system

Abstract

Provide a system. The method includes: receiving an education inquiry written in natural language; a natural language processing engine that analyzes incoming inquiries and identifies their intent; A means for searching a database for similar past educational cases based on the analysis results; A generative AI engine that generates educational method recommendations based on search results; a means of providing generated recommendations to educators; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, the field of education has seen the development of diverse teaching methods and teaching materials, but there is a lack of means for individual teachers to receive appropriate feedback and suggestions on their own teaching methods. Furthermore, there are insufficient support systems to provide quick and effective solutions to students' lack of understanding or learning difficulties that arise during class. As a result, teachers often feel anxious about their own teaching methods, making it difficult to maximize students' learning outcomes. Therefore, there is a need to provide a system that allows teachers to quickly receive appropriate suggestions for improving their teaching methods. [Means for solving the problem]

[0005] The present invention provides a system equipped with a natural language processing engine that receives educational inquiries written in natural language, analyzes them, and identifies their intent. This allows appropriate feedback to be provided to teachers in response to their specific educational concerns or concerns. Furthermore, the system includes a generative artificial intelligence engine that searches a database for similar past educational cases based on the analysis results and generates educational method recommendations based on the search results. This allows teachers to receive recommendations for rapid and effective educational improvement. Furthermore, the generated recommendations are provided to educators to support their implementation in the classroom. This provides a reliable source of information for teachers to review and improve their educational methods, thereby improving the quality of education.

[0006] A "natural language processing engine" is a computer program for understanding, analyzing, and identifying intent in natural language.

[0007] An "education database" is a collection of information that stores past cases, materials, and data related to education.

[0008] A "generative artificial intelligence engine" is a program that uses machine learning and artificial intelligence technology to generate new recommendations and solutions.

[0009] "Teacher" refers to a professional who provides educational activities to students at an educational institution.

[0010] "Educational methods" is a general term for the teaching methods and educational techniques that teachers use with students.

[0011] "Inquiry" refers to the act of a teacher asking questions about issues related to their teaching methods or students' understanding.

[0012] A "proposal" is a proposal that shows specific solutions or improvements to an issue or problem.

[0013] "Receiving" refers to the act of a terminal or server taking in data or requests from the outside.

[0014] "Analysis" refers to breaking down data or information into smaller pieces and processing it to understand its meaning and intent.

[0015] "Searching" is the act of examining a database or source to locate specific data or information.

[0016] "Generation" is the act of creating new information or data, especially when artificial intelligence creates new output based on given data.

[0017] "Providing" refers to the act of transmitting the generated information or recommendations to the user and making them available for use.

[0018] A "terminal" is a device such as a computer or tablet that is operated by a user.

[0019] A "server" is a high-performance computer that manages and processes data on a network.

[0020] "Similar cases" are situations or problems that occurred in the past that share characteristics with the current inquiry. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

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

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] This invention relates to a system that analyzes problems and provides appropriate suggestions when a teacher asks for advice or has a question about teaching methods. This system starts when a user (teacher) sends a query to a server via a terminal.

[0043] Overall system configuration

[0044] 1. User inquiry submission

[0045] Users (teachers) use their own devices to input questions or concerns about teaching methods in natural language. For example, they might type something like, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field on the screen.

[0046] 2. Receiving and analyzing on the server

[0047] The device receives this input and sends it to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine. The natural language processing engine analyzes the received query and identifies the intent of the query (e.g., "math class" or "student's lack of understanding").

[0048] 3. Search for similar past cases

[0049] Based on the analysis results, the server accesses an educational database to search for similar educational cases that have occurred in the past, thereby obtaining a list of methods and success stories that have been used to solve similar problems.

[0050] 4. Recommendation generation using a generative AI engine

[0051] The server creates and sends prompts to the generative AI engine based on the retrieved similar cases and the inquiry content. The generative AI engine then generates appropriate teaching method recommendations for the teacher based on these prompts. For example, recommendations might include "use visual tools to help students understand formulas" or "introduce group work to encourage students to discuss among themselves."

[0052] 5. Providing Recommendations

[0053] The generated recommendations are sent from the server to the client terminal and provided to the teacher. The terminal displays the received recommendations, allowing the teacher to review them and incorporate them into their own teaching methods.

[0054] Specific examples

[0055] Let's say a teacher is faced with a problem in a junior high school mathematics class where a student is struggling to solve a quadratic equation. The teacher sends an inquiry via a terminal saying, "The student is having trouble understanding how to solve a quadratic equation. Please suggest an effective solution."

[0056] The server receives the query and uses a natural language processing engine to identify the intent—"quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past examples of solving quadratic equations." Based on this data, a generative AI engine generates recommendations, providing specific suggestions to teachers, such as "use visual aids to demonstrate the process of solving the equation as an operational approach" and "implement pair work to create opportunities for students to learn from each other."

[0057] In this way, the present invention provides teachers with prompt and specific suggestions for the educational challenges they face, contributing to the improvement of teaching methods. This system is a groundbreaking means of providing support to teachers to achieve higher educational effectiveness.

[0058] The processing flow will be explained below.

[0059] Step 1: The user enters a query using a terminal.

[0060] A teacher types into the device interface, "There are some areas in my math class where students are struggling to understand. Can you suggest some effective solutions?"

[0061] When the teacher clicks the submit button, the input data is sent.

[0062] Step 2: The device sends a query to the server.

[0063] The terminal converts the teacher's input data into JSON format and sends it to the server as an HTTP POST request.

[0064] Step 3: The server receives the request.

[0065] The server receives the request from the device and records it in a log.

[0066] Check that the received data is in the correct format.

[0067] Step 4: The server calls the natural language processing engine.

[0068] The server passes the received education-related inquiries to a natural language processing engine for intent analysis.

[0069] A natural language processing engine analyzes the query and identifies the topic of the query (mathematics) and the type of problem (lack of understanding).

[0070] Step 5: The server accesses the education database.

[0071] The server accesses the education database based on the analysis results and searches for similar education cases.

[0072] Obtain a list of similar cases and check their contents.

[0073] Step 6: The server creates a prompt for the generative AI.

[0074] A prompt is created based on the similar cases acquired by the server and the inquiry content.

[0075] Prompts are instructions that the generative AI engine uses to generate appropriate recommendations.

[0076] Step 7: The server invokes the generative AI.

[0077] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[0078] A generative AI analyzes the prompts and generates new recommendations.

[0079] Step 8: The server retrieves the generated recommendations.

[0080] The server receives the recommendations generated by the generative AI engine.

[0081] Review the proposal and put it into the appropriate format.

[0082] Step 9: The server sends the recommendation to the user.

[0083] The server transmits the generated recommendations to the user's terminal.

[0084] It is sent as an HTTP response and provided to the teacher.

[0085] Step 10: Your device will display a recommendation.

[0086] The terminal receives the response from the server and displays the recommendations to the teacher on the interface.

[0087] Teachers can review the proposed methods and put them into practice.

[0088] Specific examples

[0089] For example, if a teacher is teaching a math class and a student is struggling to understand a particular formula, the process might proceed as follows:

[0090] 1. The teacher types into the terminal, "Student does not understand how to solve the quadratic equation. Please suggest a solution."

[0091] 2. The device sends the input data to the server.

[0092] 3. The server receives the query and analyzes it using a natural language processing engine.

[0093] 4. The server searches the educational database for past "case studies on understanding quadratic equations."

[0094] 5. The server creates a prompt based on the acquired examples and sends it to the generative AI.

[0095] 6. Generative AI generates recommendations such as "Use visual models to visualize how to solve quadratic equations" or "Introduce group work to encourage discussion among students."

[0096] 7. The server sends the generated proposal to the teacher's terminal, and the terminal displays the proposal to the teacher.

[0097] In this way, the system allows teachers to quickly obtain concrete suggestions for improving their teaching methods.

[0098] Example 1

[0099] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0100] It is difficult for educators to find quick and effective solutions to problems and questions about teaching methods. In particular, it takes time and effort to obtain specific teaching method recommendations while referring to past cases. To solve this problem, a system is needed that allows educators to consult about teaching methods in natural language and quickly obtain appropriate recommendations.

[0101] 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.

[0102] In this invention, the server includes means for receiving an inquiry about education written in natural language, means for transmitting the received inquiry to the server as JSON format data, means for passing the received data to a natural language processing engine and identifying the intent of the inquiry, means for searching an education database for similar past education cases based on the analysis results, means for transmitting prompts to the generative artificial intelligence engine based on the acquired case data and the inquiry content, and means for providing the generated recommendations to the educator. This enables educators to obtain quick and effective recommendations based on specific past education cases through inquiries in natural language.

[0103] "Inquiries about education written in natural language" refers to text data entered by educators in everyday language as consultations or questions about their own educational activities.

[0104] "Receiving means" refers to the mechanism or method by which the server receives data sent from the user.

[0105] "JSON format data" is a format that treats data as a text-based object representation, and refers to a simple way to describe structured data.

[0106] A "natural language processing engine" is a software engine for analyzing meaning and intent from input text data, and specifically refers to technology for understanding and processing natural language.

[0107] An "educational database" is a data storage system that stores data on previously solved educational cases and methods.

[0108] A "generative artificial intelligence engine" is an artificial intelligence engine that generates appropriate advice and recommendations based on a pre-trained model.

[0109] A "prompt" is text data of instructions or questions input to a generative AI engine.

[0110] "Means for providing recommendations" refers to the mechanisms or methods for displaying or notifying educators of generated recommendations.

[0111] This invention relates to a system that analyzes problems and provides appropriate recommendations when educators ask for advice or questions about educational methods. This system is primarily composed of a user (educator) terminal, a server, a natural language processing engine, a generative artificial intelligence engine, and an educational database.

[0112] First, the user (educator) uses their own device (PC, tablet, smartphone, etc.) to input their inquiry or question about teaching methods in natural language. The device is provided with a dedicated application or a web interface that can be accessed from a browser. Specifically, the user types, "There are some areas in my math class where students are struggling to understand. Can you suggest an effective solution?" into the text field on the screen.

[0113] The device then sends the input query as an HTTP POST request to the server. The server receives the request using Node.js and parses it into JSON-formatted data. This data is then passed to a natural language processing engine designed using Python libraries (e.g., spaCy and Transformers) to analyze the intent of the text data. The natural language processing engine extracts key keywords and phrases from the received query, such as "math class" and "student's lack of understanding."

[0114] Next, based on the analysis results, the server uses MySQL (registered trademark) or MongoDB to search an education database that stores similar educational cases that have been solved in the past. For example, it uses an SQL query in the format "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of understanding"" to retrieve related educational cases.

[0115] Based on the acquired data, the server generates and sends appropriate prompts to the generative AI engine. The generative AI engine (e.g., OpenAI's GPT-3) uses these prompts to generate specific teaching method recommendations. For example, a prompt such as "Please suggest effective ways to help students understand mathematics" can be sent. Specific examples of generated recommendations include "Use visual tools to help students understand formulas" and "Introduce group work to encourage students to discuss among themselves."

[0116] Finally, the generated recommendations are sent from the server to the client device and provided to the educator. The device analyzes the received response and displays the recommendations to the educator on an application or browser. This allows the educator to incorporate the provided specific recommendations into their teaching methods and improve the quality of their lessons.

[0117] Prompt Sentence Examples

[0118] "Please suggest effective ways to help students understand mathematics."

[0119] "My students are struggling with grammar in English class. Can you tell me how to solve this?"

[0120] "What are some good ways to ensure safety during experiments in junior high school science classes?"

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

[0122] Program processing flow

[0123] Step 1:

[0124] User inquiry submission

[0125] Specific behavior:

[0126] The user (educator) uses a dedicated application on the device or a web interface to input questions or concerns about teaching methods in natural language. For example, they might type, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field.

[0127] input:

[0128] The natural language query text entered by the user.

[0129] output:

[0130] The query text is sent from the terminal to the server as an HTTP POST request.

[0131] Step 2:

[0132] Receiving and analyzing on the server

[0133] Specific behavior:

[0134] The server receives the HTTP POST request sent from the device. The server parses this request as JSON format data and passes the data to the natural language processing engine. The server uses Node.js to receive and parse the data.

[0135] input:

[0136] HTTP POST request (query text) sent from the terminal.

[0137] output:

[0138] Query data in JSON format is generated and passed to the natural language processing engine.

[0139] Step 3:

[0140] Intention analysis using a natural language processing engine

[0141] Specific behavior:

[0142] The server uses Python libraries (e.g., spaCy and Transformers) to analyze the intent of the query text. A natural language processing engine extracts keywords and phrases such as "math lessons" and "student lack of understanding."

[0143] input:

[0144] Query data in JSON format.

[0145] output:

[0146] Analysis results (keywords and phrases) are generated.

[0147] Step 4:

[0148] Search for similar past cases

[0149] Specific behavior:

[0150] Based on the analysis results, the server searches the education database using MySQL or MongoDB. For example, it executes an SQL query such as "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of Understanding"" to retrieve relevant education cases.

[0151] input:

[0152] Intent analysis results (keywords and phrases).

[0153] output:

[0154] Data on similar past cases obtained from an educational database.

[0155] Step 5:

[0156] Recommendation generation using a generative AI engine

[0157] Specific behavior:

[0158] The server generates a prompt (instruction sentence) based on the acquired case data and the inquiry content and sends it to the generative AI engine. For example, it inputs a prompt such as "Please suggest an effective way to help students understand mathematics" and sends it to the generative AI engine (e.g., GPT-3).

[0159] input:

[0160] Past similar case data and generated prompts.

[0161] output:

[0162] A recommendation statement is generated.

[0163] Step 6:

[0164] Providing recommendations

[0165] Specific behavior:

[0166] The generated recommendations are sent from the server to the client device, which then analyzes the received response and displays the recommendations to the educator on the application or browser.

[0167] input:

[0168] The generated recommendation.

[0169] output:

[0170] Specific recommendations provided to educators.

[0171] (Application example 1)

[0172] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0173] In conventional education-related systems, there are insufficient ways for teachers to receive quick and specific suggestions regarding teaching methods, and there are no means to provide real-time advice to store clerks on customer service methods, making it difficult to provide optimal service to customers.There is a need for a system that can provide effective suggestions and advice immediately in educational settings and in physical stores.

[0174] 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.

[0175] In this invention, the server includes: means for receiving inquiries about education written in natural language; a natural language processing engine for analyzing the received inquiries and identifying their intent; means for searching a database for similar past education cases based on the analysis results; a generative artificial intelligence engine for generating recommendations for education methods based on the search results; means for providing the generated recommendations to educators; means for store clerks to receive inquiries in real time about how to explain products and how to serve customers; the generative artificial intelligence engine for analyzing inquiries received from a smart device, searching for past customer service cases, and generating recommendations based on the results; and means including a smart device for providing the generated recommendations to store clerks. This enables educators to receive quick and specific recommendations in the field of education, and allows store clerks to receive appropriate customer service advice in real time in physical stores, thereby improving customer satisfaction.

[0176] A "natural language processing engine" is a software component that analyzes text written in natural language and identifies its intent and meaning.

[0177] "Educational methods" are the means and approaches that educators use to effectively impart knowledge and skills to students.

[0178] A "generative artificial intelligence engine" is an artificial intelligence model that generates new recommendations based on past cases and data.

[0179] A "device" is a hardware device for processing digital information, and specifically includes smartphones, smart glasses, head-mounted displays, etc.

[0180] An "inquiry" is a question or inquiry sent by a user to the system.

[0181] A "recommendation" is specific advice or instructions for solving a specific problem.

[0182] A "brick and mortar store" is a physical store where customers visit in person to purchase goods or services.

[0183] "Customer service methods" refer to the way in which store staff respond to and provide service to customers.

[0184] This invention is a system that analyzes problems and provides appropriate suggestions when teachers ask for advice or questions about teaching methods. Furthermore, this invention can also be applied to situations where store clerks in physical stores ask for advice or questions about customer service methods in real time.

[0185] Overall system configuration

[0186] 1. User inquiry submission

[0187] Users (teachers or store clerks) use their own devices (smartphones, smart glasses, head-mounted displays, etc.) to input questions or concerns about teaching methods or customer service methods in natural language. This input is done through a text field or voice input function. For example, a teacher might type, "My students are having trouble solving quadratic equations. Please suggest an effective solution," or a store clerk might ask, "Please tell me how to explain a new product."

[0188] 2. Receiving and analyzing on the server

[0189] The device sends this input to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine (e.g., spaCy or the BERT model). The natural language processing engine analyzes the received query and identifies the intent of the query. For example, intents such as "quadratic equations," "lack of understanding," "new product," and "explanation method" may be identified.

[0190] 3. Search for similar past cases

[0191] Based on the analysis results, the server accesses an education database or customer service database to search for similar cases that have occurred in the past. The server obtains methods and success stories that have been used to solve similar problems. Through this database search, the server finds useful past cases.

[0192] 4. Recommendation generation using a generative AI engine

[0193] Based on the acquired similar cases and the inquiry content, the server creates and sends a prompt to a generative AI engine (for example, OpenAI's GPT-3 model). The generative AI engine generates appropriate recommendations for the user based on this prompt. For example, in the case of education, a recommendation might be "use visual tools to help understand formulas," or in the case of a physical store, "explain product usage scenarios with videos and photos."

[0194] 5. Providing Recommendations

[0195] The generated recommendations are sent from the server to the client terminal and provided to the user. The terminal displays the received recommendations, allowing the user to improve their training and customer service methods based on the information.

[0196] Specific application examples

[0197] Consider a scenario in which a teacher is teaching junior high school mathematics and a student is struggling to solve a quadratic equation. The teacher sends a query via their device saying, "The student is struggling to understand how to solve a quadratic equation. Please suggest an effective solution." The server receives the query and uses a natural language processing engine to identify the intent - "quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past cases related to solving quadratic equations." Based on this data, a generative AI engine generates specific recommendations, such as "use visual aids as an operational approach to demonstrate the process of solving the equation" and "implement pair work to create opportunities for students to learn from each other," and provides these to the teacher.

[0198] For example, if a sales associate wears smart glasses and wants to know how to explain a new product in a physical store, they can ask, "Please tell me how to explain the new product." The voice data sent from the smart glasses is converted into text data and sent to a server. The server analyzes it using a natural language processing engine to identify the intent - "new product" and "how to explain it." It then searches a customer service database to retrieve similar past cases. Based on this data, a generative AI engine generates recommendations, providing advice such as "show photos and videos of specific usage scenarios for the product" or "explain its features in line with the customer's needs."

[0199] In this way, the present invention provides prompt and specific suggestions for the educational and customer service challenges faced by teachers and store clerks, contributing to the improvement of educational and customer service methods.

[0200] Prompt Sentence Examples

[0201] User: "My student is having trouble solving quadratic equations. Can you suggest an effective solution?"

[0202] Past cases:

[0203] 1. "Use visual aids to show the process of solving an equation."

[0204] 2. "Implement pair work to create opportunities for students to learn from each other."

[0205] Generate recommendations for new teaching methods based on past examples.

[0206] The above is a detailed description of the embodiment of the present invention. This system makes it possible to obtain prompt and effective recommendations in educational and customer service settings.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] The user inputs and sends a natural language query on the terminal.

