System

Abstract

To provide a system enabling self-learning of a method for using spreadsheet software.SOLUTION: Provided is a system comprising: mean for generating a prompt text that instructs to generate a problem text relating to the use method on the basis of a question, which was inputted by a user relating to a method of using spreadsheet software, and a problem text relating to the use method by using a generative AI; means for generating a prompt text that instructs to generate an answer to the problem text, and an answer to the generated problem text; means for generating a prompt text that instructs to generate an explanation text for the answer, and an explanation text for the answer; means for presenting the problem text to the user; means for recognizing the user's emotion by using an emotion engine; means, on the basis of the user's emotion, for adjusting the answer or explanation text generated by using a prompt text that instructs to adjust the generated answer or explanation text and the generative AI; and means for presenting the adjusted answer or explanation text to the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] When new employees or those who are not good at OA-related subjects try to study by themselves, it is difficult for them to create appropriate problems and also difficult for them to obtain answers and explanations for the problems they have created. [Means for solving the problem]

[0005] We provide a system equipped with a problem generating means, an answer generating means, and an explanation generating means. This system generates problems related to Excel and spreadsheet formulas, simple automation, etc., and provides the answers and explanations. It is also possible to respond to OA-related questions in everyday work. [Brief description of the drawings]

[0006] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[0029] "Example 2"

[0030] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: The user logs into the system and selects the topic they want to learn, which can range from Excel and spreadsheet formulas to simple automation.

[0034] Step 2: Based on the selected topic, the system's problem generator will generate a problem, for example, a problem about how to use the VLOOKUP function in Excel.

[0035] Step 3: The generated question is presented to the user, who enters an answer.

[0036] Step 4: After the user submits the answer, the system's answer generation means provides the correct answer. Step 5: The system's explanation generation means provides an explanation for the answer. This allows users to save time and effort in creating questions and searching for answers and explanations when self-studying.

[0037] Step 6: When users input OA-related questions from their daily work into the system, the system will provide answers and explanations for those questions, such as how to use a specific function in Excel or how to resolve an error.

[0038] Example 1

[0039] Next, a description will be given of Example 1 of the embodiment 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".

[0040] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to respond quickly and accurately to specific questions related to clerical work in daily work.

[0041] 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.

[0042] In this invention, the server includes: a prompt sentence for instructing to generate a question sentence related to the question about how to use the spreadsheet software based on a question about how to use the spreadsheet software input by a user; a means for generating a question sentence related to the question about how to use the spreadsheet software using a generative AI; a prompt sentence for instructing to generate an answer to the generated question sentence; a means for generating an answer to the generated question sentence using the generative AI; a prompt sentence for instructing to generate an explanation for the generated answer; a means for generating an explanation for the generated answer using the generative AI; a means for presenting the generated question sentence to the user; a means for recognizing the user's emotion using an emotion engine; a prompt sentence for instructing to adjust the generated answer or explanation sentence based on the recognized emotion of the user; a means for adjusting the generated answer or explanation sentence using the generative AI; and a means for presenting the adjusted answer or explanation sentence to the user. This allows the user to efficiently self-study. The questions about how to use the spreadsheet software include questions about formulas used in the spreadsheet software or questions about automation. The questions about how to use the spreadsheet software include questions about how to use the spreadsheet software that are necessary for the user's office work, so that questions related to office work in everyday work can be quickly and accurately responded to.

[0043] The "question generation means" is a means for generating questions such as those related to formulas in a spreadsheet or simple automation based on a prompt sentence from a user.

[0044] The "answer generating means" is a means for generating an optimal answer to a generated question.

[0045] The "explanation generating means" is a means for generating a detailed explanation for the generated answer.

[0046] The "means for receiving a prompt sentence" refers to a means for receiving a specific question or request from the user in text form.

[0047] "Generative AI" is an artificial intelligence model that uses natural language processing technology to generate questions, answers, and explanations.

[0048] "Means for saving in a database" refers to means for saving the generated questions, answers, and explanations in a database.

[0049] "Spreadsheet software" is software for organizing, calculating, and analyzing data, and can process data using formulas and functions.

[0050] "Questions related to office work" are specific questions about how to use spreadsheet software and how to resolve errors that arise in daily work.

[0051] This invention is a system that allows users to efficiently self-learn and quickly and accurately respond to questions related to clerical work in their daily work. This system operates in cooperation with a server, a terminal, and a user.

[0052] Server Roles

[0053] The server manages and operates the entire system using the following means:

[0054] 1. Problem generation means

[0055] The server receives a question input by a user about how to use spreadsheet software. For example, the server receives a question sentence such as "Please tell me how to use the VLOOKUP function in Excel." The server generates a question sentence related to the question about how to use the spreadsheet software using a prompt sentence instructing the server to generate a question sentence related to the question and a generative AI (e.g., GPT-4 (registered trademark)). The generated question sentence is in the form of "Explain how to use the VLOOKUP function in Excel to get data from another sheet." The generated question sentence is stored in a database.

[0056] 2. Answer generation means

[0057] The server generates an answer to the generated question. It uses a prompt that instructs the server to generate an answer to the generated question and a generative AI to generate the optimal answer to the question. For example, an answer in the format "=VLOOKUP(search value, range, column number, search method)" is generated. The generated answer is stored in the database.

[0058] 3. Explanation Generation Method

[0059] The server generates a detailed explanation for the generated answer. A prompt that instructs the server to generate an explanation for the generated answer and a generative AI are used to generate a detailed explanation for the answer. For example, an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)" are generated. The generated explanation is saved in the database.

[0060] User Roles

[0061] A user accesses the system using a terminal and performs the following operations:

[0062] 1. Enter your question

[0063] A user uses the terminal to type in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[0064] 2. Obtaining questions

[0065] The user obtains the generated question text from the server and checks the question text on the terminal screen.

[0066] 3. Get answers

[0067] The user obtains the generated answer from the server and checks the answer on the screen of the terminal.

[0068] 4. Obtaining explanations

[0069] The user receives the generated commentary from the server and checks the commentary on the screen of the terminal.

[0070] Examples

[0071] For example, if a user enters the question "How do I use the VLOOKUP function in Excel?", the server processes the question as follows:

[0072] 1. Problem generation

[0073] The server generates a question such as, "Explain how to use Excel's VLOOKUP function to retrieve data from another sheet."

[0074] 2. Answer generation

[0075] The server generates the answer "=VLOOKUP(search value, range, column number, search method)".

[0076] 3. Description Generation

[0077] The server generates an explanatory text stating, "The VLOOKUP function searches for a search value within a specified range and returns the data from the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)."

[0078] In this way, the user can efficiently proceed with self-learning and can quickly and accurately respond to questions related to clerical work in the course of daily work.

[0079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0080] Step 1: Enter your question

[0081] Subject: User

[0082] A user accesses the system using a terminal and types in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[0083] Input: The question entered by the user

[0084] Output: The question is sent to the server.

[0085] Step 2: Receiving the question

[0086] Subject: Server

[0087] The server receives a question sent by a user.

[0088] Input: The question submitted by the user

[0089] Output: The question is ready to be processed in the server.

[0090] Step 3: Generate the problem

[0091] Subject: Server

[0092] The server uses the prompt text and generative AI to generate a question based on the question, for example, "Explain how to use the VLOOKUP function in Excel to get data from another sheet."

[0093] Input:Question

[0094] Data processing: Using prompts containing questions and generative AI, appropriate problem statements are generated.

[0095] Output: Generated problem statement

[0096] Step 4: Save the question

[0097] Subject: Server

[0098] The server stores the generated questions in a database.

[0099] Input: Generated question text

[0100] Data processing: Converting the generated questions into a database format

[0101] Output: The question is saved in the database.

[0102] Step 5: Generate the answer

[0103] Subject: Server

[0104] The server generates an answer to the generated question. It uses the prompt and generative AI to generate the optimal answer to the question. For example, it generates the answer "=VLOOKUP(search value, range, column number, search method)".

[0105] Input: Generated question text

[0106] Data processing: A generative AI model analyzes the question and generates an appropriate answer

[0107] Output: The generated answer

[0108] Step 6: Save your answers

[0109] Subject: Server

[0110] The server stores the generated answers in a database.

[0111] Input: Generated answer

[0112] Data processing: Converting the generated answers into a database format

[0113] Output: The answer is saved in the database.

[0114] Step 7: Generate a description

[0115] Subject: Server

[0116] The server generates a detailed explanation for the generated answer. It uses the prompt text and generative AI to generate a detailed explanation for the answer. For example, it generates an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. There are two search methods: TRUE (approximate match) and FALSE (exact match)."

[0117] Input: Generated answer

[0118] Data processing: A generative AI model analyzes the answers and generates appropriate explanations

[0119] Output: Generated description

[0120] Step 8: Save your commentary

[0121] Subject: Server

[0122] The server stores the generated commentary in a database.

[0123] Input: Generated description

[0124] Data processing: Convert the generated explanatory text into a database format.

[0125] Output: The explanatory text is saved in the database.

[0126] Step 9: Get the problem statement

[0127] Subject: User

[0128] The user uses a terminal to obtain the generated question text from the server and checks the question on the terminal screen.

[0129] Input: User request

[0130] Output: The generated question is displayed on the terminal.

[0131] Step 10: Getting the answer

[0132] Subject: User

[0133] The user uses the terminal to retrieve the generated answer from the server and check the answer on the terminal screen.

[0134] Input: User request

[0135] Output: The generated answer is displayed on the terminal.

[0136] Step 11: Get the description

[0137] Subject: User

[0138] The user uses the terminal to obtain the generated commentary from the server, and checks the commentary on the screen of the terminal.

[0139] Input: User request

[0140] Output: The generated commentary is displayed on the terminal. In this embodiment, when presenting a question sentence to a user, the server recognizes the user's emotion using an emotion engine, which will be described later. The server then adjusts the generated answer or commentary using a prompt sentence that instructs the user to adjust the generated answer or commentary based on the recognized user's emotion and the generative AI, and presents the adjusted answer or commentary to the user.

[0141] (Application example 1)

[0142] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0143] Conventional OA training systems were limited to providing questions related to Excel and spreadsheet formulas and simple automation, and did not address training related to the operation and maintenance of machines used in factories. This made it difficult to efficiently acquire knowledge related to the operation and maintenance of machines in factories. In addition, while the system had functions to answer OA-related questions in everyday work, it lacked functions to answer specific questions about the operation and maintenance of machines used in factories.

[0144] 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. In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a means for generating questions related to the operation and maintenance of machines used in a factory, a means for providing answers to the generated questions, and a means for providing explanations of the answers. This makes it possible to efficiently acquire knowledge related to the operation and maintenance of machines used in a factory.

[0145] The "problem generation means" is a means for generating problems related to Excel or spreadsheet formulas, simple automation, and the operation and maintenance of machines used in factories.

[0146] An "answer generating means" is a means for providing an answer to a generated question.

[0147] The "explanation generating means" is a means for providing an explanation for a generated answer.

[0148] "Machinery used in a factory" refers to various types of machinery and equipment used for production and maintenance within a factory.

[0149] "Operation" refers to the specific steps or methods for making a machine work.

[0150] "Maintenance" refers to the inspection and repair procedures to keep a machine in good working order.

[0151] The term "system" refers to a collection of a series of devices and programs including a problem generating means, an answer generating means, an explanation generating means, and a means for generating problems relating to the operation and maintenance of machines used in a factory.

[0152] A system for implementing the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems relating to the operation and maintenance of machines used in a factory, a means for providing answers to the generated problems, and a means for providing explanations for the answers.

[0153] The server implements a problem generation means, an answer generation means, and an explanation generation means using a programming language such as Python. Specifically, the problem generation means generates problems related to formulas in Excel or spreadsheets, simple automation, and the operation and maintenance of machines used in factories. For example, it generates a prompt sentence such as "Please write the code to program the operation of a robot."

[0154] The answer generation means provides an answer to the generated problem. For example, it generates a specific answer such as "Example: move_forward(10);". The explanation generation means provides an explanation for the generated answer. For example, it generates an explanation such as "This code moves the robot forward 10 meters".

[0155] Users can use this system to efficiently acquire knowledge about the operation and maintenance of machines used in factories. When a user accesses the system, the server generates questions and provides answers and explanations. This allows users to save time when self-studying by creating questions themselves and searching for answers and explanations.

[0156] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0157] Example prompt:

[0158] "Write the code to program the robot's movements."

[0159] In response to this prompt, the generative AI model provides the following answer and explanation:

[0160] Example answer:

[0161] "Example: move_forward(10);"

[0162] Example of explanation:

[0163] "This code will move the robot forward 10 meters."

[0164] In this way, training on the operation and maintenance of machines used in the factory can be carried out efficiently.

[0165] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The server receives requests from users. Users access the system and send requests to generate problems related to the operation and maintenance of machines used in the factory. The input is the user's request, and the output is the analysis result of the request.

[0168] Step 2:

[0169] The server uses a problem generation means to generate a problem based on the request content. For example, it generates a prompt such as "Please write a code to program the robot's movements." The input is the analysis result of the request content, and the output is the generated problem.

[0170] Step 3:

[0171] The server uses the answer generation means to generate an answer to the generated question. For example, it generates a specific answer such as "Example: move_forward(10);". The input is the generated question, and the output is the generated answer.

[0172] Step 4:

[0173] The server uses an explanation generation means to generate an explanation for the generated answer. For example, the server generates an explanation such as "This code will move the robot forward 10 meters." The input is the generated answer, and the output is the generated explanation.

[0174] Step 5:

[0175] The server provides the generated questions, answers, and explanations to the user. The user uses this information for self-study. The input is the generated questions, answers, and explanations, and the output is the results provided to the user.

[0176] Step 6:

[0177] The user checks the provided questions, answers, and explanations, and submits a request again if necessary. The input is the result provided to the user, and the output is the user's feedback or new requests.

[0178] In this way, the server generates questions in response to user requests and provides answers and explanations, enabling users to efficiently acquire knowledge about operating and maintaining machines used in factories.

[0179] Example 2

[0180] Next, a second embodiment of the second embodiment will be described. 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."

[0181] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to quickly provide appropriate answers and explanations for specific questions related to office automation in everyday work.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0183] In this invention, the server includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows the user to efficiently self-study and quickly respond to questions related to office automation in everyday work.

[0184] The "question generation means" is a function that generates questions for the user to study.

[0185] The "answer generating means" is a function that provides an accurate answer to a generated question.

[0186] The "explanation generating means" is a function that provides a detailed explanation for an answer.

[0187] A "generative AI model" is a model that uses artificial intelligence to generate questions, answers, and explanations.

[0188] The "means for providing answers and explanations to user questions" is a function for providing appropriate answers and explanations to questions posed to the system by the user.

[0189] "Spreadsheet software" refers to software such as Excel and spreadsheets that are used to organize and tally formulas and data.

[0190] "Office automation" is a general term for technologies and systems that aim to make clerical work more efficient.

[0191] The OA training system of the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows users to efficiently self-study and quickly respond to questions related to office automation in their daily work.

[0192] Hardware and Software Used

[0193] Hardware: Servers, user devices (PCs, tablets, smartphones, etc.)

[0194] Software: Spreadsheet software (Excel, Google® Spreadsheets), generative AI models (e.g. GPT-3®)

[0195] Specific operation of the system

[0196] 1. Problem generation

[0197] The server generates problems for the user to study. Specifically, it generates problems related to formulas in spreadsheet software, simple automation, etc.

[0198] Example: The server uses a generative AI model to generate a question by entering the prompt "Please generate a question about how to use the VLOOKUP function in Excel."

[0199] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0200] 2. Answer generation

[0201] The server provides the answers to the generated questions, allowing the user to obtain the correct answer to the question.

[0202] Example: The server inputs a prompt to the generative AI model: "Generate an answer to the following question: Explain how to use the VLOOKUP function in Excel to search for a specific value," and generates an answer.

[0203] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[0204] 3. Description Generation

[0205] The server provides detailed explanations for the answers, allowing users to understand the context of the answer and how to use it.

[0206] Example: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model and generates an explanation.

[0207] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[0208] 4. Support for user self-learning

[0209] Users can study on their own without having to create their own questions or look up answers and explanations. The app also has a function to answer questions related to office automation that users may encounter in their daily work.

[0210] Example: A user asks "How do I use the IF function in Excel?" and the server provides the answer and explanation to the question.

[0211] Examples of prompt statements

[0212] Question generation prompt: "Generate a question on how to use the VLOOKUP function in Excel."

[0213] Solution Generation Prompt: "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to find a specific value."

[0214] Explanation generation prompt: "Generate an explanation for the following answer: =VLOOKUP(lookup value, range, column number, FALSE)"

[0215] In this way, the OA training system assists users in self-study and also answers office automation-related questions in their work.

[0216] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0217] Step 1:

[0218] Problem generation

[0219] The server generates questions for the user to study.

[0220] Input: The server inputs the prompt "Generate a question about how to use the VLOOKUP function in Excel" to the generative AI model.

[0221] Data processing: The generative AI model generates questions based on the prompt text.

[0222] Output: The generated questions are returned to the server.

[0223] Specific behavior: The server stores the generated questions in a database and prepares them to be served to the user.

[0224] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0225] Step 2:

[0226] Answer generation

[0227] The server provides the answers to the generated questions.

[0228] Input: The server inputs the prompt text "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to search for a specific value" to the generative AI model.

[0229] Data processing: The generative AI model generates an answer based on the prompt.

[0230] Output: The generated answer is returned to the server.

[0231] Specific Actions: The server stores the generated answer in a database and prepares it to be served to the user.

[0232] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[0233] Step 3:

[0234] Description Generation

[0235] The server provides detailed explanations for the answers.

[0236] Input: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model.

[0237] Data processing: The generative AI model generates an explanation based on the prompt.

[0238] Output: The generated description is returned to the server.

[0239] Specific Actions: The server stores the generated description in a database and prepares it to be served to the user.

[0240] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[0241] Step 4:

[0242] Supporting users' self-learning

[0243] When self-studying, users can save time by creating their own questions and searching for answers and explanations.

[0244] Input: A user uses a terminal to access the system and ask how to use a particular function or resolve an error.

[0245] Data processing: The server receives the user's question and inputs the prompt text into the generative AI model to generate an answer and explanation.

[0246] Output: The generated answer and explanation are provided to the user.

[0247] Specific operation: When a user asks a question such as "How do I use the IF function in Excel?", the server generates an answer and explanation for the question and provides it to the user.

[0248] (Application example 2)

[0249] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0250] Conventional OA training systems had the problem that users had to create questions and look up answers and explanations when self-studying. In addition, there was a lack of efficient training systems for learning data management and automation tasks in factories. This resulted in problems of reduced work efficiency and increased labor.

[0251] 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.

[0252] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn, and also enables the effective learning of data management and automation tasks in the factory.

[0253] The "problem generation means" is a means for generating problems related to formulas in spreadsheet software or simple automation.

[0254] An "answer generating means" is a means for providing an answer to a generated question.

[0255] The "explanation generating means" is a means for providing a detailed explanation for a generated answer.

[0256] "Data management means" refers to a means for efficiently managing data within a factory.

[0257] An "automation task learning means" is a means for learning an automation task in a factory.

[0258] In order to implement the present invention, the server, the terminal, and the user must cooperate to operate the system. A specific embodiment is described below.

[0259] System Programming

[0260] The server executes a program including a problem generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn and effectively learn data management and automation tasks in a factory.

[0261] Program processing explanation

[0262] The server uses the OpenAI (registered trademark) API to generate questions, answers, and explanations for Excel and spreadsheets. Specifically, it performs the following processes.

[0263] Hardware: Computers installed in factory robots

[0264] Software: OpenAI API, Python

[0265] First, the server uses the problem generation means to generate problems related to formulas in spreadsheet software or simple automation, such as a data search problem using the VLOOKUP function in Excel.

[0266] Next, the answer generation means is used to provide an answer to the generated question. For example, a specific method using the VLOOKUP function will be shown.

[0267] In addition, an explanation generator is used to provide detailed explanations for the generated answers, for example explaining how to use the VLOOKUP function and what it means.

[0268] The data management means is a means for efficiently managing data within a factory, and makes it easy for users to organize data.

[0269] The automation task learning means is a means for learning automation tasks in a factory, and enables a user to efficiently learn the automation tasks.

[0270] Examples of concrete examples and prompts

[0271] Examples:

[0272] Question: "How can I use the VLOOKUP function in Excel to find data in column A based on data in column B?"

[0273] Solution: "To use the VLOOKUP function, do this: =VLOOKUP(A2, B:C, 2, FALSE)"

[0274] Explanation: "This function searches for the value in cell A2 in column B and returns the corresponding value in column C. FALSE means an exact match."

[0275] Example prompt:

[0276] Problem Generation Prompt: "Please generate a problem involving data lookup using the Excel VLOOKUP function."

