System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting information of a situation, a purpose of use, and a use item by a user; generation artificial intelligence means for analyzing the input information and generating a setting of puzzle-solving, a question, a hint, an item, and an ending; means for providing the generated contents of the puzzle-solving to the user; and means for collecting feedback of the user and adding the feedback to learning data of the generation artificial intelligence.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditionally, "puzzles" used in events to attract customers and in-house training have been popular, but creating them requires advanced knowledge and skills, making them difficult to do yourself. Furthermore, outsourcing them to an external company incurs significant costs, making them difficult to implement. This has led to a demand for a way to easily create original puzzles. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] The system includes a means for users to input information on the situation, purpose of use, and items used, a generating AI means for analyzing the input information and generating puzzle settings, questions, hints, items, and endings, a means for providing the generated puzzle content to users, and a means for collecting user feedback and adding it to the learning data of the generating AI. This allows users to easily create original puzzles, and furthermore, feedback after use can be used to improve the accuracy of the generating AI.

[0007] Furthermore, if there is a request to change part of the generated puzzle content, a means is provided to regenerate that part, allowing users to customize only specific parts.In addition, a means is provided to enable the generated puzzle content to be exported in text, image file, or video format, making it possible to use it in a variety of formats.

[0008] "User" refers to an individual or organization that uses this system to create original puzzles.

[0009] "Situation" refers to the specific situation or setting in which the puzzle is solved, including, for example, in-house training sessions and large-scale events.

[0010] "Purpose of use" refers to the purpose for which the puzzles are used, such as team building or promotion.

[0011] "Items used" refers to specific tools or means used to progress through or solve the puzzle, including smartphones, maps, QR codes (registered trademark), etc.

[0012] The "means for inputting information" refers to an input interface that allows the user to input information such as the situation, purpose of use, and items used into the system.

[0013] "Generative artificial intelligence means" refers to an artificial intelligence engine that generates puzzle settings, questions, hints, items, and endings based on information entered by the user.

[0014] The "means for providing the puzzle content" is a means for presenting the generated puzzle setting, questions, hints, items and endings to the user.

[0015] "Means for collecting feedback" refers to the means for collecting impressions and evaluations provided by users after the puzzle-solving experience.

[0016] The "means for adding to learning data" refers to the means for saving the collected feedback as learning data for the generative AI in order to improve accuracy.

[0017] The "means for regenerating" is a means for regenerating the puzzle for a specific part when a user issues a change instruction for that part.

[0018] "Means for making it exportable" refers to means for enabling the generated puzzle content to be saved or output in the form of text, image file, video, etc. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] 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.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] 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.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] 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.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[0041] User operations

[0042] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0043] Device behavior

[0044] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0045] Server Processing

[0046] When the server receives the input data, it analyzes the information and activates the generative AI engine. The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," or "Ending: An event that allows everyone to share a sense of accomplishment."

[0047] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0048] Provision to users

[0049] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[0050] Collecting feedback

[0051] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator to help improve its accuracy in the future.

[0052] Specific examples

[0053] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0054] Situation: In-house training

[0055] Purpose of use: Team building

[0056] Items used: smartphone, map, QR code

[0057] Once this information is sent to the server, the generative AI engine runs and generates an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the problem, and provides the updated problem. After the event ends, feedback is collected from participants and saved as AF learning data. This allows the accuracy of the generative AI to be improved.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] A user logs into the service and accesses an interface for creating new puzzles.

[0061] Step 2:

[0062] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[0063] Step 3:

[0064] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[0065] Step 4:

[0066] The terminal transmits the converted data to the server.

[0067] Step 5:

[0068] The server receives and analyzes the user's input data and uses that data to issue instructions to the generative AI engine.

[0069] Step 6:

[0070] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates content such as "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0071] Step 7:

[0072] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[0073] Step 8:

[0074] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[0075] Step 9:

[0076] The server transmits the generated puzzle-solving data package to the terminal.

[0077] Step 10:

[0078] The terminal receives all the data and displays it to the user.

[0079] Step 11:

[0080] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[0081] Step 12:

[0082] The server receives the change request and reparses the affected part.

[0083] Step 13:

[0084] The server's generation AI engine regenerates only the relevant parts, enabling updated content to be provided.

[0085] Step 14:

[0086] The server transmits the regenerated data to the terminal again.

[0087] Step 15:

[0088] The terminal receives the regenerated data and displays it to the user.

[0089] Step 16:

[0090] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[0091] Step 17:

[0092] The server receives the feedback and stores it as learning data for the AI, which helps improve the accuracy of the generating AI.

[0093] Example 1

[0094] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0095] Conventional puzzle creation systems require users to manually create settings, questions, hints, items, and endings, which is both time-consuming and prone to inconsistent quality. Furthermore, when changes are needed to the generated puzzle content, the correction process is cumbersome, making it difficult to respond quickly and efficiently. Furthermore, there is a lack of means to provide the generated puzzle in various formats, such as text, images, and videos, resulting in low user convenience. The present invention aims to solve these problems and provide a system that automatically generates efficient, high-quality puzzles.

[0096] 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.

[0097] In this invention, the server includes: a means for a user to input information about the situation, purpose of use, and items used; a generating AI means for analyzing the input information and generating a puzzle setting, question, hint, item, and ending; a means for converting the input information into an appropriate data format and sending it to the server; a means for providing the generated puzzle content to the user; and a means for collecting user feedback and adding it to the learning data of the generating AI. This enables a system that can automatically generate high-quality puzzles quickly and efficiently and flexibly respond to changes. Furthermore, by including a means for exporting the generated puzzles in text, image files, or video formats, user convenience can be improved.

[0098] text

[0099] "User" refers to a person or organization that uses the system to create and use puzzles.

[0100] "Situation" refers to the specific background or situation in which the puzzle is solved.

[0101] "Purpose of use" refers to the specific purpose or goal for which the puzzle is used.

[0102] "Items used" refers to the objects and tools used by the user while solving the puzzle.

[0103] "Means of input" refers to the method or mechanism by which a user inputs information about the situation, purpose of use, and items used into the system.

[0104] "Means of analysis" refers to the method or mechanism for analyzing the content and characteristics of data based on input information.

[0105] "Generative artificial intelligence means" refers to technologies such as generative AI models that automatically create puzzle settings, questions, hints, items, and endings based on analyzed information.

[0106] "Means for converting into data format" refers to the method or mechanism for converting information entered by the user into a format that is easy for the server to process.

[0107] "Means of sending to the server" refers to the method or mechanism for sending input information or generated data to the server via a network.

[0108] "Means for providing to users" refers to the method or mechanism for providing the content of the generated puzzle so that users can check, download or use it.

[0109] "Means of collecting feedback" refers to the methods and mechanisms for collecting opinions and impressions from users after using the service.

[0110] "Means of adding to training data" refers to the method or mechanism for adding collected feedback to the training data of the generative AI.

[0111] "Means for regeneration when a change request is received" refers to the method or mechanism for receiving a change request from a user and regenerating the relevant information.

[0112] "Means for making the solution exportable in text, image file, or video format" refers to a method or mechanism for saving or providing the generated solution in text, image file, or video format.