[0210] Specifically, the user (teacher or store clerk) enters something like "My student is having trouble understanding how to solve quadratic equations. Please suggest an effective solution" or "Please tell me how to explain a new product" into the text field of the device, and then presses the send button. At this time, the device can also use software (e.g., Google® Cloud Speech-to-Text) that converts voice input into text data.

[0211] Input: Enquiry (natural language text or voice data)

[0212] Output: Sends the query to the server as an HTTP POST request

[0213] Step 2:

[0214] The server passes the received query to a natural language processing engine for analysis.

[0215] Specifically, the server passes the received query to a natural language processing engine (e.g., spaCy or the BERT model) to analyze its intent. Through this analysis, key elements of the query (e.g., "quadratic equation," "lack of understanding," "new product," and "explanation method") are extracted.

[0216] Input: Inquiry content (text data of HTTP POST request)

[0217] Output: Analysis results (data identifying intent)

[0218] Step 3:

[0219] Based on the analysis results, the server searches a database for similar past cases.

[0220] Specifically, the server accesses the education database and customer service database to search for past cases that correspond to the analysis results. For example, it searches for "past cases related to solving quadratic equations" or "past cases related to how to explain new products." This search retrieves useful similar cases.

[0221] Input: Analysis results

[0222] Output: Past similar cases (search result data)

[0223] Step 4:

[0224] Based on similar past cases and the inquiry content acquired by the server, a prompt is created and sent to the generative artificial intelligence engine.

[0225] Specifically, the server generates a prompt that combines similar past cases and the analysis results. The generated prompt is then sent to a generative AI engine (e.g., OpenAI's GPT-3 model). For example, a prompt might read, "User inquiry: My student is struggling to understand how to solve quadratic equations. Please suggest an effective solution. Past cases: 1. Use visual aids to show the process of solving the equation. 2. Conduct pair work to create opportunities for students to learn from each other. Please generate recommendations for new teaching methods based on past cases."

[0226] Input: Past similar cases (search results data), analysis results

[0227] Output: Generated prompt statement

[0228] Step 5:

[0229] A generative artificial intelligence engine generates recommendations based on prompts.

[0230] Specifically, the generative AI engine analyzes the prompt and generates new recommendations based on it. For example, in education, it might generate specific recommendations such as "use visual tools to help understand formulas," or in a physical store, it might generate specific recommendations such as "show photos and videos of specific product usage scenarios."

[0231] Input: Generated prompt text

[0232] Output: Recommendation (generated result data)

[0233] Step 6:

[0234] The server transmits the generated recommendations to the client terminal for display.

[0235] Specifically, the server sends the generated recommendations to the client terminal, which then displays the received recommendations, allowing the user to check the content and use it in actual training or customer service.

[0236] Input: Recommendation (generated result data)

[0237] Output: Recommendations displayed on the user's terminal

[0238] 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.

[0239] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[0240] Overall system configuration

[0241] The system consists of the following components:

[0242] 1. Terminal: A device (PC, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[0243] 2. Server: A central processing unit that analyzes the received queries, generates teaching method recommendations, and provides them to educators.

[0244] 3. Natural language processing engine: Software that analyzes inquiries sent from the device and identifies their intent.

[0245] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[0246] 5. Generative AI engine: An AI program that generates recommendations for teaching methods based on analysis results and similar past cases.

[0247] 6. Emotion engine: Software that recognizes the user's emotions and incorporates this information into the generation of recommendations.

[0248] Specific processing flow

[0249] 1. User Inquiry and Emotion Recognition

[0250] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[0251] 2. Receiving and analyzing on the server

[0252] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[0253] 3. Search for similar past cases

[0254] The server then searches the educational database based on the analysis results to extract similar past educational cases, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[0255] 4. Generating Recommendations

[0256] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[0257] 5. Providing Recommendations

[0258] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[0259] Specific examples

[0260] For example, say a teacher is having trouble getting students to understand quadratic equations, and the emotion engine detects "frustration." In this case, the system would act as follows:

[0261] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[0262] 2. The device sends the query and emotion data (irritation) to the server.

[0263] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[0264] 4. Search for similar past cases in the educational database.

[0265] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[0266] 6. The proposal will be sent to the device and displayed to the teacher.

[0267] In this way, the present invention allows teachers to quickly receive specific and sensitive suggestions for improving their teaching methods.

[0268] The processing flow will be explained below.

[0269] Step 1: The user enters a query using a terminal.

[0270] The teacher types into the device interface, "My student doesn't understand how to solve quadratic equations. What should I do?" and clicks the send button.

[0271] Step 2: The device sends a query to the server.

[0272] The device converts the input query into JSON format and sends it to the server as an HTTP POST request.

[0273] Step 3: The server receives the request.

[0274] The server receives the request sent from the terminal.

[0275] Verify that the received data is in the correct format.

[0276] Step 4: The server passes the query to the natural language processing engine.

[0277] The server forwards the received query to the natural language processing engine.

[0278] A natural language processing engine analyzes the query and identifies the topic (e.g., "quadratic equation") and the type of problem (e.g., "lack of understanding").

[0279] Step 5: The device performs emotion recognition through the emotion engine.

[0280] The terminal executes an emotion engine to recognize the teacher's emotion when inputting a query.

[0281] The emotion engine analyzes the teacher's emotions (for example, "irritation") from text and voice and generates emotion data.

[0282] Step 6: The server receives the emotion data.

[0283] The emotion data generated by the device is transmitted to the server.

[0284] The server receives the emotion data and integrates it with query analysis.

[0285] Step 7: The server accesses the education database.

[0286] The server searches the educational database based on the content of the query analyzed by the natural language processing engine and the received emotional data.

[0287] Extract relevant past "educational examples on solving quadratic equations."

[0288] Step 8: The server creates a prompt for the generative AI.

[0289] The server uses the acquired educational examples, inquiry details, and emotional data to create prompts to be passed to the generative AI engine.

[0290] Prompts include information such as, "This teacher is frustrated and needs help with students understanding quadratic equations. Provide suggestions including emotional support strategies."

[0291] Step 9: The server invokes the generative AI.

[0292] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[0293] A generative AI engine analyzes the prompts and generates appropriate teaching recommendations.

[0294] Step 10: The server retrieves the generated recommendations.

[0295] The server receives the recommendations generated by the generative AI engine.

[0296] The recommendations include specific methods such as "using visual tools to visualize how to solve quadratic equations" and "introducing breaks to encourage students to relax."

[0297] Step 11: The server sends the recommendation to the user.

[0298] The server transmits the generated recommendations to the user's terminal.

[0299] The generated recommendations are returned as an HTTP response.

[0300] Step 12: The device will display the recommendations.

[0301] The terminal receives the recommendations sent from the server.

[0302] The recommendations will be displayed on teachers' screens so that they can review them and incorporate them into their teaching methods.

[0303] Specific examples

[0304] For example, consider a case where a teacher is facing a problem in a math class where a student is struggling to solve a quadratic equation, and the emotion engine detects "irritation." In this case, the system operates as follows:

[0305] 1. The teacher types "My student doesn't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[0306] 2. The device sends this query along with the "irritation" data analyzed by the emotion engine.

[0307] 3. The server receives the query and sentiment data and uses a natural language processing engine to identify the intents "quadratic equation" and "lack of understanding."

[0308] 4. Search educational databases for relevant past cases.

[0309] 5. A generative AI engine generates recommendations for teaching methods such as "use visual tools to help understand formulas" or "introduce breaks for relaxation."

[0310] 6. The proposal is sent to the user's device and displayed to the teacher.

[0311] This system allows teachers to receive specific and immediate suggestions for improving their teaching methods, which not only improves teaching effectiveness but also contributes to reducing the mental burden on teachers.

[0312] Example 2

[0313] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0314] Conventional educational support systems have had difficulty providing appropriate recommendations to address teachers' concerns and questions. Furthermore, they were unable to generate recommendations that took the teacher's emotions into account, making them impractical for practical use in the classroom. The present invention aims to solve these problems by providing a system that provides appropriate recommendations that take the teacher's emotions into account when the teacher seeks advice about their concerns and questions regarding teaching methods.

[0315] 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: means for receiving an inquiry about education written in natural language; a natural language processing engine for analyzing the received inquiry and identifying the intention of the inquiry; means for searching a database for similar past educational cases based on the analysis results; a generative artificial intelligence engine for generating educational method recommendations based on the search results; means for providing the generated recommendations to educators; emotion recognition means for recognizing the user's emotions and generating emotion data; and means for evaluating the urgency and importance of the inquiry based on the generated emotion data. As a result, when a teacher consults with a concern or question about educational methods, the intention and emotion of the teacher can be analyzed and appropriate recommendations can be provided quickly.

[0316] "Inquiries about education written in natural language" refers to questions or inquiries about education entered by teachers using natural language.

[0317] "Means of receiving" refers to the function that allows the system to receive inquiries entered by teachers through their terminals.

[0318] A "natural language processing engine" refers to software that analyzes inquiries written in received natural language and understands their intent.

[0319] "Analysis results" refers to the information and data obtained after the natural language processing engine has completed understanding the query.

[0320] "Means for searching from a database" refers to the function of searching for similar past educational cases from an educational database based on the analysis results.

[0321] A "generative artificial intelligence engine" refers to an artificial intelligence program that generates recommendations for educational methods based on analysis results and similar past cases.

[0322] "Generated recommendations" refers to specific advice and solutions regarding teaching methods output by the generative AI engine.

[0323] "Means of providing" refers to the function for delivering and displaying the generated recommendations to educators.

[0324] "Emotion recognition means" refers to a function that recognizes emotions from user input and generates those emotions as data.

[0325] "Emotion data" refers to the user's emotion information extracted by the emotion recognition means.

[0326] "Means for assessing urgency and importance" refers to a function that assesses the urgency and importance of an inquiry based on the generated emotional data.

[0327] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[0328] Overall system configuration

[0329] The system consists of the following components:

[0330] 1. Terminal: A device (personal computer, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[0331] 2. Server: It is a central processing unit that analyzes the received queries, generates teaching method recommendations and provides them to educators.

[0332] 3. Natural language processing engine: Software that analyzes queries sent from the device and identifies their intent. Specifically, it uses the Python NLTK library to analyze queries.

[0333] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[0334] 5. Generative AI engine: An AI program that generates recommendations for educational methods based on analysis results and similar past cases.

[0335] 6. Emotion engine: Software that recognizes the user's emotions and incorporates that information into the generation of recommendations.

[0336] Hardware and Software Examples

[0337] Hardware: Personal computers, tablets, smartphones

[0338] software:

[0339] Natural Language Processing Engine: Python's NLTK Library

[0340] Generative AI engine: Generative AI model (e.g. GPT-3)

[0341] Database system: SQL database

[0342] Specific processing flow

[0343] User Inquiry and Emotion Recognition

[0344] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[0345] Receiving and analyzing on the server

[0346] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[0347] Search for similar past cases

[0348] The server searches an educational database based on the analysis results to extract similar past educational examples, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[0349] Generate recommendations

[0350] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[0351] Providing recommendations

[0352] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[0353] Specific examples

[0354] For example, if a teacher is having trouble getting students to understand quadratic equations and the emotion engine detects "frustration," the system might do the following:

[0355] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[0356] 2. The device sends the query and emotion data (irritation) to the server.

[0357] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[0358] 4. Search for similar past cases in the educational database.

[0359] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[0360] 6. The proposal will be sent to the device and displayed to the teacher.

[0361] In this way, the present invention allows teachers to quickly receive specific and sensitive recommendations for improving their teaching methods.

[0362] Prompt Sentence Examples

[0363] "A teacher is having trouble with students' understanding of quadratic equations. The teacher is frustrated and would like suggestions on what teaching methods would be appropriate."

[0364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0365] Step 1:

[0366] Users use the device to input their educational concerns or questions in natural language. For example, a teacher might use a PC and type, "My student doesn't understand how to solve a quadratic equation. What should I do?" and click the send button. This input is captured as input data on the device.

[0367] Step 2:

[0368] The emotion engine recognizes the user's emotions from the text data entered into the device. For example, it identifies the emotion of "irritation" from the content of the text and the words used, and generates it as emotion data. In this way, emotion data is generated along with the input data.

[0369] Step 3:

[0370] The device sends the user's input data and the generated emotion data to the server. Specifically, it sends a JSON-formatted request containing the input data and emotion data to the server using the HTTP protocol. The server then receives the input data and emotion data.

[0371] Step 4:

[0372] The server passes the received data to a natural language processing engine. The natural language processing engine uses Python's NLTK library to analyze the input data and identify the intent of the query. For example, it extracts keywords such as "quadratic equation" and "lack of understanding" from the input text and generates analysis result data.

[0373] Step 5:

[0374] The server analyzes the emotion data and evaluates the urgency and importance of the inquiry. For example, if it recognizes from the emotion data that the user is feeling "irritated," it sets the urgency of the inquiry as "high" and records it as evaluation data. This generates analysis result data and evaluation data.

[0375] Step 6:

[0376] The server searches the educational database based on the analysis result data. Specifically, it uses an SQL query to search for "past educational cases related to a lack of understanding of quadratic equations" and extracts similar case data. This generates similar case data.

[0377] Step 7:

[0378] The server sends a prompt containing the query content, similar case data, and emotion data to the generative AI engine. Specifically, it generates a prompt sentence and sends it as a POST request to the generative AI model's API. This allows the generative AI model to generate recommendations based on the prompt.

[0379] Step 8:

[0380] The generative AI engine generates recommendations for teaching methods based on the prompts it receives, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This generates recommendation data.

[0381] Step 9:

[0382] The server sends the generated recommendation data to the user's device. Specifically, it sends a JSON-formatted response containing the recommendation data to the device using the HTTP protocol. As a result, the device receives the recommendation data.

[0383] Step 10:

[0384] The device displays the received recommendation data on the screen. The user (teacher) can then check the recommendations on the device screen, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This allows the user to make use of the generated recommendations.

[0385] (Application example 2)

[0386] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0387] In conventional education systems, teachers who have concerns or questions about teaching methods have difficulty receiving prompt and appropriate advice. Furthermore, because the teacher's emotional state is not taken into consideration, the advice is often ineffective. Furthermore, in factory work environments, workers often lack real-time advice on their questions or problems, which can lead to reduced work efficiency. To address these issues, a system is needed that allows teachers and workers to quickly resolve their concerns about teaching methods and work procedures.

[0388] 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.

[0389] In this invention, the server includes means for receiving a query written in natural language, a natural language processing engine for analyzing the received query and identifying its intent, means for searching a database for similar past cases based on the analysis results, a generative artificial intelligence engine for generating recommendations based on the analysis results and similar past cases, an emotion recognition engine for recognizing the user's emotions and reflecting them in the generation of recommendations, and means for instantly providing the generated recommendations, thereby enabling the user to receive prompt and appropriate recommendations in a manner that takes emotions into consideration.

[0390] A "natural language processing engine" is software that analyzes text written in natural language and identifies its intent and meaning.

[0391] A "database" is an information management system that stores past cases and information and makes them searchable as needed.

[0392] A "generative artificial intelligence engine" is an artificial intelligence program that generates new suggestions and answers based on analysis results and similar past cases.

[0393] An "emotion recognition engine" is software that analyzes a user's emotional state from input information.

[0394] "Recommendation provider" refers to a method or device for providing generated recommendations to a user.

[0395] To implement this invention, it is necessary to build a system in which a server, a terminal, and necessary software work together. Specifically, the server includes the following means and software:

[0396] Natural Language Processing Engine (NLP Engine)

[0397] The server first receives a query written in natural language from a user (teacher or worker) and passes it to a natural language processing engine. This engine performs text analysis, particularly using Hugging Face's Transformers, to identify keywords and intent. Based on the results of this analysis, the content of the query is clarified.

[0398] Database

[0399] Based on the analysis results, the server searches a database for similar past cases. The database contains a collection of cases and solutions, and records that match the query are searched for. This allows for quick and appropriate suggestions.

[0400] Generative AI engine

[0401] The server sends prompts to the generative AI engine based on information from the database and the analysis results of the natural language processing engine. The generative AI model generates new suggestions and answers, and generates documents to provide specific countermeasures. This is done using Hugging Face's text-generation pipeline. At this point, the system generates guidelines for the user to take specific actions.

[0402] Emotion Recognition Engine

[0403] The server uses an emotion engine to recognize emotions from the user's query text and voice. Emotion analysis assesses the user's emotional state and adjusts the content and tone of the suggestions accordingly. This emotion data is also passed to the generative AI engine, which influences the final recommendation.

[0404] Providing recommendations

[0405] The server immediately sends the generated recommendations to the user's device (e.g., a smartphone or smart glasses), which then displays the recommendations in a format that the user can easily check, supporting prompt action.

[0406] Specific examples

[0407] For example, if a factory worker sends a query such as, "Assembly line has frequent stoppages, how can we reduce this?", the system operates as follows: The server uses a natural language processing engine to identify keywords such as "Assembly line" and "frequent stoppages" and searches a database for past cases. The results are passed to a generative artificial intelligence engine, which generates a document proposing appropriate work procedures and countermeasures. At this time, an emotion recognition engine detects the worker's frustration and adjusts the tone of the proposal. Finally, the generated recommendation (for example, "It is recommended that regular machine maintenance be strengthened and the working environment be improved") is immediately sent to the worker's device and displayed.

[0408] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0409] Step 1:

[0410] The user inputs and sends inquiries about training methods and work procedures in natural language from the terminal, which then sends the inquiries to the server.

[0411] Input: User query text or voice (e.g., "Our assembly line keeps stopping. How can we improve it?")

[0412] Output: Send query text and voice data to the server

[0413] Step 2:

[0414] The server then passes the received query to a natural language processing engine to begin analysis, which identifies the intent of the query and extracts keywords and key context.

[0415] Input: Inquiry text / voice data

[0416] Data processing / calculation: A natural language processing engine analyzes text and extracts keywords and intent.

[0417] Output: Analysis results (e.g., keywords such as "assembly line" and "frequent stops")

[0418] Step 3:

[0419] Based on the analysis results, the server searches a database for similar cases from the past, including responses and solutions to similar problems faced in the past.

[0420] Input: Keywords of analysis results

[0421] Data processing / calculation: Search for similar cases using database search algorithms

[0422] Output: Similar case data (e.g., "Previous assembly line shutdown events and their solutions")

[0423] Step 4:

[0424] The server passes the query text to an emotion recognition engine to analyze the user's emotion, which identifies the emotional state (e.g., stress, impatience, irritation).

[0425] Input: Query text

[0426] Data processing / calculation: Emotion recognition through text analysis

[0427] Output: Emotion data (e.g., "frustration")

[0428] Step 5:

[0429] The server passes the analysis results, similar case data, and emotion data to a generative AI engine, which then creates prompts to generate appropriate recommendations.The generative AI model uses this information to generate new suggestions and answers.

[0430] Input: Analysis results, similar case data, emotion data

[0431] Data processing / calculation: A generative AI engine generates recommendations based on prompts

[0432] Output: Generated recommendation statement (e.g., "It is recommended to strengthen regular maintenance of machines and improve the working environment.")

[0433] Step 6:

[0434] The server immediately transmits the generated recommendations to the user's terminal, which then displays the recommendations to the user.

[0435] Input: Generated recommendation

[0436] Output: Send and display a recommendation to the user's device (e.g., "It is recommended that you strengthen regular maintenance of your machines and improve the working environment.")