[0277] Answer Generation Prompt: "Generate an answer to the following question: Explain how to use Excel's VLOOKUP function to look up data in column A based on data in column B."

[0278] Explanation Generation Prompt: "Generate an explanation for the following solution: =VLOOKUP(A2, B:C, 2, FALSE)"

[0279] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0280] Step 1:

[0281] The server receives a request from a user and starts the problem generation means. The user sends a request to generate a problem related to formulas and automation in a spreadsheet software. The server receives this request and sends a prompt to the generative AI model. The input is the user's request, and the output is the generated problem. Specifically, the server sends a prompt to the generative AI model saying, "Please generate a data search problem using Excel's VLOOKUP function."

[0282] Step 2:

[0283] The server passes the problem received from the generative AI model to the answer generation means. The answer generation means again sends a prompt sentence to the generative AI model to generate an answer to the generated problem. The input is the generated problem, and the output is the generated answer. In concrete terms, the server sends a prompt sentence to the generative AI model saying, "Please generate an answer to the following problem: Explain how to use Excel's VLOOKUP function to search for data in column A based on data in column B."

[0284] Step 3:

[0285] The server passes the answer received from the generative AI model to the explanation generation means. The explanation generation means again sends a prompt sentence to the generative AI model to generate a detailed explanation for the generated answer. The input is the generated answer, and the output is the generated explanation. In concrete terms, the server sends a prompt sentence "Please generate an explanation for the following answer: =VLOOKUP(A2, B:C, 2, FALSE)" to the generative AI model.

[0286] Step 4:

[0287] The server returns the generated questions, answers, and explanations to the user. The user receives this information and uses it for self-study or work. The input is the generated questions, answers, and explanations, and the output is the provision of information to the user. In concrete terms, the server sends the generated questions, answers, and explanations together to the user's terminal.

[0288] Step 5:

[0289] The server waits to respond to additional questions or requests from the user. When the user sends a new question or request, the server again starts the problem generation means, answer generation means, and explanation generation means, and repeats the same process. The input is a new request from the user, and the output is the newly generated problem, answer, and explanation. In concrete terms, the server receives a request from the user and again sends a prompt sentence to the generative AI model.

[0290] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0291] "Example 1"

[0292] As one embodiment of the present invention, an OA training system incorporating an emotion engine is provided. This system includes a question generation means, an answer generation means, an explanation generation means, and an emotion engine. The emotion engine recognizes the user's emotions and adjusts the difficulty of the questions and the level of detail of the explanations based on the emotions. Specifically, if it is recognized that the user is feeling stressed, it lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if it is recognized that the user is bored, it increases the difficulty of the questions or makes the explanations more concise. This can improve the user's learning efficiency and satisfaction.

[0293] "Example 2"

[0294] As one embodiment of the present invention, an OA training system incorporating an emotion engine is provided. This system includes a question generation means, an answer generation means, an explanation generation means, and an emotion engine. The emotion engine recognizes the user's emotions and adjusts the difficulty of the questions and the level of detail of the explanations based on the emotions. Specifically, if it is recognized that the user is feeling stressed, it lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if it is recognized that the user is bored, it increases the difficulty of the questions or makes the explanations more concise. This can improve the user's learning efficiency and satisfaction.

[0295] The process flow of each embodiment will be described below.

[0296] "Example 1"

[0297] Step 1: A user logs into the system. At this point, the emotion engine initializes the user's emotional state.

[0298] Step 2: The system generates problems and presents them to the user. The difficulty of the problems is adjusted based on the user's emotional state by the emotion engine.

[0299] Step 3: The user works through the problem and enters their answer.

[0300] Step 4: The system evaluates the user's answer and determines whether it is correct or incorrect.

[0301] Step 5: The system generates a commentary and presents it to the user. The detail of the commentary is adjusted by the emotion engine based on the user's emotional state.

[0302] Step 6: The emotion engine updates the user's emotional state based on the user's answer, the explanations they have read, etc.

[0303] Step 7: Go back to step 2, except that the process ends when the user logs out of the system or if there is no activity for a certain period of time.

[0304] Example 1

[0305] Next, a description will be given of Example 1 of the embodiment 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".

[0306] Conventional office automation (OA) training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, they could not flexibly respond to the user's emotions and learning situation, which could lead to a decrease in learning efficiency and satisfaction.

[0307] 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.

[0308] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, a question difficulty adjusting means, and an explanation detail adjusting means, which allows the user to efficiently proceed with self-study and further enables flexible response according to the user's emotion and learning situation.

[0309] The "question generation means" is a function that automatically generates questions for the user to study.

[0310] The "answer generating means" is a function that provides a correct answer to a generated question.

[0311] The "explanation generating means" is a function that provides a detailed explanation for the generated answer.

[0312] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[0313] The "problem difficulty adjustment means" is a function for adjusting the difficulty of questions according to the user's emotions and learning situation.

[0314] The "means for adjusting the level of detail of explanation" is a function for adjusting the level of detail of the explanation according to the user's emotions and learning situation.

[0315] "Spreadsheet software" is software for organizing and tallying formulas and data.

[0316] "Office automation" is a general term for technologies and systems that improve the efficiency of office work.

[0317] The present invention relates to an office automation (OA) training system, which is a system including a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, a question difficulty adjusting means, and an explanation detail level adjusting means.

[0318] System Configuration

[0319] Hardware and Software

[0320] The server stores and executes programs for executing the problem generation means, answer generation means, explanation generation means, emotion recognition means, problem difficulty adjustment means, and explanation detail adjustment means. These means are realized using a generative AI model. Specific software used is spreadsheet software (e.g., Excel, Spreadsheet).

[0321] The terminal provides an interface for the user to access the system and answer questions, sends the user's input to the server, and displays the responses from the server.

[0322] Program Processing

[0323] Problem generation means

[0324] Based on the topic selected by the user, the server generates questions related to spreadsheet formulas and simple automation, such as "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0325] Answer generation means

[0326] The server provides the correct answer to the generated problem. For example, for a VLOOKUP function problem, the server generates the answer "=VLOOKUP(search value, range, column number, search method)".

[0327] Explanation generation method

[0328] The server provides detailed explanations for the answers. For example, for the answer of the VLOOKUP function, it generates the explanation "The VLOOKUP function searches for a specific value within a specified range and returns the value of another column that corresponds to that value. The usage is as follows: =VLOOKUP(search value, range, column number, search method)".

[0329] emotion recognition means

[0330] The server uses an emotion engine to recognize the user's emotions. For example, if the server recognizes that the user is stressed, it will lower the difficulty of the next question or make the explanation more detailed. Conversely, if the server recognizes that the user is bored, it will increase the difficulty of the question or make the explanation more concise.

[0331] Problem difficulty adjustment method

[0332] The server adjusts the difficulty of the next problem according to the user's emotions and learning situation. For example, if the user is feeling stressed, it provides an easy problem using basic functions.

[0333] Explanation detail adjustment method

[0334] The server adjusts the level of detail of the explanation according to the user's emotions and learning situation. For example, if the user is feeling stressed, it provides a detailed step-by-step explanation.

[0335] Examples

[0336] Let's say a user wants to learn "Excel's IF function." The specific steps are as follows:

[0337] 1. A user logs into the system.

[0338] 2. The user selects "Excel IF function."

[0339] 3. The server generates the question, "Explain how to use Excel's IF function to display 'Pass' if the value of cell A1 is 50 or greater, and 'Fail' otherwise."

[0340] 4. Present the server-generated problem to the user.

[0341] 5. The user enters the answer "=IF(A1>=50, 'Pass', 'Fail')".

[0342] 6. The server evaluates the user's answer and determines it to be correct.

[0343] 7. The server generates the next problem and presents it to the user.

[0344] 8. The server recognizes the user's emotions and adjusts the difficulty of the next question.

[0345] 9. The user addresses the next problem.

[0346] Examples of prompt statements

[0347] Please explain how to use the IF function in Excel to display 'Pass' if the value of cell A1 is 50 or greater, and 'Fail' otherwise.

[0348] In this way, the user can efficiently progress with his / her studies.

[0349] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0350] Step 1:

[0351] A user logs into the system.

[0352] A user accesses the system using a terminal and enters a user ID and password on the login screen. The server receives the entered information and authenticates it by checking it against a database. If authentication is successful, the user can log in to the system.

[0353] Input: User ID, Password

[0354] Output: Authentication result (success / failure)

[0355] Step 2:

[0356] The user selects the topic they want to learn about.

[0357] The user selects the topic they want to learn from a list of topics displayed on the terminal screen. The server receives the selected topic information and proceeds to the next step.

[0358] Input: Topic selection information

[0359] Output: Selected topic information

[0360] Step 3:

[0361] The server generates questions based on the selected topic.

[0362] The server uses a generative AI model to generate questions based on the selected topic information, such as "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0363] Input: Selected topic information

[0364] Output: Generated problem

[0365] Step 4:

[0366] Present the server-generated questions to the user.

[0367] The server sends the generated questions to the terminal and displays them on the user's screen. The user checks the questions.

[0368] Input: Generated problem

[0369] Output: The problem as seen by the user

[0370] Step 5:

[0371] The user answers the question.

[0372] The user uses the terminal to input the answer to the problem, for example, "=VLOOKUP(search value, range, column number, search method)". The terminal sends the input answer to the server.

[0373] Input: User's answer

[0374] Output: Answer sent to the server

[0375] Step 6:

[0376] The server evaluates the user's answers and determines whether they are correct or incorrect.

[0377] The server evaluates the answers it receives to determine whether they are correct or incorrect, for example by checking whether they have correct syntax and meet specified conditions.

[0378] Input: User's answer

[0379] Output: Evaluation result (correct / incorrect)

[0380] Step 7:

[0381] If the answer is correct, the server presents the next question, and if the answer is incorrect, it provides the answer and an explanation.

[0382] If the user's answer is correct, the server generates the next question and presents it to the user. If the answer is incorrect, the server generates the correct answer and its explanation and provides it to the user. For example, the server may provide an explanation such as, "The VLOOKUP function searches for a specific value within a specified range and returns the value of another column that corresponds to that value."

[0383] Input: Evaluation result

[0384] Output: Next question or answer and explanation

[0385] Step 8:

[0386] The server recognizes the user's emotions and adjusts the difficulty of the next question and the level of detail of the explanation.

[0387] The server uses an emotion engine to recognize the user's emotions. For example, if the server recognizes that the user is stressed, it will lower the difficulty of the next question or make the explanation more detailed. Conversely, if the server recognizes that the user is bored, it will increase the difficulty of the question or make the explanation more concise.

[0388] Input: User emotion data

[0389] Output: Adjusted difficulty of questions and level of explanation

[0390] Step 9:

[0391] The user is faced with the following problem:

[0392] The user uses the device to solve the next problem, and the server repeats the process to help the user learn.

[0393] Input: Adjusted problem

[0394] Output: User's answer

[0395] (Application example 1)

[0396] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0397] Conventional OA training systems do not adjust the difficulty of questions or the level of detail of explanations according to the user's emotions, which can lead to low learning efficiency and satisfaction. In addition, there was a problem with the difficulty of generating appropriate questions and providing answers in training on data management and automation processes within factories. This could delay the improvement of workers' skills.

[0398] 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.

[0399] In this invention, the server includes a question generation means, an answer generation means, an explanation generation means, an emotion recognition means, and a means for adjusting the difficulty of the questions and the level of detail of the explanations based on the emotion. This makes it possible to provide appropriate questions and explanations according to the emotion of the user, thereby improving learning efficiency and satisfaction. In addition, appropriate questions can be generated and answers can be provided in data management and automation process training within a factory, which can promote the improvement of worker skills.

[0400] The "question generation means" is a function that automatically generates questions for the user to study.

[0401] The "answer generating means" is a function that provides an accurate answer to a generated question.

[0402] The "explanation generating means" is a function that provides detailed explanations for answers, making it easier for users to understand.

[0403] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[0404] "Means for adjusting the difficulty of questions and the level of detail of explanations based on emotions" refers to a function for raising or lowering the difficulty of questions and adjusting the level of detail of explanations according to the user's emotions.

[0405] "Spreadsheet software" refers to software for organizing and calculating data, and includes Excel and Spreadsheet.

[0406] "Office automation-related questions" are questions about automation and efficiency related to office work.

[0407] The system for carrying out the present invention includes a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, and a means for adjusting the difficulty of the question and the level of detail of the explanation based on the emotion. Specific embodiments will be described below.

[0408] System Configuration

[0409] Hardware

[0410] Server: Responsible for data processing and storage.

[0411] Terminal: A device that is directly operated by a user, such as a factory robot, PC, or smartphone.

[0412] Emotion Recognition Device: A device, such as a camera or microphone, that is used to recognize a user's emotions.

[0413] software

[0414] Python: A programming language used to implement the program.

[0415] OpenAI API: An API used for emotion recognition and natural language processing.

[0416] Data processing and calculation

[0417] Problem generation

[0418] The server generates questions related to spreadsheet formulas and simple automation, such as how to use the VLOOKUP function for inventory management or how to create a macro to automate product production schedules.

[0419] Answer generation

[0420] The server provides precise solutions to the generated questions, including specific instructions for using the VLOOKUP function and IF functions.

[0421] Description Generation

[0422] The server provides detailed explanations for the solutions, including explanations of each argument in the VLOOKUP function and details on the condition settings in the IF function.

[0423] emotion recognition

[0424] The emotion recognition device analyzes the user's facial expressions and tone of voice to recognize their emotions, and can determine whether they are stressed or bored.

[0425] Emotion-Based Adjustments

[0426] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of emotion recognition. For example, if the user is stressed, the server lowers the difficulty of the questions and provides more detailed explanations. Conversely, if the user is bored, the server raises the difficulty of the questions and provides more concise explanations.

[0427] Examples

[0428] Example problem

[0429] "Please explain how to use the VLOOKUP function to get the price of a specific product from an inventory table."

[0430] Example answer

[0431] Use the VLOOKUP function to search for a specific value in a range you specify and return the corresponding value.

[0432] Example of commentary

[0433] "The VLOOKUP function takes four arguments: the lookup value, the range, the column number, and the lookup method."

[0434] Examples of prompt statements

[0435] "Enter the user's emotion (e.g. stress, boredom, neutral): stress"

[0436] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. In addition, it is possible to generate appropriate questions and provide answers for training on data management and automation processes in factories, promoting the improvement of worker skills.

[0437] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0438] Step 1:

[0439] A user logs into the system using a terminal. The user's authentication information is entered and verified by the server. If authentication is successful, the server sends the user's learning history and current progress to the terminal.

[0440] Step 2:

[0441] The user inputs a command to start learning. The terminal sends this command to the server. The server prepares data for generating appropriate questions based on the user's learning history and progress.

[0442] Step 3:

[0443] The server uses the problem generation means to generate problems related to spreadsheet software formulas and simple automation, such as how to use the VLOOKUP function for inventory management and how to create a macro to automate product production schedules. The generated problems are sent to the terminal.

[0444] Step 4:

[0445] The terminal displays the generated questions to the user. The user answers the questions and inputs the answers into the terminal. The terminal transmits the input answers to the server.

[0446] Step 5:

[0447] The server uses the answer generation means to evaluate the user's answer and generate an accurate answer, which is then transmitted to the terminal.

[0448] Step 6:

[0449] The device displays the generated answer to the user, who can then review the answer and retry if necessary.

[0450] Step 7:

[0451] The server uses the explanation generation means to generate a detailed explanation for the answer, including, for example, an explanation of each argument of the VLOOKUP function, details of the condition settings of the IF function, etc. The generated explanation is sent to the terminal.

[0452] Step 8:

[0453] The terminal displays the generated explanation to the user, who can then check the explanation and deepen his or her understanding.

[0454] Step 9:

[0455] The emotion recognition device analyzes the user's facial expressions and tone of voice to recognize emotions, and the recognized emotions are transmitted to the server via the device.

[0456] Step 10:

[0457] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of emotion recognition. For example, if the user is stressed, the difficulty of the questions is lowered and the explanations are made more detailed. Conversely, if the user is bored, the difficulty of the questions is increased and the explanations are made brief. The adjusted questions and explanations are sent to the terminal.

[0458] Step 11:

[0459] The device will then display the adjusted problem and explanation to the user, who can then retry the problem and continue learning.

[0460] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. In addition, it is possible to generate appropriate questions and provide answers for training on data management and automation processes in factories, promoting the improvement of worker skills.

[0461] Example 2

[0462] Next, a second embodiment of the second embodiment will be described. 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."

[0463] Conventional office automation (OA) training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own, which was time-consuming. In addition, the learning content was not adjusted according to the user's emotions, which could lead to a decrease in learning efficiency and satisfaction. Furthermore, the system lacked the functionality to provide appropriate answers and explanations for specific questions asked in everyday work.

[0464] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0465] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, an emotion recognition means, and a difficulty level adjusting means. This allows the user to efficiently proceed with self-study, and the learning content is adjusted according to the user's emotion, improving learning efficiency and satisfaction. In addition, it is possible to provide appropriate answers and explanations for specific questions in everyday work.

[0466] The "question generation means" is a function that automatically generates questions for the user to study.

[0467] The "answer generating means" is a function that automatically generates a correct answer to a generated question.

[0468] The "explanation generating means" is a function that automatically generates a detailed explanation for the generated answer.

[0469] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[0470] The "difficulty level adjustment means" is a function that adjusts the difficulty level of the questions and the level of detail of the explanations according to the user's emotions and learning situation.

[0471] "Spreadsheet software" is software for entering numerical data, performing calculations, analysis, creating graphs, etc.

[0472] "Office automation" is a general term for technologies and systems that make office work more efficient.

[0473] The present invention relates to an office automation (OA) training system that allows users to efficiently advance self-study. The system includes a question generating means, an answer generating means, an explanation generating means, an emotion recognition means, and a difficulty level adjusting means.

[0474] System Configuration

[0475] Hardware and Software

[0476] The server is equipped with hardware and software for executing the problem generation means, the answer generation means, the explanation generation means, the emotion recognition means, and the difficulty level adjustment means. Specifically, the server generates problems, answers, and explanations using a generative AI model. In addition, as the emotion recognition means, it uses emotion analysis software to recognize the user's emotions.

[0477] The terminal is a device that allows users to access the system and display questions, answers, and explanations. The terminal can be any common device such as a PC, tablet, or smartphone.

[0478] System Operation

[0479] Problem generation means

[0480] The server generates questions based on what the user wants to learn. For example, if a user says they want to learn about Excel's VLOOKUP function, the server uses the generative AI model to generate a question like, "Explain how to use Excel's VLOOKUP function to find the corresponding value in column B based on the data in column A."

[0481] Answer generation means

[0482] The server generates an answer to the generated problem. For example, the answer to the above problem is "=VLOOKUP(A2, B:C, 2, FALSE)".

[0483] Explanation generation method

[0484] The server generates a detailed explanation for the generated answer, for example, "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches the value in cell A2 in columns B to C and returns the corresponding value in column C."

[0485] emotion recognition means

[0486] The server uses emotion recognition means to recognize the emotion of the user, for example to determine whether the user is stressed or bored.

[0487] Difficulty adjustment means

[0488] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of the emotion recognition means. For example, if the user is stressed, the server lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if the user is bored, the server raises the difficulty of the questions or makes the explanations more concise.

[0489] Examples

[0490] Users choose what to study

[0491] The user types "I want to learn how to use the VLOOKUP function" into the input field on the device.

[0492] Server Generates Problems

[0493] The server uses a generative AI model to generate a question such as, "Explain how to use Excel's VLOOKUP function to find the corresponding value in column B based on the data in column A."

[0494] The server generates the answer

[0495] The server generates the answer to the problem: "=VLOOKUP(A2, B:C, 2, FALSE)".

[0496] The server generates the description

[0497] In response to the answer, the server generates an explanation: "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches for the value in cell A2 in the range from columns B to C, and returns the corresponding value in column C."

[0498] The server recognizes the user's emotion using an emotion recognition means.

[0499] The server uses the emotion recognition means to recognize that the user is feeling stressed.

[0500] The server adjusts the difficulty of the questions and the level of detail of the explanations.

[0501] The server lowers the difficulty of the question and changes it to a simpler question: "How can I use Excel's VLOOKUP function to find data in column A from column B?"

[0502] Examples of prompt statements

[0503] "Please tell me how to use the VLOOKUP function in Excel. Please also give me some concrete examples and explanations."

[0504] In this way, the user can efficiently advance self-study.

[0505] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0506] Step 1:

[0507] Users choose what to study

[0508] The user inputs the content they want to learn into the input field of the terminal. For example, they input "I want to learn how to use the VLOOKUP function." The input content is sent to the server. The input data is text data "I want to learn how to use the VLOOKUP function." The server receives this input data and proceeds to the next processing step.