[0113] text

[0114] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[0115] User operations

[0116] First, users log in to the service and access an interface for creating new puzzles. Next, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0117] Device behavior

[0118] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0119] Server Processing

[0120] When the server receives the input data, it analyzes the information and activates a generative AI engine (e.g., GPT-3 (registered trademark)). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that gives everyone a sense of accomplishment." Each generated element is saved as an individual data object, allowing it to later accommodate partial changes from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0121] Provision to users

[0122] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[0123] Collecting feedback

[0124] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[0125] Specific examples

[0126] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0127] Situation: In-house training

[0128] Purpose of use: Team building

[0129] Items used: smartphone, map, QR code

[0130] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can submit a change request for that part. The server will accept the change request, regenerate the problem, and provide the updated problem.

[0131] After the event, feedback will be collected from participants and saved as learning data for the AI, which will improve the accuracy of the AI.

[0132] Example prompts for generative AI models

[0133] "I'd like to create a puzzle for team building to be used in our in-house training. The items to be used will be a smartphone, a map, and a QR code. I'd like specific suggestions for the puzzle, the problem, the hints, the setting, and the ending."

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] text

[0136] Step 1: User Login

[0137] A user accesses the system and enters their authentication information (such as user ID and password) into an input form. The entered authentication information is sent from the terminal to the server. The server compares the received authentication information with a database, and if authentication is successful, it redirects the user to the main interface. In this process, the input is the user's authentication information, and the output is whether the authentication was successful or not.

[0138] Step 2: Enter your information

[0139] The user accesses an interface for creating new puzzles and inputs information about the situation, purpose of use, and items used. For example, they might input "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." This information is converted into an appropriate data format (e.g., JSON format) on the device. The input is the user's information, and the output is the converted data format.

[0140] Step 3: Sending data

[0141] The terminal sends the converted information to the server, which receives the information and stores it in a database. The input is the converted data format, and the output is the successful transmission of data to the server.

[0142] Step 4: Data analysis

[0143] The server analyzes the received data and extracts information on the situation, purpose of use, and items used. For example, "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." The input is the data stored on the server, and the output is the analyzed information.

[0144] Step 5: Launching the Generative AI

[0145] The server launches a generative AI engine (for example, GPT-3) based on the analyzed information. A prompt containing the analyzed information is input to the generative AI. For example, a sample prompt is input: "I would like to create a puzzle for team building to be used in in-house training. The items to be used will be a smartphone, a map, and a QR code. Please provide specific suggestions for the puzzle question, hints, setting, and ending." The input is the analyzed information, and the output is the prompt input to the AI.

[0146] Step 6: Generate the puzzle

[0147] The generation AI generates each element of the puzzle (setting, problem, hint, item, ending) based on the input prompt. For example, it generates "Problem 1: Use a QR code to find a hidden place," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment." The input is the prompt to the AI, and the output is each generated element.

[0148] Step 7: Storing and packaging the data

[0149] The server saves each generated element as a separate data object and converts it into the user's desired format (e.g., text, image file, video, etc.) The converted data is then compiled into a data package. The input is each generated element, and the output is the data package.

[0150] Step 8: Provide to users

[0151] The server sends the final puzzle-solving data package to the user's device. The user can check the contents and download them as needed. The input is the data package, and the output is provided to the user.

[0152] Step 9: Change Requests

[0153] If the user has a change request for a specific part, they enter that information into the terminal again, convert it into JSON format, and send it to the server. The server then inputs the prompt into the generation AI again, regenerating the problem. The input is the change request, and the output is the regenerated data.

[0154] Step 10: Gather feedback

[0155] After completing the task, the user inputs feedback. The device sends the feedback to the server, which stores it as training data for the generative AI. The input is feedback, and the output is added to the training data.

[0156] (Application example 1)

[0157] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0158] Traditional in-factory education and training is often monotonous and inefficient, making it difficult to improve worker learning effectiveness and motivation. There is a need for more effective and engaging ways to communicate training content, especially to new employees and transferred employees. Another problem is the difficulty of customizing the training to meet individual needs.

[0159] 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.

[0160] In this invention, the server includes: means for a user to input information on the situation, purpose of use, and items to be used; artificial intelligence generating means for analyzing the input information and generating a setting, question, hint, item, and ending for solving the puzzle; means for providing the generated content of the puzzle to the user; means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means; and means for providing a smartphone application for implementing specialized education and training for factory workers. This makes it possible to conduct education and training in the factory interactively and effectively.

[0161] A "user" is an entity that uses the system to instruct the creation of puzzles and questions.

[0162] "Information" is data relating to the situation, purpose of use, and items used.

[0163] "Situation" is information about the scene or environment in which the puzzle is solved.

[0164] "Purpose of use" refers to the specific purpose or goal when solving the puzzle.

[0165] "Items used" is information about tools and devices used when solving puzzles.

[0166] "Generative artificial intelligence means" is a technology for automatically generating puzzle settings, questions, hints, items, and endings based on information input by the user.

[0167] "Puzzle content" is a general term for the settings, questions, hints, items, and endings of the generated puzzle.

[0168] "Feedback" refers to information provided by users regarding their evaluation of the system and areas for improvement after completing use.

[0169] A "smartphone application for providing specialized education and training for factory workers" is an application used on a specialized smartphone by factory workers to learn knowledge and skills.

[0170] This invention is a specialized education and training system for factory workers that uses generative AI to provide interactive and effective puzzle solving.

[0171] User operations

[0172] First, the user logs in to the smartphone application and accesses the interface for creating a new puzzle. There, they input information about the situation, purpose of use, and items used. For example, they can input information such as "Situation: New employee training in a factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[0173] Device behavior

[0174] When a user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to a backend server.

[0175] Server Processing

[0176] When the server receives the input data, it analyzes the information and activates a generative AI engine (e.g., OpenAI (registered trademark) GPT-3). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it generates "Question 1: Use a factory map to find a specific work area," "Hint: Check the location of a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0177] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0178] Provision to users

[0179] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can instruct the change to be made to only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle.

[0180] Collecting feedback

[0181] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[0182] Specific examples

[0183] For example, let's say a factory wants to organize an educational event using puzzles as part of new employee training. The employee logs into the system and enters the following information:

[0184] Situation: New employee training in the factory

[0185] Purpose of use: Understanding work procedures and team building

[0186] Items used: Smartphone, factory map

[0187] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server will accept the change request, regenerate the problem, and provide the updated problem. After the event, feedback from participants will be collected and saved as learning data for the generative AI. This will help improve the accuracy of the generative AI.

[0188] Prompt Sentence Examples

[0189] Situation: New employee training in the factory

[0190] Purpose of use: Understanding work procedures and team building

[0191] Items used: Smartphone, factory map

[0192] Generate a puzzle using the following information:

[0193] In this way, factory workers can acquire the necessary knowledge and skills more effectively and in a fun way.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] The user inputs information about the situation, purpose of use, and items used. This input data is collected on the smartphone application and converted into JSON format. Specific inputs include "Situation: New employee training in the factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[0197] Step 2:

[0198] The terminal receives input data, converts it to JSON format, and sends it to the server. Network communication is performed to send the input data (JSON format) to the server. The input here is JSON data received from the terminal, and an output is generated to send it to the server.

[0199] Step 3:

[0200] The server receives the JSON-formatted data, analyzes it, and generates a prompt. Here, the server analyzes the JSON data to extract information on the "situation," "purpose of use," and "items used." As a specific example, the following prompt is generated: "Situation: New employee training within the factory. Purpose of use: Understanding work procedures and team building. Items used: Smartphone, factory map. Please generate a solution to the puzzle based on the information below."

