

[2031] "User" refers to a person who accesses the system and enters a question.

[2032] The "server" refers to a computer system that receives questions from users, works with an emotion engine and generative AI models to generate hints, and responds to the user.

[2033] "Emotion engine" refers to software or hardware for analyzing a user's question and identifying the user's emotion.

[2034] A "generative AI model" refers to an artificial intelligence model that generates hints to answer a user's question based on a prompt sentence.

[2035] A "prompt sentence" refers to text data that contains instructions for generating hints for a generative AI model.

[2036] A "hint" is information that provides a method or clue for the user to find the answer on their own.

[2037] "Natural language processing technology" refers to technology for analyzing text data and understanding meaning and emotions.

[2038] This invention is a system that utilizes a generative AI model to provide hints to users' questions. The system includes a series of processes: a user inputs a question, a server receives the question, an emotion engine analyzes the user's emotions, a generative AI model generates a prompt sentence to generate a hint, and finally a response to the user.

[2039] Hardware and software used

[2040] server

[2041] The server receives questions from users, works with the emotion engine and generative AI model to generate hints, and responds to the users. The server is a computer system equipped with a high-performance processor and sufficient memory.

[2042] Terminal

[2043] A terminal is a device that allows users to access the system and input questions. Terminals include PCs, smartphones, tablets, etc.

[2044] Emotion Engine

[2045] The emotion engine is software that analyzes user questions and identifies their emotions. It uses natural language processing technology to analyze emotions from text data.

[2046] Generative AI Models

[2047] A generative AI model is an artificial intelligence model that generates hints for a user's question based on a prompt sentence. The generative AI model is trained using deep learning techniques.

[2048] Data processing and calculation

[2049] When the server receives a question from a user, it sends the question to the emotion engine, which uses natural language processing technology to analyze the question text and identify the user's emotion. The analysis results are sent back to the server, which then sends a prompt to the generative AI model based on the results.

[2050] The generative AI model receives the prompt sentence and generates appropriate hints according to the user's emotions. The generated hints are sent back to the server, which then responds to the user.

[2051] Specific examples

[2052] For example, consider the case where a user uses a terminal to input a question such as "What's the weather like in Tokyo?" The server receives this question and sends it to the emotion engine. The emotion engine analyzes the question to determine that the user is expressing the emotion of happiness, and sends the result back to the server.

[2053] The server sends the following prompt to the generative AI model:

[2054] The user asks "What's the weather in Tokyo?" and expresses joy. Generate a positive hint.

[2055] Based on this prompt, the generative AI model generates a hint: "Why don't you check the weather forecast website?" The server returns this hint to the user, who can then check it on their device.

[2056] In this way, the system provides appropriate hints according to the user's emotions and helps the user find the answer by themselves.

[2057] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2058] Step 1:

[2059] The user inputs a question using a terminal. The user opens the terminal's browser, accesses the system's web page, enters "What's the weather in Tokyo?" in the search bar, and presses the send button. The input data is sent to the server in text format.

[2060] Step 2:

[2061] The server receives the question. The server receives the HTTP request and extracts the text "What's the weather in Tokyo?" from the request body. This text is temporarily stored in memory. The input is the user's question text, and the output is the extracted text data.

[2062] Step 3:

[2063] The server sends a question to the emotion engine. The server uses the REST API to send the text "What's the weather in Tokyo?" to the emotion engine. The API request contains text data. The input is the extracted text data, and the output is the API request to the emotion engine.

[2064] Step 4:

[2065] The emotion engine analyzes the user's emotions. The emotion engine analyzes the received text using a natural language processing algorithm and determines that the user is expressing the emotion of joy. The result is sent back to the server in JSON format. The input is text data, and the output is the JSON data of the analysis results.

[2066] Step 5:

[2067] The server sends a prompt to the generative AI model. Based on the analysis results obtained from the emotion engine, the server sends a prompt to the generative AI model saying, "The user is expressing joy. Please generate a positive hint." The prompt is sent as an API request. The input is the JSON data of the analysis results, and the output is the prompt to the generative AI model.

[2068] Step 6:

[2069] The generative AI model generates a hint. The generative AI model receives the prompt and generates a hint such as "Why not check the weather forecast website?" This hint is sent back to the server in text format. The input is the prompt, and the output is the generated hint text data.

[2070] Step 7:

[2071] The server returns the generated hint to the user. The server sends the hint received from the generative AI model back to the user as an HTTP response. The user can check the hint "Why don't you check the weather forecast website?" in the browser on their device. The input is the text data of the generated hint, and the output is the HTTP response to the user.

[2072] (Application example 1)

[2073] Next, a description will be given of Application Example 1 of Form 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."

[2074] Conventional generative AI systems often provide direct answers to user questions, making it difficult for users to develop the ability to find answers on their own. Furthermore, they provide uniform hints without considering the user's feelings, which means they are unable to provide appropriate support based on the user's situation and emotions. For security-related questions in particular, it is necessary to provide specific and useful hints while easing the user's anxiety.

[2075] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for utilizing generative AI to provide hints and methods for finding answers on the user's own rather than providing direct answers to questions from the user, means for adjusting the generation of hints based on the user's emotions using an emotion engine that recognizes the user's emotions, and means for providing solutions and hints when the user asks a security question. This makes it possible to provide appropriate hints according to the user's emotions and develop the user's ability to find answers on their own.

[2076] "Generative AI" is an artificial intelligence technology that generates new information and answers based on user input.

[2077] An "emotion engine" is a technology that recognizes a user's emotions and adjusts the system's response based on those emotions.