[0509] Step 2:

[0510] Server Generates Problems

[0511] The server generates questions using a generative AI model based on input data received from the user. For example, it generates a question such as "Explain how to use Excel's VLOOKUP function to search for the corresponding value in column B based on the data in column A." The input data is the text data "I want to learn how to use the VLOOKUP function," and the output data is the text data of the generated question.

[0512] Step 3:

[0513] The server generates the answer

[0514] The server generates an answer to the generated problem. For example, the server generates an answer to the problem, such as "=VLOOKUP(A2, B:C, 2, FALSE)". The input data is the text data of the generated problem, and the output data is the text data of the generated answer.

[0515] Step 4:

[0516] The server generates the description

[0517] The server generates a detailed explanation for the generated answer. For example, it generates an explanation like "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches for the value in cell A2 in the range from column B to column C, and returns the corresponding value in column C." The input data is the text data of the generated answer, and the output data is the text data of the generated explanation.

[0518] Step 5:

[0519] The server recognizes the user's emotion using an emotion recognition means.

[0520] The server recognizes the user's emotions using emotion recognition means, for example, determining whether the user is stressed or bored. The input data is emotion-related data such as the user's facial expression and input speed, and the output data is data indicating the user's emotional state.

[0521] Step 6:

[0522] The server adjusts the difficulty of the questions and the level of detail of the explanations.

[0523] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of the emotion recognition means. For example, if the user is stressed, the difficulty of the questions is lowered or the explanations are made more detailed. Conversely, if the user is bored, the difficulty of the questions is increased or the explanations are made more concise. The input data is data indicating the user's emotional state, and the output data is text data of the adjusted questions and explanations.

[0524] Step 7:

[0525] The device displays the questions, answers, and explanations to the user.

[0526] The terminal displays the questions, answers, and explanations received from the server to the user, who can then proceed with his or her studies. The input data is the adjusted text data of the questions, answers, and explanations, and the output data is the information displayed on the terminal.

[0527] (Application example 2)

[0528] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0529] Conventional OA training systems did not adjust the difficulty of questions or the level of detail of explanations according to the user's emotions, which led to problems with low learning efficiency and satisfaction. In addition, there was a lack of means to provide appropriate OA training to employees working in factories. This could lead to delayed improvement of employees' skills and reduced productivity.

[0530] 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.

[0531] In this invention, the server includes a question generation means, an answer generation means, an explanation generation means, an emotion recognition means, a question difficulty adjustment means, and an explanation detail adjustment means. This makes it possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. It also makes it possible to provide effective OA training to employees working in factories.

[0532] A "problem generation means" is a means for generating problems for a user, such as problems related to spreadsheet software formulas or simple automation.

[0533] An "answer generating means" is a means for providing an answer to a generated question.

[0534] The "explanation generating means" is a means for generating a detailed explanation for a provided answer.

[0535] An "emotion recognition means" is a means for recognizing a user's emotions, and determines emotions from the user's facial expressions and voice using a camera and emotion recognition software.

[0536] The "means for adjusting the difficulty of questions" refers to a means for adjusting the difficulty of questions based on the recognized user's emotions.

[0537] The "means for adjusting the level of detail of explanation" is a means for adjusting the level of detail of the explanation to be provided based on the recognized user's feelings.

[0538] A system for implementing this invention includes a robot for teaching factory workers how to use Excel and spreadsheets. The robot recognizes the emotions of the workers, asks them questions of appropriate difficulty, and provides answers and explanations.

[0539] Hardware and Software Used

[0540] Hardware: Factory robots, cameras (for emotion recognition)

[0541] Software: EmotionRecognizer (emotion recognition library), Python

[0542] System processing explanation

[0543] emotion recognition

[0544] The robot uses a camera to capture a picture of the employee's face and recognizes emotions using the EmotionRecognizer library, which determines emotions from the user's facial expressions and voice to identify states such as stress or boredom.

[0545] Problem generation

[0546] Based on the emotion data obtained by the emotion recognition means, the problem difficulty adjustment means selects problems of appropriate difficulty. For example, if an employee is stressed, it generates easy problems, and if an employee is bored, it generates difficult problems.

[0547] Providing answers and explanations

[0548] The answer generating means provides an answer to the question generated by the question generating means. Furthermore, the explanation generating means generates a detailed explanation and provides it to the employee. The explanation detail adjusting means adjusts the detail of the explanation based on the emotion data.

[0549] Examples

[0550] If your employees are stressed:

[0551] The robot asks a simple question: "Please explain how to use the VLOOKUP function," and then provides a detailed explanation.

[0552] If your employees are bored:

[0553] The robot asks a difficult question: "Please explain how to use the IF function," and provides a concise explanation.

[0554] Examples of prompt statements

[0555] "If employees are feeling stressed, give them some easy questions and provide detailed explanations."

[0556] "If employees are bored, give them challenging questions and provide concise commentary."

[0557] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. It is also possible to provide effective OA training to employees working in factories.

[0558] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0559] Step 1:

[0560] The server uses a camera to take a picture of the user's face and recognizes emotions using the EmotionRecognizer library. The input is the user's face image, and the output is the user's emotion data (e.g., stress, boredom, etc.). In concrete terms, the camera captures the user's face and sends the image data to EmotionRecognizer to analyze the emotions.

[0561] Step 2:

[0562] The server selects a problem of appropriate difficulty using the problem difficulty adjustment means based on the emotion data obtained by the emotion recognition means. The input is the emotion data, and the output is the selected problem. In concrete terms, if the emotion data is recognized as "stress," the server selects an easy problem, and if it is recognized as "boredom," the server selects a difficult problem.

[0563] Step 3:

[0564] The server generates the selected problem using the problem generation means. The input is the selected problem type (e.g., how to use the VLOOKUP function), and the output is a specific problem statement. As a specific operation, the server retrieves the corresponding problem from the problem database and presents it to the user.

[0565] Step 4:

[0566] The server provides answers to questions generated using the answer generation means. The input is the generated question text, and the output is the answer to the question. In concrete terms, the server retrieves the corresponding answer from the question database and presents it to the user.

[0567] Step 5:

[0568] The server uses an explanation generating means to generate a detailed explanation for the provided answer. The input is the answer to the problem, and the output is an explanation for the answer. In specific operations, the server retrieves the corresponding explanation from the explanation database and presents it to the user.

[0569] Step 6:

[0570] The server adjusts the level of detail of the commentary based on the emotion data using the explanation detail adjustment means. The input is the emotion data and the answer explanation, and the output is the adjusted explanation. In specific operations, if the emotion data is recognized as "stress", the server provides a detailed explanation, and if the emotion data is recognized as "boredom", the server provides a concise explanation.

[0571] Step 7:

[0572] The server provides the user with the tailored explanation to support the user's learning. The input is the tailored explanation, and the output is the user's improved understanding. In concrete terms, the server displays the tailored explanation on the user's screen, encouraging the user to read and understand the explanation.

[0573] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0574] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0575] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0576] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0577] [Second embodiment]

[0578] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0579] 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.

[0580] 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 wide area network (WAN) and / or a local area network (LAN).

[0581] 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.

[0582] 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 the voice according to instructions from the processor 46.

[0583] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0584] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0585] Fig. 4 shows an example of 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0590] "Example 1"

[0591] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[0592] "Example 2"

[0593] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[0594] The process flow of each embodiment will be described below.

[0595] "Example 1"

[0596] Step 1: The user logs into the system and selects the topic they want to learn, which can range from Excel and spreadsheet formulas to simple automation.

[0597] Step 2: Based on the selected topic, the system's problem generator will generate a problem, for example, a problem about how to use the VLOOKUP function in Excel.

[0598] Step 3: The generated question is presented to the user, who enters an answer.

[0599] Step 4: After the user submits the answer, the system's answer generation means provides the correct answer. Step 5: The system's explanation generation means provides an explanation for the answer. This allows users to save time and effort in creating questions and searching for answers and explanations when self-studying.

[0600] Step 6: When users input OA-related questions from their daily work into the system, the system will provide answers and explanations for those questions, such as how to use a specific function in Excel or how to resolve an error.

[0601] Example 1

[0602] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0603] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to respond quickly and accurately to specific questions related to clerical work in daily work.

[0604] 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.

[0605] In this invention, the server includes: a prompt sentence for instructing to generate a question sentence related to the question about how to use the spreadsheet software based on a question about how to use the spreadsheet software input by a user; a means for generating a question sentence related to the question about how to use the spreadsheet software using a generative AI; a prompt sentence for instructing to generate an answer to the generated question sentence; a means for generating an answer to the generated question sentence using the generative AI; a prompt sentence for instructing to generate an explanation for the generated answer; a means for generating an explanation for the generated answer using the generative AI; a means for presenting the generated question sentence to the user; a means for recognizing the user's emotion using an emotion engine; a prompt sentence for instructing to adjust the generated answer or explanation sentence based on the recognized emotion of the user; a means for adjusting the generated answer or explanation sentence using the generative AI; and a means for presenting the adjusted answer or explanation sentence to the user. This allows the user to efficiently self-study. The questions about how to use the spreadsheet software include questions about formulas used in the spreadsheet software or questions about automation. The questions about how to use the spreadsheet software include questions about how to use the spreadsheet software that are necessary for the user's office work, so that questions related to office work in everyday work can be quickly and accurately responded to.

[0606] The "question generation means" is a means for generating questions such as those related to formulas in a spreadsheet or simple automation based on a prompt sentence from a user.

[0607] The "answer generating means" is a means for generating an optimal answer to a generated question.

[0608] The "explanation generating means" is a means for generating a detailed explanation for the generated answer.

[0609] The "means for receiving a prompt sentence" refers to a means for receiving a specific question or request from the user in text form.

[0610] "Generative AI" is an artificial intelligence model that uses natural language processing technology to generate questions, answers, and explanations.

[0611] "Means for saving in a database" refers to means for saving the generated questions, answers, and explanations in a database.

[0612] "Spreadsheet software" is software for organizing, calculating, and analyzing data, and can process data using formulas and functions.

[0613] "Questions related to office work" are specific questions about how to use spreadsheet software and how to resolve errors that arise in daily work.

[0614] This invention is a system that allows users to efficiently self-learn and quickly and accurately respond to questions related to clerical work in their daily work. This system operates in cooperation with a server, a terminal, and a user.

[0615] Server Roles

[0616] The server manages and operates the entire system using the following means:

[0617] 1. Problem generation means

[0618] The server receives a question input by a user about how to use spreadsheet software. For example, the server receives a question sentence such as "Please tell me how to use the VLOOKUP function in Excel." The server generates a question sentence related to the question about how to use the spreadsheet software using a prompt sentence instructing the server to generate a question sentence related to the question and a generative AI (e.g., GPT-4 (registered trademark)). The generated question sentence is in the form of "Explain how to use the VLOOKUP function in Excel to get data from another sheet." The generated question sentence is stored in a database.

[0619] 2. Answer generation means

[0620] The server generates an answer to the generated question. It uses a prompt that instructs the server to generate an answer to the generated question and a generative AI to generate the optimal answer to the question. For example, an answer in the format "=VLOOKUP(search value, range, column number, search method)" is generated. The generated answer is stored in the database.

[0621] 3. Explanation Generation Method

[0622] The server generates a detailed explanation for the generated answer. A prompt that instructs the server to generate an explanation for the generated answer and a generative AI are used to generate a detailed explanation for the answer. For example, an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)" are generated. The generated explanation is saved in the database.

[0623] User Roles

[0624] A user accesses the system using a terminal and performs the following operations:

[0625] 1. Enter your question

[0626] A user uses the terminal to type in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[0627] 2. Obtaining questions

[0628] The user obtains the generated question text from the server and checks the question text on the terminal screen.

[0629] 3. Get answers

[0630] The user obtains the generated answer from the server and checks the answer on the screen of the terminal.

[0631] 4. Obtaining explanations

[0632] The user receives the generated commentary from the server and checks the commentary on the screen of the terminal.

[0633] Examples

[0634] For example, if a user enters the question "How do I use the VLOOKUP function in Excel?", the server processes the question as follows:

[0635] 1. Problem generation

[0636] The server generates a question such as, "Explain how to use Excel's VLOOKUP function to retrieve data from another sheet."

[0637] 2. Answer generation

[0638] The server generates the answer "=VLOOKUP(search value, range, column number, search method)".

[0639] 3. Description Generation

[0640] The server generates an explanatory text stating, "The VLOOKUP function searches for a search value within a specified range and returns the data from the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)."

[0641] In this way, the user can efficiently proceed with self-learning and can quickly and accurately respond to questions related to clerical work in the course of daily work.

[0642] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0643] Step 1: Enter your question

[0644] Subject: User

[0645] A user accesses the system using a terminal and types in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[0646] Input: The question entered by the user

[0647] Output: The question is sent to the server.

[0648] Step 2: Receiving the question

[0649] Subject: Server

[0650] The server receives a question sent by a user.

[0651] Input: The question submitted by the user

[0652] Output: The question is ready to be processed in the server.

[0653] Step 3: Generate the problem

[0654] Subject: Server

[0655] The server uses the prompt text and generative AI to generate a question based on the question. For example, it generates a question like, "Explain how to use the VLOOKUP function in Excel to get data from another sheet."

[0656] Input:Question

[0657] Data processing: Using prompts containing questions and generative AI, appropriate problem statements are generated.

[0658] Output: Generated problem statement

[0659] Step 4: Save the question

[0660] Subject: Server

[0661] The server stores the generated questions in a database.

[0662] Input: Generated question text

[0663] Data processing: Converting the generated questions into a database format

[0664] Output: The question is saved in the database.

[0665] Step 5: Generate the answer

[0666] Subject: Server

[0667] The server generates an answer to the generated question. It uses the prompt and generative AI to generate the optimal answer to the question. For example, it generates the answer "=VLOOKUP(search value, range, column number, search method)".

[0668] Input: Generated question text

[0669] Data processing: A generative AI model analyzes the question and generates an appropriate answer

[0670] Output: The generated answer

[0671] Step 6: Save your answers

[0672] Subject: Server

[0673] The server stores the generated answers in a database.

[0674] Input: Generated answer

[0675] Data processing: Converting the generated answers into a database format

[0676] Output: The answer is saved in the database.

[0677] Step 7: Generate a description

[0678] Subject: Server

[0679] The server generates a detailed explanation for the generated answer. It uses the prompt text and generative AI to generate a detailed explanation for the answer. For example, it generates an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. There are two search methods: TRUE (approximate match) and FALSE (exact match)."

[0680] Input: Generated answer

[0681] Data processing: A generative AI model analyzes the answers and generates appropriate explanations

[0682] Output: Generated description

[0683] Step 8: Save your commentary

[0684] Subject: Server

[0685] The server stores the generated commentary in a database.

[0686] Input: Generated description

[0687] Data processing: Convert the generated explanatory text into a database format.

[0688] Output: The explanatory text is saved in the database.

[0689] Step 9: Get the problem statement

[0690] Subject: User

[0691] The user uses a terminal to obtain the generated question text from the server and checks the question on the terminal screen.

[0692] Input: User request

[0693] Output: The generated question is displayed on the terminal.

[0694] Step 10: Getting the answer

[0695] Subject: User

[0696] The user uses the terminal to retrieve the generated answer from the server and check the answer on the terminal screen.

[0697] Input: User request

[0698] Output: The generated answer is displayed on the terminal.

[0699] Step 11: Get the description

[0700] Subject: User

[0701] The user uses the terminal to obtain the generated commentary from the server, and checks the commentary on the screen of the terminal.

[0702] Input: User request

[0703] Output: The generated commentary is displayed on the terminal. In this embodiment, when presenting a question sentence to a user, the server recognizes the user's emotion using an emotion engine, which will be described later. The server then adjusts the generated answer or commentary using a prompt sentence that instructs the user to adjust the generated answer or commentary based on the recognized user's emotion and the generative AI, and presents the adjusted answer or commentary to the user.

[0704] (Application example 1)

[0705] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0706] Conventional OA training systems were limited to providing questions related to Excel and spreadsheet formulas and simple automation, and did not address training related to the operation and maintenance of machines used in factories. This made it difficult to efficiently acquire knowledge related to the operation and maintenance of machines in factories. In addition, while the system had functions to answer OA-related questions in everyday work, it lacked functions to answer specific questions about the operation and maintenance of machines used in factories.

[0707] 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. In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a means for generating questions related to the operation and maintenance of machines used in a factory, a means for providing answers to the generated questions, and a means for providing explanations of the answers. This makes it possible to efficiently acquire knowledge related to the operation and maintenance of machines used in a factory.

[0708] The "problem generation means" is a means for generating problems related to Excel or spreadsheet formulas, simple automation, and the operation and maintenance of machines used in factories.

[0709] An "answer generating means" is a means for providing an answer to a generated question.

[0710] The "explanation generating means" is a means for providing an explanation for a generated answer.

[0711] "Machinery used in a factory" refers to various types of machinery and equipment used for production and maintenance within a factory.

[0712] "Operation" refers to the specific steps or methods for making a machine work.

[0713] "Maintenance" refers to the inspection and repair procedures to keep a machine in good working order.

[0714] The term "system" refers to a collection of a series of devices and programs including a problem generating means, an answer generating means, an explanation generating means, and a means for generating problems relating to the operation and maintenance of machines used in a factory.

[0715] A system for implementing the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems relating to the operation and maintenance of machines used in a factory, a means for providing answers to the generated problems, and a means for providing explanations for the answers.

[0716] The server implements a problem generation means, an answer generation means, and an explanation generation means using a programming language such as Python. Specifically, the problem generation means generates problems related to formulas in Excel or spreadsheets, simple automation, and the operation and maintenance of machines used in factories. For example, it generates a prompt sentence such as "Please write the code to program the operation of a robot."

[0717] The answer generation means provides an answer to the generated problem. For example, it generates a specific answer such as "Example: move_forward(10);". The explanation generation means provides an explanation for the generated answer. For example, it generates an explanation such as "This code moves the robot forward 10 meters".

[0718] Users can use this system to efficiently acquire knowledge about the operation and maintenance of machines used in factories. When a user accesses the system, the server generates questions and provides answers and explanations. This allows users to save time when self-studying by creating questions themselves and searching for answers and explanations.

[0719] As a concrete example, the following prompt sentence can be input to a generative AI model:

[0720] Example prompt:

[0721] "Write the code to program the robot's movements."

[0722] In response to this prompt, the generative AI model provides the following answer and explanation:

[0723] Example answer:

[0724] "Example: move_forward(10);"

[0725] Example of explanation:

[0726] "This code will move the robot forward 10 meters."

[0727] In this way, training on the operation and maintenance of machines used in the factory can be carried out efficiently.

[0728] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0729] Step 1:

[0730] The server receives requests from users. Users access the system and send requests to generate problems related to the operation and maintenance of machines used in the factory. The input is the user's request, and the output is the analysis result of the request.

[0731] Step 2:

[0732] The server uses a problem generation means to generate a problem based on the request content. For example, it generates a prompt such as "Please write a code to program the robot's movements." The input is the analysis result of the request content, and the output is the generated problem.

[0733] Step 3:

[0734] The server uses the answer generation means to generate an answer to the generated question. For example, it generates a specific answer such as "Example: move_forward(10);". The input is the generated question, and the output is the generated answer.

[0735] Step 4:

[0736] The server uses an explanation generation means to generate an explanation for the generated answer. For example, the server generates an explanation such as "This code will move the robot forward 10 meters." The input is the generated answer, and the output is the generated explanation.

[0737] Step 5:

[0738] The server provides the generated questions, answers, and explanations to the user. The user uses this information for self-study. The input is the generated questions, answers, and explanations, and the output is the results provided to the user.

[0739] Step 6:

[0740] The user checks the provided questions, answers, and explanations, and submits a request again if necessary. The input is the result provided to the user, and the output is the user's feedback or new requests.

[0741] In this way, the server generates questions in response to user requests and provides answers and explanations, enabling users to efficiently acquire knowledge about operating and maintaining machines used in factories.

[0742] Example 2

[0743] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0744] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to quickly provide appropriate answers and explanations for specific questions related to office automation in everyday work.

[0745] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0746] In this invention, the server includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows the user to efficiently self-study and quickly respond to questions related to office automation in everyday work.

[0747] The "question generation means" is a function that generates questions for the user to study.

[0748] The "answer generating means" is a function that provides an accurate answer to a generated question.

[0749] The "explanation generating means" is a function that provides a detailed explanation for an answer.

[0750] A "generative AI model" is a model that uses artificial intelligence to generate questions, answers, and explanations.

[0751] The "means for providing answers and explanations to user questions" is a function for providing appropriate answers and explanations to questions posed to the system by the user.

[0752] "Spreadsheet software" refers to software such as Excel and spreadsheets that are used to organize and tally formulas and data.

[0753] "Office automation" is a general term for technologies and systems that aim to make clerical work more efficient.