[0201] Step 4:

[0202] The server starts a generative AI engine (e.g., OpenAI GPT-3) and provides the prompt as input. The generative AI engine generates appropriate puzzle settings, questions, hints, items, and endings based on the prompt. In this step, the prompt is the input, and the generated puzzle content is the output.

[0203] Step 5:

[0204] The generated puzzles are converted into individual data objects and saved. For example, they might include a problem such as "Problem 1: Use the factory map to find a specific work area" and a hint such as "Check the location of a specific mark on the map." The output obtained through this process is saved in a database.

[0205] Step 6:

[0206] The server sends the generated puzzle-solving data package to the user's device. The user can check the contents and make changes to specific parts as needed. The sent data package is the output here. Meanwhile, the change request from the user is returned to the server as input.

[0207] Step 7:

[0208] The server that receives the change request regenerates the relevant part. It generates a prompt for regeneration and sends it to the AI ​​engine again. The regenerated puzzle content becomes the output and is sent to the user again as a data package.

[0209] Step 8:

[0210] After completing the task, the user enters feedback, which is added to the database and then used as training data for the generative AI. This feedback becomes the final input, which generates an output that contributes to improving the accuracy of the generative AI.

[0211] The above is the flow of processing of the system program that realizes this application example.

[0212] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0213] This invention is a system that uses generative AI and an emotion engine to easily create original puzzles. The emotion engine can recognize the user's emotions and provide appropriate solutions.

[0214] User operations

[0215] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0216] Device behavior

[0217] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0218] Server Processing

[0219] When the server receives the input data, it analyzes the information and activates the generative AI engine and emotion engine. The generative AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. The emotion engine analyzes the input data and user feedback and recognizes the user's emotions. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0220] Each generated element is saved as an individual data object, allowing for later partial modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package. Furthermore, the generation AI optimizes the output content based on emotional information recognized by the emotion engine.

[0221] Provision to users

[0222] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle. The emotion engine adjusts the content to reflect the user's emotions even when regenerating.

[0223] Collecting feedback

[0224] After completing the task, the user enters feedback. The server adds the collected feedback to the learning data of the generative AI to help improve its accuracy in the future. The emotion engine also analyzes the feedback and reflects it in optimizing the generative AI.

[0225] Specific examples

[0226] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0227] Situation: In-house training

[0228] Purpose of use: Team building

[0229] Items used: smartphone, map, QR code

[0230] Once this information is sent to the server, the generative AI engine is activated and generates an appropriate puzzle. The emotion engine recognizes emotions from the input data, the user's facial expressions, voice, etc., and adjusts the generated content based on that information. For example, if the user is enjoying themselves, the difficulty level will be increased, or if they are confused, the difficulty level will be lowered.

[0231] The user checks the generated puzzles, and if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the puzzle, and provides the updated problem. The emotion engine also adjusts the content to reflect the user's emotions when regenerating. After the event, feedback is collected from participants and saved as AI learning data. This improves the accuracy of the generation AI and emotion engine.

[0232] The processing flow will be explained below.

[0233] Step 1:

[0234] A user logs into the service and accesses an interface for creating new puzzles.

[0235] Step 2:

[0236] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[0237] Step 3:

[0238] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[0239] Step 4:

[0240] The terminal transmits the converted data to the server.

[0241] Step 5:

[0242] The server receives and analyzes the user's input data and uses that data to activate the generative AI engine and emotion engine.

[0243] Step 6:

[0244] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0245] Step 7:

[0246] The server's emotion engine analyzes input data and user feedback to recognize the user's emotions, such as whether the user is enjoying or confused.

[0247] Step 8:

[0248] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[0249] Step 9:

[0250] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[0251] Step 10:

[0252] The server transmits the generated puzzle-solving data package to the terminal.

[0253] Step 11:

[0254] The terminal receives all the data and displays it to the user.

[0255] Step 12:

[0256] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[0257] Step 13:

[0258] The server receives the change request and reparses the affected part.

[0259] Step 14:

[0260] The server's emotion engine analyzes the user's emotions again and provides information to reflect them when regenerating. For example, if the user's emotion is confusion, it will adjust the difficulty level accordingly.

[0261] Step 15:

[0262] The server uses a generation AI engine to regenerate only the relevant parts and provide updated content.

[0263] Step 16:

[0264] The server transmits the regenerated data to the terminal again.

[0265] Step 17:

[0266] The terminal receives the regenerated data and displays it to the user.

[0267] Step 18:

[0268] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[0269] Step 19:

[0270] The server receives the feedback and stores it as learning data for the AI, which improves the accuracy of the generative AI and emotion engine.

[0271] Example 2

[0272] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0273] Conventional puzzle generation systems have difficulty generating adaptive content that takes user emotions into account, making it difficult to increase user engagement and satisfaction. In addition, there are limited ways to effectively utilize feedback on the generated content and improve the accuracy of the system.

[0274] 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.

[0275] In this invention, the server includes: means for the user to input information on the situation, purpose of use, and items used; artificial intelligence generating means for analyzing the input information and generating puzzle settings, questions, hints, items, and endings; emotion analyzing means for analyzing the user's emotions and applying them to the generated puzzle content; means for providing the generated puzzle content to the user; and means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means. This makes it possible to generate adaptive, satisfying puzzle content that responds to the user's emotions.

[0276] "User" refers to the person who operates the system and inputs information such as the situation and purpose of use.

[0277] "Situation" refers to the situation, scene, or specific setting in which the mystery is solved.

[0278] "Purpose of use" refers to the goal or intention that the user wishes to achieve by solving the puzzle.

[0279] "Used items" refers to objects, tools, and devices used to progress through the puzzle.

[0280] "Input means" refers to an interface or tool that allows a user to input information into a system.

[0281] "Analysis means" refers to a function for analyzing input information and extracting necessary data.

[0282] "Generative artificial intelligence means" refers to artificial intelligence for generating puzzle settings, questions, hints, items, and endings based on input information.

[0283] "Emotion analysis means" refers to a function for analyzing the user's emotions and reflecting them in the generated puzzle content.

[0284] "Providing means" refers to a function for presenting the generated puzzle content to the user and making it available for use.

[0285] "Feedback collection means" refers to a function for collecting user feedback and using it as learning data for the system.

[0286] "Data package" refers to a collection of puzzle elements stored as individual data objects.

[0287] "Change instructions" refer to requests made by the user to correct or change part of the generated puzzle content.

[0288] "Regeneration means" refers to a function for regenerating a part of the puzzle content that has already been generated based on a change instruction.

[0289] "Text format" refers to a data format expressed as a character string.

[0290] "Image file" refers to a data format that contains visual information represented in bitmap or vector format.

[0291] "Video" refers to a data format that contains dynamic visual information.

[0292] This invention is a system that can easily create original puzzles that adapt to the user's emotions by combining a generative AI and an emotion analysis engine. This system is characterized by analyzing the information entered by the user, and the generative AI generates appropriate puzzles, while the emotion analysis engine analyzes the user's emotions and adjusts the content accordingly.

[0293] User Action:

[0294] First, the user logs into the system and accesses the interface for creating a new puzzle. Then, the user enters the following information into the input form:

[0295] Situation

[0296] Purpose of use

[0297] Items used

[0298] For example, enter "Situation: In-house training," "Purpose of use: Team building," "Items used: Smartphone, map, QR code," etc.

[0299] Terminal behavior:

[0300] When input data is sent from the device to the server, the device converts the information into an appropriate format, such as JSON, and then sends the converted data to the server.