[0437] Through these steps, users can receive prompt and appropriate recommendations in real time.

[0438] 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.

[0439] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0440] 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.

[0441] [Second embodiment]

[0442] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0454] This invention relates to a system that analyzes problems and provides appropriate suggestions when a teacher asks for advice or has a question about teaching methods. This system starts when a user (teacher) sends a query to a server via a terminal.

[0455] Overall system configuration

[0456] 1. User inquiry submission

[0457] Users (teachers) use their own devices to input questions or concerns about teaching methods in natural language. For example, they might type something like, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field on the screen.

[0458] 2. Receiving and analyzing on the server

[0459] The device receives this input and sends it to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine. The natural language processing engine analyzes the received query and identifies the intent of the query (e.g., "math class" or "student's lack of understanding").

[0460] 3. Search for similar past cases

[0461] Based on the analysis results, the server accesses an educational database to search for similar educational cases that have occurred in the past, thereby obtaining a list of methods and success stories that have been used to solve similar problems.

[0462] 4. Recommendation generation using a generative AI engine

[0463] The server creates and sends prompts to the generative AI engine based on the retrieved similar cases and the inquiry content. The generative AI engine then generates appropriate teaching method recommendations for the teacher based on these prompts. For example, recommendations might include "use visual tools to help students understand formulas" or "introduce group work to encourage students to discuss among themselves."

[0464] 5. Providing Recommendations

[0465] The generated recommendations are sent from the server to the client terminal and provided to the teacher. The terminal displays the received recommendations, allowing the teacher to review them and incorporate them into their own teaching methods.

[0466] Specific examples

[0467] Let's say a teacher is faced with a problem in a junior high school mathematics class where a student is struggling to solve a quadratic equation. The teacher sends an inquiry via a terminal saying, "The student is having trouble understanding how to solve a quadratic equation. Please suggest an effective solution."

[0468] The server receives the query and uses a natural language processing engine to identify the intent—"quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past examples of solving quadratic equations." Based on this data, a generative AI engine generates recommendations, providing specific suggestions to teachers, such as "use visual aids to demonstrate the process of solving the equation as an operational approach" and "implement pair work to create opportunities for students to learn from each other."

[0469] In this way, the present invention provides teachers with prompt and specific suggestions for the educational challenges they face, contributing to the improvement of teaching methods. This system is a groundbreaking means of providing support to teachers to achieve higher educational effectiveness.

[0470] The processing flow will be explained below.

[0471] Step 1: The user enters a query using a terminal.

[0472] A teacher types into the device interface, "There are some areas in my math class where students are struggling to understand. Can you suggest some effective solutions?"

[0473] When the teacher clicks the submit button, the input data is sent.

[0474] Step 2: The device sends a query to the server.

[0475] The terminal converts the teacher's input data into JSON format and sends it to the server as an HTTP POST request.

[0476] Step 3: The server receives the request.

[0477] The server receives the request from the device and records it in a log.

[0478] Check that the received data is in the correct format.

[0479] Step 4: The server calls the natural language processing engine.

[0480] The server passes the received education-related inquiries to a natural language processing engine for intent analysis.

[0481] A natural language processing engine analyzes the query and identifies the topic of the query (mathematics) and the type of problem (lack of understanding).

[0482] Step 5: The server accesses the education database.

[0483] The server accesses the education database based on the analysis results and searches for similar education cases.

[0484] Obtain a list of similar cases and check their contents.

[0485] Step 6: The server creates a prompt for the generative AI.

[0486] A prompt is created based on the similar cases acquired by the server and the inquiry content.

[0487] Prompts are instructions that the generative AI engine uses to generate appropriate recommendations.

[0488] Step 7: The server invokes the generative AI.

[0489] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[0490] A generative AI analyzes the prompts and generates new recommendations.

[0491] Step 8: The server retrieves the generated recommendations.

[0492] The server receives the recommendations generated by the generative AI engine.

[0493] Review the proposal and put it into the appropriate format.

[0494] Step 9: The server sends the recommendation to the user.

[0495] The server transmits the generated recommendations to the user's terminal.

[0496] It is sent as an HTTP response and provided to the teacher.

[0497] Step 10: Your device will display a recommendation.

[0498] The terminal receives the response from the server and displays the recommendations to the teacher on the interface.

[0499] Teachers can review the proposed methods and put them into practice.

[0500] Specific examples

[0501] For example, if a teacher is teaching a math class and a student is struggling to understand a particular formula, the process might proceed as follows:

[0502] 1. The teacher types into the terminal, "Student does not understand how to solve the quadratic equation. Please suggest a solution."

[0503] 2. The device sends the input data to the server.

[0504] 3. The server receives the query and analyzes it using a natural language processing engine.

[0505] 4. The server searches the educational database for past "case studies on understanding quadratic equations."

[0506] 5. The server creates a prompt based on the acquired examples and sends it to the generative AI.

[0507] 6. Generative AI generates recommendations such as "Use visual models to visualize how to solve quadratic equations" or "Introduce group work to encourage discussion among students."

[0508] 7. The server sends the generated proposal to the teacher's terminal, and the terminal displays the proposal to the teacher.

[0509] In this way, the system allows teachers to quickly obtain concrete suggestions for improving their teaching methods.

[0510] Example 1

[0511] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0512] It is difficult for educators to find quick and effective solutions to problems and questions about teaching methods. In particular, it takes time and effort to obtain specific teaching method recommendations while referring to past cases. To solve this problem, a system is needed that allows educators to consult about teaching methods in natural language and quickly obtain appropriate recommendations.

[0513] 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.

[0514] In this invention, the server includes means for receiving an inquiry about education written in natural language, means for transmitting the received inquiry to the server as JSON format data, means for passing the received data to a natural language processing engine and identifying the intent of the inquiry, means for searching an education database for similar past education cases based on the analysis results, means for transmitting prompts to the generative artificial intelligence engine based on the acquired case data and the inquiry content, and means for providing the generated recommendations to the educator. This enables educators to obtain quick and effective recommendations based on specific past education cases through inquiries in natural language.

[0515] "Inquiries about education written in natural language" refers to text data entered by educators in everyday language as consultations or questions about their own educational activities.

[0516] "Receiving means" refers to the mechanism or method by which the server receives data sent from the user.

[0517] "JSON format data" is a format that treats data as a text-based object representation, and refers to a simple way to describe structured data.

[0518] A "natural language processing engine" is a software engine for analyzing meaning and intent from input text data, and specifically refers to technology for understanding and processing natural language.

[0519] An "educational database" is a data storage system that stores data on previously solved educational cases and methods.

[0520] A "generative artificial intelligence engine" is an artificial intelligence engine that generates appropriate advice and recommendations based on a pre-trained model.

[0521] A "prompt" is text data of instructions or questions input to a generative AI engine.

[0522] "Means for providing recommendations" refers to the mechanisms or methods for displaying or notifying educators of generated recommendations.

[0523] This invention relates to a system that analyzes problems and provides appropriate recommendations when educators ask for advice or questions about educational methods. This system is primarily composed of a user (educator) terminal, a server, a natural language processing engine, a generative artificial intelligence engine, and an educational database.

[0524] First, the user (educator) uses their own device (PC, tablet, smartphone, etc.) to input their inquiry or question about teaching methods in natural language. The device is provided with a dedicated application or a web interface that can be accessed from a browser. Specifically, the user types, "There are some areas in my math class where students are struggling to understand. Can you suggest an effective solution?" into the text field on the screen.

[0525] The device then sends the input query as an HTTP POST request to the server. The server receives the request using Node.js and parses it into JSON-formatted data. This data is then passed to a natural language processing engine designed using Python libraries (e.g., spaCy and Transformers) to analyze the intent of the text data. The natural language processing engine extracts key keywords and phrases from the received query, such as "math class" and "student's lack of understanding."

[0526] Next, based on the analysis results, the server uses MySQL or MongoDB to search an education database that stores similar educational cases that have been solved in the past. For example, it uses an SQL query in the format "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of understanding"" to retrieve related educational cases.

[0527] Based on the acquired data, the server generates and sends appropriate prompts to the generative AI engine. The generative AI engine (e.g., OpenAI's GPT-3) uses these prompts to generate specific teaching method recommendations. For example, a prompt such as "Please suggest effective ways to help students understand mathematics" can be sent. Specific examples of generated recommendations include "Use visual tools to help students understand formulas" and "Introduce group work to encourage students to discuss among themselves."

[0528] Finally, the generated recommendations are sent from the server to the client device and provided to the educator. The device analyzes the received response and displays the recommendations to the educator on an application or browser. This allows the educator to incorporate the provided specific recommendations into their teaching methods and improve the quality of their lessons.

[0529] Prompt Sentence Examples

[0530] "Please suggest effective ways to help students understand mathematics."

[0531] "My students are struggling with grammar in English class. Can you tell me how to solve this?"

[0532] "What are some good ways to ensure safety during experiments in junior high school science classes?"

[0533] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0534] Program processing flow

[0535] Step 1:

[0536] User inquiry submission

[0537] Specific behavior:

[0538] The user (educator) uses a dedicated application on the device or a web interface to input questions or concerns about teaching methods in natural language. For example, they might type, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field.

[0539] input:

[0540] The natural language query text entered by the user.

[0541] output:

[0542] The query text is sent from the terminal to the server as an HTTP POST request.

[0543] Step 2:

[0544] Receiving and analyzing on the server

[0545] Specific behavior:

[0546] The server receives the HTTP POST request sent from the device. The server parses this request as JSON format data and passes the data to the natural language processing engine. The server uses Node.js to receive and parse the data.

[0547] input:

[0548] HTTP POST request (query text) sent from the terminal.

[0549] output:

[0550] Query data in JSON format is generated and passed to the natural language processing engine.

[0551] Step 3:

[0552] Intention analysis using a natural language processing engine

[0553] Specific behavior:

[0554] The server uses Python libraries (e.g., spaCy and Transformers) to analyze the intent of the query text. A natural language processing engine extracts keywords and phrases such as "math lessons" and "student lack of understanding."

[0555] input:

[0556] Query data in JSON format.

[0557] output:

[0558] Analysis results (keywords and phrases) are generated.

[0559] Step 4:

[0560] Search for similar past cases

[0561] Specific behavior:

[0562] Based on the analysis results, the server searches the education database using MySQL or MongoDB. For example, it executes an SQL query such as "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of Understanding"" to retrieve relevant education cases.

[0563] input:

[0564] Intent analysis results (keywords and phrases).

[0565] output:

[0566] Data on similar past cases obtained from an educational database.

[0567] Step 5:

[0568] Recommendation generation using a generative AI engine

[0569] Specific behavior:

[0570] The server generates a prompt (instruction sentence) based on the acquired case data and the inquiry content and sends it to the generative AI engine. For example, it inputs a prompt such as "Please suggest an effective way to help students understand mathematics" and sends it to the generative AI engine (e.g., GPT-3).

[0571] input:

[0572] Past similar case data and generated prompts.

[0573] output:

[0574] A recommendation statement is generated.

[0575] Step 6:

[0576] Providing recommendations

[0577] Specific behavior:

[0578] The generated recommendations are sent from the server to the client device, which then analyzes the received response and displays the recommendations to the educator on the application or browser.

[0579] input:

[0580] The generated recommendation.

[0581] output:

[0582] Specific recommendations provided to educators.

[0583] (Application example 1)

[0584] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0585] In conventional education-related systems, there are insufficient ways for teachers to receive quick and specific suggestions regarding teaching methods, and there are no means to provide real-time advice to store clerks on customer service methods, making it difficult to provide optimal service to customers.There is a need for a system that can provide effective suggestions and advice immediately in educational settings and in physical stores.

[0586] 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.

[0587] In this invention, the server includes: means for receiving inquiries about education written in natural language; a natural language processing engine for analyzing the received inquiries and identifying their intent; means for searching a database for similar past education cases based on the analysis results; a generative artificial intelligence engine for generating recommendations for education methods based on the search results; means for providing the generated recommendations to educators; means for store clerks to receive inquiries in real time about how to explain products and how to serve customers; the generative artificial intelligence engine for analyzing inquiries received from a smart device, searching for past customer service cases, and generating recommendations based on the results; and means including a smart device for providing the generated recommendations to store clerks. This enables educators to receive quick and specific recommendations in the field of education, and allows store clerks to receive appropriate customer service advice in real time in physical stores, thereby improving customer satisfaction.

[0588] A "natural language processing engine" is a software component that analyzes text written in natural language and identifies its intent and meaning.

[0589] "Educational methods" are the means and approaches that educators use to effectively impart knowledge and skills to students.

[0590] A "generative artificial intelligence engine" is an artificial intelligence model that generates new recommendations based on past cases and data.

[0591] A "device" is a hardware device for processing digital information, and specifically includes smartphones, smart glasses, head-mounted displays, etc.

[0592] An "inquiry" is a question or inquiry sent by a user to the system.

[0593] A "recommendation" is specific advice or instructions for solving a specific problem.

[0594] A "brick and mortar store" is a physical store where customers visit in person to purchase goods or services.

[0595] "Customer service methods" refer to the way in which store staff respond to and provide service to customers.

[0596] This invention is a system that analyzes problems and provides appropriate suggestions when teachers ask for advice or questions about teaching methods. Furthermore, this invention can also be applied to situations where store clerks in physical stores ask for advice or questions about customer service methods in real time.

[0597] Overall system configuration

[0598] 1. User inquiry submission

[0599] Users (teachers or store clerks) use their own devices (smartphones, smart glasses, head-mounted displays, etc.) to input questions or concerns about teaching methods or customer service methods in natural language. This input is done through a text field or voice input function. For example, a teacher might type, "My students are having trouble solving quadratic equations. Please suggest an effective solution," or a store clerk might ask, "Please tell me how to explain a new product."

[0600] 2. Receiving and analyzing on the server

[0601] The device sends this input to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine (e.g., spaCy or the BERT model). The natural language processing engine analyzes the received query and identifies the intent of the query. For example, intents such as "quadratic equations," "lack of understanding," "new product," and "explanation method" may be identified.

[0602] 3. Search for similar past cases

[0603] Based on the analysis results, the server accesses an education database or customer service database to search for similar cases that have occurred in the past. The server obtains methods and success stories that have been used to solve similar problems. Through this database search, the server finds useful past cases.

[0604] 4. Recommendation generation using a generative AI engine

[0605] Based on the acquired similar cases and the inquiry content, the server creates and sends a prompt to a generative AI engine (for example, OpenAI's GPT-3 model). The generative AI engine generates appropriate recommendations for the user based on this prompt. For example, in the case of education, a recommendation might be "use visual tools to help understand formulas," or in the case of a physical store, "explain product usage scenarios with videos and photos."

[0606] 5. Providing Recommendations

[0607] The generated recommendations are sent from the server to the client terminal and provided to the user. The terminal displays the received recommendations, allowing the user to improve their training and customer service methods based on the information.

[0608] Specific application examples

[0609] Consider a scenario in which a teacher is teaching junior high school mathematics and a student is struggling to solve a quadratic equation. The teacher sends a query via their device saying, "The student is struggling to understand how to solve a quadratic equation. Please suggest an effective solution." The server receives the query and uses a natural language processing engine to identify the intent - "quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past cases related to solving quadratic equations." Based on this data, a generative AI engine generates specific recommendations, such as "use visual aids as an operational approach to demonstrate the process of solving the equation" and "implement pair work to create opportunities for students to learn from each other," and provides these to the teacher.

[0610] For example, if a sales associate wears smart glasses and wants to know how to explain a new product in a physical store, they can ask, "Please tell me how to explain the new product." The voice data sent from the smart glasses is converted into text data and sent to a server. The server analyzes it using a natural language processing engine to identify the intent - "new product" and "how to explain it." It then searches a customer service database to retrieve similar past cases. Based on this data, a generative AI engine generates recommendations, providing advice such as "show photos and videos of specific usage scenarios for the product" or "explain its features in line with the customer's needs."

[0611] In this way, the present invention provides prompt and specific suggestions for the educational and customer service challenges faced by teachers and store clerks, contributing to the improvement of educational and customer service methods.

[0612] Prompt Sentence Examples

[0613] User: "My student is having trouble solving quadratic equations. Can you suggest an effective solution?"

[0614] Past cases:

[0615] 1. "Use visual aids to show the process of solving an equation."

[0616] 2. "Implement pair work to create opportunities for students to learn from each other."

[0617] Generate recommendations for new teaching methods based on past examples.

[0618] The above is a detailed description of the embodiment of the present invention. This system makes it possible to obtain prompt and effective recommendations in educational and customer service settings.

[0619] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0620] Step 1:

[0621] The user inputs and sends a natural language query on the terminal.

[0622] Specifically, the user (teacher or store clerk) enters something like "My student is having trouble understanding how to solve quadratic equations. Please suggest an effective solution" or "Please tell me how to explain our new product" into the text field on the device, and then presses the send button. At this time, the device can also use software (e.g., Google Cloud Speech-to-Text) that converts voice input into text data.

[0623] Input: Enquiry (natural language text or voice data)

[0624] Output: Sends the query to the server as an HTTP POST request

[0625] Step 2:

[0626] The server passes the received query to a natural language processing engine for analysis.

[0627] Specifically, the server passes the received query to a natural language processing engine (e.g., spaCy or the BERT model) to analyze its intent. Through this analysis, key elements of the query (e.g., "quadratic equation," "lack of understanding," "new product," and "explanation method") are extracted.

[0628] Input: Inquiry content (text data of HTTP POST request)

[0629] Output: Analysis results (data identifying intent)

[0630] Step 3:

[0631] Based on the analysis results, the server searches a database for similar past cases.

[0632] Specifically, the server accesses the education database and customer service database to search for past cases that correspond to the analysis results. For example, it searches for "past cases related to solving quadratic equations" or "past cases related to how to explain new products." This search retrieves useful similar cases.

[0633] Input: Analysis results

[0634] Output: Past similar cases (search result data)

[0635] Step 4:

[0636] Based on similar past cases and the inquiry content acquired by the server, a prompt is created and sent to the generative artificial intelligence engine.

[0637] Specifically, the server generates a prompt that combines similar past cases and the analysis results. The generated prompt is then sent to a generative AI engine (e.g., OpenAI's GPT-3 model). For example, a prompt might read, "User inquiry: My student is struggling to understand how to solve quadratic equations. Please suggest an effective solution. Past cases: 1. Use visual aids to show the process of solving the equation. 2. Conduct pair work to create opportunities for students to learn from each other. Please generate recommendations for new teaching methods based on past cases."

[0638] Input: Past similar cases (search results data), analysis results

[0639] Output: Generated prompt statement

[0640] Step 5:

[0641] A generative artificial intelligence engine generates recommendations based on prompts.

[0642] Specifically, the generative AI engine analyzes the prompt and generates new recommendations based on it. For example, in education, it might generate specific recommendations such as "use visual tools to help understand formulas," or in a physical store, it might generate specific recommendations such as "show photos and videos of specific product usage scenarios."

[0643] Input: Generated prompt text

[0644] Output: Recommendation (generated result data)

[0645] Step 6:

[0646] The server transmits the generated recommendations to the client terminal for display.

[0647] Specifically, the server sends the generated recommendations to the client terminal, which then displays the received recommendations, allowing the user to check the content and use it in actual training or customer service.