[0754] The OA training system of the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows users to efficiently self-study and quickly respond to questions related to office automation in their daily work.

[0755] Hardware and Software Used

[0756] Hardware: Servers, user devices (PCs, tablets, smartphones, etc.)

[0757] Software: Spreadsheet software (Excel, Google Spreadsheet), generative AI model (e.g. GPT-3)

[0758] Specific operation of the system

[0759] 1. Problem generation

[0760] The server generates problems for the user to study. Specifically, it generates problems related to formulas in spreadsheet software, simple automation, etc.

[0761] Example: The server uses a generative AI model to generate a question by entering the prompt "Please generate a question about how to use the VLOOKUP function in Excel."

[0762] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0763] 2. Answer generation

[0764] The server provides the answers to the generated questions, allowing the user to obtain the correct answer to the question.

[0765] Example: The server inputs a prompt to the generative AI model: "Generate an answer to the following question: Explain how to use the VLOOKUP function in Excel to search for a specific value," and generates an answer.

[0766] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[0767] 3. Description Generation

[0768] The server provides detailed explanations for the answers, allowing users to understand the context of the answer and how to use it.

[0769] Example: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model and generates an explanation.

[0770] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[0771] 4. Support for user self-learning

[0772] Users can study on their own without having to create their own questions or look up answers and explanations. The app also has a function to answer questions related to office automation that users may encounter in their daily work.

[0773] Example: A user asks "How do I use the IF function in Excel?" and the server provides the answer and explanation to the question.

[0774] Examples of prompt statements

[0775] Question generation prompt: "Generate a question on how to use the VLOOKUP function in Excel."

[0776] Solution Generation Prompt: "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to find a specific value."

[0777] Explanation generation prompt: "Generate an explanation for the following answer: =VLOOKUP(lookup value, range, column number, FALSE)"

[0778] In this way, the OA training system assists users in self-study and also answers office automation-related questions in their work.

[0779] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0780] Step 1:

[0781] Problem generation

[0782] The server generates questions for the user to study.

[0783] Input: The server inputs the prompt "Generate a question about how to use the VLOOKUP function in Excel" to the generative AI model.

[0784] Data processing: The generative AI model generates questions based on the prompt text.

[0785] Output: The generated questions are returned to the server.

[0786] Specific behavior: The server stores the generated questions in a database and prepares them to be served to the user.

[0787] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0788] Step 2:

[0789] Answer generation

[0790] The server provides the answers to the generated questions.

[0791] Input: The server inputs the prompt text "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to search for a specific value" to the generative AI model.

[0792] Data processing: The generative AI model generates an answer based on the prompt.

[0793] Output: The generated answer is returned to the server.

[0794] Specific Actions: The server stores the generated answer in a database and prepares it to be served to the user.

[0795] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[0796] Step 3:

[0797] Description Generation

[0798] The server provides detailed explanations for the answers.

[0799] Input: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model.

[0800] Data processing: The generative AI model generates an explanation based on the prompt.

[0801] Output: The generated description is returned to the server.

[0802] Specific Actions: The server stores the generated description in a database and prepares it to be served to the user.

[0803] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[0804] Step 4:

[0805] Supporting users' self-learning

[0806] When self-studying, users can save time by creating their own questions and searching for answers and explanations.

[0807] Input: A user uses a terminal to access the system and ask how to use a particular function or resolve an error.

[0808] Data processing: The server receives the user's question and inputs the prompt text into the generative AI model to generate an answer and explanation.

[0809] Output: The generated answer and explanation are provided to the user.

[0810] Specific operation: When a user asks a question such as "How do I use the IF function in Excel?", the server generates an answer and explanation for the question and provides it to the user.

[0811] (Application example 2)

[0812] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[0813] Conventional OA training systems had the problem that users had to create questions and look up answers and explanations when self-studying. In addition, there was a lack of efficient training systems for learning data management and automation tasks in factories. This resulted in problems of reduced work efficiency and increased labor.

[0814] 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.

[0815] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn, and also enables the effective learning of data management and automation tasks in the factory.

[0816] The "problem generation means" is a means for generating problems related to formulas in spreadsheet software or simple automation.

[0817] An "answer generating means" is a means for providing an answer to a generated question.

[0818] The "explanation generating means" is a means for providing a detailed explanation for a generated answer.

[0819] "Data management means" refers to a means for efficiently managing data within a factory.

[0820] An "automation task learning means" is a means for learning an automation task in a factory.

[0821] In order to implement the present invention, the server, the terminal, and the user must cooperate to operate the system. A specific embodiment is described below.

[0822] System Programming

[0823] The server executes a program including a problem generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn and effectively learn data management and automation tasks in a factory.

[0824] Program processing explanation

[0825] The server uses the OpenAI API to generate questions, answers, and explanations for Excel and spreadsheets. Specifically, it performs the following processes:

[0826] Hardware: Computers installed in factory robots

[0827] Software: OpenAI API, Python

[0828] First, the server uses the problem generation means to generate problems related to formulas in spreadsheet software or simple automation, such as a data search problem using the VLOOKUP function in Excel.

[0829] Next, the answer generation means is used to provide an answer to the generated question. For example, a specific method using the VLOOKUP function will be shown.

[0830] In addition, an explanation generator is used to provide detailed explanations for the generated answers, for example explaining how to use the VLOOKUP function and what it means.

[0831] The data management means is a means for efficiently managing data within a factory, and makes it easy for users to organize data.

[0832] The automation task learning means is a means for learning automation tasks in a factory, and enables a user to efficiently learn the automation tasks.

[0833] Examples of concrete examples and prompts

[0834] Examples:

[0835] Question: "How can I use the VLOOKUP function in Excel to find data in column A based on data in column B?"

[0836] Solution: "To use the VLOOKUP function, do this: =VLOOKUP(A2, B:C, 2, FALSE)"

[0837] Explanation: "This function searches for the value in cell A2 in column B and returns the corresponding value in column C. FALSE means an exact match."

[0838] Example prompt:

[0839] Problem Generation Prompt: "Please generate a problem involving data lookup using the Excel VLOOKUP function."

[0840] Answer Generation Prompt: "Generate an answer to the following question: Explain how to use Excel's VLOOKUP function to look up data in column A based on data in column B."

[0841] Explanation Generation Prompt: "Generate an explanation for the following solution: =VLOOKUP(A2, B:C, 2, FALSE)"

[0842] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0843] Step 1:

[0844] The server receives a request from a user and starts the problem generation means. The user sends a request to generate a problem related to formulas and automation in a spreadsheet software. The server receives this request and sends a prompt to the generative AI model. The input is the user's request, and the output is the generated problem. Specifically, the server sends a prompt to the generative AI model saying, "Please generate a data search problem using Excel's VLOOKUP function."

[0845] Step 2:

[0846] The server passes the problem received from the generative AI model to the answer generation means. The answer generation means again sends a prompt sentence to the generative AI model to generate an answer to the generated problem. The input is the generated problem, and the output is the generated answer. In concrete terms, the server sends a prompt sentence to the generative AI model saying, "Please generate an answer to the following problem: Explain how to use Excel's VLOOKUP function to search for data in column A based on data in column B."

[0847] Step 3:

[0848] The server passes the answer received from the generative AI model to the explanation generation means. The explanation generation means again sends a prompt sentence to the generative AI model to generate a detailed explanation for the generated answer. The input is the generated answer, and the output is the generated explanation. In concrete terms, the server sends a prompt sentence "Please generate an explanation for the following answer: =VLOOKUP(A2, B:C, 2, FALSE)" to the generative AI model.

[0849] Step 4:

[0850] The server returns the generated questions, answers, and explanations to the user. The user receives this information and uses it for self-study or work. The input is the generated questions, answers, and explanations, and the output is the provision of information to the user. In concrete terms, the server sends the generated questions, answers, and explanations together to the user's terminal.

[0851] Step 5:

[0852] The server waits to respond to additional questions or requests from the user. When the user sends a new question or request, the server again starts the problem generation means, answer generation means, and explanation generation means, and repeats the same process. The input is a new request from the user, and the output is the newly generated problem, answer, and explanation. In concrete terms, the server receives a request from the user and again sends a prompt sentence to the generative AI model.

[0853] In addition, 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.

[0854] "Example 1"

[0855] As one embodiment of the present invention, an OA training system incorporating an emotion engine is provided. This system includes a question generation means, an answer generation means, an explanation generation means, and an emotion engine. The emotion engine recognizes the user's emotions and adjusts the difficulty of the questions and the level of detail of the explanations based on the emotions. Specifically, if it is recognized that the user is feeling stressed, it lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if it is recognized that the user is bored, it increases the difficulty of the questions or makes the explanations more concise. This can improve the user's learning efficiency and satisfaction.

[0856] "Example 2"

[0857] As one embodiment of the present invention, an OA training system incorporating an emotion engine is provided. This system includes a question generation means, an answer generation means, an explanation generation means, and an emotion engine. The emotion engine recognizes the user's emotions and adjusts the difficulty of the questions and the level of detail of the explanations based on the emotions. Specifically, if it is recognized that the user is feeling stressed, it lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if it is recognized that the user is bored, it increases the difficulty of the questions or makes the explanations more concise. This can improve the user's learning efficiency and satisfaction.

[0858] The process flow of each embodiment will be described below.

[0859] "Example 1"

[0860] Step 1: A user logs into the system. At this point, the emotion engine initializes the user's emotional state.

[0861] Step 2: The system generates problems and presents them to the user. The difficulty of the problems is adjusted based on the user's emotional state by the emotion engine.

[0862] Step 3: The user works through the problem and enters their answer.

[0863] Step 4: The system evaluates the user's answer and determines whether it is correct or incorrect.

[0864] Step 5: The system generates a commentary and presents it to the user. The detail of the commentary is adjusted by the emotion engine based on the user's emotional state.

[0865] Step 6: The emotion engine updates the user's emotional state based on the user's answer, the explanations they have read, etc.

[0866] Step 7: Go back to step 2, except that the process ends when the user logs out of the system or if there is no activity for a certain period of time.

[0867] Example 1

[0868] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0869] Conventional office automation (OA) training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, they could not flexibly respond to the user's emotions and learning situation, which could lead to a decrease in learning efficiency and satisfaction.

[0870] 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.

[0871] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, a question difficulty adjusting means, and an explanation detail adjusting means, which allows the user to efficiently proceed with self-study and further enables flexible response according to the user's emotion and learning situation.

[0872] The "question generation means" is a function that automatically generates questions for the user to study.

[0873] The "answer generating means" is a function that provides a correct answer to a generated question.

[0874] The "explanation generating means" is a function that provides a detailed explanation for the generated answer.

[0875] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[0876] The "problem difficulty adjustment means" is a function for adjusting the difficulty of questions according to the user's emotions and learning situation.

[0877] The "means for adjusting the level of detail of explanation" is a function for adjusting the level of detail of the explanation according to the user's emotions and learning situation.

[0878] "Spreadsheet software" is software for organizing and tallying formulas and data.

[0879] "Office automation" is a general term for technologies and systems that improve the efficiency of office work.

[0880] The present invention relates to an office automation (OA) training system, which is a system including a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, a question difficulty adjusting means, and an explanation detail level adjusting means.

[0881] System Configuration

[0882] Hardware and Software

[0883] The server stores and executes programs for executing the problem generation means, answer generation means, explanation generation means, emotion recognition means, problem difficulty adjustment means, and explanation detail adjustment means. These means are realized using a generative AI model. Specific software used is spreadsheet software (e.g., Excel, Spreadsheet).

[0884] The terminal provides an interface for the user to access the system and answer questions, sends the user's input to the server, and displays the responses from the server.

[0885] Program Processing

[0886] Problem generation means

[0887] Based on the topic selected by the user, the server generates questions related to spreadsheet formulas and simple automation, such as "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0888] Answer generation means

[0889] The server provides the correct answer to the generated problem. For example, for a VLOOKUP function problem, the server generates the answer "=VLOOKUP(search value, range, column number, search method)".

[0890] Explanation generation method

[0891] The server provides detailed explanations for the answers. For example, for the answer of the VLOOKUP function, it generates the explanation "The VLOOKUP function searches for a specific value within a specified range and returns the value of another column that corresponds to that value. The usage is as follows: =VLOOKUP(search value, range, column number, search method)".

[0892] emotion recognition means

[0893] The server uses an emotion engine to recognize the user's emotions. For example, if the server recognizes that the user is stressed, it will lower the difficulty of the next question or make the explanation more detailed. Conversely, if the server recognizes that the user is bored, it will increase the difficulty of the question or make the explanation more concise.

[0894] Problem difficulty adjustment method

[0895] The server adjusts the difficulty of the next problem according to the user's emotions and learning situation. For example, if the user is feeling stressed, it provides an easy problem using basic functions.

[0896] Explanation detail adjustment method

[0897] The server adjusts the level of detail of the explanation according to the user's emotions and learning situation. For example, if the user is feeling stressed, it provides a detailed step-by-step explanation.

[0898] Examples

[0899] Let's say a user wants to learn "Excel's IF function." The specific steps are as follows:

[0900] 1. A user logs into the system.

[0901] 2. The user selects "Excel IF function."

[0902] 3. The server generates the question, "Explain how to use Excel's IF function to display 'Pass' if the value of cell A1 is 50 or greater, and 'Fail' otherwise."

[0903] 4. Present the server-generated problem to the user.

[0904] 5. The user enters the answer "=IF(A1>=50, 'Pass', 'Fail')".

[0905] 6. The server evaluates the user's answer and determines it to be correct.

[0906] 7. The server generates the next problem and presents it to the user.

[0907] 8. The server recognizes the user's emotions and adjusts the difficulty of the next question.

[0908] 9. The user addresses the next problem.

[0909] Examples of prompt statements

[0910] Please explain how to use the IF function in Excel to display 'Pass' if the value of cell A1 is 50 or greater, and 'Fail' otherwise.

[0911] In this way, the user can efficiently progress with his / her studies.

[0912] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0913] Step 1:

[0914] A user logs into the system.

[0915] A user accesses the system using a terminal and enters a user ID and password on the login screen. The server receives the entered information and authenticates it by checking it against a database. If authentication is successful, the user can log in to the system.

[0916] Input: User ID, Password

[0917] Output: Authentication result (success / failure)

[0918] Step 2:

[0919] The user selects the topic they want to learn about.

[0920] The user selects the topic they want to learn from a list of topics displayed on the terminal screen. The server receives the selected topic information and proceeds to the next step.

[0921] Input: Topic selection information

[0922] Output: Selected topic information

[0923] Step 3:

[0924] The server generates questions based on the selected topic.

[0925] The server uses a generative AI model to generate questions based on the selected topic information, such as "Explain how to use the VLOOKUP function in Excel to find a specific value."

[0926] Input: Selected topic information

[0927] Output: Generated problem

[0928] Step 4:

[0929] Present the server-generated questions to the user.

[0930] The server sends the generated questions to the terminal and displays them on the user's screen. The user checks the questions.

[0931] Input: Generated problem

[0932] Output: The problem as seen by the user

[0933] Step 5:

[0934] The user answers the question.

[0935] The user uses the terminal to input the answer to the problem, for example, "=VLOOKUP(search value, range, column number, search method)". The terminal sends the input answer to the server.

[0936] Input: User's answer

[0937] Output: Answer sent to the server

[0938] Step 6:

[0939] The server evaluates the user's answers and determines whether they are correct or incorrect.

[0940] The server evaluates the answers it receives to determine whether they are correct or incorrect, for example by checking whether they contain correct syntax or meet specified conditions.

[0941] Input: User's answer

[0942] Output: Evaluation result (correct / incorrect)

[0943] Step 7:

[0944] If the answer is correct, the server presents the next question, and if the answer is incorrect, it provides the answer and an explanation.

[0945] If the user's answer is correct, the server generates the next question and presents it to the user. If the answer is incorrect, the server generates the correct answer and its explanation and provides it to the user. For example, the server may provide an explanation such as, "The VLOOKUP function searches for a specific value within a specified range and returns the value of another column that corresponds to that value."

[0946] Input: Evaluation result

[0947] Output: Next question or answer and explanation

[0948] Step 8:

[0949] The server recognizes the user's emotions and adjusts the difficulty of the next question and the level of detail of the explanation.

[0950] The server uses an emotion engine to recognize the user's emotions. For example, if the server recognizes that the user is stressed, it will lower the difficulty of the next question or make the explanation more detailed. Conversely, if the server recognizes that the user is bored, it will increase the difficulty of the question or make the explanation more concise.

[0951] Input: User emotion data

[0952] Output: Adjusted difficulty of questions and level of explanation

[0953] Step 9:

[0954] The user is faced with the following problem:

[0955] The user uses the device to solve the next problem, and the server repeats the process to help the user learn.

[0956] Input: Adjusted problem

[0957] Output: User's answer

[0958] (Application example 1)

[0959] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal".

[0960] Conventional OA training systems do not adjust the difficulty of questions or the level of detail of explanations according to the user's emotions, which can lead to low learning efficiency and satisfaction. In addition, there was a problem with the difficulty of generating appropriate questions and providing answers in training on data management and automation processes within factories. This could delay the improvement of workers' skills.

[0961] 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.

[0962] In this invention, the server includes a question generation means, an answer generation means, an explanation generation means, an emotion recognition means, and a means for adjusting the difficulty of the questions and the level of detail of the explanations based on the emotion. This makes it possible to provide appropriate questions and explanations according to the emotion of the user, thereby improving learning efficiency and satisfaction. In addition, appropriate questions can be generated and answers can be provided in data management and automation process training within a factory, which can promote the improvement of worker skills.

[0963] The "question generation means" is a function that automatically generates questions for the user to study.

[0964] The "answer generating means" is a function that provides an accurate answer to a generated question.

[0965] The "explanation generating means" is a function that provides detailed explanations for answers, making it easier for users to understand.

[0966] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[0967] "Means for adjusting the difficulty of questions and the level of detail of explanations based on emotions" refers to a function for raising or lowering the difficulty of questions and adjusting the level of detail of explanations according to the user's emotions.

[0968] "Spreadsheet software" refers to software for organizing and calculating data, and includes Excel and Spreadsheet.

[0969] "Office automation-related questions" are questions about automation and efficiency related to office work.

[0970] The system for carrying out the present invention includes a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, and a means for adjusting the difficulty of the question and the level of detail of the explanation based on the emotion. Specific embodiments will be described below.

[0971] System Configuration

[0972] Hardware

[0973] Server: Responsible for data processing and storage.

[0974] Terminal: A device that is directly operated by a user, such as a factory robot, PC, or smartphone.

[0975] Emotion Recognition Device: A device, such as a camera or microphone, that is used to recognize a user's emotions.

[0976] software

[0977] Python: A programming language used to implement the program.

[0978] OpenAI API: An API used for emotion recognition and natural language processing.

[0979] Data processing and calculation

[0980] Problem generation

[0981] The server generates questions related to spreadsheet formulas and simple automation, such as how to use the VLOOKUP function for inventory management or how to create a macro to automate product production schedules.

[0982] Answer generation

[0983] The server provides precise solutions to the generated questions, including specific instructions for using the VLOOKUP function and IF functions.

[0984] Description Generation

[0985] The server provides detailed explanations for the solutions, including explanations of each argument in the VLOOKUP function and details on the condition settings in the IF function.

[0986] emotion recognition

[0987] The emotion recognition device analyzes the user's facial expressions and tone of voice to recognize their emotions, and can determine whether they are stressed or bored.

[0988] Emotion-Based Adjustments

[0989] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of emotion recognition. For example, if the user is stressed, the server lowers the difficulty of the questions and provides more detailed explanations. Conversely, if the user is bored, the server raises the difficulty of the questions and provides more concise explanations.

[0990] Examples

[0991] Example problem

[0992] "Please explain how to use the VLOOKUP function to get the price of a specific product from an inventory table."

[0993] Example answer

[0994] Use the VLOOKUP function to search for a specific value in a range you specify and return the corresponding value.

[0995] Example of commentary

[0996] "The VLOOKUP function takes four arguments: the lookup value, the range, the column number, and the lookup method."

[0997] Examples of prompt statements

[0998] "Enter the user's emotion (e.g. stress, boredom, neutral): stress"

[0999] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. In addition, it is possible to generate appropriate questions and provide answers for training on data management and automation processes in factories, promoting the improvement of worker skills.

[1000] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1001] Step 1:

[1002] A user logs into the system using a terminal. The user's authentication information is entered and verified by the server. If authentication is successful, the server sends the user's learning history and current progress to the terminal.

[1003] Step 2:

[1004] The user inputs a command to start learning. The terminal sends this command to the server. The server prepares data for generating appropriate questions based on the user's learning history and progress.

[1005] Step 3:

[1006] The server uses the problem generation means to generate problems related to spreadsheet software formulas and simple automation, such as how to use the VLOOKUP function for inventory management and how to create a macro to automate product production schedules. The generated problems are sent to the terminal.