[0301] Server Action:

[0302] The server analyzes the received data and activates the generation AI engine and emotion analysis engine. The generation AI engine generates the puzzle setting, questions, hints, items, and endings based on the input information. For example, it generates questions such as "use a QR code to find a hidden location," hints such as "there is a specific mark on a map," and endings such as "an event that allows everyone to share a sense of accomplishment." The emotion analysis engine analyzes the user's emotions and optimizes the generated content based on that information.

[0303] Format conversion and storage of generated data:

[0304] Each generated element is saved as an individual data object and can be regenerated later in response to a user request for partial changes. The generated elements are converted into the user's desired format (text, image, video, etc.) and compiled into a data package.

[0305] Provide to users:

[0306] The generated data package is sent from the server to the user's device, where the user can check its contents and download them as necessary. If the user requests changes to specific parts, the server accepts the request and the generation AI engine regenerates the data. When regenerating, the emotion analysis engine also adjusts the content to reflect the user's emotions.

[0307] Collecting feedback:

[0308] After solving the puzzle, users can enter feedback, which the server collects and adds to the learning data of the generative AI. This improves the accuracy of the system. The sentiment analysis engine also analyzes the feedback and uses it to optimize the generative AI.

[0309] Examples:

[0310] For example, if a company uses this system to hold a team-building event as part of its in-house training, the steps would be as follows:

[0311] 1. The person in charge logs in to the system and enters the following information:

[0312] Situation: In-house training

[0313] Purpose of use: Team building

[0314] Items used: smartphone, map, QR code

[0315] 2. The entered information is sent from the terminal to the server, and the server analyzes the received data.

[0316] 3. The generative AI engine and sentiment analysis engine are activated to generate an appropriate puzzle, such as "find a hidden place using a QR code," "there is a specific mark on a map," or "an event that everyone can share a sense of accomplishment in."

[0317] 4. If the user checks the generated puzzle and requests changes to specific parts, the server accepts the request and regenerates it.

[0318] 5. After the event, users enter their feedback, which is then added to the AI ​​training data.

[0319] Example prompt sentence:

[0320] "I want to create a team building puzzle suitable for in-house training. The situation is in-house training, and the purpose is team building. The items used are a smartphone, a map, and a QR code."

[0321] The above is the specific content of the "Mode for Carrying Out the Invention." This system makes it possible to generate adaptive puzzle-solving content that responds to the user's emotions and provides a high level of satisfaction.

[0322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0323] Step 1:

[0324] User Login

[0325] A user enters a username and password to log in to this system. The server authenticates the user based on the entered authentication information, and if successful, provides the user with access to the system.

[0326] Input and Output:

[0327] Input: Username, Password

[0328] Data processing: The server checks the received authentication information against the information in the database.

[0329] Output: User authentication success or failure

[0330] Step 2:

[0331] Entering input data into a form

[0332] The user accesses an interface for creating a new puzzle and enters the following information:

[0333] Situation

[0334] Purpose of use

[0335] Items used

[0336] Input and Output:

[0337] Input: situation, purpose of use, item used

[0338] Data processing: The terminal converts the input data into an appropriate format (e.g., JSON format).

[0339] Output: The transformed data

[0340] Step 3:

[0341] Sending input data

[0342] The terminal transmits the converted data to the server.

[0343] Input and Output:

[0344] Input: Formatted data

[0345] Data processing: Preparing and sending data

[0346] Output: Notification of successful data transmission to the server

[0347] Step 4:

[0348] Data analysis and engine startup

[0349] The server analyzes the received data and activates the generative AI engine and sentiment analysis engine based on the content.

[0350] Input and Output:

[0351] Input: Received data (situation, purpose of use, items used)

[0352] Data processing: Extracting information through data analysis and triggering engine activation

[0353] Output: Engine start success notification

[0354] Step 5:

[0355] Puzzle generation and emotion analysis

[0356] The generative AI engine generates puzzle settings, questions, hints, items, and endings based on input data, while the sentiment analysis engine analyzes the user's emotions and uses that information to adjust the generated content.

[0357] Input and Output:

[0358] Input: Parsed data

[0359] Data processing: Data generation by a generative AI engine and adjustment by a sentiment analysis engine

[0360] Output: Generated puzzle content

[0361] Step 6:

[0362] Format conversion and storage of generated data

[0363] The server stores each generated element as a separate data object, converts each element into the format desired by the user (text, image, video, etc.), and assembles them into a data package.

[0364] Input and Output:

[0365] Input: Generated puzzle content

[0366] Data processing: format conversion and data packaging

[0367] Output: Data package

[0368] Step 7:

[0369] Data package offerings

[0370] The server transmits the generated data package to the user's terminal.

[0371] Input and Output:

[0372] Input: Data package

[0373] Data processing: Data preparation and transmission

[0374] Output: Notification of successful data transmission to the user device

[0375] Step 8:

[0376] Change Request Processing

[0377] If a user requests a change to a part of the generated puzzle, the request is sent to the server. The server accepts the request, and the AI ​​generation engine regenerates it. During regeneration, the emotion analysis engine adjusts the content to reflect the user's emotions.

[0378] Input and Output:

[0379] Input: Change Request

[0380] Data processing: Requirement analysis and regeneration process execution

[0381] Output: Regenerated puzzle content

[0382] Step 9:

[0383] Collecting and analyzing feedback

[0384] After solving the puzzle, the user inputs feedback, which the server uses as learning data for the AI ​​generation engine and the emotion analysis engine.

[0385] Input and Output:

[0386] Input: User feedback

[0387] Data processing: analyzing feedback and adding it to the training data

[0388] Output: Improved system accuracy

[0389] (Application example 2)

[0390] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0391] Factory training and operational guidance require flexible content adjustments according to the emotions and stress levels of individual employees. In addition, since it is effective to conduct training in a format that is close to actual operating scenarios, it is necessary for the system to recognize emotions on the spot and optimize the content and difficulty in real time.

[0392] 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.

[0393] In this invention, the server includes: a means for a user to input information on the situation, purpose of use, and tools used; a generating AI means for analyzing the input information and generating puzzle settings, questions, hints, tools, and endings; a means for providing the information to the user; a means including an emotion recognition engine for recognizing the user's emotions and adjusting the difficulty and content of the generated puzzle; and a means for collecting user feedback and adding it to the learning data of the generating AI. This makes it possible to adapt training content in real time to match the emotions of employees.

[0394] "User" refers to a person who uses the system to input information and experience or evaluate the puzzles provided.

[0395] "Situation" refers to the setting, such as the situation, environment, and context in which the puzzle is solved.

[0396] "Purpose of use" refers to the goal or purpose that you intend to achieve by using the system.

[0397] "Tools used" refers to tools and equipment used to solve the puzzle, such as smartphones and robots.

[0398] "Generative artificial intelligence means" refers to a function that uses artificial intelligence technology to generate each element of the puzzle (setting, problem, hint, tool, ending, etc.) based on information entered by the user.

[0399] "Means of provision" refers to the means for presenting and delivering the generated puzzle content to the user.

[0400] An "emotion recognition engine" refers to a technology that has the ability to recognize emotions from a user's facial expressions, voice, actions, etc., and adjust the system's output content based on that.

[0401] "Feedback" refers to information such as impressions, evaluations, and areas for improvement that users provide after using the system.

[0402] "Training data" refers to data that the system uses to generate more accurate results, including, for example, user feedback.

[0403] This invention is a puzzle-solving type education system aimed at operational training and efficiency improvement in a factory. The system is implemented as follows.