[0648] Input: Recommendation (generated result data)

[0649] Output: Recommendations displayed on the user's terminal

[0650] 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.

[0651] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[0652] Overall system configuration

[0653] The system consists of the following components:

[0654] 1. Terminal: A device (PC, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[0655] 2. Server: A central processing unit that analyzes the received queries, generates teaching method recommendations, and provides them to educators.

[0656] 3. Natural language processing engine: Software that analyzes inquiries sent from the device and identifies their intent.

[0657] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[0658] 5. Generative AI engine: An AI program that generates recommendations for teaching methods based on analysis results and similar past cases.

[0659] 6. Emotion engine: Software that recognizes the user's emotions and incorporates this information into the generation of recommendations.

[0660] Specific processing flow

[0661] 1. User Inquiry and Emotion Recognition

[0662] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[0663] 2. Receiving and analyzing on the server

[0664] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[0665] 3. Search for similar past cases

[0666] The server then searches the educational database based on the analysis results to extract similar past educational cases, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[0667] 4. Generating Recommendations

[0668] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[0669] 5. Providing Recommendations

[0670] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[0671] Specific examples

[0672] For example, say a teacher is having trouble getting students to understand quadratic equations, and the emotion engine detects "frustration." In this case, the system would act as follows:

[0673] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[0674] 2. The device sends the query and emotion data (irritation) to the server.

[0675] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[0676] 4. Search for similar past cases in the educational database.

[0677] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[0678] 6. The proposal will be sent to the device and displayed to the teacher.

[0679] In this way, the present invention allows teachers to quickly receive specific and sensitive suggestions for improving their teaching methods.

[0680] The processing flow will be explained below.

[0681] Step 1: The user enters a query using a terminal.

[0682] The teacher types into the device interface, "My student doesn't understand how to solve quadratic equations. What should I do?" and clicks the send button.

[0683] Step 2: The device sends a query to the server.

[0684] The device converts the input query into JSON format and sends it to the server as an HTTP POST request.

[0685] Step 3: The server receives the request.

[0686] The server receives the request sent from the terminal.

[0687] Verify that the received data is in the correct format.

[0688] Step 4: The server passes the query to the natural language processing engine.

[0689] The server forwards the received query to the natural language processing engine.

[0690] A natural language processing engine analyzes the query and identifies the topic (e.g., "quadratic equation") and the type of problem (e.g., "lack of understanding").

[0691] Step 5: The device performs emotion recognition through the emotion engine.

[0692] The terminal executes an emotion engine to recognize the teacher's emotion when inputting a query.

[0693] The emotion engine analyzes the teacher's emotions (for example, "irritation") from text and voice and generates emotion data.

[0694] Step 6: The server receives the emotion data.

[0695] The emotion data generated by the device is transmitted to the server.

[0696] The server receives the emotion data and integrates it with query analysis.

[0697] Step 7: The server accesses the education database.

[0698] The server searches the educational database based on the content of the query analyzed by the natural language processing engine and the received emotional data.

[0699] Extract relevant past "educational examples on solving quadratic equations."

[0700] Step 8: The server creates a prompt for the generative AI.

[0701] The server uses the acquired educational examples, inquiry details, and emotional data to create prompts to be passed to the generative AI engine.

[0702] Prompts include information such as, "This teacher is frustrated and needs help with students understanding quadratic equations. Provide suggestions including emotional support strategies."

[0703] Step 9: The server invokes the generative AI.

[0704] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[0705] A generative AI engine analyzes the prompts and generates appropriate teaching recommendations.

[0706] Step 10: The server retrieves the generated recommendations.

[0707] The server receives the recommendations generated by the generative AI engine.

[0708] The recommendations include specific methods such as "using visual tools to visualize how to solve quadratic equations" and "introducing breaks to encourage students to relax."

[0709] Step 11: The server sends the recommendation to the user.

[0710] The server transmits the generated recommendations to the user's terminal.

[0711] The generated recommendations are returned as an HTTP response.

[0712] Step 12: The device will display the recommendations.

[0713] The terminal receives the recommendations sent from the server.

[0714] The recommendations will be displayed on teachers' screens so that they can review them and incorporate them into their teaching methods.

[0715] Specific examples

[0716] For example, consider a case where a teacher is facing a problem in a math class where a student is struggling to solve a quadratic equation, and the emotion engine detects "irritation." In this case, the system operates as follows:

[0717] 1. The teacher types "My student doesn't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[0718] 2. The device sends this query along with the "irritation" data analyzed by the emotion engine.

[0719] 3. The server receives the query and sentiment data and uses a natural language processing engine to identify the intents "quadratic equation" and "lack of understanding."

[0720] 4. Search educational databases for relevant past cases.

[0721] 5. A generative AI engine generates recommendations for teaching methods such as "use visual tools to help understand formulas" or "introduce breaks for relaxation."

[0722] 6. The proposal is sent to the user's device and displayed to the teacher.

[0723] This system allows teachers to receive specific and immediate suggestions for improving their teaching methods, which not only improves teaching effectiveness but also contributes to reducing the mental burden on teachers.

[0724] Example 2

[0725] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0726] Conventional educational support systems have had difficulty providing appropriate recommendations to address teachers' concerns and questions. Furthermore, they were unable to generate recommendations that took the teacher's emotions into account, making them impractical for practical use in the classroom. The present invention aims to solve these problems by providing a system that provides appropriate recommendations that take the teacher's emotions into account when the teacher seeks advice about their concerns and questions regarding teaching methods.

[0727] 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: means for receiving an inquiry about education written in natural language; a natural language processing engine for analyzing the received inquiry and identifying the intention of the inquiry; means for searching a database for similar past educational cases based on the analysis results; a generative artificial intelligence engine for generating educational method recommendations based on the search results; means for providing the generated recommendations to educators; emotion recognition means for recognizing the user's emotions and generating emotion data; and means for evaluating the urgency and importance of the inquiry based on the generated emotion data. As a result, when a teacher consults with a concern or question about educational methods, the intention and emotion of the teacher can be analyzed and appropriate recommendations can be provided quickly.

[0728] "Inquiries about education written in natural language" refers to questions or inquiries about education entered by teachers using natural language.

[0729] "Means of receiving" refers to the function that allows the system to receive inquiries entered by teachers through their terminals.

[0730] A "natural language processing engine" refers to software that analyzes inquiries written in received natural language and understands their intent.

[0731] "Analysis results" refers to the information and data obtained after the natural language processing engine has completed understanding the query.

[0732] "Means for searching from a database" refers to the function of searching for similar past educational cases from an educational database based on the analysis results.

[0733] A "generative artificial intelligence engine" refers to an artificial intelligence program that generates recommendations for educational methods based on analysis results and similar past cases.

[0734] "Generated recommendations" refers to specific advice and solutions regarding teaching methods output by the generative AI engine.

[0735] "Means of providing" refers to the function for delivering and displaying the generated recommendations to educators.

[0736] "Emotion recognition means" refers to a function that recognizes emotions from user input and generates those emotions as data.

[0737] "Emotion data" refers to the user's emotion information extracted by the emotion recognition means.

[0738] "Means for assessing urgency and importance" refers to a function that assesses the urgency and importance of an inquiry based on the generated emotional data.

[0739] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[0740] Overall system configuration

[0741] The system consists of the following components:

[0742] 1. Terminal: A device (personal computer, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[0743] 2. Server: It is a central processing unit that analyzes the received queries, generates teaching method recommendations and provides them to educators.

[0744] 3. Natural language processing engine: Software that analyzes queries sent from the device and identifies their intent. Specifically, it uses the Python NLTK library to analyze queries.

[0745] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[0746] 5. Generative AI engine: An AI program that generates recommendations for educational methods based on analysis results and similar past cases.

[0747] 6. Emotion engine: Software that recognizes the user's emotions and incorporates that information into the generation of recommendations.

[0748] Hardware and Software Examples

[0749] Hardware: Personal computers, tablets, smartphones

[0750] software:

[0751] Natural Language Processing Engine: Python's NLTK Library

[0752] Generative AI engine: Generative AI model (e.g. GPT-3)

[0753] Database system: SQL database

[0754] Specific processing flow

[0755] User Inquiry and Emotion Recognition

[0756] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[0757] Receiving and analyzing on the server

[0758] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[0759] Search for similar past cases

[0760] The server searches an educational database based on the analysis results to extract similar past educational examples, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[0761] Generate recommendations

[0762] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[0763] Providing recommendations

[0764] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[0765] Specific examples

[0766] For example, if a teacher is having trouble getting students to understand quadratic equations and the emotion engine detects "frustration," the system might do the following:

[0767] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[0768] 2. The device sends the query and emotion data (irritation) to the server.

[0769] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[0770] 4. Search for similar past cases in the educational database.

[0771] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[0772] 6. The proposal will be sent to the device and displayed to the teacher.

[0773] In this way, the present invention allows teachers to quickly receive specific and sensitive recommendations for improving their teaching methods.

[0774] Prompt Sentence Examples

[0775] "A teacher is having trouble with students' understanding of quadratic equations. The teacher is frustrated and would like suggestions on what teaching methods would be appropriate."

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

[0777] Step 1:

[0778] Users use the device to input their educational concerns or questions in natural language. For example, a teacher might use a PC and type, "My student doesn't understand how to solve a quadratic equation. What should I do?" and click the send button. This input is captured as input data on the device.

[0779] Step 2:

[0780] The emotion engine recognizes the user's emotions from the text data entered into the device. For example, it identifies the emotion of "irritation" from the content of the text and the words used, and generates it as emotion data. In this way, emotion data is generated along with the input data.

[0781] Step 3:

[0782] The device sends the user's input data and the generated emotion data to the server. Specifically, it sends a JSON-formatted request containing the input data and emotion data to the server using the HTTP protocol. The server then receives the input data and emotion data.

[0783] Step 4:

[0784] The server passes the received data to a natural language processing engine. The natural language processing engine uses Python's NLTK library to analyze the input data and identify the intent of the query. For example, it extracts keywords such as "quadratic equation" and "lack of understanding" from the input text and generates analysis result data.

[0785] Step 5:

[0786] The server analyzes the emotion data and evaluates the urgency and importance of the inquiry. For example, if it recognizes from the emotion data that the user is feeling "irritated," it sets the urgency of the inquiry as "high" and records it as evaluation data. This generates analysis result data and evaluation data.

[0787] Step 6:

[0788] The server searches the educational database based on the analysis result data. Specifically, it uses an SQL query to search for "past educational cases related to a lack of understanding of quadratic equations" and extracts similar case data. This generates similar case data.

[0789] Step 7:

[0790] The server sends a prompt containing the query content, similar case data, and emotion data to the generative AI engine. Specifically, it generates a prompt sentence and sends it as a POST request to the generative AI model's API. This allows the generative AI model to generate recommendations based on the prompt.

[0791] Step 8:

[0792] The generative AI engine generates recommendations for teaching methods based on the prompts it receives, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This generates recommendation data.

[0793] Step 9:

[0794] The server sends the generated recommendation data to the user's device. Specifically, it sends a JSON-formatted response containing the recommendation data to the device using the HTTP protocol. As a result, the device receives the recommendation data.

[0795] Step 10:

[0796] The device displays the received recommendation data on the screen. The user (teacher) can then check the recommendations on the device screen, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This allows the user to make use of the generated recommendations.

[0797] (Application example 2)

[0798] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0799] In conventional education systems, teachers who have concerns or questions about teaching methods have difficulty receiving prompt and appropriate advice. Furthermore, because the teacher's emotional state is not taken into consideration, the advice is often ineffective. Furthermore, in factory work environments, workers often lack real-time advice on their questions or problems, which can lead to reduced work efficiency. To address these issues, a system is needed that allows teachers and workers to quickly resolve their concerns about teaching methods and work procedures.

[0800] 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.

[0801] In this invention, the server includes means for receiving a query written in natural language, a natural language processing engine for analyzing the received query and identifying its intent, means for searching a database for similar past cases based on the analysis results, a generative artificial intelligence engine for generating recommendations based on the analysis results and similar past cases, an emotion recognition engine for recognizing the user's emotions and reflecting them in the generation of recommendations, and means for instantly providing the generated recommendations, thereby enabling the user to receive prompt and appropriate recommendations in a manner that takes emotions into consideration.

[0802] A "natural language processing engine" is software that analyzes text written in natural language and identifies its intent and meaning.

[0803] A "database" is an information management system that stores past cases and information and makes them searchable as needed.

[0804] A "generative artificial intelligence engine" is an artificial intelligence program that generates new suggestions and answers based on analysis results and similar past cases.

[0805] An "emotion recognition engine" is software that analyzes a user's emotional state from input information.

[0806] "Recommendation provider" refers to a method or device for providing generated recommendations to a user.

[0807] To implement this invention, it is necessary to build a system in which a server, a terminal, and necessary software work together. Specifically, the server includes the following means and software:

[0808] Natural Language Processing Engine (NLP Engine)

[0809] The server first receives a query written in natural language from a user (teacher or worker) and passes it to a natural language processing engine. This engine performs text analysis, particularly using Hugging Face's Transformers, to identify keywords and intent. Based on the results of this analysis, the content of the query is clarified.

[0810] Database

[0811] Based on the analysis results, the server searches a database for similar past cases. The database contains a collection of cases and solutions, and records that match the query are searched for. This allows for quick and appropriate suggestions.

[0812] Generative AI engine

[0813] The server sends prompts to the generative AI engine based on information from the database and the analysis results of the natural language processing engine. The generative AI model generates new suggestions and answers, and generates documents to provide specific countermeasures. This is done using Hugging Face's text-generation pipeline. At this point, the system generates guidelines for the user to take specific actions.

[0814] Emotion Recognition Engine

[0815] The server uses an emotion engine to recognize emotions from the user's query text and voice. Emotion analysis assesses the user's emotional state and adjusts the content and tone of the suggestions accordingly. This emotion data is also passed to the generative AI engine, which influences the final recommendation.

[0816] Providing recommendations

[0817] The server immediately sends the generated recommendations to the user's device (e.g., a smartphone or smart glasses), which then displays the recommendations in a format that the user can easily check, supporting prompt action.

[0818] Specific examples

[0819] For example, if a factory worker sends a query such as, "Assembly line has frequent stoppages, how can we reduce this?", the system operates as follows: The server uses a natural language processing engine to identify keywords such as "Assembly line" and "frequent stoppages" and searches a database for past cases. The results are passed to a generative artificial intelligence engine, which generates a document proposing appropriate work procedures and countermeasures. At this time, an emotion recognition engine detects the worker's frustration and adjusts the tone of the proposal. Finally, the generated recommendation (for example, "It is recommended that regular machine maintenance be strengthened and the working environment be improved") is immediately sent to the worker's device and displayed.

[0820] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0821] Step 1:

[0822] The user inputs and sends inquiries about training methods and work procedures in natural language from the terminal, which then sends the inquiries to the server.

[0823] Input: User query text or voice (e.g., "Our assembly line keeps stopping. How can we improve it?")

[0824] Output: Send query text and voice data to the server

[0825] Step 2:

[0826] The server then passes the received query to a natural language processing engine to begin analysis, which identifies the intent of the query and extracts keywords and key context.

[0827] Input: Inquiry text / voice data

[0828] Data processing / calculation: A natural language processing engine analyzes text and extracts keywords and intent.

[0829] Output: Analysis results (e.g., keywords such as "assembly line" and "frequent stops")

[0830] Step 3:

[0831] Based on the analysis results, the server searches a database for similar cases from the past, including responses and solutions to similar problems faced in the past.

[0832] Input: Keywords of analysis results

[0833] Data processing / calculation: Search for similar cases using database search algorithms

[0834] Output: Similar case data (e.g., "Previous assembly line shutdown events and their solutions")

[0835] Step 4:

[0836] The server passes the query text to an emotion recognition engine to analyze the user's emotion, which identifies the emotional state (e.g., stress, impatience, irritation).

[0837] Input: Query text

[0838] Data processing / calculation: Emotion recognition through text analysis

[0839] Output: Emotion data (e.g., "frustration")

[0840] Step 5:

[0841] The server passes the analysis results, similar case data, and emotion data to a generative AI engine, which then creates prompts to generate appropriate recommendations.The generative AI model uses this information to generate new suggestions and answers.

[0842] Input: Analysis results, similar case data, emotion data

[0843] Data processing / calculation: A generative AI engine generates recommendations based on prompts

[0844] Output: Generated recommendation statement (e.g., "It is recommended to strengthen regular maintenance of machines and improve the working environment.")

[0845] Step 6:

[0846] The server immediately transmits the generated recommendations to the user's terminal, which then displays the recommendations to the user.

[0847] Input: Generated recommendation

[0848] Output: Send and display a recommendation to the user's device (e.g., "It is recommended that you strengthen regular maintenance of your machines and improve the working environment.")

[0849] Through these steps, users can receive prompt and appropriate recommendations in real time.

[0850] 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.

[0851] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0852] 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.

[0853] [Third embodiment]

[0854] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0855] 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.

[0856] 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).

[0857] 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.

[0858] 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.

[0859] 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).

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0866] This invention relates to a system that analyzes problems and provides appropriate suggestions when a teacher asks for advice or has a question about teaching methods. This system starts when a user (teacher) sends a query to a server via a terminal.

[0867] Overall system configuration

[0868] 1. User inquiry submission

[0869] Users (teachers) use their own devices to input questions or concerns about teaching methods in natural language. For example, they might type something like, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field on the screen.

[0870] 2. Receiving and analyzing on the server

[0871] The device receives this input and sends it to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine. The natural language processing engine analyzes the received query and identifies the intent of the query (e.g., "math class" or "student's lack of understanding").

[0872] 3. Search for similar past cases

[0873] Based on the analysis results, the server accesses an educational database to search for similar educational cases that have occurred in the past, thereby obtaining a list of methods and success stories that have been used to solve similar problems.

[0874] 4. Recommendation generation using a generative AI engine

[0875] The server creates and sends prompts to the generative AI engine based on the retrieved similar cases and the inquiry content. The generative AI engine then generates appropriate teaching method recommendations for the teacher based on these prompts. For example, recommendations might include "use visual tools to help students understand formulas" or "introduce group work to encourage students to discuss among themselves."

[0876] 5. Providing Recommendations

[0877] The generated recommendations are sent from the server to the client terminal and provided to the teacher. The terminal displays the received recommendations, allowing the teacher to review them and incorporate them into their own teaching methods.

[0878] Specific examples

[0879] Let's say a teacher is faced with a problem in a junior high school mathematics class where a student is struggling to solve a quadratic equation. The teacher sends an inquiry via a terminal saying, "The student is having trouble understanding how to solve a quadratic equation. Please suggest an effective solution."

[0880] The server receives the query and uses a natural language processing engine to identify the intent—"quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past examples of solving quadratic equations." Based on this data, a generative AI engine generates recommendations, providing specific suggestions to teachers, such as "use visual aids to demonstrate the process of solving the equation as an operational approach" and "implement pair work to create opportunities for students to learn from each other."

[0881] In this way, the present invention provides teachers with prompt and specific suggestions for the educational challenges they face, contributing to the improvement of teaching methods. This system is a groundbreaking means of providing support to teachers to achieve higher educational effectiveness.

[0882] The processing flow will be explained below.

[0883] Step 1: The user enters a query using a terminal.