[2078] A "hint" is information that provides clues or methods to help users find the answer themselves.

[2079] "Security" refers to the technologies and methods used to protect information and systems from unauthorized access and attacks.

[2080] A "question" is an inquiry a user makes to the system about information they want to know or a problem they want to solve.

[2081] "Solutions" are information that provides specific solutions or steps to address problems or questions users face.

[2082] "User" refers to any individual or organization that uses the System.

[2083] "Adjustment" refers to changing the system's responses and hints based on the user's emotions and situation.

[2084] The system for implementing this invention consists of a server including a generative AI, an emotion engine, and a user interface, and a terminal used by the user.

[2085] System Program

[2086] Program processing explanation

[2087] 1. Input Processing:

[2088] The user enters the question in text format using a device such as a smartphone or PC.

[2089] Hardware used: Smartphone, PC

[2090] Software used: Text input interface

[2091] 2. Emotion recognition:

[2092] The server receives the user's input text and recognizes the user's emotion using an emotion engine.

[2093] Software used: Emotion recognition API (e.g. IBM Watson Tone Analyzer)

[2094] 3. Hint generation:

[2095] The server uses a generative AI model to generate hints for the user's questions.

[2096] Software used: Generative AI models (e.g., OpenAI GPT-4)

[2097] 4. Adjusting the hints:

[2098] The server adjusts the generated hints based on the results of the emotion engine.

[2099] Software used: Custom logic

[2100] 5. Output Processing:

[2101] Display tailored hints on the user's device.

[2102] Hardware used: Smartphone, PC

[2103] Software used: Text display interface

[2104] Specific examples

[2105] For example, if a user asks, "I've been receiving a lot of phishing emails lately. What should I do about it?" the system will act as follows:

[2106] 1. The user enters a question using their smartphone.

[2107] 2. The server receives the question and uses the emotion engine to recognize the user's emotion. In this case, it recognizes that the user is feeling anxious.

[2108] 3. The generative AI model learns the characteristics of phishing emails and generates hints such as "Don't open suspicious emails."

[2109] 4. Based on the results of the sentiment engine, the server adjusts to provide more detailed hints, such as "Let's take a look at some specific examples of phishing emails."

[2110] 5. The tailored hints are displayed on the user's smartphone.

[2111] Example prompt sentence:

[2112] User Question: I've been getting a lot of phishing emails lately, what should I do?

[2113] User Emotion: Anxiety

[2114] Tip: Learn the signs of phishing emails and avoid opening suspicious emails. Let's look at some examples of phishing emails.

[2115] In this way, it is possible to provide appropriate hints according to the user's emotions and develop the user's ability to find the answer by themselves.

[2116] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2117] Step 1:

[2118] The user inputs a question in text format using a terminal. The input text is sent to the server through the terminal's text input interface. The input data is the user's question.

[2119] Step 2:

[2120] The server passes the received user question text to the emotion engine. The emotion engine analyzes the text data and recognizes the user's emotion. Specifically, it uses an emotion recognition API (e.g., IBM Watson Tone Analyzer) to extract emotional information from the text. The output is the user's emotional state (e.g., anxiety, joy, confusion).

[2121] Step 3:

[2122] The server passes the user's question text and the emotion engine's output to a generative AI model. The generative AI model (e.g., OpenAI GPT-4) generates hints for the user's question based on these input data. The generated hints are information that provides clues and methods for the user to find the answer themselves.

[2123] Step 4:

[2124] The server adjusts the generated hints based on the results of the emotion engine. Specifically, it changes the content and level of detail of the hints depending on the user's emotional state. For example, if the user is feeling anxious, it adjusts the hints to provide more specific and detailed information. The output is the adjusted hint information.

[2125] Step 5:

[2126] The server sends the adjusted hint information to the user's terminal, which displays the received hint information to the user through a text display interface, allowing the user to find the answer by themselves using the displayed hint.

[2127] In this way, it is possible to provide appropriate hints according to the user's feelings and develop the user's ability to find the answer by themselves.

[2128] Example 2

[2129] Next, a description will be given of Example 2 of Form 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."

[2130] Conventional generative AI systems primarily provide direct answers to user questions, but lack the support required for users to find answers on their own. Furthermore, they do not generate hints that take into account the user's learning ability or interests, and they lack the ability to track changes in the user's emotions to optimize the generation of next hints. This reduces the effectiveness of user learning and reduces satisfaction.

[2131] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2132] In this invention, the server does not provide direct answers to questions from users, but includes means for providing hints and methods for finding answers on the user's own, means for utilizing generative AI to analyze user input and identify interests, means for generating appropriate hints based on the user's interests, and mean...

Claims

[Claim 1] A system that uses generative AI to provide a user with suggestions to help the user reach an answer to a question from the user, means for receiving a question from the user; means for analyzing the user's interests from the user's past question history using a machine learning algorithm; means for recording, in a log, behavioral data of the user leading up to the answer, including search keywords, web pages viewed, and the time taken to find the answer; means for recognizing, in real time, the emotions of the user based on the facial expressions of the user by using an emotion engine and an emotion recognition algorithm; means for generating a prompt sentence that instructs the user to provide suggestions leading to an answer to the question, the prompt sentence including an instruction to take into consideration the user's interests and an instruction to adjust the difficulty of the suggestions to be provided to the user in response to the behavioral data or the emotional data, based on the interest analysis result, the behavioral data recorded in the log, and the emotional data recognized by the emotional engine; A means for inputting the generated prompt sentence into the generation system AI; means for receiving an output from the generative AI; means for providing the received output to the user; A system including:

Images