[0404] Program processing explanation

[0405] User operations

[0406] The user first inputs information about the situation, purpose of use, and tools used into the system interface. For example, they might enter information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." This information is converted into JSON format by the device and sent to the server.

[0407] Server Processing

[0408] The server first analyzes the information entered by the user. The analyzed information is used by a generative artificial intelligence means to generate a setting, questions, hints, tools, and ending for solving the puzzle. For example, specific questions and hints related to assembly line training are generated.

[0409] Introducing emotion recognition

[0410] The generated puzzles are then adapted using an emotion recognition engine that recognizes the user's emotions, automatically adjusting the difficulty level, lowering it if the user is confused and raising it if the user is enjoying it.

[0411] Submissions and Feedback

[0412] The final puzzle content generated is provided to the user, who can then train based on it. After the user actually trains, they input their feedback into the system. This feedback is collected on the server and added to the learning data of the generating AI.

[0413] Hardware and software used

[0414] Hardware: robots, smartphones, augmented reality devices

[0415] Software: Generative AI method (generative AI model), emotion recognition engine, JSON parser

[0416] Specific examples

[0417] For example, when operation training is carried out for new employees in a factory, the system operates as follows.

[0418] Prompt Sentence Examples

[0419] Situation: Assembly line training

[0420] Purpose of use: To improve work efficiency

[0421] Tools used: Robot, smartphone, augmented reality

[0422] Based on this prompt, a generative artificial intelligence means generates training content, and an emotion recognition engine adjusts the difficulty and content in real time to match the user's emotional state. Specifically, for example, instructions for each step to be performed on an assembly line and hints appropriate to the situation are generated. The generated content is then provided to the user, who can use an augmented reality device to continue training in an actual factory environment. Feedback from the user is used to improve the accuracy of future training content.

[0423] conclusion

[0424] This invention makes it possible to dynamically provide operational training in factories in a format that is tailored to each individual user, which is expected to improve training effectiveness and work efficiency.

[0425] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0426] Step 1:

[0427] The user logs into the system and inputs information about the situation, purpose of use, and tools used into the interface. At this stage, the input is specific information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." The input data is converted into JSON format by the terminal, which prepares the input data in a format that can be processed on the server side.

[0428] Step 2:

[0429] The user's input data, converted into JSON format, is sent from the device to the server. The server parses the received JSON data and understands its contents. The parsed data is sent to a generative AI model, which generates specific puzzle-solving settings, questions, hints, tools, and endings based on the training scenario. The output at this stage is structured data containing each element.

[0430] Step 3:

[0431] The server sends the generated puzzle data to an emotion recognition engine. The emotion recognition engine collects the user's facial expressions, voice data, and other data, and analyzes their emotional state in real time. The obtained emotion data is used to adjust the difficulty and content of the generated puzzle data. For example, if the system recognizes that the user is confused, it lowers the difficulty of the problem, and conversely, if the user is enjoying the problem, it increases the difficulty. The final output is puzzle data optimized according to the user's emotion.

[0432] Step 4:

[0433] The optimized puzzle-solving data is then sent back to the device from the server and provided to the user. The device displays the puzzle content visually or audibly, and the user actually practices using a smartphone or an augmented reality device.

[0434] Step 5:

[0435] Users train by solving puzzles and input feedback on the process and results. This feedback data is then sent from the device to the server. The server analyzes the collected feedback data and stores it as training data for the generative AI model. This improves the quality and accuracy of future puzzle-solving scenarios generated by the system.

[0436] Step 6:

[0437] The server accepts requests to change parts of the generated puzzle as needed. If the user wishes to change the difficulty or content of a specific part, it regenerates only that part. In this case, adjustments are made according to the user's emotional state, and the changed data is provided again.

[0438] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0440] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0441] [Second embodiment]

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

[0443] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0444] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0445] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0446] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0447] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0448] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0449] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0450] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0451] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0452] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0454] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[0455] User operations

[0456] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0457] Device behavior

[0458] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0459] Server Processing

[0460] When the server receives the input data, it analyzes the information and activates the generative AI engine. The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," or "Ending: An event that allows everyone to share a sense of accomplishment."

[0461] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0462] Provision to users

[0463] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[0464] Collecting feedback

[0465] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator to help improve its accuracy in the future.

[0466] Specific examples

[0467] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0468] Situation: In-house training

[0469] Purpose of use: Team building

[0470] Items used: smartphone, map, QR code

[0471] Once this information is sent to the server, the generative AI engine runs and generates an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the problem, and provides the updated problem. After the event ends, feedback is collected from participants and saved as AF learning data. This allows the accuracy of the generative AI to be improved.

[0472] The processing flow will be explained below.

[0473] Step 1:

[0474] A user logs into the service and accesses an interface for creating new puzzles.

[0475] Step 2:

[0476] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[0477] Step 3:

[0478] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[0479] Step 4:

[0480] The terminal transmits the converted data to the server.

[0481] Step 5:

[0482] The server receives and analyzes the user's input data and uses that data to issue instructions to the generative AI engine.

[0483] Step 6:

[0484] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates content such as "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0485] Step 7:

[0486] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[0487] Step 8:

[0488] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[0489] Step 9:

[0490] The server transmits the generated puzzle-solving data package to the terminal.

[0491] Step 10:

[0492] The terminal receives all the data and displays it to the user.

[0493] Step 11:

[0494] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[0495] Step 12:

[0496] The server receives the change request and reparses the affected part.

[0497] Step 13:

[0498] The server's generation AI engine regenerates only the relevant parts, enabling updated content to be provided.

[0499] Step 14:

[0500] The server transmits the regenerated data to the terminal again.

[0501] Step 15:

[0502] The terminal receives the regenerated data and displays it to the user.

[0503] Step 16:

[0504] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[0505] Step 17:

[0506] The server receives the feedback and stores it as learning data for the AI, which helps improve the accuracy of the generating AI.

[0507] Example 1

[0508] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0509] Conventional puzzle creation systems require users to manually create settings, questions, hints, items, and endings, which is both time-consuming and prone to inconsistent quality. Furthermore, when changes are needed to the generated puzzle content, the correction process is cumbersome, making it difficult to respond quickly and efficiently. Furthermore, there is a lack of means to provide the generated puzzle in various formats, such as text, images, and videos, resulting in low user convenience. The present invention aims to solve these problems and provide a system that automatically generates efficient, high-quality puzzles.

[0510] 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.

[0511] In this invention, the server includes: a means for a user to input information about the situation, purpose of use, and items used; a generating AI means for analyzing the input information and generating a puzzle setting, question, hint, item, and ending; a means for converting the input information into an appropriate data format and sending it to the server; a means for providing the generated puzzle content to the user; and a means for collecting user feedback and adding it to the learning data of the generating AI. This enables a system that can automatically generate high-quality puzzles quickly and efficiently and flexibly respond to changes. Furthermore, by including a means for exporting the generated puzzles in text, image files, or video formats, user convenience can be improved.

[0512] text

[0513] "User" refers to a person or organization that uses the system to create and use puzzles.

[0514] "Situation" refers to the specific background or situation in which the puzzle is solved.

[0515] "Purpose of use" refers to the specific purpose or goal for which the puzzle is used.

[0516] "Items used" refers to the objects and tools used by the user while solving the puzzle.

[0517] "Means of input" refers to the method or mechanism by which a user inputs information about the situation, purpose of use, and items used into the system.

[0518] "Means of analysis" refers to the method or mechanism for analyzing the content and characteristics of data based on input information.