[0884] A teacher types into the device interface, "There are some areas in my math class where students are struggling to understand. Can you suggest some effective solutions?"

[0885] When the teacher clicks the submit button, the input data is sent.

[0886] Step 2: The device sends a query to the server.

[0887] The terminal converts the teacher's input data into JSON format and sends it to the server as an HTTP POST request.

[0888] Step 3: The server receives the request.

[0889] The server receives the request from the device and records it in a log.

[0890] Check that the received data is in the correct format.

[0891] Step 4: The server calls the natural language processing engine.

[0892] The server passes the received education-related inquiries to a natural language processing engine for intent analysis.

[0893] A natural language processing engine analyzes the query and identifies the topic of the query (mathematics) and the type of problem (lack of understanding).

[0894] Step 5: The server accesses the education database.

[0895] The server accesses the education database based on the analysis results and searches for similar education cases.

[0896] Obtain a list of similar cases and check their contents.

[0897] Step 6: The server creates a prompt for the generative AI.

[0898] A prompt is created based on the similar cases acquired by the server and the inquiry content.

[0899] Prompts are instructions that the generative AI engine uses to generate appropriate recommendations.

[0900] Step 7: The server invokes the generative AI.

[0901] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[0902] A generative AI analyzes the prompts and generates new recommendations.

[0903] Step 8: The server retrieves the generated recommendations.

[0904] The server receives the recommendations generated by the generative AI engine.

[0905] Review the proposal and put it into the appropriate format.

[0906] Step 9: The server sends the recommendation to the user.

[0907] The server transmits the generated recommendations to the user's terminal.

[0908] It is sent as an HTTP response and provided to the teacher.

[0909] Step 10: Your device will display a recommendation.

[0910] The terminal receives the response from the server and displays the recommendations to the teacher on the interface.

[0911] Teachers can review the proposed methods and put them into practice.

[0912] Specific examples

[0913] For example, if a teacher is teaching a math class and a student is struggling to understand a particular formula, the process might proceed as follows:

[0914] 1. The teacher types into the terminal, "Student does not understand how to solve the quadratic equation. Please suggest a solution."

[0915] 2. The device sends the input data to the server.

[0916] 3. The server receives the query and analyzes it using a natural language processing engine.

[0917] 4. The server searches the educational database for past "case studies on understanding quadratic equations."

[0918] 5. The server creates a prompt based on the acquired examples and sends it to the generative AI.

[0919] 6. Generative AI generates recommendations such as "Use visual models to visualize how to solve quadratic equations" or "Introduce group work to encourage discussion among students."

[0920] 7. The server sends the generated proposal to the teacher's terminal, and the terminal displays the proposal to the teacher.

[0921] In this way, the system allows teachers to quickly obtain concrete suggestions for improving their teaching methods.

[0922] Example 1

[0923] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0924] It is difficult for educators to find quick and effective solutions to problems and questions about teaching methods. In particular, it takes time and effort to obtain specific teaching method recommendations while referring to past cases. To solve this problem, a system is needed that allows educators to consult about teaching methods in natural language and quickly obtain appropriate recommendations.

[0925] 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.

[0926] In this invention, the server includes means for receiving an inquiry about education written in natural language, means for transmitting the received inquiry to the server as JSON format data, means for passing the received data to a natural language processing engine and identifying the intent of the inquiry, means for searching an education database for similar past education cases based on the analysis results, means for transmitting prompts to the generative artificial intelligence engine based on the acquired case data and the inquiry content, and means for providing the generated recommendations to the educator. This enables educators to obtain quick and effective recommendations based on specific past education cases through inquiries in natural language.

[0927] "Inquiries about education written in natural language" refers to text data entered by educators in everyday language as consultations or questions about their own educational activities.

[0928] "Receiving means" refers to the mechanism or method by which the server receives data sent from the user.

[0929] "JSON format data" is a format that treats data as a text-based object representation, and refers to a simple way to describe structured data.

[0930] A "natural language processing engine" is a software engine for analyzing meaning and intent from input text data, and specifically refers to technology for understanding and processing natural language.

[0931] An "educational database" is a data storage system that stores data on previously solved educational cases and methods.

[0932] A "generative artificial intelligence engine" is an artificial intelligence engine that generates appropriate advice and recommendations based on a pre-trained model.

[0933] A "prompt" is text data of instructions or questions input to a generative AI engine.

[0934] "Means for providing recommendations" refers to the mechanisms or methods for displaying or notifying educators of generated recommendations.

[0935] This invention relates to a system that analyzes problems and provides appropriate recommendations when educators ask for advice or questions about educational methods. This system is primarily composed of a user (educator) terminal, a server, a natural language processing engine, a generative artificial intelligence engine, and an educational database.

[0936] First, the user (educator) uses their own device (PC, tablet, smartphone, etc.) to input their inquiry or question about teaching methods in natural language. The device is provided with a dedicated application or a web interface that can be accessed from a browser. Specifically, the user types, "There are some areas in my math class where students are struggling to understand. Can you suggest an effective solution?" into the text field on the screen.

[0937] The device then sends the input query as an HTTP POST request to the server. The server receives the request using Node.js and parses it into JSON-formatted data. This data is then passed to a natural language processing engine designed using Python libraries (e.g., spaCy and Transformers) to analyze the intent of the text data. The natural language processing engine extracts key keywords and phrases from the received query, such as "math class" and "student's lack of understanding."

[0938] Next, based on the analysis results, the server uses MySQL or MongoDB to search an education database that stores similar educational cases that have been solved in the past. For example, it uses an SQL query in the format "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of understanding"" to retrieve related educational cases.

[0939] Based on the acquired data, the server generates and sends appropriate prompts to the generative AI engine. The generative AI engine (e.g., OpenAI's GPT-3) uses these prompts to generate specific teaching method recommendations. For example, a prompt such as "Please suggest effective ways to help students understand mathematics" can be sent. Specific examples of generated recommendations include "Use visual tools to help students understand formulas" and "Introduce group work to encourage students to discuss among themselves."

[0940] Finally, the generated recommendations are sent from the server to the client device and provided to the educator. The device analyzes the received response and displays the recommendations to the educator on an application or browser. This allows the educator to incorporate the provided specific recommendations into their teaching methods and improve the quality of their lessons.

[0941] Prompt Sentence Examples

[0942] "Please suggest effective ways to help students understand mathematics."

[0943] "My students are struggling with grammar in English class. Can you tell me how to solve this?"

[0944] "What are some good ways to ensure safety during experiments in junior high school science classes?"

[0945] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0946] Program processing flow

[0947] Step 1:

[0948] User inquiry submission

[0949] Specific behavior:

[0950] The user (educator) uses a dedicated application on the device or a web interface to input questions or concerns about teaching methods in natural language. For example, they might type, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field.

[0951] input:

[0952] The natural language query text entered by the user.

[0953] output:

[0954] The query text is sent from the terminal to the server as an HTTP POST request.

[0955] Step 2:

[0956] Receiving and analyzing on the server

[0957] Specific behavior:

[0958] The server receives the HTTP POST request sent from the device. The server parses this request as JSON format data and passes the data to the natural language processing engine. The server uses Node.js to receive and parse the data.

[0959] input:

[0960] HTTP POST request (query text) sent from the terminal.

[0961] output:

[0962] Query data in JSON format is generated and passed to the natural language processing engine.

[0963] Step 3:

[0964] Intention analysis using a natural language processing engine

[0965] Specific behavior:

[0966] The server uses Python libraries (e.g., spaCy and Transformers) to analyze the intent of the query text. A natural language processing engine extracts keywords and phrases such as "math lessons" and "student lack of understanding."

[0967] input:

[0968] Query data in JSON format.

[0969] output:

[0970] Analysis results (keywords and phrases) are generated.

[0971] Step 4:

[0972] Search for similar past cases

[0973] Specific behavior:

[0974] Based on the analysis results, the server searches the education database using MySQL or MongoDB. For example, it executes an SQL query such as "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of Understanding"" to retrieve relevant education cases.

[0975] input:

[0976] Intent analysis results (keywords and phrases).

[0977] output:

[0978] Data on similar past cases obtained from an educational database.

[0979] Step 5:

[0980] Recommendation generation using a generative AI engine

[0981] Specific behavior:

[0982] The server generates a prompt (instruction sentence) based on the acquired case data and the inquiry content and sends it to the generative AI engine. For example, it inputs a prompt such as "Please suggest an effective way to help students understand mathematics" and sends it to the generative AI engine (e.g., GPT-3).

[0983] input:

[0984] Past similar case data and generated prompts.

[0985] output:

[0986] A recommendation statement is generated.

[0987] Step 6:

[0988] Providing recommendations

[0989] Specific behavior:

[0990] The generated recommendations are sent from the server to the client device, which then analyzes the received response and displays the recommendations to the educator on the application or browser.

[0991] input:

[0992] The generated recommendation.

[0993] output:

[0994] Specific recommendations provided to educators.

[0995] (Application example 1)

[0996] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0997] In conventional education-related systems, there are insufficient ways for teachers to receive quick and specific suggestions regarding teaching methods, and there are no means to provide real-time advice to store clerks on customer service methods, making it difficult to provide optimal service to customers.There is a need for a system that can provide effective suggestions and advice immediately in educational settings and in physical stores.

[0998] 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.

[0999] In this invention, the server includes: means for receiving inquiries about education written in natural language; a natural language processing engine for analyzing the received inquiries and identifying their intent; means for searching a database for similar past education cases based on the analysis results; a generative artificial intelligence engine for generating recommendations for education methods based on the search results; means for providing the generated recommendations to educators; means for store clerks to receive inquiries in real time about how to explain products and how to serve customers; the generative artificial intelligence engine for analyzing inquiries received from a smart device, searching for past customer service cases, and generating recommendations based on the results; and means including a smart device for providing the generated recommendations to store clerks. This enables educators to receive quick and specific recommendations in the field of education, and allows store clerks to receive appropriate customer service advice in real time in physical stores, thereby improving customer satisfaction.

[1000] A "natural language processing engine" is a software component that analyzes text written in natural language and identifies its intent and meaning.

[1001] "Educational methods" are the means and approaches that educators use to effectively impart knowledge and skills to students.

[1002] A "generative artificial intelligence engine" is an artificial intelligence model that generates new recommendations based on past cases and data.

[1003] A "device" is a hardware device for processing digital information, and specifically includes smartphones, smart glasses, head-mounted displays, etc.

[1004] An "inquiry" is a question or inquiry sent by a user to the system.

[1005] A "recommendation" is specific advice or instructions for solving a specific problem.

[1006] A "brick and mortar store" is a physical store where customers visit in person to purchase goods or services.

[1007] "Customer service methods" refer to the way in which store staff respond to and provide service to customers.

[1008] This invention is a system that analyzes problems and provides appropriate suggestions when teachers ask for advice or questions about teaching methods. Furthermore, this invention can also be applied to situations where store clerks in physical stores ask for advice or questions about customer service methods in real time.

[1009] Overall system configuration

[1010] 1. User inquiry submission

[1011] Users (teachers or store clerks) use their own devices (smartphones, smart glasses, head-mounted displays, etc.) to input questions or concerns about teaching methods or customer service methods in natural language. This input is done through a text field or voice input function. For example, a teacher might type, "My students are having trouble solving quadratic equations. Please suggest an effective solution," or a store clerk might ask, "Please tell me how to explain a new product."

[1012] 2. Receiving and analyzing on the server

[1013] The device sends this input to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine (e.g., spaCy or the BERT model). The natural language processing engine analyzes the received query and identifies the intent of the query. For example, intents such as "quadratic equations," "lack of understanding," "new product," and "explanation method" may be identified.

[1014] 3. Search for similar past cases

[1015] Based on the analysis results, the server accesses an education database or customer service database to search for similar cases that have occurred in the past. The server obtains methods and success stories that have been used to solve similar problems. Through this database search, the server finds useful past cases.

[1016] 4. Recommendation generation using a generative AI engine

[1017] Based on the acquired similar cases and the inquiry content, the server creates and sends a prompt to a generative AI engine (for example, OpenAI's GPT-3 model). The generative AI engine generates appropriate recommendations for the user based on this prompt. For example, in the case of education, a recommendation might be "use visual tools to help understand formulas," or in the case of a physical store, "explain product usage scenarios with videos and photos."

[1018] 5. Providing Recommendations

[1019] The generated recommendations are sent from the server to the client terminal and provided to the user. The terminal displays the received recommendations, allowing the user to improve their training and customer service methods based on the information.

[1020] Specific application examples

[1021] Consider a scenario in which a teacher is teaching junior high school mathematics and a student is struggling to solve a quadratic equation. The teacher sends a query via their device saying, "The student is struggling to understand how to solve a quadratic equation. Please suggest an effective solution." The server receives the query and uses a natural language processing engine to identify the intent - "quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past cases related to solving quadratic equations." Based on this data, a generative AI engine generates specific recommendations, such as "use visual aids as an operational approach to demonstrate the process of solving the equation" and "implement pair work to create opportunities for students to learn from each other," and provides these to the teacher.

[1022] For example, if a sales associate wears smart glasses and wants to know how to explain a new product in a physical store, they can ask, "Please tell me how to explain the new product." The voice data sent from the smart glasses is converted into text data and sent to a server. The server analyzes it using a natural language processing engine to identify the intent - "new product" and "how to explain it." It then searches a customer service database to retrieve similar past cases. Based on this data, a generative AI engine generates recommendations, providing advice such as "show photos and videos of specific usage scenarios for the product" or "explain its features in line with the customer's needs."

[1023] In this way, the present invention provides prompt and specific suggestions for the educational and customer service challenges faced by teachers and store clerks, contributing to the improvement of educational and customer service methods.

[1024] Prompt Sentence Examples

[1025] User: "My student is having trouble solving quadratic equations. Can you suggest an effective solution?"

[1026] Past cases:

[1027] 1. "Use visual aids to show the process of solving an equation."

[1028] 2. "Implement pair work to create opportunities for students to learn from each other."

[1029] Generate recommendations for new teaching methods based on past examples.

[1030] The above is a detailed description of the embodiment of the present invention. This system makes it possible to obtain prompt and effective recommendations in educational and customer service settings.

[1031] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1032] Step 1:

[1033] The user inputs and sends a natural language query on the terminal.

[1034] Specifically, the user (teacher or store clerk) enters something like "My student is having trouble understanding how to solve quadratic equations. Please suggest an effective solution" or "Please tell me how to explain our new product" into the text field on the device, and then presses the send button. At this time, the device can also use software (e.g., Google Cloud Speech-to-Text) that converts voice input into text data.

[1035] Input: Enquiry (natural language text or voice data)

[1036] Output: Sends the query to the server as an HTTP POST request

[1037] Step 2:

[1038] The server passes the received query to a natural language processing engine for analysis.

[1039] Specifically, the server passes the received query to a natural language processing engine (e.g., spaCy or the BERT model) to analyze its intent. Through this analysis, key elements of the query (e.g., "quadratic equation," "lack of understanding," "new product," and "explanation method") are extracted.

[1040] Input: Inquiry content (text data of HTTP POST request)

[1041] Output: Analysis results (data identifying intent)

[1042] Step 3:

[1043] Based on the analysis results, the server searches a database for similar past cases.

[1044] Specifically, the server accesses the education database and customer service database to search for past cases that correspond to the analysis results. For example, it searches for "past cases related to solving quadratic equations" or "past cases related to how to explain new products." This search retrieves useful similar cases.

[1045] Input: Analysis results

[1046] Output: Past similar cases (search result data)

[1047] Step 4:

[1048] Based on similar past cases and the inquiry content acquired by the server, a prompt is created and sent to the generative artificial intelligence engine.

[1049] Specifically, the server generates a prompt that combines similar past cases and the analysis results. The generated prompt is then sent to a generative AI engine (e.g., OpenAI's GPT-3 model). For example, a prompt might read, "User inquiry: My student is struggling to understand how to solve quadratic equations. Please suggest an effective solution. Past cases: 1. Use visual aids to show the process of solving the equation. 2. Conduct pair work to create opportunities for students to learn from each other. Please generate recommendations for new teaching methods based on past cases."

[1050] Input: Past similar cases (search results data), analysis results

[1051] Output: Generated prompt statement

[1052] Step 5:

[1053] A generative artificial intelligence engine generates recommendations based on prompts.

[1054] Specifically, the generative AI engine analyzes the prompt and generates new recommendations based on it. For example, in education, it might generate specific recommendations such as "use visual tools to help understand formulas," or in a physical store, it might generate specific recommendations such as "show photos and videos of specific product usage scenarios."

[1055] Input: Generated prompt text

[1056] Output: Recommendation (generated result data)

[1057] Step 6:

[1058] The server transmits the generated recommendations to the client terminal for display.

[1059] Specifically, the server sends the generated recommendations to the client terminal, which then displays the received recommendations, allowing the user to check the content and use it in actual training or customer service.

[1060] Input: Recommendation (generated result data)

[1061] Output: Recommendations displayed on the user's terminal

[1062] 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.

[1063] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[1064] Overall system configuration

[1065] The system consists of the following components:

[1066] 1. Terminal: A device (PC, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[1067] 2. Server: A central processing unit that analyzes the received queries, generates teaching method recommendations, and provides them to educators.

[1068] 3. Natural language processing engine: Software that analyzes inquiries sent from the device and identifies their intent.

[1069] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[1070] 5. Generative AI engine: An AI program that generates recommendations for teaching methods based on analysis results and similar past cases.

[1071] 6. Emotion engine: Software that recognizes the user's emotions and incorporates this information into the generation of recommendations.

[1072] Specific processing flow

[1073] 1. User Inquiry and Emotion Recognition

[1074] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[1075] 2. Receiving and analyzing on the server

[1076] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[1077] 3. Search for similar past cases

[1078] The server then searches the educational database based on the analysis results to extract similar past educational cases, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[1079] 4. Generating Recommendations

[1080] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[1081] 5. Providing Recommendations

[1082] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[1083] Specific examples

[1084] For example, say a teacher is having trouble getting students to understand quadratic equations, and the emotion engine detects "frustration." In this case, the system would act as follows:

[1085] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[1086] 2. The device sends the query and emotion data (irritation) to the server.

[1087] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[1088] 4. Search for similar past cases in the educational database.

[1089] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[1090] 6. The proposal will be sent to the device and displayed to the teacher.

[1091] In this way, the present invention allows teachers to quickly receive specific and sensitive suggestions for improving their teaching methods.

[1092] The processing flow will be explained below.

[1093] Step 1: The user enters a query using a terminal.

[1094] The teacher types into the device interface, "My student doesn't understand how to solve quadratic equations. What should I do?" and clicks the send button.

[1095] Step 2: The device sends a query to the server.

[1096] The device converts the input query into JSON format and sends it to the server as an HTTP POST request.

[1097] Step 3: The server receives the request.

[1098] The server receives the request sent from the terminal.

[1099] Verify that the received data is in the correct format.

[1100] Step 4: The server passes the query to the natural language processing engine.

[1101] The server forwards the received query to the natural language processing engine.

[1102] A natural language processing engine analyzes the query and identifies the topic (e.g., "quadratic equation") and the type of problem (e.g., "lack of understanding").

[1103] Step 5: The device performs emotion recognition through the emotion engine.

[1104] The terminal executes an emotion engine to recognize the teacher's emotion when inputting a query.