[1007] Step 4:

[1008] The terminal displays the generated questions to the user. The user answers the questions and inputs the answers into the terminal. The terminal transmits the input answers to the server.

[1009] Step 5:

[1010] The server uses the answer generation means to evaluate the user's answer and generate an accurate answer, which is then transmitted to the terminal.

[1011] Step 6:

[1012] The device displays the generated answer to the user, who can then review the answer and retry if necessary.

[1013] Step 7:

[1014] The server uses the explanation generation means to generate a detailed explanation for the answer, including, for example, an explanation of each argument of the VLOOKUP function, details of the condition settings of the IF function, etc. The generated explanation is sent to the terminal.

[1015] Step 8:

[1016] The terminal displays the generated explanation to the user, who can then check the explanation and deepen his or her understanding.

[1017] Step 9:

[1018] The emotion recognition device analyzes the user's facial expressions and tone of voice to recognize emotions, and the recognized emotions are transmitted to the server via the device.

[1019] Step 10:

[1020] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of emotion recognition. For example, if the user is stressed, the difficulty of the questions is lowered and the explanations are made more detailed. Conversely, if the user is bored, the difficulty of the questions is increased and the explanations are made brief. The adjusted questions and explanations are sent to the terminal.

[1021] Step 11:

[1022] The device will then display the adjusted problem and explanation to the user, who can then retry the problem and continue learning.

[1023] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. In addition, it is possible to generate appropriate questions and provide answers for training on data management and automation processes in factories, promoting the improvement of worker skills.

[1024] Example 2

[1025] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1026] Conventional office automation (OA) training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own, which was time-consuming. In addition, the learning content was not adjusted according to the user's emotions, which could lead to a decrease in learning efficiency and satisfaction. Furthermore, the system lacked the functionality to provide appropriate answers and explanations for specific questions asked in everyday work.

[1027] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1028] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, an emotion recognition means, and a difficulty level adjusting means. This allows the user to efficiently proceed with self-study, and the learning content is adjusted according to the user's emotion, improving learning efficiency and satisfaction. In addition, it is possible to provide appropriate answers and explanations for specific questions in everyday work.

[1029] The "question generation means" is a function that automatically generates questions for the user to study.

[1030] The "answer generating means" is a function that automatically generates a correct answer to a generated question.

[1031] The "explanation generating means" is a function that automatically generates a detailed explanation for the generated answer.

[1032] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[1033] The "difficulty level adjustment means" is a function that adjusts the difficulty level of the questions and the level of detail of the explanations according to the user's emotions and learning situation.

[1034] "Spreadsheet software" is software for entering numerical data, performing calculations, analysis, creating graphs, etc.

[1035] "Office automation" is a general term for technologies and systems that make office work more efficient.

[1036] The present invention relates to an office automation (OA) training system that allows users to efficiently advance self-study. The system includes a question generating means, an answer generating means, an explanation generating means, an emotion recognition means, and a difficulty level adjusting means.

[1037] System Configuration

[1038] Hardware and Software

[1039] The server is equipped with hardware and software for executing the problem generation means, the answer generation means, the explanation generation means, the emotion recognition means, and the difficulty level adjustment means. Specifically, the server generates problems, answers, and explanations using a generative AI model. In addition, as the emotion recognition means, it uses emotion analysis software to recognize the user's emotions.

[1040] The terminal is a device that allows users to access the system and display questions, answers, and explanations. The terminal can be any common device such as a PC, tablet, or smartphone.

[1041] System Operation

[1042] Problem generation means

[1043] The server generates questions based on what the user wants to learn. For example, if a user says they want to learn about Excel's VLOOKUP function, the server uses the generative AI model to generate a question like, "Explain how to use Excel's VLOOKUP function to find the corresponding value in column B based on the data in column A."

[1044] Answer generation means

[1045] The server generates an answer to the generated problem. For example, the answer to the above problem is "=VLOOKUP(A2, B:C, 2, FALSE)".

[1046] Explanation generation method

[1047] The server generates a detailed explanation for the generated answer, for example, "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches the value in cell A2 in columns B to C and returns the corresponding value in column C."

[1048] emotion recognition means

[1049] The server uses emotion recognition means to recognize the emotion of the user, for example to determine whether the user is stressed or bored.

[1050] Difficulty adjustment means

[1051] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of the emotion recognition means. For example, if the user is stressed, the server lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if the user is bored, the server raises the difficulty of the questions or makes the explanations more concise.

[1052] Examples

[1053] Users choose what to study

[1054] The user types "I want to learn how to use the VLOOKUP function" into the input field on the device.

[1055] Server Generates Problems

[1056] The server uses a generative AI model to generate a question such as, "Explain how to use Excel's VLOOKUP function to find the corresponding value in column B based on the data in column A."

[1057] The server generates the answer

[1058] The server generates the answer to the problem: "=VLOOKUP(A2, B:C, 2, FALSE)".

[1059] The server generates the description

[1060] In response to the answer, the server generates an explanation: "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches for the value in cell A2 in the range from columns B to C, and returns the corresponding value in column C."

[1061] The server recognizes the user's emotion using an emotion recognition means.

[1062] The server uses the emotion recognition means to recognize that the user is feeling stressed.

[1063] The server adjusts the difficulty of the questions and the level of detail of the explanations.

[1064] The server lowers the difficulty of the question and changes it to a simpler question: "How can I use Excel's VLOOKUP function to find data in column A from column B?"

[1065] Examples of prompt statements

[1066] "Please tell me how to use the VLOOKUP function in Excel. Please also give me some concrete examples and explanations."

[1067] In this way, the user can efficiently advance self-study.

[1068] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1069] Step 1:

[1070] Users choose what to study

[1071] The user inputs the content they want to learn into the input field of the terminal. For example, they input "I want to learn how to use the VLOOKUP function." The input content is sent to the server. The input data is text data "I want to learn how to use the VLOOKUP function." The server receives this input data and proceeds to the next processing step.

[1072] Step 2:

[1073] Server Generates Problems

[1074] The server generates questions using a generative AI model based on input data received from the user. For example, it generates a question such as "Explain how to use Excel's VLOOKUP function to search for the corresponding value in column B based on the data in column A." The input data is the text data "I want to learn how to use the VLOOKUP function," and the output data is the text data of the generated question.

[1075] Step 3:

[1076] The server generates the answer

[1077] The server generates an answer to the generated problem. For example, the server generates an answer to the problem, such as "=VLOOKUP(A2, B:C, 2, FALSE)". The input data is the text data of the generated problem, and the output data is the text data of the generated answer.

[1078] Step 4:

[1079] The server generates the description

[1080] The server generates a detailed explanation for the generated answer. For example, it generates an explanation like "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches for the value in cell A2 in the range from column B to column C, and returns the corresponding value in column C." The input data is the text data of the generated answer, and the output data is the text data of the generated explanation.

[1081] Step 5:

[1082] The server recognizes the user's emotion using an emotion recognition means.

[1083] The server recognizes the user's emotions using emotion recognition means, for example, determining whether the user is stressed or bored. The input data is emotion-related data such as the user's facial expression and input speed, and the output data is data indicating the user's emotional state.

[1084] Step 6:

[1085] The server adjusts the difficulty of the questions and the level of detail of the explanations.

[1086] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of the emotion recognition means. For example, if the user is stressed, the difficulty of the questions is lowered or the explanations are made more detailed. Conversely, if the user is bored, the difficulty of the questions is increased or the explanations are made more concise. The input data is data indicating the user's emotional state, and the output data is text data of the adjusted questions and explanations.

[1087] Step 7:

[1088] The device displays the questions, answers, and explanations to the user.

[1089] The terminal displays the questions, answers, and explanations received from the server to the user, who can then proceed with his or her studies. The input data is the adjusted text data of the questions, answers, and explanations, and the output data is the information displayed on the terminal.

[1090] (Application example 2)

[1091] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the smart glasses 214 will be referred to as a "terminal".

[1092] Conventional OA training systems did not adjust the difficulty of questions or the level of detail of explanations according to the user's emotions, which led to problems with low learning efficiency and satisfaction. In addition, there was a lack of means to provide appropriate OA training to employees working in factories. This could lead to delayed improvement of employees' skills and reduced productivity.

[1093] 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.

[1094] In this invention, the server includes a question generation means, an answer generation means, an explanation generation means, an emotion recognition means, a question difficulty adjustment means, and an explanation detail adjustment means. This makes it possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. It also makes it possible to provide effective OA training to employees working in factories.

[1095] A "problem generation means" is a means for generating problems for a user, such as problems related to spreadsheet software formulas or simple automation.

[1096] An "answer generating means" is a means for providing an answer to a generated question.

[1097] The "explanation generating means" is a means for generating a detailed explanation for a provided answer.

[1098] An "emotion recognition means" is a means for recognizing a user's emotions, and determines emotions from the user's facial expressions and voice using a camera and emotion recognition software.

[1099] The "means for adjusting the difficulty of questions" refers to a means for adjusting the difficulty of questions based on the recognized user's emotions.

[1100] The "means for adjusting the level of detail of explanation" is a means for adjusting the level of detail of the explanation to be provided based on the recognized user's feelings.

[1101] A system for implementing this invention includes a robot for teaching factory workers how to use Excel and spreadsheets. The robot recognizes the emotions of the workers, asks them questions of appropriate difficulty, and provides answers and explanations.

[1102] Hardware and Software Used

[1103] Hardware: Factory robots, cameras (for emotion recognition)

[1104] Software: EmotionRecognizer (emotion recognition library), Python

[1105] System processing explanation

[1106] emotion recognition

[1107] The robot uses a camera to capture a picture of the employee's face and recognizes emotions using the EmotionRecognizer library, which determines emotions from the user's facial expressions and voice to identify states such as stress or boredom.

[1108] Problem generation

[1109] Based on the emotion data obtained by the emotion recognition means, the problem difficulty adjustment means selects problems of appropriate difficulty. For example, if an employee is stressed, it generates easy problems, and if an employee is bored, it generates difficult problems.

[1110] Providing answers and explanations

[1111] The answer generating means provides an answer to the question generated by the question generating means. Furthermore, the explanation generating means generates a detailed explanation and provides it to the employee. The explanation detail adjusting means adjusts the detail of the explanation based on the emotion data.

[1112] Examples

[1113] If your employees are stressed:

[1114] The robot asks a simple question: "Please explain how to use the VLOOKUP function," and then provides a detailed explanation.

[1115] If your employees are bored:

[1116] The robot asks a difficult question: "Please explain how to use the IF function," and provides a concise explanation.

[1117] Examples of prompt statements

[1118] "If employees are feeling stressed, give them some easy questions and provide detailed explanations."

[1119] "If employees are bored, give them challenging questions and provide concise commentary."

[1120] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. It is also possible to provide effective OA training to employees working in factories.

[1121] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1122] Step 1:

[1123] The server uses a camera to take a picture of the user's face and recognizes emotions using the EmotionRecognizer library. The input is the user's face image, and the output is the user's emotion data (e.g., stress, boredom, etc.). In concrete terms, the camera captures the user's face and sends the image data to EmotionRecognizer to analyze the emotions.

[1124] Step 2:

[1125] The server selects a problem of appropriate difficulty using the problem difficulty adjustment means based on the emotion data obtained by the emotion recognition means. The input is the emotion data, and the output is the selected problem. In concrete terms, if the emotion data is recognized as "stress," the server selects an easy problem, and if it is recognized as "boredom," the server selects a difficult problem.

[1126] Step 3:

[1127] The server generates the selected problem using the problem generation means. The input is the selected problem type (e.g., how to use the VLOOKUP function), and the output is a specific problem statement. As a specific operation, the server retrieves the corresponding problem from the problem database and presents it to the user.

[1128] Step 4:

[1129] The server provides answers to questions generated using the answer generation means. The input is the generated question text, and the output is the answer to the question. In concrete terms, the server retrieves the corresponding answer from the question database and presents it to the user.

[1130] Step 5:

[1131] The server uses an explanation generating means to generate a detailed explanation for the provided answer. The input is the answer to the problem, and the output is an explanation for the answer. In specific operations, the server retrieves the corresponding explanation from the explanation database and presents it to the user.

[1132] Step 6:

[1133] The server adjusts the level of detail of the commentary based on the emotion data using the explanation detail adjustment means. The input is the emotion data and the answer explanation, and the output is the adjusted explanation. In specific operations, if the emotion data is recognized as "stress", the server provides a detailed explanation, and if the emotion data is recognized as "boredom", the server provides a concise explanation.

[1134] Step 7:

[1135] The server provides the user with the tailored explanation to support the user's learning. The input is the tailored explanation, and the output is the user's improved understanding. In concrete terms, the server displays the tailored explanation on the user's screen, encouraging the user to read and understand the explanation.

[1136] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1137] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1138] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1139] 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 smart glasses 214.

[1140] [Third embodiment]

[1141] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1142] 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.

[1143] 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 wide area network (WAN) and / or a local area network (LAN).

[1144] 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.

[1145] 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 the voice according to instructions from the processor 46.

[1146] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1148] Fig. 6 shows an example of 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.

[1149] 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.

[1150] 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.

[1151] In the headset type terminal 314, 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.

[1152] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1153] "Example 1"

[1154] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[1155] "Example 2"

[1156] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[1157] The process flow of each embodiment will be described below.

[1158] "Example 1"

[1159] Step 1: The user logs into the system and selects the topic they want to learn, which can range from Excel and spreadsheet formulas to simple automation.

[1160] Step 2: Based on the selected topic, the system's problem generator will generate a problem, for example, a problem about how to use the VLOOKUP function in Excel.

[1161] Step 3: The generated question is presented to the user, who enters an answer.

[1162] Step 4: After the user submits the answer, the system's answer generation means provides the correct answer. Step 5: The system's explanation generation means provides an explanation for the answer. This allows users to save time and effort in creating questions and searching for answers and explanations when self-studying.

[1163] Step 6: When users input OA-related questions from their daily work into the system, the system will provide answers and explanations for those questions, such as how to use a specific function in Excel or how to resolve an error.

[1164] Example 1

[1165] Next, a description will be given of Example 1 of the embodiment 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".

[1166] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to respond quickly and accurately to specific questions related to clerical work in daily work.

[1167] 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.

[1168] In this invention, the server includes: a prompt sentence for instructing to generate a question sentence related to the question about how to use the spreadsheet software based on a question about how to use the spreadsheet software input by a user; a means for generating a question sentence related to the question about how to use the spreadsheet software using a generative AI; a prompt sentence for instructing to generate an answer to the generated question sentence; a means for generating an answer to the generated question sentence using the generative AI; a prompt sentence for instructing to generate an explanation for the generated answer; a means for generating an explanation for the generated answer using the generative AI; a means for presenting the generated question sentence to the user; a means for recognizing the user's emotion using an emotion engine; a prompt sentence for instructing to adjust the generated answer or explanation sentence based on the recognized emotion of the user; a means for adjusting the generated answer or explanation sentence using the generative AI; and a means for presenting the adjusted answer or explanation sentence to the user. This allows the user to efficiently self-study. The questions about how to use the spreadsheet software include questions about formulas used in the spreadsheet software or questions about automation. The questions about how to use the spreadsheet software include questions about how to use the spreadsheet software that are necessary for the user's office work, so that questions related to office work in everyday work can be quickly and accurately responded to.

[1169] The "question generation means" is a means for generating questions such as those related to formulas in a spreadsheet or simple automation based on a prompt sentence from a user.

[1170] The "answer generating means" is a means for generating an optimal answer to a generated question.

[1171] The "explanation generating means" is a means for generating a detailed explanation for the generated answer.

[1172] The "means for receiving a prompt sentence" refers to a means for receiving a specific question or request from the user in text form.

[1173] "Generative AI" is an artificial intelligence model that uses natural language processing technology to generate questions, answers, and explanations.

[1174] "Means for saving in a database" refers to means for saving the generated questions, answers, and explanations in a database.

[1175] "Spreadsheet software" is software for organizing, calculating, and analyzing data, and can process data using formulas and functions.

[1176] "Questions related to office work" are specific questions about how to use spreadsheet software and how to resolve errors that arise in daily work.

[1177] This invention is a system that allows users to efficiently self-learn and quickly and accurately respond to questions related to clerical work in their daily work. This system operates in cooperation with a server, a terminal, and a user.

[1178] Server Roles

[1179] The server manages and operates the entire system using the following means:

[1180] 1. Problem generation means

[1181] The server receives a question input by a user about how to use spreadsheet software. For example, the server receives a question sentence such as "Please tell me how to use the VLOOKUP function in Excel." The server generates a question sentence related to the question about how to use the spreadsheet software using a prompt sentence instructing the server to generate a question sentence related to the question and a generative AI (e.g., GPT-4 (registered trademark)). The generated question sentence is in the form of "Explain how to use the VLOOKUP function in Excel to get data from another sheet." The generated question sentence is stored in a database.

[1182] 2. Answer generation means

[1183] The server generates an answer to the generated question. It uses a prompt that instructs the server to generate an answer to the generated question and a generative AI to generate the optimal answer to the question. For example, an answer in the format "=VLOOKUP(search value, range, column number, search method)" is generated. The generated answer is stored in the database.

[1184] 3. Explanation Generation Method

[1185] The server generates a detailed explanation for the generated answer. A prompt that instructs the server to generate an explanation for the generated answer and a generative AI are used to generate a detailed explanation for the answer. For example, an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)" are generated. The generated explanation is saved in the database.

[1186] User Roles

[1187] A user accesses the system using a terminal and performs the following operations:

[1188] 1. Enter your question

[1189] A user uses the terminal to type in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[1190] 2. Obtaining questions

[1191] The user obtains the generated question text from the server and checks the question text on the terminal screen.

[1192] 3. Get answers

[1193] The user obtains the generated answer from the server and checks the answer on the screen of the terminal.

[1194] 4. Obtaining explanations

[1195] The user receives the generated commentary from the server and checks the commentary on the screen of the terminal.

[1196] Examples

[1197] For example, if a user enters the question "How do I use the VLOOKUP function in Excel?", the server processes the question as follows:

[1198] 1. Problem generation

[1199] The server generates a question such as, "Explain how to use Excel's VLOOKUP function to retrieve data from another sheet."

[1200] 2. Answer generation

[1201] The server generates the answer "=VLOOKUP(search value, range, column number, search method)".

[1202] 3. Description Generation

[1203] The server generates an explanatory text stating, "The VLOOKUP function searches for a search value within a specified range and returns the data from the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)."

[1204] In this way, the user can efficiently proceed with self-learning and can quickly and accurately respond to questions related to clerical work in the course of daily work.

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

[1206] Step 1: Enter your question

[1207] Subject: User

[1208] A user accesses the system using a terminal and types in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[1209] Input: The question entered by the user

[1210] Output: The question is sent to the server.

[1211] Step 2: Receiving the question

[1212] Subject: Server

[1213] The server receives a question sent by a user.

[1214] Input: The question submitted by the user

[1215] Output: The question is ready to be processed in the server.

[1216] Step 3: Generate the problem

[1217] Subject: Server

[1218] The server uses the prompt text and generative AI to generate a question based on the question, for example, "Explain how to use the VLOOKUP function in Excel to get data from another sheet."

[1219] Input:Question

[1220] Data processing: Using prompts containing questions and generative AI, appropriate problem statements are generated.

[1221] Output: Generated problem statement

[1222] Step 4: Save the question

[1223] Subject: Server

[1224] The server stores the generated questions in a database.

[1225] Input: Generated question text

[1226] Data processing: Converting the generated questions into a database format

[1227] Output: The question is saved in the database.

[1228] Step 5: Generate the answer

[1229] Subject: Server

[1230] The server generates an answer to the generated question. It uses the prompt and generative AI to generate the optimal answer to the question. For example, it generates the answer "=VLOOKUP(search value, range, column number, search method)".

[1231] Input: Generated question text

[1232] Data processing: A generative AI model analyzes the question and generates an appropriate answer

[1233] Output: The generated answer

[1234] Step 6: Save your answers

[1235] Subject: Server

[1236] The server stores the generated answers in a database.

[1237] Input: Generated answer

[1238] Data processing: Converting the generated answers into a database format

[1239] Output: The answer is saved in the database.

[1240] Step 7: Generate a description

[1241] Subject: Server

[1242] The server generates a detailed explanation for the generated answer. It uses the prompt text and generative AI to generate a detailed explanation for the answer. For example, it generates an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. There are two search methods: TRUE (approximate match) and FALSE (exact match)."

[1243] Input: Generated answer

[1244] Data processing: A generative AI model analyzes the answers and generates appropriate explanations

[1245] Output: Generated description

[1246] Step 8: Save your commentary

[1247] Subject: Server

[1248] The server stores the generated commentary in a database.