[0519] "Generative artificial intelligence means" refers to technologies such as generative AI models that automatically create puzzle settings, questions, hints, items, and endings based on analyzed information.

[0520] "Means for converting into data format" refers to the method or mechanism for converting information entered by the user into a format that is easy for the server to process.

[0521] "Means of sending to the server" refers to the method or mechanism for sending input information or generated data to the server via a network.

[0522] "Means for providing to users" refers to the method or mechanism for providing the content of the generated puzzle so that users can check, download or use it.

[0523] "Means of collecting feedback" refers to the methods and mechanisms for collecting opinions and impressions from users after using the service.

[0524] "Means of adding to training data" refers to the method or mechanism for adding collected feedback to the training data of the generative AI.

[0525] "Means for regeneration when a change request is received" refers to the method or mechanism for receiving a change request from a user and regenerating the relevant information.

[0526] "Means for making the solution exportable in text, image file, or video format" refers to a method or mechanism for saving or providing the generated solution in text, image file, or video format.

[0527] text

[0528] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[0529] User operations

[0530] First, users log in to the service and access an interface for creating new puzzles. Next, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0531] Device behavior

[0532] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0533] Server Processing

[0534] When the server receives the input data, it analyzes the information and launches a generative AI engine (e.g., GPT-3). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that gives everyone a sense of accomplishment." Each generated element is saved as an individual data object, allowing for later partial modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0535] Provision to users

[0536] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[0537] Collecting feedback

[0538] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[0539] Specific examples

[0540] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0541] Situation: In-house training

[0542] Purpose of use: Team building

[0543] Items used: smartphone, map, QR code

[0544] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can submit a change request for that part. The server will accept the change request, regenerate the problem, and provide the updated problem.

[0545] After the event, feedback will be collected from participants and saved as learning data for the AI, which will improve the accuracy of the AI.

[0546] Example prompts for generative AI models

[0547] "I'd like to create a puzzle for team building to be used in our in-house training. The items to be used will be a smartphone, a map, and a QR code. I'd like specific suggestions for the puzzle, the problem, the hints, the setting, and the ending."

[0548] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0549] text

[0550] Step 1: User Login

[0551] A user accesses the system and enters their authentication information (such as user ID and password) into an input form. The entered authentication information is sent from the terminal to the server. The server compares the received authentication information with a database, and if authentication is successful, it redirects the user to the main interface. In this process, the input is the user's authentication information, and the output is whether the authentication was successful or not.

[0552] Step 2: Enter your information

[0553] The user accesses an interface for creating new puzzles and inputs information about the situation, purpose of use, and items used. For example, they might input "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." This information is converted into an appropriate data format (e.g., JSON format) on the device. The input is the user's information, and the output is the converted data format.

[0554] Step 3: Sending data

[0555] The terminal sends the converted information to the server, which receives the information and stores it in a database. The input is the converted data format, and the output is the successful transmission of data to the server.

[0556] Step 4: Data analysis

[0557] The server analyzes the received data and extracts information on the situation, purpose of use, and items used. For example, "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." The input is the data stored on the server, and the output is the analyzed information.

[0558] Step 5: Launching the Generative AI

[0559] The server launches a generative AI engine (for example, GPT-3) based on the analyzed information. A prompt containing the analyzed information is input to the generative AI. For example, a sample prompt is input: "I would like to create a puzzle for team building to be used in in-house training. The items to be used will be a smartphone, a map, and a QR code. Please provide specific suggestions for the puzzle question, hints, setting, and ending." The input is the analyzed information, and the output is the prompt input to the AI.

[0560] Step 6: Generate the puzzle

[0561] The generation AI generates each element of the puzzle (setting, problem, hint, item, ending) based on the input prompt. For example, it generates "Problem 1: Use a QR code to find a hidden place," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment." The input is the prompt to the AI, and the output is each generated element.

[0562] Step 7: Storing and packaging the data

[0563] The server saves each generated element as a separate data object and converts it into the user's desired format (e.g., text, image file, video, etc.) The converted data is then compiled into a data package. The input is each generated element, and the output is the data package.

[0564] Step 8: Provide to users

[0565] The server sends the final puzzle-solving data package to the user's device. The user can check the contents and download them as needed. The input is the data package, and the output is provided to the user.

[0566] Step 9: Change Requests

[0567] If the user has a change request for a specific part, they enter that information into the terminal again, convert it into JSON format, and send it to the server. The server then inputs the prompt into the generation AI again, regenerating the problem. The input is the change request, and the output is the regenerated data.

[0568] Step 10: Gather feedback

[0569] After completing the task, the user inputs feedback. The device sends the feedback to the server, which stores it as training data for the generative AI. The input is feedback, and the output is added to the training data.

[0570] (Application example 1)

[0571] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0572] Traditional in-factory education and training is often monotonous and inefficient, making it difficult to improve worker learning effectiveness and motivation. There is a need for more effective and engaging ways to communicate training content, especially to new employees and transferred employees. Another problem is the difficulty of customizing the training to meet individual needs.

[0573] 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.

[0574] In this invention, the server includes: means for a user to input information on the situation, purpose of use, and items to be used; artificial intelligence generating means for analyzing the input information and generating a setting, question, hint, item, and ending for solving the puzzle; means for providing the generated content of the puzzle to the user; means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means; and means for providing a smartphone application for implementing specialized education and training for factory workers. This makes it possible to conduct education and training in the factory interactively and effectively.

[0575] A "user" is an entity that uses the system to instruct the creation of puzzles and questions.

[0576] "Information" is data relating to the situation, purpose of use, and items used.

[0577] "Situation" is information about the scene or environment in which the puzzle is solved.

[0578] "Purpose of use" refers to the specific purpose or goal when solving the puzzle.

[0579] "Items used" is information about tools and devices used when solving puzzles.

[0580] "Generative artificial intelligence means" is a technology for automatically generating puzzle settings, questions, hints, items, and endings based on information input by the user.

[0581] "Puzzle content" is a general term for the settings, questions, hints, items, and endings of the generated puzzle.

[0582] "Feedback" refers to information provided by users regarding their evaluation of the system and areas for improvement after completing use.

[0583] A "smartphone application for providing specialized education and training for factory workers" is an application used on a specialized smartphone by factory workers to learn knowledge and skills.

[0584] This invention is a specialized education and training system for factory workers that uses generative AI to provide interactive and effective puzzle solving.

[0585] User operations

[0586] First, the user logs in to the smartphone application and accesses the interface for creating a new puzzle. There, they input information about the situation, purpose of use, and items used. For example, they can input information such as "Situation: New employee training in a factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[0587] Device behavior

[0588] When a user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to a backend server.

[0589] Server Processing

[0590] When the server receives the input data, it analyzes the information and activates a generative AI engine (e.g., OpenAI GPT-3). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it generates "Question 1: Use a factory map to find a specific work area," "Hint: Check the location of a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0591] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0592] Provision to users

[0593] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can instruct the change to be made to only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle.

[0594] Collecting feedback

[0595] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[0596] Specific examples

[0597] For example, let's say a factory wants to organize an educational event using puzzles as part of new employee training. The employee logs into the system and enters the following information:

[0598] Situation: New employee training in the factory

[0599] Purpose of use: Understanding work procedures and team building

[0600] Items used: Smartphone, factory map

[0601] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server will accept the change request, regenerate the problem, and provide the updated problem. After the event, feedback from participants will be collected and saved as learning data for the generative AI. This will help improve the accuracy of the generative AI.