[1105] The emotion engine analyzes the teacher's emotions (for example, "irritation") from text and voice and generates emotion data.

[1106] Step 6: The server receives the emotion data.

[1107] The emotion data generated by the device is transmitted to the server.

[1108] The server receives the emotion data and integrates it with query analysis.

[1109] Step 7: The server accesses the education database.

[1110] The server searches the educational database based on the content of the query analyzed by the natural language processing engine and the received emotional data.

[1111] Extract relevant past "educational examples on solving quadratic equations."

[1112] Step 8: The server creates a prompt for the generative AI.

[1113] The server uses the acquired educational examples, inquiry details, and emotional data to create prompts to be passed to the generative AI engine.

[1114] Prompts include information such as, "This teacher is frustrated and needs help with students understanding quadratic equations. Provide suggestions including emotional support strategies."

[1115] Step 9: The server invokes the generative AI.

[1116] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[1117] A generative AI engine analyzes the prompts and generates appropriate teaching recommendations.

[1118] Step 10: The server retrieves the generated recommendations.

[1119] The server receives the recommendations generated by the generative AI engine.

[1120] The recommendations include specific methods such as "using visual tools to visualize how to solve quadratic equations" and "introducing breaks to encourage students to relax."

[1121] Step 11: The server sends the recommendation to the user.

[1122] The server transmits the generated recommendations to the user's terminal.

[1123] The generated recommendations are returned as an HTTP response.

[1124] Step 12: The device will display the recommendations.

[1125] The terminal receives the recommendations sent from the server.

[1126] The recommendations will be displayed on teachers' screens so that they can review them and incorporate them into their teaching methods.

[1127] Specific examples

[1128] For example, consider a case where a teacher is facing a problem in a math class where a student is struggling to solve a quadratic equation, and the emotion engine detects "irritation." In this case, the system operates as follows:

[1129] 1. The teacher types "My student doesn't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[1130] 2. The device sends this query along with the "irritation" data analyzed by the emotion engine.

[1131] 3. The server receives the query and sentiment data and uses a natural language processing engine to identify the intents "quadratic equation" and "lack of understanding."

[1132] 4. Search educational databases for relevant past cases.

[1133] 5. A generative AI engine generates recommendations for teaching methods such as "use visual tools to help understand formulas" or "introduce breaks for relaxation."

[1134] 6. The proposal is sent to the user's device and displayed to the teacher.

[1135] This system allows teachers to receive specific and immediate suggestions for improving their teaching methods, which not only improves teaching effectiveness but also contributes to reducing the mental burden on teachers.

[1136] Example 2

[1137] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1138] Conventional educational support systems have had difficulty providing appropriate recommendations to address teachers' concerns and questions. Furthermore, they were unable to generate recommendations that took the teacher's emotions into account, making them impractical for practical use in the classroom. The present invention aims to solve these problems by providing a system that provides appropriate recommendations that take the teacher's emotions into account when the teacher seeks advice about their concerns and questions regarding teaching methods.

[1139] 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: means for receiving an inquiry about education written in natural language; a natural language processing engine for analyzing the received inquiry and identifying the intention of the inquiry; means for searching a database for similar past educational cases based on the analysis results; a generative artificial intelligence engine for generating educational method recommendations based on the search results; means for providing the generated recommendations to educators; emotion recognition means for recognizing the user's emotions and generating emotion data; and means for evaluating the urgency and importance of the inquiry based on the generated emotion data. As a result, when a teacher consults with a concern or question about educational methods, the intention and emotion of the teacher can be analyzed and appropriate recommendations can be provided quickly.

[1140] "Inquiries about education written in natural language" refers to questions or inquiries about education entered by teachers using natural language.

[1141] "Means of receiving" refers to the function that allows the system to receive inquiries entered by teachers through their terminals.

[1142] A "natural language processing engine" refers to software that analyzes inquiries written in received natural language and understands their intent.

[1143] "Analysis results" refers to the information and data obtained after the natural language processing engine has completed understanding the query.

[1144] "Means for searching from a database" refers to the function of searching for similar past educational cases from an educational database based on the analysis results.

[1145] A "generative artificial intelligence engine" refers to an artificial intelligence program that generates recommendations for educational methods based on analysis results and similar past cases.

[1146] "Generated recommendations" refers to specific advice and solutions regarding teaching methods output by the generative AI engine.

[1147] "Means of providing" refers to the function for delivering and displaying the generated recommendations to educators.

[1148] "Emotion recognition means" refers to a function that recognizes emotions from user input and generates those emotions as data.

[1149] "Emotion data" refers to the user's emotion information extracted by the emotion recognition means.

[1150] "Means for assessing urgency and importance" refers to a function that assesses the urgency and importance of an inquiry based on the generated emotional data.

[1151] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[1152] Overall system configuration

[1153] The system consists of the following components:

[1154] 1. Terminal: A device (personal computer, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[1155] 2. Server: It is a central processing unit that analyzes the received queries, generates teaching method recommendations and provides them to educators.

[1156] 3. Natural language processing engine: Software that analyzes queries sent from the device and identifies their intent. Specifically, it uses the Python NLTK library to analyze queries.

[1157] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[1158] 5. Generative AI engine: An AI program that generates recommendations for educational methods based on analysis results and similar past cases.

[1159] 6. Emotion engine: Software that recognizes the user's emotions and incorporates that information into the generation of recommendations.

[1160] Hardware and Software Examples

[1161] Hardware: Personal computers, tablets, smartphones

[1162] software:

[1163] Natural Language Processing Engine: Python's NLTK Library

[1164] Generative AI engine: Generative AI model (e.g. GPT-3)

[1165] Database system: SQL database

[1166] Specific processing flow

[1167] User Inquiry and Emotion Recognition

[1168] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[1169] Receiving and analyzing on the server

[1170] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[1171] Search for similar past cases

[1172] The server searches an educational database based on the analysis results to extract similar past educational examples, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[1173] Generate recommendations

[1174] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[1175] Providing recommendations

[1176] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[1177] Specific examples

[1178] For example, if a teacher is having trouble getting students to understand quadratic equations and the emotion engine detects "frustration," the system might do the following:

[1179] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[1180] 2. The device sends the query and emotion data (irritation) to the server.

[1181] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[1182] 4. Search for similar past cases in the educational database.

[1183] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[1184] 6. The proposal will be sent to the device and displayed to the teacher.

[1185] In this way, the present invention allows teachers to quickly receive specific and sensitive recommendations for improving their teaching methods.

[1186] Prompt Sentence Examples

[1187] "A teacher is having trouble with students' understanding of quadratic equations. The teacher is frustrated and would like suggestions on what teaching methods would be appropriate."

[1188] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] Users use the device to input their educational concerns or questions in natural language. For example, a teacher might use a PC and type, "My student doesn't understand how to solve a quadratic equation. What should I do?" and click the send button. This input is captured as input data on the device.

[1191] Step 2:

[1192] The emotion engine recognizes the user's emotions from the text data entered into the device. For example, it identifies the emotion of "irritation" from the content of the text and the words used, and generates it as emotion data. In this way, emotion data is generated along with the input data.

[1193] Step 3:

[1194] The device sends the user's input data and the generated emotion data to the server. Specifically, it sends a JSON-formatted request containing the input data and emotion data to the server using the HTTP protocol. The server then receives the input data and emotion data.

[1195] Step 4:

[1196] The server passes the received data to a natural language processing engine. The natural language processing engine uses Python's NLTK library to analyze the input data and identify the intent of the query. For example, it extracts keywords such as "quadratic equation" and "lack of understanding" from the input text and generates analysis result data.

[1197] Step 5:

[1198] The server analyzes the emotion data and evaluates the urgency and importance of the inquiry. For example, if it recognizes from the emotion data that the user is feeling "irritated," it sets the urgency of the inquiry as "high" and records it as evaluation data. This generates analysis result data and evaluation data.

[1199] Step 6:

[1200] The server searches the educational database based on the analysis result data. Specifically, it uses an SQL query to search for "past educational cases related to a lack of understanding of quadratic equations" and extracts similar case data. This generates similar case data.

[1201] Step 7:

[1202] The server sends a prompt containing the query content, similar case data, and emotion data to the generative AI engine. Specifically, it generates a prompt sentence and sends it as a POST request to the generative AI model's API. This allows the generative AI model to generate recommendations based on the prompt.

[1203] Step 8:

[1204] The generative AI engine generates recommendations for teaching methods based on the prompts it receives, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This generates recommendation data.

[1205] Step 9:

[1206] The server sends the generated recommendation data to the user's device. Specifically, it sends a JSON-formatted response containing the recommendation data to the device using the HTTP protocol. As a result, the device receives the recommendation data.

[1207] Step 10:

[1208] The device displays the received recommendation data on the screen. The user (teacher) can then check the recommendations on the device screen, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This allows the user to make use of the generated recommendations.

[1209] (Application example 2)

[1210] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1211] In conventional education systems, teachers who have concerns or questions about teaching methods have difficulty receiving prompt and appropriate advice. Furthermore, because the teacher's emotional state is not taken into consideration, the advice is often ineffective. Furthermore, in factory work environments, workers often lack real-time advice on their questions or problems, which can lead to reduced work efficiency. To address these issues, a system is needed that allows teachers and workers to quickly resolve their concerns about teaching methods and work procedures.

[1212] 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.

[1213] In this invention, the server includes means for receiving a query written in natural language, a natural language processing engine for analyzing the received query and identifying its intent, means for searching a database for similar past cases based on the analysis results, a generative artificial intelligence engine for generating recommendations based on the analysis results and similar past cases, an emotion recognition engine for recognizing the user's emotions and reflecting them in the generation of recommendations, and means for instantly providing the generated recommendations, thereby enabling the user to receive prompt and appropriate recommendations in a manner that takes emotions into consideration.

[1214] A "natural language processing engine" is software that analyzes text written in natural language and identifies its intent and meaning.

[1215] A "database" is an information management system that stores past cases and information and makes them searchable as needed.

[1216] A "generative artificial intelligence engine" is an artificial intelligence program that generates new suggestions and answers based on analysis results and similar past cases.

[1217] An "emotion recognition engine" is software that analyzes a user's emotional state from input information.

[1218] "Recommendation provider" refers to a method or device for providing generated recommendations to a user.

[1219] To implement this invention, it is necessary to build a system in which a server, a terminal, and necessary software work together. Specifically, the server includes the following means and software:

[1220] Natural Language Processing Engine (NLP Engine)

[1221] The server first receives a query written in natural language from a user (teacher or worker) and passes it to a natural language processing engine. This engine performs text analysis, particularly using Hugging Face's Transformers, to identify keywords and intent. Based on the results of this analysis, the content of the query is clarified.

[1222] Database

[1223] Based on the analysis results, the server searches a database for similar past cases. The database contains a collection of cases and solutions, and records that match the query are searched for. This allows for quick and appropriate suggestions.

[1224] Generative AI engine

[1225] The server sends prompts to the generative AI engine based on information from the database and the analysis results of the natural language processing engine. The generative AI model generates new suggestions and answers, and generates documents to provide specific countermeasures. This is done using Hugging Face's text-generation pipeline. At this point, the system generates guidelines for the user to take specific actions.

[1226] Emotion Recognition Engine

[1227] The server uses an emotion engine to recognize emotions from the user's query text and voice. Emotion analysis assesses the user's emotional state and adjusts the content and tone of the suggestions accordingly. This emotion data is also passed to the generative AI engine, which influences the final recommendation.

[1228] Providing recommendations

[1229] The server immediately sends the generated recommendations to the user's device (e.g., a smartphone or smart glasses), which then displays the recommendations in a format that the user can easily check, supporting prompt action.

[1230] Specific examples

[1231] For example, if a factory worker sends a query such as, "Assembly line has frequent stoppages, how can we reduce this?", the system operates as follows: The server uses a natural language processing engine to identify keywords such as "Assembly line" and "frequent stoppages" and searches a database for past cases. The results are passed to a generative artificial intelligence engine, which generates a document proposing appropriate work procedures and countermeasures. At this time, an emotion recognition engine detects the worker's frustration and adjusts the tone of the proposal. Finally, the generated recommendation (for example, "It is recommended that regular machine maintenance be strengthened and the working environment be improved") is immediately sent to the worker's device and displayed.

[1232] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1233] Step 1:

[1234] The user inputs and sends inquiries about training methods and work procedures in natural language from the terminal, which then sends the inquiries to the server.

[1235] Input: User query text or voice (e.g., "Our assembly line keeps stopping. How can we improve it?")

[1236] Output: Send query text and voice data to the server

[1237] Step 2:

[1238] The server then passes the received query to a natural language processing engine to begin analysis, which identifies the intent of the query and extracts keywords and key context.

[1239] Input: Inquiry text / voice data

[1240] Data processing / calculation: A natural language processing engine analyzes text and extracts keywords and intent.

[1241] Output: Analysis results (e.g., keywords such as "assembly line" and "frequent stops")

[1242] Step 3:

[1243] Based on the analysis results, the server searches a database for similar cases from the past, including responses and solutions to similar problems faced in the past.

[1244] Input: Keywords of analysis results

[1245] Data processing / calculation: Search for similar cases using database search algorithms

[1246] Output: Similar case data (e.g., "Previous assembly line shutdown events and their solutions")

[1247] Step 4:

[1248] The server passes the query text to an emotion recognition engine to analyze the user's emotion, which identifies the emotional state (e.g., stress, impatience, irritation).

[1249] Input: Query text

[1250] Data processing / calculation: Emotion recognition through text analysis

[1251] Output: Emotion data (e.g., "frustration")

[1252] Step 5:

[1253] The server passes the analysis results, similar case data, and emotion data to a generative AI engine, which then creates prompts to generate appropriate recommendations.The generative AI model uses this information to generate new suggestions and answers.

[1254] Input: Analysis results, similar case data, emotion data

[1255] Data processing / calculation: A generative AI engine generates recommendations based on prompts

[1256] Output: Generated recommendation statement (e.g., "It is recommended to strengthen regular maintenance of machines and improve the working environment.")

[1257] Step 6:

[1258] The server immediately transmits the generated recommendations to the user's terminal, which then displays the recommendations to the user.

[1259] Input: Generated recommendation

[1260] Output: Send and display a recommendation to the user's device (e.g., "It is recommended that you strengthen regular maintenance of your machines and improve the working environment.")

[1261] Through these steps, users can receive prompt and appropriate recommendations in real time.

[1262] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1263] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1264] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1265] [Fourth embodiment]

[1266] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1267] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1268] 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).

[1269] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1270] 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.

[1271] 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).

[1272] 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.

[1273] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1274] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1275] 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.

[1276] 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.

[1277] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1278] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1279] This invention relates to a system that analyzes problems and provides appropriate suggestions when a teacher asks for advice or has a question about teaching methods. This system starts when a user (teacher) sends a query to a server via a terminal.

[1280] Overall system configuration

[1281] 1. User inquiry submission

[1282] Users (teachers) use their own devices to input questions or concerns about teaching methods in natural language. For example, they might type something like, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field on the screen.

[1283] 2. Receiving and analyzing on the server

[1284] The device receives this input and sends it to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine. The natural language processing engine analyzes the received query and identifies the intent of the query (e.g., "math class" or "student's lack of understanding").

[1285] 3. Search for similar past cases

[1286] Based on the analysis results, the server accesses an educational database to search for similar educational cases that have occurred in the past, thereby obtaining a list of methods and success stories that have been used to solve similar problems.

[1287] 4. Recommendation generation using a generative AI engine

[1288] The server creates and sends prompts to the generative AI engine based on the retrieved similar cases and the inquiry content. The generative AI engine then generates appropriate teaching method recommendations for the teacher based on these prompts. For example, recommendations might include "use visual tools to help students understand formulas" or "introduce group work to encourage students to discuss among themselves."

[1289] 5. Providing Recommendations

[1290] The generated recommendations are sent from the server to the client terminal and provided to the teacher. The terminal displays the received recommendations, allowing the teacher to review them and incorporate them into their own teaching methods.

[1291] Specific examples

[1292] Let's say a teacher is faced with a problem in a junior high school mathematics class where a student is struggling to solve a quadratic equation. The teacher sends an inquiry via a terminal saying, "The student is having trouble understanding how to solve a quadratic equation. Please suggest an effective solution."

[1293] The server receives the query and uses a natural language processing engine to identify the intent—"quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past examples of solving quadratic equations." Based on this data, a generative AI engine generates recommendations, providing specific suggestions to teachers, such as "use visual aids to demonstrate the process of solving the equation as an operational approach" and "implement pair work to create opportunities for students to learn from each other."

[1294] In this way, the present invention provides teachers with prompt and specific suggestions for the educational challenges they face, contributing to the improvement of teaching methods. This system is a groundbreaking means of providing support to teachers to achieve higher educational effectiveness.

[1295] The processing flow will be explained below.

[1296] Step 1: The user enters a query using a terminal.

[1297] A teacher types into the device interface, "There are some areas in my math class where students are struggling to understand. Can you suggest some effective solutions?"

[1298] When the teacher clicks the submit button, the input data is sent.

[1299] Step 2: The device sends a query to the server.

[1300] The terminal converts the teacher's input data into JSON format and sends it to the server as an HTTP POST request.

[1301] Step 3: The server receives the request.

[1302] The server receives the request from the device and records it in a log.

[1303] Check that the received data is in the correct format.

[1304] Step 4: The server calls the natural language processing engine.

[1305] The server passes the received education-related inquiries to a natural language processing engine for intent analysis.

[1306] A natural language processing engine analyzes the query and identifies the topic of the query (mathematics) and the type of problem (lack of understanding).

[1307] Step 5: The server accesses the education database.

[1308] The server accesses the education database based on the analysis results and searches for similar education cases.

[1309] Obtain a list of similar cases and check their contents.

[1310] Step 6: The server creates a prompt for the generative AI.

[1311] A prompt is created based on the similar cases acquired by the server and the inquiry content.

[1312] Prompts are instructions that the generative AI engine uses to generate appropriate recommendations.

[1313] Step 7: The server invokes the generative AI.

[1314] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[1315] A generative AI analyzes the prompts and generates new recommendations.

[1316] Step 8: The server retrieves the generated recommendations.

[1317] The server receives the recommendations generated by the generative AI engine.

[1318] Review the proposal and put it into the appropriate format.

[1319] Step 9: The server sends the recommendation to the user.

[1320] The server transmits the generated recommendations to the user's terminal.

[1321] It is sent as an HTTP response and provided to the teacher.

[1322] Step 10: Your device will display a recommendation.

[1323] The terminal receives the response from the server and displays the recommendations to the teacher on the interface.

[1324] Teachers can review the proposed methods and put them into practice.

[1325] Specific examples

[1326] For example, if a teacher is teaching a math class and a student is struggling to understand a particular formula, the process might proceed as follows:

[1327] 1. The teacher types into the terminal, "Student does not understand how to solve the quadratic equation. Please suggest a solution."

[1328] 2. The device sends the input data to the server.

[1329] 3. The server receives the query and analyzes it using a natural language processing engine.

[1330] 4. The server searches the educational database for past "case studies on understanding quadratic equations."

[1331] 5. The server creates a prompt based on the acquired examples and sends it to the generative AI.

[1332] 6. Generative AI generates recommendations such as "Use visual models to visualize how to solve quadratic equations" or "Introduce group work to encourage discussion among students."