[1249] Input: Generated description

[1250] Data processing: Convert the generated explanatory text into a database format.

[1251] Output: The explanatory text is saved in the database.

[1252] Step 9: Get the problem statement

[1253] Subject: User

[1254] The user uses a terminal to obtain the generated question text from the server and checks the question on the terminal screen.

[1255] Input: User request

[1256] Output: The generated question is displayed on the terminal.

[1257] Step 10: Getting the answer

[1258] Subject: User

[1259] The user uses the terminal to retrieve the generated answer from the server and check the answer on the terminal screen.

[1260] Input: User request

[1261] Output: The generated answer is displayed on the terminal.

[1262] Step 11: Get the description

[1263] Subject: User

[1264] The user uses the terminal to obtain the generated commentary from the server, and checks the commentary on the screen of the terminal.

[1265] Input: User request

[1266] Output: The generated commentary is displayed on the terminal. In this embodiment, when presenting a question sentence to a user, the server recognizes the user's emotion using an emotion engine, which will be described later. The server then adjusts the generated answer or commentary using a prompt sentence that instructs the user to adjust the generated answer or commentary based on the recognized user's emotion and the generative AI, and presents the adjusted answer or commentary to the user.

[1267] (Application example 1)

[1268] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1269] Conventional OA training systems were limited to providing questions related to Excel and spreadsheet formulas and simple automation, and did not address training related to the operation and maintenance of machines used in factories. This made it difficult to efficiently acquire knowledge related to the operation and maintenance of machines in factories. In addition, while the system had functions to answer OA-related questions in everyday work, it lacked functions to answer specific questions about the operation and maintenance of machines used in factories.

[1270] 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. In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a means for generating questions related to the operation and maintenance of machines used in a factory, a means for providing answers to the generated questions, and a means for providing explanations of the answers. This makes it possible to efficiently acquire knowledge related to the operation and maintenance of machines used in a factory.

[1271] The "problem generation means" is a means for generating problems related to Excel or spreadsheet formulas, simple automation, and the operation and maintenance of machines used in factories.

[1272] An "answer generating means" is a means for providing an answer to a generated question.

[1273] The "explanation generating means" is a means for providing an explanation for a generated answer.

[1274] "Machinery used in a factory" refers to various types of machinery and equipment used for production and maintenance within a factory.

[1275] "Operation" refers to the specific steps or methods for making a machine work.

[1276] "Maintenance" refers to the inspection and repair procedures to keep a machine in good working order.

[1277] The term "system" refers to a collection of a series of devices and programs including a problem generating means, an answer generating means, an explanation generating means, and a means for generating problems relating to the operation and maintenance of machines used in a factory.

[1278] A system for implementing the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems relating to the operation and maintenance of machines used in a factory, a means for providing answers to the generated problems, and a means for providing explanations for the answers.

[1279] The server implements a problem generation means, an answer generation means, and an explanation generation means using a programming language such as Python. Specifically, the problem generation means generates problems related to formulas in Excel or spreadsheets, simple automation, and the operation and maintenance of machines used in factories. For example, it generates a prompt sentence such as "Please write the code to program the operation of a robot."

[1280] The answer generation means provides an answer to the generated problem. For example, it generates a specific answer such as "Example: move_forward(10);". The explanation generation means provides an explanation for the generated answer. For example, it generates an explanation such as "This code moves the robot forward 10 meters".

[1281] Users can use this system to efficiently acquire knowledge about the operation and maintenance of machines used in factories. When a user accesses the system, the server generates questions and provides answers and explanations. This allows users to save time when self-studying by creating questions themselves and searching for answers and explanations.

[1282] As a concrete example, the following prompt sentence can be input to a generative AI model:

[1283] Example prompt:

[1284] "Write the code to program the robot's movements."

[1285] In response to this prompt, the generative AI model provides the following answer and explanation:

[1286] Example answer:

[1287] "Example: move_forward(10);"

[1288] Example of explanation:

[1289] "This code will move the robot forward 10 meters."

[1290] In this way, training on the operation and maintenance of machines used in the factory can be carried out efficiently.

[1291] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1292] Step 1:

[1293] The server receives requests from users. Users access the system and send requests to generate problems related to the operation and maintenance of machines used in the factory. The input is the user's request, and the output is the analysis result of the request.

[1294] Step 2:

[1295] The server uses a problem generation means to generate a problem based on the request content. For example, it generates a prompt such as "Please write a code to program the robot's movements." The input is the analysis result of the request content, and the output is the generated problem.

[1296] Step 3:

[1297] The server uses the answer generation means to generate an answer to the generated question. For example, it generates a specific answer such as "Example: move_forward(10);". The input is the generated question, and the output is the generated answer.

[1298] Step 4:

[1299] The server uses an explanation generation means to generate an explanation for the generated answer. For example, the server generates an explanation such as "This code will move the robot forward 10 meters." The input is the generated answer, and the output is the generated explanation.

[1300] Step 5:

[1301] The server provides the generated questions, answers, and explanations to the user. The user uses this information for self-study. The input is the generated questions, answers, and explanations, and the output is the results provided to the user.

[1302] Step 6:

[1303] The user checks the provided questions, answers, and explanations, and submits a request again if necessary. The input is the result provided to the user, and the output is the user's feedback or new requests.

[1304] In this way, the server generates questions in response to user requests and provides answers and explanations, enabling users to efficiently acquire knowledge about operating and maintaining machines used in factories.

[1305] Example 2

[1306] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1307] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to quickly provide appropriate answers and explanations for specific questions related to office automation in everyday work.

[1308] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1309] In this invention, the server includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows the user to efficiently self-study and quickly respond to questions related to office automation in everyday work.

[1310] The "question generation means" is a function that generates questions for the user to study.

[1311] The "answer generating means" is a function that provides an accurate answer to a generated question.

[1312] The "explanation generating means" is a function that provides a detailed explanation for an answer.

[1313] A "generative AI model" is a model that uses artificial intelligence to generate questions, answers, and explanations.

[1314] The "means for providing answers and explanations to user questions" is a function for providing appropriate answers and explanations to questions posed to the system by the user.

[1315] "Spreadsheet software" refers to software such as Excel and spreadsheets that are used to organize and tally formulas and data.

[1316] "Office automation" is a general term for technologies and systems that aim to make clerical work more efficient.

[1317] The OA training system of the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows users to efficiently self-study and quickly respond to questions related to office automation in their daily work.

[1318] Hardware and Software Used

[1319] Hardware: Servers, user devices (PCs, tablets, smartphones, etc.)

[1320] Software: Spreadsheet software (Excel, Google Spreadsheet), generative AI model (e.g. GPT-3)

[1321] Specific operation of the system

[1322] 1. Problem generation

[1323] The server generates problems for the user to study. Specifically, it generates problems related to formulas in spreadsheet software, simple automation, etc.

[1324] Example: The server uses a generative AI model to generate a question by entering the prompt "Please generate a question about how to use the VLOOKUP function in Excel."

[1325] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[1326] 2. Answer generation

[1327] The server provides the answers to the generated questions, allowing the user to obtain the correct answer to the question.

[1328] Example: The server inputs a prompt to the generative AI model: "Generate an answer to the following question: Explain how to use the VLOOKUP function in Excel to search for a specific value," and generates an answer.

[1329] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[1330] 3. Description Generation

[1331] The server provides detailed explanations for the answers, allowing users to understand the context of the answer and how to use it.

[1332] Example: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model and generates an explanation.

[1333] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[1334] 4. Support for user self-learning

[1335] Users can study on their own without having to create their own questions or look up answers and explanations. The app also has a function to answer questions related to office automation that users may encounter in their daily work.

[1336] Example: A user asks "How do I use the IF function in Excel?" and the server provides the answer and explanation to the question.

[1337] Examples of prompt statements

[1338] Question generation prompt: "Generate a question on how to use the VLOOKUP function in Excel."

[1339] Solution Generation Prompt: "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to find a specific value."

[1340] Explanation generation prompt: "Generate an explanation for the following answer: =VLOOKUP(lookup value, range, column number, FALSE)"

[1341] In this way, the OA training system assists users in self-study and also answers office automation-related questions in their work.

[1342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1343] Step 1:

[1344] Problem generation

[1345] The server generates questions for the user to study.

[1346] Input: The server inputs the prompt "Generate a question about how to use the VLOOKUP function in Excel" to the generative AI model.

[1347] Data processing: The generative AI model generates questions based on the prompt text.

[1348] Output: The generated questions are returned to the server.

[1349] Specific behavior: The server stores the generated questions in a database and prepares them to be served to the user.

[1350] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[1351] Step 2:

[1352] Answer generation

[1353] The server provides the answers to the generated questions.

[1354] Input: The server inputs the prompt text "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to search for a specific value" to the generative AI model.

[1355] Data processing: The generative AI model generates an answer based on the prompt.

[1356] Output: The generated answer is returned to the server.

[1357] Specific Actions: The server stores the generated answer in a database and prepares it to be served to the user.

[1358] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[1359] Step 3:

[1360] Description Generation

[1361] The server provides detailed explanations for the answers.

[1362] Input: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model.

[1363] Data processing: The generative AI model generates an explanation based on the prompt.

[1364] Output: The generated description is returned to the server.

[1365] Specific Actions: The server stores the generated description in a database and prepares it to be served to the user.

[1366] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[1367] Step 4:

[1368] Supporting users' self-learning

[1369] When self-studying, users can save time by creating their own questions and searching for answers and explanations.

[1370] Input: A user uses a terminal to access the system and ask how to use a particular function or resolve an error.

[1371] Data processing: The server receives the user's question and inputs the prompt text into the generative AI model to generate an answer and explanation.

[1372] Output: The generated answer and explanation are provided to the user.

[1373] Specific operation: When a user asks a question such as "How do I use the IF function in Excel?", the server generates an answer and explanation for the question and provides it to the user.

[1374] (Application example 2)

[1375] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1376] Conventional OA training systems had the problem that users had to create questions and look up answers and explanations when self-studying. In addition, there was a lack of efficient training systems for learning data management and automation tasks in factories. This resulted in problems of reduced work efficiency and increased labor.

[1377] 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.

[1378] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn, and also enables the effective learning of data management and automation tasks in the factory.

[1379] The "problem generation means" is a means for generating problems related to formulas in spreadsheet software or simple automation.

[1380] An "answer generating means" is a means for providing an answer to a generated question.

[1381] The "explanation generating means" is a means for providing a detailed explanation for a generated answer.

[1382] "Data management means" refers to a means for efficiently managing data within a factory.

[1383] An "automation task learning means" is a means for learning an automation task in a factory.

[1384] In order to implement the present invention, the server, the terminal, and the user must cooperate to operate the system. A specific embodiment is described below.

[1385] System Programming

[1386] The server executes a program including a problem generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn and effectively learn data management and automation tasks in a factory.

[1387] Program processing explanation

[1388] The server uses the OpenAI API to generate questions, answers, and explanations for Excel and spreadsheets. Specifically, it performs the following processes:

[1389] Hardware: Computers installed in factory robots

[1390] Software: OpenAI API, Python

[1391] First, the server uses the problem generation means to generate problems related to formulas in spreadsheet software or simple automation, such as a data search problem using the VLOOKUP function in Excel.

[1392] Next, the answer generation means is used to provide an answer to the generated question. For example, a specific method using the VLOOKUP function will be shown.

[1393] In addition, an explanation generator is used to provide detailed explanations for the generated answers, for example explaining how to use the VLOOKUP function and what it means.

[1394] The data management means is a means for efficiently managing data within a factory, and makes it easy for users to organize data.

[1395] The automation task learning means is a means for learning automation tasks in a factory, and enables a user to efficiently learn the automation tasks.

[1396] Examples of concrete examples and prompts

[1397] Examples:

[1398] Question: "How can I use the VLOOKUP function in Excel to find data in column A based on data in column B?"

[1399] Solution: "To use the VLOOKUP function, do this: =VLOOKUP(A2, B:C, 2, FALSE)"

[1400] Explanation: "This function searches for the value in cell A2 in column B and returns the corresponding value in column C. FALSE means an exact match."

[1401] Example prompt:

[1402] Problem Generation Prompt: "Please generate a problem involving data lookup using the Excel VLOOKUP function."

[1403] Answer Generation Prompt: "Generate an answer to the following question: Explain how to use Excel's VLOOKUP function to look up data in column A based on data in column B."

[1404] Explanation Generation Prompt: "Generate an explanation for the following solution: =VLOOKUP(A2, B:C, 2, FALSE)"

[1405] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1406] Step 1:

[1407] The server receives a request from a user and starts the problem generation means. The user sends a request to generate a problem related to formulas and automation in a spreadsheet software. The server receives this request and sends a prompt to the generative AI model. The input is the user's request, and the output is the generated problem. Specifically, the server sends a prompt to the generative AI model saying, "Please generate a data search problem using Excel's VLOOKUP function."

[1408] Step 2:

[1409] The server passes the problem received from the generative AI model to the answer generation means. The answer generation means again sends a prompt sentence to the generative AI model to generate an answer to the generated problem. The input is the generated problem, and the output is the generated answer. In concrete terms, the server sends a prompt sentence to the generative AI model saying, "Please generate an answer to the following problem: Explain how to use Excel's VLOOKUP function to search for data in column A based on data in column B."

[1410] Step 3:

[1411] The server passes the answer received from the generative AI model to the explanation generation means. The explanation generation means again sends a prompt sentence to the generative AI model to generate a detailed explanation for the generated answer. The input is the generated answer, and the output is the generated explanation. In concrete terms, the server sends a prompt sentence "Please generate an explanation for the following answer: =VLOOKUP(A2, B:C, 2, FALSE)" to the generative AI model.

[1412] Step 4:

[1413] The server returns the generated questions, answers, and explanations to the user. The user receives this information and uses it for self-study or work. The input is the generated questions, answers, and explanations, and the output is the provision of information to the user. In concrete terms, the server sends the generated questions, answers, and explanations together to the user's terminal.

[1414] Step 5:

[1415] The server waits to respond to additional questions or requests from the user. When the user sends a new question or request, the server again starts the problem generation means, answer generation means, and explanation generation means, and repeats the same process. The input is a new request from the user, and the output is the newly generated problem, answer, and explanation. In concrete terms, the server receives a request from the user and again sends a prompt sentence to the generative AI model.

[1416] In addition, an emotion engine for estimating the user's emotion may be further combined. That is, the identification processing unit 290 estimates the user's emotion using the emotion identification model 59, and

[1417] It is also possible to carry out specific processing using the above.

[1418] "Example 1"

[1419] As one embodiment of the present invention, an OA training system incorporating an emotion engine is provided. This system includes a question generation means, an answer generation means, an explanation generation means, and an emotion engine. The emotion engine recognizes the user's emotions and adjusts the difficulty of the questions and the level of detail of the explanations based on the emotions. Specifically, if it is recognized that the user is feeling stressed, it lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if it is recognized that the user is bored, it increases the difficulty of the questions or makes the explanations more concise. This can improve the user's learning efficiency and satisfaction.

[1420] "Example 2"

[1421] As one embodiment of the present invention, an OA training system incorporating an emotion engine is provided. This system includes a question generation means, an answer generation means, an explanation generation means, and an emotion engine. The emotion engine recognizes the user's emotions and adjusts the difficulty of the questions and the level of detail of the explanations based on the emotions. Specifically, if it is recognized that the user is feeling stressed, it lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if it is recognized that the user is bored, it increases the difficulty of the questions or makes the explanations more concise. This can improve the user's learning efficiency and satisfaction.

[1422] The process flow of each embodiment will be described below.

[1423] "Example 1"

[1424] Step 1: A user logs into the system. At this point, the emotion engine initializes the user's emotional state.

[1425] Step 2: The system generates problems and presents them to the user. The difficulty of the problems is adjusted based on the user's emotional state by the emotion engine.

[1426] Step 3: The user works through the problem and enters their answer.

[1427] Step 4: The system evaluates the user's answer and determines whether it is correct or incorrect.

[1428] Step 5: The system generates a commentary and presents it to the user. The detail of the commentary is adjusted by the emotion engine based on the user's emotional state.

[1429] Step 6: The emotion engine updates the user's emotional state based on the user's answer, the explanations they have read, etc.

[1430] Step 7: Go back to step 2, except that the process ends when the user logs out of the system or if there is no activity for a certain period of time.

[1431] Example 1

[1432] Next, a description will be given of Example 1 of the embodiment 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".

[1433] Conventional office automation (OA) training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, they could not flexibly respond to the user's emotions and learning situation, which could lead to a decrease in learning efficiency and satisfaction.

[1434] 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.

[1435] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, a question difficulty adjusting means, and an explanation detail adjusting means, which allows the user to efficiently proceed with self-study and further enables flexible response according to the user's emotion and learning situation.

[1436] The "question generation means" is a function that automatically generates questions for the user to study.

[1437] The "answer generating means" is a function that provides a correct answer to a generated question.

[1438] The "explanation generating means" is a function that provides a detailed explanation for the generated answer.

[1439] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[1440] The "problem difficulty adjustment means" is a function for adjusting the difficulty of questions according to the user's emotions and learning situation.

[1441] The "means for adjusting the level of detail of explanation" is a function for adjusting the level of detail of the explanation according to the user's emotions and learning situation.

[1442] "Spreadsheet software" is software for organizing and tallying formulas and data.

[1443] "Office automation" is a general term for technologies and systems that improve the efficiency of office work.

[1444] The present invention relates to an office automation (OA) training system, which is a system including a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, a question difficulty adjusting means, and an explanation detail level adjusting means.

[1445] System Configuration

[1446] Hardware and Software

[1447] The server stores and executes programs for executing the problem generation means, answer generation means, explanation generation means, emotion recognition means, problem difficulty adjustment means, and explanation detail adjustment means. These means are realized using a generative AI model. Specific software used is spreadsheet software (e.g., Excel, Spreadsheet).

[1448] The terminal provides an interface for the user to access the system and answer questions, sends the user's input to the server, and displays the responses from the server.

[1449] Program Processing

[1450] Problem generation means

[1451] Based on the topic selected by the user, the server generates questions related to spreadsheet formulas and simple automation, such as "Explain how to use the VLOOKUP function in Excel to find a specific value."

[1452] Answer generation means

[1453] The server provides the correct answer to the generated problem. For example, for a VLOOKUP function problem, the server generates the answer "=VLOOKUP(search value, range, column number, search method)".

[1454] Explanation generation method

[1455] The server provides detailed explanations for the answers. For example, for the answer of the VLOOKUP function, it generates the explanation "The VLOOKUP function searches for a specific value within a specified range and returns the value of another column that corresponds to that value. The usage is as follows: =VLOOKUP(search value, range, column number, search method)".

[1456] emotion recognition means

[1457] The server uses an emotion engine to recognize the user's emotions. For example, if the server recognizes that the user is stressed, it will lower the difficulty of the next question or make the explanation more detailed. Conversely, if the server recognizes that the user is bored, it will increase the difficulty of the question or make the explanation more concise.

[1458] Problem difficulty adjustment method

[1459] The server adjusts the difficulty of the next problem according to the user's emotions and learning situation. For example, if the user is feeling stressed, it provides an easy problem using basic functions.

[1460] Explanation detail adjustment method

[1461] The server adjusts the level of detail of the explanation according to the user's emotions and learning situation. For example, if the user is feeling stressed, it provides a detailed step-by-step explanation.

[1462] Examples

[1463] Let's say a user wants to learn "Excel's IF function." The specific steps are as follows:

[1464] 1. A user logs into the system.

[1465] 2. The user selects "Excel IF function."

[1466] 3. The server generates the question, "Explain how to use Excel's IF function to display 'Pass' if the value of cell A1 is 50 or greater, and 'Fail' otherwise."

[1467] 4. Present the server-generated problem to the user.

[1468] 5. The user enters the answer "=IF(A1>=50, 'Pass', 'Fail')".

[1469] 6. The server evaluates the user's answer and determines it to be correct.

[1470] 7. The server generates the next problem and presents it to the user.

[1471] 8. The server recognizes the user's emotions and adjusts the difficulty of the next question.

[1472] 9. The user addresses the next problem.

[1473] Examples of prompt statements

[1474] Please explain how to use the IF function in Excel to display 'Pass' if the value of cell A1 is 50 or greater, and 'Fail' otherwise.

[1475] In this way, the user can efficiently progress with his / her studies.

[1476] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1477] Step 1:

[1478] A user logs into the system.

[1479] A user accesses the system using a terminal and enters a user ID and password on the login screen. The server receives the entered information and authenticates it by checking it against a database. If authentication is successful, the user can log in to the system.

[1480] Input: User ID, Password

[1481] Output: Authentication result (success / failure)

[1482] Step 2:

[1483] The user selects the topic they want to learn about.

[1484] The user selects the topic they want to learn from a list of topics displayed on the terminal screen. The server receives the selected topic information and proceeds to the next step.