[0602] Prompt Sentence Examples

[0603] Situation: New employee training in the factory

[0604] Purpose of use: Understanding work procedures and team building

[0605] Items used: Smartphone, factory map

[0606] Generate a puzzle using the following information:

[0607] In this way, factory workers can acquire the necessary knowledge and skills more effectively and in a fun way.

[0608] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0609] Step 1:

[0610] The user inputs information about the situation, purpose of use, and items used. This input data is collected on the smartphone application and converted into JSON format. Specific inputs include "Situation: New employee training in the factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[0611] Step 2:

[0612] The terminal receives input data, converts it to JSON format, and sends it to the server. Network communication is performed to send the input data (JSON format) to the server. The input here is JSON data received from the terminal, and an output is generated to send it to the server.

[0613] Step 3:

[0614] The server receives the JSON-formatted data, analyzes it, and generates a prompt. Here, the server analyzes the JSON data to extract information on the "situation," "purpose of use," and "items used." As a specific example, the following prompt is generated: "Situation: New employee training within the factory. Purpose of use: Understanding work procedures and team building. Items used: Smartphone, factory map. Please generate a solution to the puzzle based on the information below."

[0615] Step 4:

[0616] The server starts a generative AI engine (e.g., OpenAI GPT-3) and provides the prompt as input. The generative AI engine generates appropriate puzzle settings, questions, hints, items, and endings based on the prompt. In this step, the prompt is the input, and the generated puzzle content is the output.

[0617] Step 5:

[0618] The generated puzzles are converted into individual data objects and saved. For example, they might include a problem such as "Problem 1: Use the factory map to find a specific work area" and a hint such as "Check the location of a specific mark on the map." The output obtained through this process is saved in a database.

[0619] Step 6:

[0620] The server sends the generated puzzle-solving data package to the user's device. The user can check the contents and make changes to specific parts as needed. The sent data package is the output here. Meanwhile, the change request from the user is returned to the server as input.

[0621] Step 7:

[0622] The server that receives the change request regenerates the relevant part. It generates a prompt for regeneration and sends it to the AI ​​engine again. The regenerated puzzle content becomes the output and is sent to the user again as a data package.

[0623] Step 8:

[0624] After completing the task, the user enters feedback, which is added to the database and then used as training data for the generative AI. This feedback becomes the final input, which generates an output that contributes to improving the accuracy of the generative AI.

[0625] The above is the flow of processing of the system program that realizes this application example.

[0626] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0627] This invention is a system that uses generative AI and an emotion engine to easily create original puzzles. The emotion engine can recognize the user's emotions and provide appropriate solutions.

[0628] User operations

[0629] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0630] Device behavior

[0631] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0632] Server Processing

[0633] When the server receives the input data, it analyzes the information and activates the generative AI engine and emotion engine. The generative AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. The emotion engine analyzes the input data and user feedback and recognizes the user's emotions. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0634] Each generated element is saved as an individual data object, allowing for later partial modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package. Furthermore, the generation AI optimizes the output content based on emotional information recognized by the emotion engine.

[0635] Provision to users

[0636] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle. The emotion engine adjusts the content to reflect the user's emotions even when regenerating.

[0637] Collecting feedback

[0638] After completing the task, the user enters feedback. The server adds the collected feedback to the learning data of the generative AI to help improve its accuracy in the future. The emotion engine also analyzes the feedback and reflects it in optimizing the generative AI.

[0639] Specific examples

[0640] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0641] Situation: In-house training

[0642] Purpose of use: Team building

[0643] Items used: smartphone, map, QR code

[0644] Once this information is sent to the server, the generative AI engine is activated and generates an appropriate puzzle. The emotion engine recognizes emotions from the input data, the user's facial expressions, voice, etc., and adjusts the generated content based on that information. For example, if the user is enjoying themselves, the difficulty level will be increased, or if they are confused, the difficulty level will be lowered.

[0645] The user checks the generated puzzles, and if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the puzzle, and provides the updated problem. The emotion engine also adjusts the content to reflect the user's emotions when regenerating. After the event, feedback is collected from participants and saved as AI learning data. This improves the accuracy of the generation AI and emotion engine.

[0646] The processing flow will be explained below.

[0647] Step 1:

[0648] A user logs into the service and accesses an interface for creating new puzzles.

[0649] Step 2:

[0650] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[0651] Step 3:

[0652] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[0653] Step 4:

[0654] The terminal transmits the converted data to the server.

[0655] Step 5:

[0656] The server receives and analyzes the user's input data and uses that data to activate the generative AI engine and emotion engine.

[0657] Step 6:

[0658] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0659] Step 7:

[0660] The server's emotion engine analyzes input data and user feedback to recognize the user's emotions, such as whether the user is enjoying or confused.

[0661] Step 8:

[0662] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[0663] Step 9:

[0664] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[0665] Step 10:

[0666] The server transmits the generated puzzle-solving data package to the terminal.

[0667] Step 11:

[0668] The terminal receives all the data and displays it to the user.

[0669] Step 12:

[0670] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[0671] Step 13:

[0672] The server receives the change request and reparses the affected part.

[0673] Step 14:

[0674] The server's emotion engine analyzes the user's emotions again and provides information to reflect them when regenerating. For example, if the user's emotion is confusion, it will adjust the difficulty level accordingly.

[0675] Step 15:

[0676] The server uses a generation AI engine to regenerate only the relevant parts and provide updated content.

[0677] Step 16:

[0678] The server transmits the regenerated data to the terminal again.

[0679] Step 17:

[0680] The terminal receives the regenerated data and displays it to the user.

[0681] Step 18:

[0682] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[0683] Step 19:

[0684] The server receives the feedback and stores it as learning data for the AI, which improves the accuracy of the generative AI and emotion engine.

[0685] Example 2

[0686] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0687] Conventional puzzle generation systems have difficulty generating adaptive content that takes user emotions into account, making it difficult to increase user engagement and satisfaction. In addition, there are limited ways to effectively utilize feedback on the generated content and improve the accuracy of the system.

[0688] 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.

[0689] In this invention, the server includes: means for the user to input information on the situation, purpose of use, and items used; artificial intelligence generating means for analyzing the input information and generating puzzle settings, questions, hints, items, and endings; emotion analyzing means for analyzing the user's emotions and applying them to the generated puzzle content; means for providing the generated puzzle content to the user; and means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means. This makes it possible to generate adaptive, satisfying puzzle content that responds to the user's emotions.

[0690] "User" refers to the person who operates the system and inputs information such as the situation and purpose of use.

[0691] "Situation" refers to the situation, scene, or specific setting in which the mystery is solved.

[0692] "Purpose of use" refers to the goal or intention that the user wishes to achieve by solving the puzzle.

[0693] "Used items" refers to objects, tools, and devices used to progress through the puzzle.

[0694] "Input means" refers to an interface or tool that allows a user to input information into a system.

[0695] "Analysis means" refers to a function for analyzing input information and extracting necessary data.

[0696] "Generative artificial intelligence means" refers to artificial intelligence for generating puzzle settings, questions, hints, items, and endings based on input information.

[0697] "Emotion analysis means" refers to a function for analyzing the user's emotions and reflecting them in the generated puzzle content.

[0698] "Providing means" refers to a function for presenting the generated puzzle content to the user and making it available for use.

[0699] "Feedback collection means" refers to a function for collecting user feedback and using it as learning data for the system.

[0700] "Data package" refers to a collection of puzzle elements stored as individual data objects.