[1333] 7. The server sends the generated proposal to the teacher's terminal, and the terminal displays the proposal to the teacher.

[1334] In this way, the system allows teachers to quickly obtain concrete suggestions for improving their teaching methods.

[1335] Example 1

[1336] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1337] It is difficult for educators to find quick and effective solutions to problems and questions about teaching methods. In particular, it takes time and effort to obtain specific teaching method recommendations while referring to past cases. To solve this problem, a system is needed that allows educators to consult about teaching methods in natural language and quickly obtain appropriate recommendations.

[1338] 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.

[1339] In this invention, the server includes means for receiving an inquiry about education written in natural language, means for transmitting the received inquiry to the server as JSON format data, means for passing the received data to a natural language processing engine and identifying the intent of the inquiry, means for searching an education database for similar past education cases based on the analysis results, means for transmitting prompts to the generative artificial intelligence engine based on the acquired case data and the inquiry content, and means for providing the generated recommendations to the educator. This enables educators to obtain quick and effective recommendations based on specific past education cases through inquiries in natural language.

[1340] "Inquiries about education written in natural language" refers to text data entered by educators in everyday language as consultations or questions about their own educational activities.

[1341] "Receiving means" refers to the mechanism or method by which the server receives data sent from the user.

[1342] "JSON format data" is a format that treats data as a text-based object representation, and refers to a simple way to describe structured data.

[1343] A "natural language processing engine" is a software engine for analyzing meaning and intent from input text data, and specifically refers to technology for understanding and processing natural language.

[1344] An "educational database" is a data storage system that stores data on previously solved educational cases and methods.

[1345] A "generative artificial intelligence engine" is an artificial intelligence engine that generates appropriate advice and recommendations based on a pre-trained model.

[1346] A "prompt" is text data of instructions or questions input to a generative AI engine.

[1347] "Means for providing recommendations" refers to the mechanisms or methods for displaying or notifying educators of generated recommendations.

[1348] This invention relates to a system that analyzes problems and provides appropriate recommendations when educators ask for advice or questions about educational methods. This system is primarily composed of a user (educator) terminal, a server, a natural language processing engine, a generative artificial intelligence engine, and an educational database.

[1349] First, the user (educator) uses their own device (PC, tablet, smartphone, etc.) to input their inquiry or question about teaching methods in natural language. The device is provided with a dedicated application or a web interface that can be accessed from a browser. Specifically, the user types, "There are some areas in my math class where students are struggling to understand. Can you suggest an effective solution?" into the text field on the screen.

[1350] The device then sends the input query as an HTTP POST request to the server. The server receives the request using Node.js and parses it into JSON-formatted data. This data is then passed to a natural language processing engine designed using Python libraries (e.g., spaCy and Transformers) to analyze the intent of the text data. The natural language processing engine extracts key keywords and phrases from the received query, such as "math class" and "student's lack of understanding."

[1351] Next, based on the analysis results, the server uses MySQL or MongoDB to search an education database that stores similar educational cases that have been solved in the past. For example, it uses an SQL query in the format "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of understanding"" to retrieve related educational cases.

[1352] Based on the acquired data, the server generates and sends appropriate prompts to the generative AI engine. The generative AI engine (e.g., OpenAI's GPT-3) uses these prompts to generate specific teaching method recommendations. For example, a prompt such as "Please suggest effective ways to help students understand mathematics" can be sent. Specific examples of generated recommendations include "Use visual tools to help students understand formulas" and "Introduce group work to encourage students to discuss among themselves."

[1353] Finally, the generated recommendations are sent from the server to the client device and provided to the educator. The device analyzes the received response and displays the recommendations to the educator on an application or browser. This allows the educator to incorporate the provided specific recommendations into their teaching methods and improve the quality of their lessons.

[1354] Prompt Sentence Examples

[1355] "Please suggest effective ways to help students understand mathematics."

[1356] "My students are struggling with grammar in English class. Can you tell me how to solve this?"

[1357] "What are some good ways to ensure safety during experiments in junior high school science classes?"

[1358] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1359] Program processing flow

[1360] Step 1:

[1361] User inquiry submission

[1362] Specific behavior:

[1363] The user (educator) uses a dedicated application on the device or a web interface to input questions or concerns about teaching methods in natural language. For example, they might type, "In my math class, there are some areas where students are struggling to understand. Can you suggest an effective solution?" into a text field.

[1364] input:

[1365] The natural language query text entered by the user.

[1366] output:

[1367] The query text is sent from the terminal to the server as an HTTP POST request.

[1368] Step 2:

[1369] Receiving and analyzing on the server

[1370] Specific behavior:

[1371] The server receives the HTTP POST request sent from the device. The server parses this request as JSON format data and passes the data to the natural language processing engine. The server uses Node.js to receive and parse the data.

[1372] input:

[1373] HTTP POST request (query text) sent from the terminal.

[1374] output:

[1375] Query data in JSON format is generated and passed to the natural language processing engine.

[1376] Step 3:

[1377] Intention analysis using a natural language processing engine

[1378] Specific behavior:

[1379] The server uses Python libraries (e.g., spaCy and Transformers) to analyze the intent of the query text. A natural language processing engine extracts keywords and phrases such as "math lessons" and "student lack of understanding."

[1380] input:

[1381] Query data in JSON format.

[1382] output:

[1383] Analysis results (keywords and phrases) are generated.

[1384] Step 4:

[1385] Search for similar past cases

[1386] Specific behavior:

[1387] Based on the analysis results, the server searches the education database using MySQL or MongoDB. For example, it executes an SQL query such as "SELECT FROM EducationCases WHERE Subject="Mathematics" AND Issue="Lack of Understanding"" to retrieve relevant education cases.

[1388] input:

[1389] Intent analysis results (keywords and phrases).

[1390] output:

[1391] Data on similar past cases obtained from an educational database.

[1392] Step 5:

[1393] Recommendation generation using a generative AI engine

[1394] Specific behavior:

[1395] The server generates a prompt (instruction sentence) based on the acquired case data and the inquiry content and sends it to the generative AI engine. For example, it inputs a prompt such as "Please suggest an effective way to help students understand mathematics" and sends it to the generative AI engine (e.g., GPT-3).

[1396] input:

[1397] Past similar case data and generated prompts.

[1398] output:

[1399] A recommendation statement is generated.

[1400] Step 6:

[1401] Providing recommendations

[1402] Specific behavior:

[1403] The generated recommendations are sent from the server to the client device, which then analyzes the received response and displays the recommendations to the educator on the application or browser.

[1404] input:

[1405] The generated recommendation.

[1406] output:

[1407] Specific recommendations provided to educators.

[1408] (Application example 1)

[1409] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1410] In conventional education-related systems, there are insufficient ways for teachers to receive quick and specific suggestions regarding teaching methods, and there are no means to provide real-time advice to store clerks on customer service methods, making it difficult to provide optimal service to customers.There is a need for a system that can provide effective suggestions and advice immediately in educational settings and in physical stores.

[1411] 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.

[1412] In this invention, the server includes: means for receiving inquiries about education written in natural language; a natural language processing engine for analyzing the received inquiries and identifying their intent; means for searching a database for similar past education cases based on the analysis results; a generative artificial intelligence engine for generating recommendations for education methods based on the search results; means for providing the generated recommendations to educators; means for store clerks to receive inquiries in real time about how to explain products and how to serve customers; the generative artificial intelligence engine for analyzing inquiries received from a smart device, searching for past customer service cases, and generating recommendations based on the results; and means including a smart device for providing the generated recommendations to store clerks. This enables educators to receive quick and specific recommendations in the field of education, and allows store clerks to receive appropriate customer service advice in real time in physical stores, thereby improving customer satisfaction.

[1413] A "natural language processing engine" is a software component that analyzes text written in natural language and identifies its intent and meaning.

[1414] "Educational methods" are the means and approaches that educators use to effectively impart knowledge and skills to students.

[1415] A "generative artificial intelligence engine" is an artificial intelligence model that generates new recommendations based on past cases and data.

[1416] A "device" is a hardware device for processing digital information, and specifically includes smartphones, smart glasses, head-mounted displays, etc.

[1417] An "inquiry" is a question or inquiry sent by a user to the system.

[1418] A "recommendation" is specific advice or instructions for solving a specific problem.

[1419] A "brick and mortar store" is a physical store where customers visit in person to purchase goods or services.

[1420] "Customer service methods" refer to the way in which store staff respond to and provide service to customers.

[1421] This invention is a system that analyzes problems and provides appropriate suggestions when teachers ask for advice or questions about teaching methods. Furthermore, this invention can also be applied to situations where store clerks in physical stores ask for advice or questions about customer service methods in real time.

[1422] Overall system configuration

[1423] 1. User inquiry submission

[1424] Users (teachers or store clerks) use their own devices (smartphones, smart glasses, head-mounted displays, etc.) to input questions or concerns about teaching methods or customer service methods in natural language. This input is done through a text field or voice input function. For example, a teacher might type, "My students are having trouble solving quadratic equations. Please suggest an effective solution," or a store clerk might ask, "Please tell me how to explain a new product."

[1425] 2. Receiving and analyzing on the server

[1426] The device sends this input to the server as an HTTP POST request. The server receives the request and passes the content to a natural language processing engine (e.g., spaCy or the BERT model). The natural language processing engine analyzes the received query and identifies the intent of the query. For example, intents such as "quadratic equations," "lack of understanding," "new product," and "explanation method" may be identified.

[1427] 3. Search for similar past cases

[1428] Based on the analysis results, the server accesses an education database or customer service database to search for similar cases that have occurred in the past. The server obtains methods and success stories that have been used to solve similar problems. Through this database search, the server finds useful past cases.

[1429] 4. Recommendation generation using a generative AI engine

[1430] Based on the acquired similar cases and the inquiry content, the server creates and sends a prompt to a generative AI engine (for example, OpenAI's GPT-3 model). The generative AI engine generates appropriate recommendations for the user based on this prompt. For example, in the case of education, a recommendation might be "use visual tools to help understand formulas," or in the case of a physical store, "explain product usage scenarios with videos and photos."

[1431] 5. Providing Recommendations

[1432] The generated recommendations are sent from the server to the client terminal and provided to the user. The terminal displays the received recommendations, allowing the user to improve their training and customer service methods based on the information.

[1433] Specific application examples

[1434] Consider a scenario in which a teacher is teaching junior high school mathematics and a student is struggling to solve a quadratic equation. The teacher sends a query via their device saying, "The student is struggling to understand how to solve a quadratic equation. Please suggest an effective solution." The server receives the query and uses a natural language processing engine to identify the intent - "quadratic equation" and "lack of understanding." It then searches an educational database to retrieve "past cases related to solving quadratic equations." Based on this data, a generative AI engine generates specific recommendations, such as "use visual aids as an operational approach to demonstrate the process of solving the equation" and "implement pair work to create opportunities for students to learn from each other," and provides these to the teacher.

[1435] For example, if a sales associate wears smart glasses and wants to know how to explain a new product in a physical store, they can ask, "Please tell me how to explain the new product." The voice data sent from the smart glasses is converted into text data and sent to a server. The server analyzes it using a natural language processing engine to identify the intent - "new product" and "how to explain it." It then searches a customer service database to retrieve similar past cases. Based on this data, a generative AI engine generates recommendations, providing advice such as "show photos and videos of specific usage scenarios for the product" or "explain its features in line with the customer's needs."

[1436] In this way, the present invention provides prompt and specific suggestions for the educational and customer service challenges faced by teachers and store clerks, contributing to the improvement of educational and customer service methods.

[1437] Prompt Sentence Examples

[1438] User: "My student is having trouble solving quadratic equations. Can you suggest an effective solution?"

[1439] Past cases:

[1440] 1. "Use visual aids to show the process of solving an equation."

[1441] 2. "Implement pair work to create opportunities for students to learn from each other."

[1442] Generate recommendations for new teaching methods based on past examples.

[1443] The above is a detailed description of the embodiment of the present invention. This system makes it possible to obtain prompt and effective recommendations in educational and customer service settings.

[1444] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1445] Step 1:

[1446] The user inputs and sends a natural language query on the terminal.

[1447] Specifically, the user (teacher or store clerk) enters something like "My student is having trouble understanding how to solve quadratic equations. Please suggest an effective solution" or "Please tell me how to explain our new product" into the text field on the device, and then presses the send button. At this time, the device can also use software (e.g., Google Cloud Speech-to-Text) that converts voice input into text data.

[1448] Input: Enquiry (natural language text or voice data)

[1449] Output: Sends the query to the server as an HTTP POST request

[1450] Step 2:

[1451] The server passes the received query to a natural language processing engine for analysis.

[1452] Specifically, the server passes the received query to a natural language processing engine (e.g., spaCy or the BERT model) to analyze its intent. Through this analysis, key elements of the query (e.g., "quadratic equation," "lack of understanding," "new product," and "explanation method") are extracted.

[1453] Input: Inquiry content (text data of HTTP POST request)

[1454] Output: Analysis results (data identifying intent)

[1455] Step 3:

[1456] Based on the analysis results, the server searches a database for similar past cases.

[1457] Specifically, the server accesses the education database and customer service database to search for past cases that correspond to the analysis results. For example, it searches for "past cases related to solving quadratic equations" or "past cases related to how to explain new products." This search retrieves useful similar cases.

[1458] Input: Analysis results

[1459] Output: Past similar cases (search result data)

[1460] Step 4:

[1461] Based on similar past cases and the inquiry content acquired by the server, a prompt is created and sent to the generative artificial intelligence engine.

[1462] Specifically, the server generates a prompt that combines similar past cases and the analysis results. The generated prompt is then sent to a generative AI engine (e.g., OpenAI's GPT-3 model). For example, a prompt might read, "User inquiry: My student is struggling to understand how to solve quadratic equations. Please suggest an effective solution. Past cases: 1. Use visual aids to show the process of solving the equation. 2. Conduct pair work to create opportunities for students to learn from each other. Please generate recommendations for new teaching methods based on past cases."

[1463] Input: Past similar cases (search results data), analysis results

[1464] Output: Generated prompt statement

[1465] Step 5:

[1466] A generative artificial intelligence engine generates recommendations based on prompts.

[1467] Specifically, the generative AI engine analyzes the prompt and generates new recommendations based on it. For example, in education, it might generate specific recommendations such as "use visual tools to help understand formulas," or in a physical store, it might generate specific recommendations such as "show photos and videos of specific product usage scenarios."

[1468] Input: Generated prompt text

[1469] Output: Recommendation (generated result data)

[1470] Step 6:

[1471] The server transmits the generated recommendations to the client terminal for display.

[1472] Specifically, the server sends the generated recommendations to the client terminal, which then displays the received recommendations, allowing the user to check the content and use it in actual training or customer service.

[1473] Input: Recommendation (generated result data)

[1474] Output: Recommendations displayed on the user's terminal

[1475] 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.

[1476] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[1477] Overall system configuration

[1478] The system consists of the following components:

[1479] 1. Terminal: A device (PC, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[1480] 2. Server: A central processing unit that analyzes the received queries, generates teaching method recommendations, and provides them to educators.

[1481] 3. Natural language processing engine: Software that analyzes inquiries sent from the device and identifies their intent.

[1482] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[1483] 5. Generative AI engine: An AI program that generates recommendations for teaching methods based on analysis results and similar past cases.

[1484] 6. Emotion engine: Software that recognizes the user's emotions and incorporates this information into the generation of recommendations.

[1485] Specific processing flow

[1486] 1. User Inquiry and Emotion Recognition

[1487] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[1488] 2. Receiving and analyzing on the server

[1489] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[1490] 3. Search for similar past cases

[1491] The server then searches the educational database based on the analysis results to extract similar past educational cases, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[1492] 4. Generating Recommendations

[1493] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[1494] 5. Providing Recommendations

[1495] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[1496] Specific examples

[1497] For example, say a teacher is having trouble getting students to understand quadratic equations, and the emotion engine detects "frustration." In this case, the system would act as follows:

[1498] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[1499] 2. The device sends the query and emotion data (irritation) to the server.

[1500] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[1501] 4. Search for similar past cases in the educational database.

[1502] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[1503] 6. The proposal will be sent to the device and displayed to the teacher.

[1504] In this way, the present invention allows teachers to quickly receive specific and sensitive suggestions for improving their teaching methods.

[1505] The processing flow will be explained below.

[1506] Step 1: The user enters a query using a terminal.

[1507] The teacher types into the device interface, "My student doesn't understand how to solve quadratic equations. What should I do?" and clicks the send button.

[1508] Step 2: The device sends a query to the server.

[1509] The device converts the input query into JSON format and sends it to the server as an HTTP POST request.

[1510] Step 3: The server receives the request.

[1511] The server receives the request sent from the terminal.

[1512] Verify that the received data is in the correct format.

[1513] Step 4: The server passes the query to the natural language processing engine.

[1514] The server forwards the received query to the natural language processing engine.

[1515] A natural language processing engine analyzes the query and identifies the topic (e.g., "quadratic equation") and the type of problem (e.g., "lack of understanding").

[1516] Step 5: The device performs emotion recognition through the emotion engine.

[1517] The terminal executes an emotion engine to recognize the teacher's emotion when inputting a query.

[1518] The emotion engine analyzes the teacher's emotions (for example, "irritation") from text and voice and generates emotion data.

[1519] Step 6: The server receives the emotion data.

[1520] The emotion data generated by the device is transmitted to the server.

[1521] The server receives the emotion data and integrates it with query analysis.

[1522] Step 7: The server accesses the education database.

[1523] The server searches the educational database based on the content of the query analyzed by the natural language processing engine and the received emotional data.

[1524] Extract relevant past "educational examples on solving quadratic equations."

[1525] Step 8: The server creates a prompt for the generative AI.

[1526] The server uses the acquired educational examples, inquiry details, and emotional data to create prompts to be passed to the generative AI engine.

[1527] Prompts include information such as, "This teacher is frustrated and needs help with students understanding quadratic equations. Provide suggestions including emotional support strategies."

[1528] Step 9: The server invokes the generative AI.

[1529] The server sends a prompt to the generative AI engine, asking it to generate a recommendation.

[1530] A generative AI engine analyzes the prompts and generates appropriate teaching recommendations.

[1531] Step 10: The server retrieves the generated recommendations.

[1532] The server receives the recommendations generated by the generative AI engine.

[1533] The recommendations include specific methods such as "using visual tools to visualize how to solve quadratic equations" and "introducing breaks to encourage students to relax."

[1534] Step 11: The server sends the recommendation to the user.

[1535] The server transmits the generated recommendations to the user's terminal.

[1536] The generated recommendations are returned as an HTTP response.

[1537] Step 12: The device will display the recommendations.

[1538] The terminal receives the recommendations sent from the server.

[1539] The recommendations will be displayed on teachers' screens so that they can review them and incorporate them into their teaching methods.

[1540] Specific examples

[1541] For example, consider a case where a teacher is facing a problem in a math class where a student is struggling to solve a quadratic equation, and the emotion engine detects "irritation." In this case, the system operates as follows:

[1542] 1. The teacher types "My student doesn't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[1543] 2. The device sends this query along with the "irritation" data analyzed by the emotion engine.

[1544] 3. The server receives the query and sentiment data and uses a natural language processing engine to identify the intents "quadratic equation" and "lack of understanding."

[1545] 4. Search educational databases for relevant past cases.