[1485] Input: Topic selection information

[1486] Output: Selected topic information

[1487] Step 3:

[1488] The server generates questions based on the selected topic.

[1489] The server uses a generative AI model to generate questions based on the selected topic information, such as "Explain how to use the VLOOKUP function in Excel to find a specific value."

[1490] Input: Selected topic information

[1491] Output: Generated problem

[1492] Step 4:

[1493] Present the server-generated questions to the user.

[1494] The server sends the generated questions to the terminal and displays them on the user's screen. The user checks the questions.

[1495] Input: Generated problem

[1496] Output: The problem as seen by the user

[1497] Step 5:

[1498] The user answers the question.

[1499] The user uses the terminal to input the answer to the problem, for example, "=VLOOKUP(search value, range, column number, search method)". The terminal sends the input answer to the server.

[1500] Input: User's answer

[1501] Output: Answer sent to the server

[1502] Step 6:

[1503] The server evaluates the user's answers and determines whether they are correct or incorrect.

[1504] The server evaluates the answers it receives to determine whether they are correct or incorrect, for example by checking whether they have correct syntax and meet specified conditions.

[1505] Input: User's answer

[1506] Output: Evaluation result (correct / incorrect)

[1507] Step 7:

[1508] If the answer is correct, the server presents the next question, and if the answer is incorrect, it provides the answer and an explanation.

[1509] If the user's answer is correct, the server generates the next question and presents it to the user. If the answer is incorrect, the server generates the correct answer and its explanation and provides it to the user. For example, the server may provide an explanation such as, "The VLOOKUP function searches for a specific value within a specified range and returns the value of another column that corresponds to that value."

[1510] Input: Evaluation result

[1511] Output: Next question or answer and explanation

[1512] Step 8:

[1513] The server recognizes the user's emotions and adjusts the difficulty of the next question and the level of detail of the explanation.

[1514] The server uses an emotion engine to recognize the user's emotions. For example, if the server recognizes that the user is stressed, it will lower the difficulty of the next question or make the explanation more detailed. Conversely, if the server recognizes that the user is bored, it will increase the difficulty of the question or make the explanation more concise.

[1515] Input: User emotion data

[1516] Output: Adjusted difficulty of questions and level of explanation

[1517] Step 9:

[1518] The user is faced with the following problem:

[1519] The user uses the device to solve the next problem, and the server repeats the process to help the user learn.

[1520] Input: Adjusted problem

[1521] Output: User's answer

[1522] (Application example 1)

[1523] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1524] Conventional OA training systems do not adjust the difficulty of questions or the level of detail of explanations according to the user's emotions, which can lead to low learning efficiency and satisfaction. In addition, there was a problem with the difficulty of generating appropriate questions and providing answers in training on data management and automation processes within factories. This could delay the improvement of workers' skills.

[1525] 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.

[1526] In this invention, the server includes a question generation means, an answer generation means, an explanation generation means, an emotion recognition means, and a means for adjusting the difficulty of the questions and the level of detail of the explanations based on the emotion. This makes it possible to provide appropriate questions and explanations according to the emotion of the user, thereby improving learning efficiency and satisfaction. In addition, appropriate questions can be generated and answers can be provided in data management and automation process training within a factory, which can promote the improvement of worker skills.

[1527] The "question generation means" is a function that automatically generates questions for the user to study.

[1528] The "answer generating means" is a function that provides an accurate answer to a generated question.

[1529] The "explanation generating means" is a function that provides detailed explanations for answers, making it easier for users to understand.

[1530] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[1531] "Means for adjusting the difficulty of questions and the level of detail of explanations based on emotions" refers to a function for raising or lowering the difficulty of questions and adjusting the level of detail of explanations according to the user's emotions.

[1532] "Spreadsheet software" refers to software for organizing and calculating data, and includes Excel and Spreadsheet.

[1533] "Office automation-related questions" are questions about automation and efficiency related to office work.

[1534] The system for carrying out the present invention includes a question generating means, an answer generating means, an explanation generating means, an emotion recognizing means, and a means for adjusting the difficulty of the question and the level of detail of the explanation based on the emotion. Specific embodiments will be described below.

[1535] System Configuration

[1536] Hardware

[1537] Server: Responsible for data processing and storage.

[1538] Terminal: A device that is directly operated by a user, such as a factory robot, PC, or smartphone.

[1539] Emotion Recognition Device: A device, such as a camera or microphone, that is used to recognize a user's emotions.

[1540] software

[1541] Python: A programming language used to implement the program.

[1542] OpenAI API: An API used for emotion recognition and natural language processing.

[1543] Data processing and calculation

[1544] Problem generation

[1545] The server generates questions related to spreadsheet formulas and simple automation, such as how to use the VLOOKUP function for inventory management or how to create a macro to automate product production schedules.

[1546] Answer generation

[1547] The server provides precise solutions to the generated questions, including specific instructions for using the VLOOKUP function and IF functions.

[1548] Description Generation

[1549] The server provides detailed explanations for the solutions, including explanations of each argument in the VLOOKUP function and details on the condition settings in the IF function.

[1550] emotion recognition

[1551] The emotion recognition device analyzes the user's facial expressions and tone of voice to recognize their emotions, and can determine whether they are stressed or bored.

[1552] Emotion-Based Adjustments

[1553] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of emotion recognition. For example, if the user is stressed, the server lowers the difficulty of the questions and provides more detailed explanations. Conversely, if the user is bored, the server raises the difficulty of the questions and provides more concise explanations.

[1554] Examples

[1555] Example problem

[1556] "Please explain how to use the VLOOKUP function to get the price of a specific product from an inventory table."

[1557] Example answer

[1558] Use the VLOOKUP function to search for a specific value in a range you specify and return the corresponding value.

[1559] Example of commentary

[1560] "The VLOOKUP function takes four arguments: the lookup value, the range, the column number, and the lookup method."

[1561] Examples of prompt statements

[1562] "Enter the user's emotion (e.g. stress, boredom, neutral): stress"

[1563] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. In addition, it is possible to generate appropriate questions and provide answers for training on data management and automation processes in factories, promoting the improvement of worker skills.

[1564] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1565] Step 1:

[1566] A user logs into the system using a terminal. The user's authentication information is entered and verified by the server. If authentication is successful, the server sends the user's learning history and current progress to the terminal.

[1567] Step 2:

[1568] The user inputs a command to start learning. The terminal sends this command to the server. The server prepares data for generating appropriate questions based on the user's learning history and progress.

[1569] Step 3:

[1570] The server uses the problem generation means to generate problems related to spreadsheet software formulas and simple automation, such as how to use the VLOOKUP function for inventory management and how to create a macro to automate product production schedules. The generated problems are sent to the terminal.

[1571] Step 4:

[1572] The terminal displays the generated questions to the user. The user answers the questions and inputs the answers into the terminal. The terminal transmits the input answers to the server.

[1573] Step 5:

[1574] The server uses the answer generation means to evaluate the user's answer and generate an accurate answer, which is then transmitted to the terminal.

[1575] Step 6:

[1576] The device displays the generated answer to the user, who can then review the answer and retry if necessary.

[1577] Step 7:

[1578] The server uses the explanation generation means to generate a detailed explanation for the answer, including, for example, an explanation of each argument of the VLOOKUP function, details of the condition settings of the IF function, etc. The generated explanation is sent to the terminal.

[1579] Step 8:

[1580] The terminal displays the generated explanation to the user, who can then check the explanation and deepen his or her understanding.

[1581] Step 9:

[1582] The emotion recognition device analyzes the user's facial expressions and tone of voice to recognize emotions, and the recognized emotions are transmitted to the server via the device.

[1583] Step 10:

[1584] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of emotion recognition. For example, if the user is stressed, the difficulty of the questions is lowered and the explanations are made more detailed. Conversely, if the user is bored, the difficulty of the questions is increased and the explanations are made brief. The adjusted questions and explanations are sent to the terminal.

[1585] Step 11:

[1586] The device will then display the adjusted problem and explanation to the user, who can then retry the problem and continue learning.

[1587] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. In addition, it is possible to generate appropriate questions and provide answers for training on data management and automation processes in factories, promoting the improvement of worker skills.

[1588] Example 2

[1589] Next, a second embodiment of the second form will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal".

[1590] Conventional office automation (OA) training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own, which was time-consuming. In addition, the learning content was not adjusted according to the user's emotions, which could lead to a decrease in learning efficiency and satisfaction. Furthermore, the system lacked the functionality to provide appropriate answers and explanations for specific questions asked in everyday work.

[1591] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1592] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, an emotion recognition means, and a difficulty level adjusting means. This allows the user to efficiently proceed with self-study, and the learning content is adjusted according to the user's emotion, improving learning efficiency and satisfaction. In addition, it is possible to provide appropriate answers and explanations for specific questions in everyday work.

[1593] The "question generation means" is a function that automatically generates questions for the user to study.

[1594] The "answer generating means" is a function that automatically generates a correct answer to a generated question.

[1595] The "explanation generating means" is a function that automatically generates a detailed explanation for the generated answer.

[1596] An "emotion recognition means" is a function that recognizes the user's emotions and adjusts the system's operation based on those emotions.

[1597] The "difficulty level adjustment means" is a function that adjusts the difficulty level of the questions and the level of detail of the explanations according to the user's emotions and learning situation.

[1598] "Spreadsheet software" is software for entering numerical data, performing calculations, analysis, creating graphs, etc.

[1599] "Office automation" is a general term for technologies and systems that make office work more efficient.

[1600] The present invention relates to an office automation (OA) training system that allows users to efficiently advance self-study. The system includes a question generating means, an answer generating means, an explanation generating means, an emotion recognition means, and a difficulty level adjusting means.

[1601] System Configuration

[1602] Hardware and Software

[1603] The server is equipped with hardware and software for executing the problem generation means, the answer generation means, the explanation generation means, the emotion recognition means, and the difficulty level adjustment means. Specifically, the server generates problems, answers, and explanations using a generative AI model. In addition, as the emotion recognition means, it uses emotion analysis software to recognize the user's emotions.

[1604] The terminal is a device that allows users to access the system and display questions, answers, and explanations. The terminal can be any common device such as a PC, tablet, or smartphone.

[1605] System Operation

[1606] Problem generation means

[1607] The server generates questions based on what the user wants to learn. For example, if a user says they want to learn about Excel's VLOOKUP function, the server uses the generative AI model to generate a question like, "Explain how to use Excel's VLOOKUP function to find the corresponding value in column B based on the data in column A."

[1608] Answer generation means

[1609] The server generates an answer to the generated problem. For example, the answer to the above problem is "=VLOOKUP(A2, B:C, 2, FALSE)".

[1610] Explanation generation method

[1611] The server generates a detailed explanation for the generated answer, for example, "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches the value in cell A2 in columns B to C and returns the corresponding value in column C."

[1612] emotion recognition means

[1613] The server uses emotion recognition means to recognize the emotion of the user, for example to determine whether the user is stressed or bored.

[1614] Difficulty adjustment means

[1615] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of the emotion recognition means. For example, if the user is stressed, the server lowers the difficulty of the questions or makes the explanations more detailed. Conversely, if the user is bored, the server raises the difficulty of the questions or makes the explanations more concise.

[1616] Examples

[1617] Users choose what to study

[1618] The user types "I want to learn how to use the VLOOKUP function" into the input field on the device.

[1619] Server Generates Problems

[1620] The server uses a generative AI model to generate a question such as, "Explain how to use Excel's VLOOKUP function to find the corresponding value in column B based on the data in column A."

[1621] The server generates the answer

[1622] The server generates the answer to the problem: "=VLOOKUP(A2, B:C, 2, FALSE)".

[1623] The server generates the description

[1624] In response to the answer, the server generates an explanation: "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches for the value in cell A2 in the range from columns B to C, and returns the corresponding value in column C."

[1625] The server recognizes the user's emotion using an emotion recognition means.

[1626] The server uses the emotion recognition means to recognize that the user is feeling stressed.

[1627] The server adjusts the difficulty of the questions and the level of detail of the explanations.

[1628] The server lowers the difficulty of the question and changes it to a simpler question: "How can I use Excel's VLOOKUP function to find data in column A from column B?"

[1629] Examples of prompt statements

[1630] "Please tell me how to use the VLOOKUP function in Excel. Please also give me some concrete examples and explanations."

[1631] In this way, the user can efficiently advance self-study.

[1632] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1633] Step 1:

[1634] Users choose what to study

[1635] The user inputs the content they want to learn into the input field of the terminal. For example, they input "I want to learn how to use the VLOOKUP function." The input content is sent to the server. The input data is text data "I want to learn how to use the VLOOKUP function." The server receives this input data and proceeds to the next processing step.

[1636] Step 2:

[1637] Server Generates Problems

[1638] The server generates questions using a generative AI model based on input data received from the user. For example, it generates a question such as "Explain how to use Excel's VLOOKUP function to search for the corresponding value in column B based on the data in column A." The input data is the text data "I want to learn how to use the VLOOKUP function," and the output data is the text data of the generated question.

[1639] Step 3:

[1640] The server generates the answer

[1641] The server generates an answer to the generated problem. For example, the server generates an answer to the problem, such as "=VLOOKUP(A2, B:C, 2, FALSE)". The input data is the text data of the generated problem, and the output data is the text data of the generated answer.

[1642] Step 4:

[1643] The server generates the description

[1644] The server generates a detailed explanation for the generated answer. For example, it generates an explanation like "The VLOOKUP function searches for a search value within a specified range and returns a value from a specified column in that row. Here, it searches for the value in cell A2 in the range from column B to column C, and returns the corresponding value in column C." The input data is the text data of the generated answer, and the output data is the text data of the generated explanation.

[1645] Step 5:

[1646] The server recognizes the user's emotion using an emotion recognition means.

[1647] The server recognizes the user's emotions using emotion recognition means, for example, determining whether the user is stressed or bored. The input data is emotion-related data such as the user's facial expression and input speed, and the output data is data indicating the user's emotional state.

[1648] Step 6:

[1649] The server adjusts the difficulty of the questions and the level of detail of the explanations.

[1650] The server adjusts the difficulty of the questions and the level of detail of the explanations based on the results of the emotion recognition means. For example, if the user is stressed, the difficulty of the questions is lowered or the explanations are made more detailed. Conversely, if the user is bored, the difficulty of the questions is increased or the explanations are made more concise. The input data is data indicating the user's emotional state, and the output data is text data of the adjusted questions and explanations.

[1651] Step 7:

[1652] The device displays the questions, answers, and explanations to the user.

[1653] The terminal displays the questions, answers, and explanations received from the server to the user, who can then proceed with his or her studies. The input data is the adjusted text data of the questions, answers, and explanations, and the output data is the information displayed on the terminal.

[1654] (Application example 2)

[1655] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server", and the headset type terminal 314 will be referred to as a "terminal".

[1656] Conventional OA training systems did not adjust the difficulty of questions or the level of detail of explanations according to the user's emotions, which led to problems with low learning efficiency and satisfaction. In addition, there was a lack of means to provide appropriate OA training to employees working in factories. This could lead to delayed improvement of employees' skills and reduced productivity.

[1657] 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.

[1658] In this invention, the server includes a question generation means, an answer generation means, an explanation generation means, an emotion recognition means, a question difficulty adjustment means, and an explanation detail adjustment means. This makes it possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. It also makes it possible to provide effective OA training to employees working in factories.

[1659] A "problem generation means" is a means for generating problems for a user, such as problems related to spreadsheet software formulas or simple automation.

[1660] An "answer generating means" is a means for providing an answer to a generated question.

[1661] The "explanation generating means" is a means for generating a detailed explanation for a provided answer.

[1662] An "emotion recognition means" is a means for recognizing a user's emotions, and determines emotions from the user's facial expressions and voice using a camera and emotion recognition software.

[1663] The "means for adjusting the difficulty of questions" refers to a means for adjusting the difficulty of questions based on the recognized user's emotions.

[1664] The "means for adjusting the level of detail of explanation" is a means for adjusting the level of detail of the explanation to be provided based on the recognized user's feelings.

[1665] A system for implementing this invention includes a robot for teaching factory workers how to use Excel and spreadsheets. The robot recognizes the emotions of the workers, asks them questions of appropriate difficulty, and provides answers and explanations.

[1666] Hardware and Software Used

[1667] Hardware: Factory robots, cameras (for emotion recognition)

[1668] Software: EmotionRecognizer (emotion recognition library), Python

[1669] System processing explanation

[1670] emotion recognition

[1671] The robot uses a camera to capture a picture of the employee's face and recognizes emotions using the EmotionRecognizer library, which determines emotions from the user's facial expressions and voice to identify states such as stress or boredom.

[1672] Problem generation

[1673] Based on the emotion data obtained by the emotion recognition means, the problem difficulty adjustment means selects problems of appropriate difficulty. For example, if an employee is stressed, it generates easy problems, and if an employee is bored, it generates difficult problems.

[1674] Providing answers and explanations

[1675] The answer generating means provides an answer to the question generated by the question generating means. Furthermore, the explanation generating means generates a detailed explanation and provides it to the employee. The explanation detail adjusting means adjusts the detail of the explanation based on the emotion data.

[1676] Examples

[1677] If your employees are stressed:

[1678] The robot asks a simple question: "Please explain how to use the VLOOKUP function," and then provides a detailed explanation.

[1679] If your employees are bored:

[1680] The robot asks a difficult question: "Please explain how to use the IF function," and provides a concise explanation.

[1681] Examples of prompt statements

[1682] "If employees are feeling stressed, give them some easy questions and provide detailed explanations."

[1683] "If employees are bored, give them challenging questions and provide concise commentary."

[1684] In this way, it is possible to provide appropriate questions and explanations according to the user's emotions, improving learning efficiency and satisfaction. It is also possible to provide effective OA training to employees working in factories.

[1685] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1686] Step 1:

[1687] The server uses a camera to take a picture of the user's face and recognizes emotions using the EmotionRecognizer library. The input is the user's face image, and the output is the user's emotion data (e.g., stress, boredom, etc.). In concrete terms, the camera captures the user's face and sends the image data to EmotionRecognizer to analyze the emotions.

[1688] Step 2:

[1689] The server selects a problem of appropriate difficulty using the problem difficulty adjustment means based on the emotion data obtained by the emotion recognition means. The input is the emotion data, and the output is the selected problem. In concrete terms, if the emotion data is recognized as "stress," the server selects an easy problem, and if it is recognized as "boredom," the server selects a difficult problem.

[1690] Step 3:

[1691] The server generates the selected problem using the problem generation means. The input is the selected problem type (e.g., how to use the VLOOKUP function), and the output is a specific problem statement. As a specific operation, the server retrieves the corresponding problem from the problem database and presents it to the user.

[1692] Step 4:

[1693] The server provides answers to questions generated using the answer generation means. The input is the generated question text, and the output is the answer to the question. In concrete terms, the server retrieves the corresponding answer from the question database and presents it to the user.

[1694] Step 5:

[1695] The server uses an explanation generating means to generate a detailed explanation for the provided answer. The input is the answer to the problem, and the output is an explanation for the answer. In specific operations, the server retrieves the corresponding explanation from the explanation database and presents it to the user.

[1696] Step 6:

[1697] The server adjusts the level of detail of the commentary based on the emotion data using the explanation detail adjustment means. The input is the emotion data and the answer explanation, and the output is the adjusted explanation. In specific operations, if the emotion data is recognized as "stress", the server provides a detailed explanation, and if the emotion data is recognized as "boredom", the server provides a concise explanation.

[1698] Step 7:

[1699] The server provides the user with the tailored explanation to support the user's learning. The input is the tailored explanation, and the output is the user's improved understanding. In concrete terms, the server displays the tailored explanation on the user's screen, encouraging the user to read and understand the explanation.

[1700] 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 voice indicating a user input for 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.

[1701] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1702] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1703] 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.

[1704] [Fourth embodiment]

[1705] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1706] 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.

[1707] 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 wide area network (WAN) and / or a local area network (LAN).

[1708] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1709] 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 the voice according to instructions from the processor 46.

[1710] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1711] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1712] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[1713] Fig. 8 shows an example of 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.

[1714] 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.

[1715] 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.

[1716] In the robot 414, 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.

[1717] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1718] "Example 1"

[1719] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[1720] "Example 2"

[1721] The OA training system of the present invention includes a problem generating means, an answer generating means, and an explanation generating means. The problem generating means generates problems related to formulas in Excel or spreadsheets, simple automation, etc. For example, it generates problems related to how to use Excel's VLOOKUP function or IF function, and problems related to data organization and aggregation in spreadsheets. The answer generating means provides answers to the generated problems. The explanation generating means provides explanations for the answers. This allows users to save the trouble of creating their own problems and searching for answers and explanations when self-studying. It also has a function for responding to OA-related questions in everyday work. For example, it provides answers and explanations for specific questions, such as how to use a specific Excel function or how to resolve an error.