[1546] 5. A generative AI engine generates recommendations for teaching methods such as "use visual tools to help understand formulas" or "introduce breaks for relaxation."

[1547] 6. The proposal is sent to the user's device and displayed to the teacher.

[1548] This system allows teachers to receive specific and immediate suggestions for improving their teaching methods, which not only improves teaching effectiveness but also contributes to reducing the mental burden on teachers.

[1549] Example 2

[1550] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1551] Conventional educational support systems have had difficulty providing appropriate recommendations to address teachers' concerns and questions. Furthermore, they were unable to generate recommendations that took the teacher's emotions into account, making them impractical for practical use in the classroom. The present invention aims to solve these problems by providing a system that provides appropriate recommendations that take the teacher's emotions into account when the teacher seeks advice about their concerns and questions regarding teaching methods.

[1552] 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: means for receiving an inquiry about education written in natural language; a natural language processing engine for analyzing the received inquiry and identifying the intention of the inquiry; means for searching a database for similar past educational cases based on the analysis results; a generative artificial intelligence engine for generating educational method recommendations based on the search results; means for providing the generated recommendations to educators; emotion recognition means for recognizing the user's emotions and generating emotion data; and means for evaluating the urgency and importance of the inquiry based on the generated emotion data. As a result, when a teacher consults with a concern or question about educational methods, the intention and emotion of the teacher can be analyzed and appropriate recommendations can be provided quickly.

[1553] "Inquiries about education written in natural language" refers to questions or inquiries about education entered by teachers using natural language.

[1554] "Means of receiving" refers to the function that allows the system to receive inquiries entered by teachers through their terminals.

[1555] A "natural language processing engine" refers to software that analyzes inquiries written in received natural language and understands their intent.

[1556] "Analysis results" refers to the information and data obtained after the natural language processing engine has completed understanding the query.

[1557] "Means for searching from a database" refers to the function of searching for similar past educational cases from an educational database based on the analysis results.

[1558] A "generative artificial intelligence engine" refers to an artificial intelligence program that generates recommendations for educational methods based on analysis results and similar past cases.

[1559] "Generated recommendations" refers to specific advice and solutions regarding teaching methods output by the generative AI engine.

[1560] "Means of providing" refers to the function for delivering and displaying the generated recommendations to educators.

[1561] "Emotion recognition means" refers to a function that recognizes emotions from user input and generates those emotions as data.

[1562] "Emotion data" refers to the user's emotion information extracted by the emotion recognition means.

[1563] "Means for assessing urgency and importance" refers to a function that assesses the urgency and importance of an inquiry based on the generated emotional data.

[1564] This invention relates to a system that analyzes problems and provides appropriate suggestions when teachers consult with them about their worries or questions about teaching methods. In addition, by adding an emotion engine that recognizes the user's emotions, the accuracy and applicability of the teaching method suggestions are further improved.

[1565] Overall system configuration

[1566] The system consists of the following components:

[1567] 1. Terminal: A device (personal computer, tablet, smartphone, etc.) that allows users (teachers) to input educational inquiries and send them to the server.

[1568] 2. Server: It is a central processing unit that analyzes the received queries, generates teaching method recommendations and provides them to educators.

[1569] 3. Natural language processing engine: Software that analyzes queries sent from the device and identifies their intent. Specifically, it uses the Python NLTK library to analyze queries.

[1570] 4. Educational database: A database that stores past educational cases and makes them searchable as needed.

[1571] 5. Generative AI engine: An AI program that generates recommendations for educational methods based on analysis results and similar past cases.

[1572] 6. Emotion engine: Software that recognizes the user's emotions and incorporates that information into the generation of recommendations.

[1573] Hardware and Software Examples

[1574] Hardware: Personal computers, tablets, smartphones

[1575] software:

[1576] Natural Language Processing Engine: Python's NLTK Library

[1577] Generative AI engine: Generative AI model (e.g. GPT-3)

[1578] Database system: SQL database

[1579] Specific processing flow

[1580] User Inquiry and Emotion Recognition

[1581] The user (teacher) uses a terminal to input their educational concerns or questions in natural language. For example, they might input, "My student doesn't understand how to solve a quadratic equation. What should I do?" The emotion engine then recognizes the teacher's emotions (impatience, anxiety, irritation, etc.) from the input text and voice and attaches them as emotion data.

[1582] Receiving and analyzing on the server

[1583] The device sends emotion data along with the inquiry to the server. The server then passes the received data to a natural language processing engine to analyze the intent of the inquiry. Specifically, the server identifies the keywords "quadratic equation" and "lack of understanding." The server also uses the emotion engine data to evaluate the urgency and importance of the inquiry.

[1584] Search for similar past cases

[1585] The server searches an educational database based on the analysis results to extract similar past educational examples, such as "how to deal with a student who had difficulty understanding quadratic equations in the past."

[1586] Generate recommendations

[1587] The server sends prompts to the generative AI engine based on the query, similar cases, and emotional data. The generative AI engine then takes this information into account to generate teaching method recommendations. For example, recommendations might include "use visual tools to demonstrate how to solve quadratic equations" or "introduce pair work between students." The user's emotional data also influences the content and tone of the recommendations.

[1588] Providing recommendations

[1589] The server sends the generated recommendations to the user's device and provides them to the educator. The device displays the received recommendations on the screen so that the teacher can easily check them.

[1590] Specific examples

[1591] For example, if a teacher is having trouble getting students to understand quadratic equations and the emotion engine detects "frustration," the system might do the following:

[1592] 1. The teacher types "I don't understand how to solve quadratic equations. What should I do?" into the terminal and submits it.

[1593] 2. The device sends the query and emotion data (irritation) to the server.

[1594] 3. The server uses a natural language processing engine to identify "quadratic equations" and "lack of understanding" and evaluate the emotional data.

[1595] 4. Search for similar past cases in the educational database.

[1596] 5. A generative AI engine generates recommendations such as "Use visual tools and set aside time to promote relaxation as part of emotional care."

[1597] 6. The proposal will be sent to the device and displayed to the teacher.

[1598] In this way, the present invention allows teachers to quickly receive specific and sensitive recommendations for improving their teaching methods.

[1599] Prompt Sentence Examples

[1600] "A teacher is having trouble with students' understanding of quadratic equations. The teacher is frustrated and would like suggestions on what teaching methods would be appropriate."

[1601] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1602] Step 1:

[1603] Users use the device to input their educational concerns or questions in natural language. For example, a teacher might use a PC and type, "My student doesn't understand how to solve a quadratic equation. What should I do?" and click the send button. This input is captured as input data on the device.

[1604] Step 2:

[1605] The emotion engine recognizes the user's emotions from the text data entered into the device. For example, it identifies the emotion of "irritation" from the content of the text and the words used, and generates it as emotion data. In this way, emotion data is generated along with the input data.

[1606] Step 3:

[1607] The device sends the user's input data and the generated emotion data to the server. Specifically, it sends a JSON-formatted request containing the input data and emotion data to the server using the HTTP protocol. The server then receives the input data and emotion data.

[1608] Step 4:

[1609] The server passes the received data to a natural language processing engine. The natural language processing engine uses Python's NLTK library to analyze the input data and identify the intent of the query. For example, it extracts keywords such as "quadratic equation" and "lack of understanding" from the input text and generates analysis result data.

[1610] Step 5:

[1611] The server analyzes the emotion data and evaluates the urgency and importance of the inquiry. For example, if it recognizes from the emotion data that the user is feeling "irritated," it sets the urgency of the inquiry as "high" and records it as evaluation data. This generates analysis result data and evaluation data.

[1612] Step 6:

[1613] The server searches the educational database based on the analysis result data. Specifically, it uses an SQL query to search for "past educational cases related to a lack of understanding of quadratic equations" and extracts similar case data. This generates similar case data.

[1614] Step 7:

[1615] The server sends a prompt containing the query content, similar case data, and emotion data to the generative AI engine. Specifically, it generates a prompt sentence and sends it as a POST request to the generative AI model's API. This allows the generative AI model to generate recommendations based on the prompt.

[1616] Step 8:

[1617] The generative AI engine generates recommendations for teaching methods based on the prompts it receives, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This generates recommendation data.

[1618] Step 9:

[1619] The server sends the generated recommendation data to the user's device. Specifically, it sends a JSON-formatted response containing the recommendation data to the device using the HTTP protocol. As a result, the device receives the recommendation data.

[1620] Step 10:

[1621] The device displays the received recommendation data on the screen. The user (teacher) can then check the recommendations on the device screen, such as "Use visual tools to demonstrate how to solve quadratic equations" or "Allow time to encourage relaxation." This allows the user to make use of the generated recommendations.

[1622] (Application example 2)

[1623] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1624] In conventional education systems, teachers who have concerns or questions about teaching methods have difficulty receiving prompt and appropriate advice. Furthermore, because the teacher's emotional state is not taken into consideration, the advice is often ineffective. Furthermore, in factory work environments, workers often lack real-time advice on their questions or problems, which can lead to reduced work efficiency. To address these issues, a system is needed that allows teachers and workers to quickly resolve their concerns about teaching methods and work procedures.

[1625] 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.

[1626] In this invention, the server includes means for receiving a query written in natural language, a natural language processing engine for analyzing the received query and identifying its intent, means for searching a database for similar past cases based on the analysis results, a generative artificial intelligence engine for generating recommendations based on the analysis results and similar past cases, an emotion recognition engine for recognizing the user's emotions and reflecting them in the generation of recommendations, and means for instantly providing the generated recommendations, thereby enabling the user to receive prompt and appropriate recommendations in a manner that takes emotions into consideration.

[1627] A "natural language processing engine" is software that analyzes text written in natural language and identifies its intent and meaning.

[1628] A "database" is an information management system that stores past cases and information and makes them searchable as needed.

[1629] A "generative artificial intelligence engine" is an artificial intelligence program that generates new suggestions and answers based on analysis results and similar past cases.

[1630] An "emotion recognition engine" is software that analyzes a user's emotional state from input information.

[1631] "Recommendation provider" refers to a method or device for providing generated recommendations to a user.

[1632] To implement this invention, it is necessary to build a system in which a server, a terminal, and necessary software work together. Specifically, the server includes the following means and software:

[1633] Natural Language Processing Engine (NLP Engine)

[1634] The server first receives a query written in natural language from a user (teacher or worker) and passes it to a natural language processing engine. This engine performs text analysis, particularly using Hugging Face's Transformers, to identify keywords and intent. Based on the results of this analysis, the content of the query is clarified.

[1635] Database

[1636] Based on the analysis results, the server searches a database for similar past cases. The database contains a collection of cases and solutions, and records that match the query are searched for. This allows for quick and appropriate suggestions.

[1637] Generative AI engine

[1638] The server sends prompts to the generative AI engine based on information from the database and the analysis results of the natural language processing engine. The generative AI model generates new suggestions and answers, and generates documents to provide specific countermeasures. This is done using Hugging Face's text-generation pipeline. At this point, the system generates guidelines for the user to take specific actions.

[1639] Emotion Recognition Engine

[1640] The server uses an emotion engine to recognize emotions from the user's query text and voice. Emotion analysis assesses the user's emotional state and adjusts the content and tone of the suggestions accordingly. This emotion data is also passed to the generative AI engine, which influences the final recommendation.

[1641] Providing recommendations

[1642] The server immediately sends the generated recommendations to the user's device (e.g., a smartphone or smart glasses), which then displays the recommendations in a format that the user can easily check, supporting prompt action.

[1643] Specific examples

[1644] For example, if a factory worker sends a query such as, "Assembly line has frequent stoppages, how can we reduce this?", the system operates as follows: The server uses a natural language processing engine to identify keywords such as "Assembly line" and "frequent stoppages" and searches a database for past cases. The results are passed to a generative artificial intelligence engine, which generates a document proposing appropriate work procedures and countermeasures. At this time, an emotion recognition engine detects the worker's frustration and adjusts the tone of the proposal. Finally, the generated recommendation (for example, "It is recommended that regular machine maintenance be strengthened and the working environment be improved") is immediately sent to the worker's device and displayed.

[1645] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1646] Step 1:

[1647] The user inputs and sends inquiries about training methods and work procedures in natural language from the terminal, which then sends the inquiries to the server.

[1648] Input: User query text or voice (e.g., "Our assembly line keeps stopping. How can we improve it?")

[1649] Output: Send query text and voice data to the server

[1650] Step 2:

[1651] The server then passes the received query to a natural language processing engine to begin analysis, which identifies the intent of the query and extracts keywords and key context.

[1652] Input: Inquiry text / voice data

[1653] Data processing / calculation: A natural language processing engine analyzes text and extracts keywords and intent.

[1654] Output: Analysis results (e.g., keywords such as "assembly line" and "frequent stops")

[1655] Step 3:

[1656] Based on the analysis results, the server searches a database for similar cases from the past, including responses and solutions to similar problems faced in the past.

[1657] Input: Keywords of analysis results

[1658] Data processing / calculation: Search for similar cases using database search algorithms

[1659] Output: Similar case data (e.g., "Previous assembly line shutdown events and their solutions")

[1660] Step 4:

[1661] The server passes the query text to an emotion recognition engine to analyze the user's emotion, which identifies the emotional state (e.g., stress, impatience, irritation).

[1662] Input: Query text

[1663] Data processing / calculation: Emotion recognition through text analysis

[1664] Output: Emotion data (e.g., "frustration")

[1665] Step 5:

[1666] The server passes the analysis results, similar case data, and emotion data to a generative AI engine, which then creates prompts to generate appropriate recommendations.The generative AI model uses this information to generate new suggestions and answers.

[1667] Input: Analysis results, similar case data, emotion data

[1668] Data processing / calculation: A generative AI engine generates recommendations based on prompts

[1669] Output: Generated recommendation statement (e.g., "It is recommended to strengthen regular maintenance of machines and improve the working environment.")

[1670] Step 6:

[1671] The server immediately transmits the generated recommendations to the user's terminal, which then displays the recommendations to the user.

[1672] Input: Generated recommendation

[1673] Output: Send and display a recommendation to the user's device (e.g., "It is recommended that you strengthen regular maintenance of your machines and improve the working environment.")

[1674] Through these steps, users can receive prompt and appropriate recommendations in real time.

[1675] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1676] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1677] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1678] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1679] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1680] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1681] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1682] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1683] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1684] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1685] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1686] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1687] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1688] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1689] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1690] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1691] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1692] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1693] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1694] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1695] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1696] The following is further disclosed regarding the above embodiment.

[1697] (Claim 1)

[1698] means for receiving an education inquiry written in natural language;

[1699] a natural language processing engine that analyzes incoming inquiries and identifies their intent;

[1700] A means for searching a database for similar past educational cases based on the analysis results;

[1701] A generative AI engine that generates educational method recommendations based on search results;

[1702] a means of providing generated recommendations to educators;

[1703] A system including:

[1704] (Claim 2)

[1705] 2. The system according to claim 1, further comprising a step of passing the received query to a natural language processing engine for intent analysis.

[1706] (Claim 3)

[1707] The system according to claim 1, characterized in that the generative artificial intelligence engine generates educational method recommendations taking into account past similar cases and the content of the inquiry.

[1708] "Example 1"

[1709] (Claim 1)

[1710] means for receiving an education inquiry written in natural language;

[1711] A means for sending received queries to a server as JSON format data;

[1712] A means for passing the received data to a natural language processing engine to identify its intent;

[1713] A means for searching for similar past educational cases from an educational database based on the analysis results;

[1714] a means for sending prompts to a generative artificial intelligence engine based on the acquired case data and the content of the inquiry;

[1715] a means of providing generated recommendations to educators;

[1716] A system including:

[1717] (Claim 2)

[1718] 2. The system according to claim 1, further comprising a step of passing the received query to a natural language processing engine for intent analysis.

[1719] (Claim 3)

[1720] The system according to claim 1, characterized in that the generative artificial intelligence engine generates educational method recommendations taking into account past similar cases and the content of the inquiry.

[1721] "Application Example 1"

[1722] (Claim 1)

[1723] means for receiving an education inquiry written in natural language;

[1724] a natural language processing engine that analyzes incoming inquiries and identifies their intent;

[1725] A means for searching a database for similar past educational cases based on the analysis results;

[1726] A generative AI engine that generates educational method recommendations based on search results;

[1727] a means of providing generated recommendations to educators;

[1728] A means for store staff to receive real-time inquiries about how to explain products and how to serve customers,

[1729] A generative AI engine that analyzes inquiries received from smart devices, searches for past customer service cases, and generates recommendations based on those cases;

[1730] a means including a smart device for providing the generated recommendations to a store associate;

[1731] A system including:

[1732] (Claim 2)

[1733] 2. The system according to claim 1, further comprising a step of passing the received query to a natural language processing engine for intent analysis.

[1734] (Claim 3)

[1735] The system according to claim 1, characterized in that the generative artificial intelligence engine generates recommendations on customer service methods by taking into account similar past cases and the content of the inquiry.

[1736] "Example 2: Combining Emotion Engines"

[1737] (Claim 1)

[1738] means for receiving an education inquiry written in natural language;

[1739] a natural language processing engine that analyzes incoming inquiries and identifies their intent;

[1740] A means for searching a database for similar past educational cases based on the analysis results;

[1741] A generative AI engine that generates educational recommendations based on search results;

[1742] a means of providing generated recommendations to educators;

[1743] emotion recognition means for recognizing an emotion of a user and generating emotion data;

[1744] A means for evaluating the urgency and importance of an inquiry based on the generated emotion data;

[1745] A system including:

[1746] (Claim 2)

[1747] 2. The system according to claim 1, further comprising a step of passing the received query to a natural language processing engine for intent analysis.

[1748] (Claim 3)

[1749] The system according to claim 1, characterized in that the generative artificial intelligence engine generates educational method recommendations taking into account past similar cases, the content of the inquiry, and emotional data.

[1750] "Application example 2 when combining emotion engines"

[1751] (Claim 1)

[1752] means for receiving an education inquiry written in natural language;

[1753] a natural language processing engine that analyzes incoming inquiries and identifies their intent;

[1754] A means for searching a database for similar past educational cases based on the analysis results;

[1755] A generative AI engine that generates educational method recommendations based on the analysis results and similar past cases;

[1756] an emotion recognition engine that recognizes the user's emotions and reflects them in generating recommendations;

[1757] a means of providing the generated recommendations immediately;

[1758] A system including:

[1759] (Claim 2)

[1760] 2. The system according to claim 1, further comprising a step of recognizing a user's emotion from a received inquiry using an emotion recognition engine, passing the emotion to a natural language processing engine, and performing intent analysis.

[1761] (Claim 3)

[1762] The system according to claim 1, characterized in that the generative artificial intelligence engine generates educational method recommendations taking into account past similar cases, the content of the inquiry, and the user's emotional data. [Explanation of symbols]

[1763] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving an education inquiry written in natural language; a natural language processing engine that analyzes incoming inquiries and identifies their intent; A means for searching a database for similar past educational cases based on the analysis results; A generative AI engine that generates educational method recommendations based on search results; a means of providing generated recommendations to educators; A system including:

2. 2. The system according to claim 1, further comprising a step of passing the received query to a natural language processing engine for intent analysis.

3. 2. The system according to claim 1, wherein the generative artificial intelligence engine generates educational method recommendations taking into account similar past cases and the content of the inquiry.

Images