[1722] The process flow of each embodiment will be described below.

[1723] "Example 1"

[1724] Step 1: The user logs into the system and selects the topic they want to learn, which can range from Excel and spreadsheet formulas to simple automation.

[1725] Step 2: Based on the selected topic, the system's problem generator will generate a problem, for example, a problem about how to use the VLOOKUP function in Excel.

[1726] Step 3: The generated question is presented to the user, who enters an answer.

[1727] Step 4: After the user submits the answer, the system's answer generation means provides the correct answer. Step 5: The system's explanation generation means provides an explanation for the answer. This allows users to save time and effort in creating questions and searching for answers and explanations when self-studying.

[1728] Step 6: When users input OA-related questions from their daily work into the system, the system will provide answers and explanations for those questions, such as how to use a specific function in Excel or how to resolve an error.

[1729] Example 1

[1730] Next, a description will be given of Example 1 of the embodiment 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".

[1731] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to respond quickly and accurately to specific questions related to clerical work in daily work.

[1732] 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.

[1733] In this invention, the server includes: a prompt sentence for instructing to generate a question sentence related to the question about how to use the spreadsheet software based on a question about how to use the spreadsheet software input by a user; a means for generating a question sentence related to the question about how to use the spreadsheet software using a generative AI; a prompt sentence for instructing to generate an answer to the generated question sentence; a means for generating an answer to the generated question sentence using the generative AI; a prompt sentence for instructing to generate an explanation for the generated answer; a means for generating an explanation for the generated answer using the generative AI; a means for presenting the generated question sentence to the user; a means for recognizing the user's emotion using an emotion engine; a prompt sentence for instructing to adjust the generated answer or explanation sentence based on the recognized emotion of the user; a means for adjusting the generated answer or explanation sentence using the generative AI; and a means for presenting the adjusted answer or explanation sentence to the user. This allows the user to efficiently self-study. The questions about how to use the spreadsheet software include questions about formulas used in the spreadsheet software or questions about automation. The questions about how to use the spreadsheet software include questions about how to use the spreadsheet software that are necessary for the user's office work, so that questions related to office work in everyday work can be quickly and accurately responded to.

[1734] The "question generation means" is a means for generating questions such as those related to formulas in a spreadsheet or simple automation based on a prompt sentence from a user.

[1735] The "answer generating means" is a means for generating an optimal answer to a generated question.

[1736] The "explanation generating means" is a means for generating a detailed explanation for the generated answer.

[1737] The "means for receiving a prompt sentence" refers to a means for receiving a specific question or request from the user in text form.

[1738] "Generative AI" is an artificial intelligence model that uses natural language processing technology to generate questions, answers, and explanations.

[1739] "Means for saving in a database" refers to means for saving the generated questions, answers, and explanations in a database.

[1740] "Spreadsheet software" is software for organizing, calculating, and analyzing data, and can process data using formulas and functions.

[1741] "Questions related to office work" are specific questions about how to use spreadsheet software and how to resolve errors that arise in daily work.

[1742] This invention is a system that allows users to efficiently self-learn and quickly and accurately respond to questions related to clerical work in their daily work. This system operates in cooperation with a server, a terminal, and a user.

[1743] Server Roles

[1744] The server manages and operates the entire system using the following means:

[1745] 1. Problem generation means

[1746] The server receives a question input by a user about how to use spreadsheet software. For example, the server receives a question sentence such as "Please tell me how to use the VLOOKUP function in Excel." The server generates a question sentence related to the question about how to use the spreadsheet software using a prompt sentence instructing the server to generate a question sentence related to the question and a generative AI (e.g., GPT-4 (registered trademark)). The generated question sentence is in the form of "Explain how to use the VLOOKUP function in Excel to get data from another sheet." The generated question sentence is stored in a database.

[1747] 2. Answer generation means

[1748] The server generates an answer to the generated question. It uses a prompt that instructs the server to generate an answer to the generated question and a generative AI to generate the optimal answer to the question. For example, an answer in the format "=VLOOKUP(search value, range, column number, search method)" is generated. The generated answer is stored in the database.

[1749] 3. Explanation Generation Method

[1750] The server generates a detailed explanation for the generated answer. A prompt that instructs the server to generate an explanation for the generated answer and a generative AI are used to generate a detailed explanation for the answer. For example, an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)" are generated. The generated explanation is saved in the database.

[1751] User Roles

[1752] A user accesses the system using a terminal and performs the following operations:

[1753] 1. Enter your question

[1754] A user uses the terminal to type in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[1755] 2. Obtaining questions

[1756] The user obtains the generated question text from the server and checks the question text on the terminal screen.

[1757] 3. Get answers

[1758] The user obtains the generated answer from the server and checks the answer on the screen of the terminal.

[1759] 4. Obtaining explanations

[1760] The user receives the generated commentary from the server and checks the commentary on the screen of the terminal.

[1761] Examples

[1762] For example, if a user enters the question "How do I use the VLOOKUP function in Excel?", the server processes the question as follows:

[1763] 1. Problem generation

[1764] The server generates a question such as, "Explain how to use Excel's VLOOKUP function to retrieve data from another sheet."

[1765] 2. Answer generation

[1766] The server generates the answer "=VLOOKUP(search value, range, column number, search method)".

[1767] 3. Description Generation

[1768] The server generates an explanatory text stating, "The VLOOKUP function searches for a search value within a specified range and returns the data from the specified column number. Search methods include TRUE (approximate match) and FALSE (exact match)."

[1769] In this way, the user can efficiently proceed with self-learning and can quickly and accurately respond to questions related to clerical work in the course of daily work.

[1770] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1771] Step 1: Enter your question

[1772] Subject: User

[1773] A user accesses the system using a terminal and types in a specific question, for example, "How do I use the VLOOKUP function in Excel?"

[1774] Input: The question entered by the user

[1775] Output: The question is sent to the server.

[1776] Step 2: Receiving the question

[1777] Subject: Server

[1778] The server receives a question sent by a user.

[1779] Input: The question submitted by the user

[1780] Output: The question is ready to be processed in the server.

[1781] Step 3: Generate the problem

[1782] Subject: Server

[1783] The server uses the prompt text and generative AI to generate a question based on the question, for example, "Explain how to use the VLOOKUP function in Excel to get data from another sheet."

[1784] Input:Question

[1785] Data processing: Using prompts containing questions and generative AI, appropriate problem statements are generated.

[1786] Output: Generated problem statement

[1787] Step 4: Save the question

[1788] Subject: Server

[1789] The server stores the generated questions in a database.

[1790] Input: Generated question text

[1791] Data processing: Converting the generated questions into a database format

[1792] Output: The question is saved in the database.

[1793] Step 5: Generate the answer

[1794] Subject: Server

[1795] The server generates an answer to the generated question. It uses the prompt and generative AI to generate the optimal answer to the question. For example, it generates the answer "=VLOOKUP(search value, range, column number, search method)".

[1796] Input: Generated question text

[1797] Data processing: A generative AI model analyzes the question and generates an appropriate answer

[1798] Output: The generated answer

[1799] Step 6: Save your answers

[1800] Subject: Server

[1801] The server stores the generated answers in a database.

[1802] Input: Generated answer

[1803] Data processing: Converting the generated answers into a database format

[1804] Output: The answer is saved in the database.

[1805] Step 7: Generate a description

[1806] Subject: Server

[1807] The server generates a detailed explanation for the generated answer. It uses the prompt text and generative AI to generate a detailed explanation for the answer. For example, it generates an explanation such as "The VLOOKUP function searches for a search value within a specified range and returns the data of the specified column number. There are two search methods: TRUE (approximate match) and FALSE (exact match)."

[1808] Input: Generated answer

[1809] Data processing: A generative AI model analyzes the answers and generates appropriate explanations

[1810] Output: Generated description

[1811] Step 8: Save your commentary

[1812] Subject: Server

[1813] The server stores the generated commentary in a database.

[1814] Input: Generated description

[1815] Data processing: Convert the generated explanatory text into a database format.

[1816] Output: The explanatory text is saved in the database.

[1817] Step 9: Get the problem statement

[1818] Subject: User

[1819] The user uses a terminal to obtain the generated question text from the server and checks the question on the terminal screen.

[1820] Input: User request

[1821] Output: The generated question is displayed on the terminal.

[1822] Step 10: Getting the answer

[1823] Subject: User

[1824] The user uses the terminal to retrieve the generated answer from the server and check the answer on the terminal screen.

[1825] Input: User request

[1826] Output: The generated answer is displayed on the terminal.

[1827] Step 11: Get the description

[1828] Subject: User

[1829] The user uses the terminal to obtain the generated commentary from the server, and checks the commentary on the screen of the terminal.

[1830] Input: User request

[1831] Output: The generated commentary is displayed on the terminal. In this embodiment, when presenting a question sentence to a user, the server recognizes the user's emotion using an emotion engine, which will be described later. The server then adjusts the generated answer or commentary using a prompt sentence that instructs the user to adjust the generated answer or commentary based on the recognized user's emotion and the generative AI. The server then presents the adjusted answer or commentary to the user. This allows the difficulty of the answer or commentary to be adjusted in consideration of the user's emotion when the question sentence is presented.

[1832] (Application example 1)

[1833] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1834] Conventional OA training systems were limited to providing questions related to Excel and spreadsheet formulas and simple automation, and did not address training related to the operation and maintenance of machines used in factories. This made it difficult to efficiently acquire knowledge related to the operation and maintenance of machines in factories. In addition, while the system had functions to answer OA-related questions in everyday work, it lacked functions to answer specific questions about the operation and maintenance of machines used in factories.

[1835] 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. In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a means for generating questions related to the operation and maintenance of machines used in a factory, a means for providing answers to the generated questions, and a means for providing explanations of the answers. This makes it possible to efficiently acquire knowledge related to the operation and maintenance of machines used in a factory.

[1836] The "problem generation means" is a means for generating problems related to Excel or spreadsheet formulas, simple automation, and the operation and maintenance of machines used in factories.

[1837] An "answer generating means" is a means for providing an answer to a generated question.

[1838] The "explanation generating means" is a means for providing an explanation for a generated answer.

[1839] "Machinery used in a factory" refers to various types of machinery and equipment used for production and maintenance within a factory.

[1840] "Operation" refers to the specific steps or methods for making a machine work.

[1841] "Maintenance" refers to the inspection and repair procedures to keep a machine in good working order.

[1842] The term "system" refers to a collection of a series of devices and programs including a problem generating means, an answer generating means, an explanation generating means, and a means for generating problems relating to the operation and maintenance of machines used in a factory.

[1843] A system for implementing the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems relating to the operation and maintenance of machines used in a factory, a means for providing answers to the generated problems, and a means for providing explanations for the answers.

[1844] The server implements a problem generation means, an answer generation means, and an explanation generation means using a programming language such as Python. Specifically, the problem generation means generates problems related to formulas in Excel or spreadsheets, simple automation, and the operation and maintenance of machines used in factories. For example, it generates a prompt sentence such as "Please write the code to program the operation of a robot."

[1845] The answer generation means provides an answer to the generated problem. For example, it generates a specific answer such as "Example: move_forward(10);". The explanation generation means provides an explanation for the generated answer. For example, it generates an explanation such as "This code moves the robot forward 10 meters".

[1846] Users can use this system to efficiently acquire knowledge about the operation and maintenance of machines used in factories. When a user accesses the system, the server generates questions and provides answers and explanations. This allows users to save time when self-studying by creating questions themselves and searching for answers and explanations.

[1847] As a concrete example, the following prompt sentence can be input to a generative AI model:

[1848] Example prompt:

[1849] "Write the code to program the robot's movements."

[1850] In response to this prompt, the generative AI model provides the following answer and explanation:

[1851] Example answer:

[1852] "Example: move_forward(10);"

[1853] Example of explanation:

[1854] "This code will move the robot forward 10 meters."

[1855] In this way, training on the operation and maintenance of machines used in the factory can be carried out efficiently.

[1856] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1857] Step 1:

[1858] The server receives requests from users. Users access the system and send requests to generate problems related to the operation and maintenance of machines used in the factory. The input is the user's request, and the output is the analysis result of the request.

[1859] Step 2:

[1860] The server uses a problem generation means to generate a problem based on the request content. For example, it generates a prompt such as "Please write a code to program the robot's movements." The input is the analysis result of the request content, and the output is the generated problem.

[1861] Step 3:

[1862] The server uses the answer generation means to generate an answer to the generated question. For example, it generates a specific answer such as "Example: move_forward(10);". The input is the generated question, and the output is the generated answer.

[1863] Step 4:

[1864] The server uses an explanation generation means to generate an explanation for the generated answer. For example, the server generates an explanation such as "This code will move the robot forward 10 meters." The input is the generated answer, and the output is the generated explanation.

[1865] Step 5:

[1866] The server provides the generated questions, answers, and explanations to the user. The user uses this information for self-study. The input is the generated questions, answers, and explanations, and the output is the results provided to the user.

[1867] Step 6:

[1868] The user checks the provided questions, answers, and explanations, and submits a request again if necessary. The input is the result provided to the user, and the output is the user's feedback or new requests.

[1869] In this way, the server generates questions in response to user requests and provides answers and explanations, enabling users to efficiently acquire knowledge about operating and maintaining machines used in factories.

[1870] Example 2

[1871] Next, a second embodiment of the second embodiment will be described. 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".

[1872] Conventional OA training systems had the problem that users had to create their own questions and look up answers and explanations when studying on their own. In addition, it was difficult to quickly provide appropriate answers and explanations for specific questions related to office automation in everyday work.

[1873] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1874] In this invention, the server includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows the user to efficiently self-study and quickly respond to questions related to office automation in everyday work.

[1875] The "question generation means" is a function that generates questions for the user to study.

[1876] The "answer generating means" is a function that provides an accurate answer to a generated question.

[1877] The "explanation generating means" is a function that provides a detailed explanation for an answer.

[1878] A "generative AI model" is a model that uses artificial intelligence to generate questions, answers, and explanations.

[1879] The "means for providing answers and explanations to user questions" is a function for providing appropriate answers and explanations to questions posed to the system by the user.

[1880] "Spreadsheet software" refers to software such as Excel and spreadsheets that are used to organize and tally formulas and data.

[1881] "Office automation" is a general term for technologies and systems that aim to make clerical work more efficient.

[1882] The OA training system of the present invention includes a problem generating means, an answer generating means, an explanation generating means, a means for generating problems, answers, and explanations using a generative AI model, and a means for providing answers and explanations to user questions, which allows users to efficiently self-study and quickly respond to questions related to office automation in their daily work.

[1883] Hardware and Software Used

[1884] Hardware: Servers, user devices (PCs, tablets, smartphones, etc.)

[1885] Software: Spreadsheet software (Excel, Google Spreadsheet), generative AI model (e.g. GPT-3)

[1886] Specific operation of the system

[1887] 1. Problem generation

[1888] The server generates problems for the user to study. Specifically, it generates problems related to formulas in spreadsheet software, simple automation, etc.

[1889] Example: The server uses a generative AI model to generate a question by entering the prompt "Please generate a question about how to use the VLOOKUP function in Excel."

[1890] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[1891] 2. Answer generation

[1892] The server provides the answers to the generated questions, allowing the user to obtain the correct answer to the question.

[1893] Example: The server inputs a prompt to the generative AI model: "Generate an answer to the following question: Explain how to use the VLOOKUP function in Excel to search for a specific value," and generates an answer.

[1894] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[1895] 3. Description Generation

[1896] The server provides detailed explanations for the answers, allowing users to understand the context of the answer and how to use it.

[1897] Example: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model and generates an explanation.

[1898] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[1899] 4. Support for user self-learning

[1900] Users can study on their own without having to create their own questions or look up answers and explanations. The app also has a function to answer questions related to office automation that users may encounter in their daily work.

[1901] Example: A user asks "How do I use the IF function in Excel?" and the server provides the answer and explanation to the question.

[1902] Examples of prompt statements

[1903] Question generation prompt: "Generate a question on how to use the VLOOKUP function in Excel."

[1904] Solution Generation Prompt: "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to find a specific value."

[1905] Explanation generation prompt: "Generate an explanation for the following answer: =VLOOKUP(lookup value, range, column number, FALSE)"

[1906] In this way, the OA training system assists users in self-study and also answers office automation-related questions in their work.

[1907] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1908] Step 1:

[1909] Problem generation

[1910] The server generates questions for the user to study.

[1911] Input: The server inputs the prompt "Generate a question about how to use the VLOOKUP function in Excel" to the generative AI model.

[1912] Data processing: The generative AI model generates questions based on the prompt text.

[1913] Output: The generated questions are returned to the server.

[1914] Specific behavior: The server stores the generated questions in a database and prepares them to be served to the user.

[1915] Example of a generated question: "Explain how to use the VLOOKUP function in Excel to find a specific value."

[1916] Step 2:

[1917] Answer generation

[1918] The server provides the answers to the generated questions.

[1919] Input: The server inputs the prompt text "Generate an answer to the following problem: Explain how to use the VLOOKUP function in Excel to search for a specific value" to the generative AI model.

[1920] Data processing: The generative AI model generates an answer based on the prompt.

[1921] Output: The generated answer is returned to the server.

[1922] Specific Actions: The server stores the generated answer in a database and prepares it to be served to the user.

[1923] Example of a generated answer: "=VLOOKUP(lookup value, range, column number, FALSE)"

[1924] Step 3:

[1925] Description Generation

[1926] The server provides detailed explanations for the answers.

[1927] Input: The server inputs the prompt "Generate an explanation for the following answer: =VLOOKUP(search value, range, column number, FALSE)" to the generative AI model.

[1928] Data processing: The generative AI model generates an explanation based on the prompt.

[1929] Output: The generated description is returned to the server.

[1930] Specific Actions: The server stores the generated description in a database and prepares it to be served to the user.

[1931] Example of generated explanation: "The VLOOKUP function searches for a search value within a specified range, and if found, returns the value of the specified column in the same row."

[1932] Step 4:

[1933] Supporting users' self-learning

[1934] When self-studying, users can save time by creating their own questions and searching for answers and explanations.

[1935] Input: A user uses a terminal to access the system and ask how to use a particular function or resolve an error.

[1936] Data processing: The server receives the user's question and inputs the prompt text into the generative AI model to generate an answer and explanation.

[1937] Output: The generated answer and explanation are provided to the user.

[1938] Specific operation: When a user asks a question such as "How do I use the IF function in Excel?", the server generates an answer and explanation for the question and provides it to the user.

[1939] (Application example 2)

[1940] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1941] Conventional OA training systems had the problem that users had to create questions and look up answers and explanations when self-studying. In addition, there was a lack of efficient training systems for learning data management and automation tasks in factories. This resulted in problems of reduced work efficiency and increased labor.

[1942] 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.

[1943] In this invention, the server includes a question generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn, and also enables the effective learning of data management and automation tasks in the factory.

[1944] The "problem generation means" is a means for generating problems related to formulas in spreadsheet software or simple automation.

[1945] An "answer generating means" is a means for providing an answer to a generated question.

[1946] The "explanation generating means" is a means for providing a detailed explanation for a generated answer.

[1947] "Data management means" refers to a means for efficiently managing data within a factory.

[1948] An "automation task learning means" is a means for learning an automation task in a factory.

[1949] In order to implement the present invention, the server, the terminal, and the user must cooperate to operate the system. A specific embodiment is described below.

[1950] System Programming

[1951] The server executes a program including a problem generating means, an answer generating means, an explanation generating means, a data management means, and an automation task learning means, which allows the user to efficiently self-learn and effectively learn data management and automation tasks in a factory.

[1952] Program processing explanation...

Claims

1. a means for generating a question sentence relating to the method of using the spreadsheet software, the question sentence being related to the question and related to the method of using the spreadsheet software, using a prompt sentence for instructing the user to generate a question sentence relating to the question and related to the method of using the spreadsheet software, the prompt sentence being related to the question and related to the method of using the spreadsheet software, the generative AI; A prompt sentence instructing to generate an answer to the generated question sentence and a means for generating an answer to the generated question sentence using the generation system AI; A prompt sentence instructing to generate an explanation for the generated answer and a means for generating an explanation for the generated answer using the generation system AI; means for presenting the generated question sentence to the user; means for recognizing emotions of the user using an emotion engine; A prompt sentence that instructs the user to adjust the generated answer or commentary based on the recognized emotion of the user, and a means for adjusting the generated answer or commentary using the generative AI; means for presenting the adjusted answer or explanation to the user; A system including:

2. The system of claim 1 , wherein the questions about how to use the spreadsheet software include questions about formulas used in the spreadsheet software or questions about automation.

3. 2. The system according to claim 1, wherein the questions about how to use the spreadsheet software include questions about how to use the spreadsheet software required for the user's office work.

Images