[0701] "Change instructions" refer to requests made by the user to correct or change part of the generated puzzle content.

[0702] "Regeneration means" refers to a function for regenerating a part of the puzzle content that has already been generated based on a change instruction.

[0703] "Text format" refers to a data format expressed as a character string.

[0704] "Image file" refers to a data format that contains visual information represented in bitmap or vector format.

[0705] "Video" refers to a data format that contains dynamic visual information.

[0706] This invention is a system that can easily create original puzzles that adapt to the user's emotions by combining a generative AI and an emotion analysis engine. This system is characterized by analyzing the information entered by the user, and the generative AI generates appropriate puzzles, while the emotion analysis engine analyzes the user's emotions and adjusts the content accordingly.

[0707] User Action:

[0708] First, the user logs into the system and accesses the interface for creating a new puzzle. Then, the user enters the following information into the input form:

[0709] Situation

[0710] Purpose of use

[0711] Items used

[0712] For example, enter "Situation: In-house training," "Purpose of use: Team building," "Items used: Smartphone, map, QR code," etc.

[0713] Terminal behavior:

[0714] When input data is sent from the device to the server, the device converts the information into an appropriate format, such as JSON, and then sends the converted data to the server.

[0715] Server Action:

[0716] The server analyzes the received data and activates the generation AI engine and emotion analysis engine. The generation AI engine generates the puzzle setting, questions, hints, items, and endings based on the input information. For example, it generates questions such as "use a QR code to find a hidden location," hints such as "there is a specific mark on a map," and endings such as "an event that allows everyone to share a sense of accomplishment." The emotion analysis engine analyzes the user's emotions and optimizes the generated content based on that information.

[0717] Format conversion and storage of generated data:

[0718] Each generated element is saved as an individual data object and can be regenerated later in response to a user request for partial changes. The generated elements are converted into the user's desired format (text, image, video, etc.) and compiled into a data package.

[0719] Provide to users:

[0720] The generated data package is sent from the server to the user's device, where the user can check its contents and download them as necessary. If the user requests changes to specific parts, the server accepts the request and the generation AI engine regenerates the data. When regenerating, the emotion analysis engine also adjusts the content to reflect the user's emotions.

[0721] Collecting feedback:

[0722] After solving the puzzle, users can enter feedback, which the server collects and adds to the learning data of the generative AI. This improves the accuracy of the system. The sentiment analysis engine also analyzes the feedback and uses it to optimize the generative AI.

[0723] Examples:

[0724] For example, if a company uses this system to hold a team-building event as part of its in-house training, the steps would be as follows:

[0725] 1. The person in charge logs in to the system and enters the following information:

[0726] Situation: In-house training

[0727] Purpose of use: Team building

[0728] Items used: smartphone, map, QR code

[0729] 2. The entered information is sent from the terminal to the server, and the server analyzes the received data.

[0730] 3. The generative AI engine and sentiment analysis engine are activated to generate an appropriate puzzle, such as "find a hidden place using a QR code," "there is a specific mark on a map," or "an event that everyone can share a sense of accomplishment in."

[0731] 4. If the user checks the generated puzzle and requests changes to specific parts, the server accepts the request and regenerates it.

[0732] 5. After the event, users enter their feedback, which is then added to the AI ​​training data.

[0733] Example prompt sentence:

[0734] "I want to create a team building puzzle suitable for in-house training. The situation is in-house training, and the purpose is team building. The items used are a smartphone, a map, and a QR code."

[0735] The above is the specific content of the "Mode for Carrying Out the Invention." This system makes it possible to generate adaptive puzzle-solving content that responds to the user's emotions and provides a high level of satisfaction.

[0736] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0737] Step 1:

[0738] User Login

[0739] A user enters a username and password to log in to this system. The server authenticates the user based on the entered authentication information, and if successful, provides the user with access to the system.

[0740] Input and Output:

[0741] Input: Username, Password

[0742] Data processing: The server checks the received authentication information against the information in the database.

[0743] Output: User authentication success or failure

[0744] Step 2:

[0745] Entering input data into a form

[0746] The user accesses an interface for creating a new puzzle and enters the following information:

[0747] Situation

[0748] Purpose of use

[0749] Items used

[0750] Input and Output:

[0751] Input: situation, purpose of use, item used

[0752] Data processing: The terminal converts the input data into an appropriate format (e.g., JSON format).

[0753] Output: The transformed data

[0754] Step 3:

[0755] Sending input data

[0756] The terminal transmits the converted data to the server.

[0757] Input and Output:

[0758] Input: Formatted data

[0759] Data processing: Preparing and sending data

[0760] Output: Notification of successful data transmission to the server

[0761] Step 4:

[0762] Data analysis and engine startup

[0763] The server analyzes the received data and activates the generative AI engine and sentiment analysis engine based on the content.

[0764] Input and Output:

[0765] Input: Received data (situation, purpose of use, items used)

[0766] Data processing: Extracting information through data analysis and triggering engine activation

[0767] Output: Engine start success notification

[0768] Step 5:

[0769] Puzzle generation and emotion analysis

[0770] The generative AI engine generates puzzle settings, questions, hints, items, and endings based on input data, while the sentiment analysis engine analyzes the user's emotions and uses that information to adjust the generated content.

[0771] Input and Output:

[0772] Input: Parsed data

[0773] Data processing: Data generation by a generative AI engine and adjustment by a sentiment analysis engine

[0774] Output: Generated puzzle content

[0775] Step 6:

[0776] Format conversion and storage of generated data

[0777] The server stores each generated element as a separate data object, converts each element into the format desired by the user (text, image, video, etc.), and assembles them into a data package.

[0778] Input and Output:

[0779] Input: Generated puzzle content

[0780] Data processing: format conversion and data packaging

[0781] Output: Data package

[0782] Step 7:

[0783] Data package offerings

[0784] The server transmits the generated data package to the user's terminal.

[0785] Input and Output:

[0786] Input: Data package

[0787] Data processing: Data preparation and transmission

[0788] Output: Notification of successful data transmission to the user device

[0789] Step 8:

[0790] Change Request Processing

[0791] If a user requests a change to a part of the generated puzzle, the request is sent to the server. The server accepts the request, and the AI ​​generation engine regenerates it. During regeneration, the emotion analysis engine adjusts the content to reflect the user's emotions.

[0792] Input and Output:

[0793] Input: Change Request

[0794] Data processing: Requirement analysis and regeneration process execution

[0795] Output: Regenerated puzzle content

[0796] Step 9:

[0797] Collecting and analyzing feedback

[0798] After solving the puzzle, the user inputs feedback, which the server uses as learning data for the AI ​​generation engine and the emotion analysis engine.

[0799] Input and Output:

[0800] Input: User feedback

[0801] Data processing: analyzing feedback and adding it to the training data

[0802] Output: Improved system accuracy

[0803] (Application example 2)

[0804] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0805] Factory training and operational guidance require flexible content adjustments according to the emotions and stress levels of individual employees. In addition, since it is effective to conduct training in a format that is close to actual operating scenarios, it is necessary for the system to recognize emotions on the spot and optimize the content and difficulty in real time.

[0806] 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.

[0807] In this invention, the server includes: a means for a user to input information on the situation, purpose of use, and tools used; a generating AI means for analyzing the input information and generating puzzle settings, questions, hints, tools, and endings; a means for providing the information to the user; a means including an emotion recognition engine for recognizing the user's emotions and adjusting the difficulty and content of the generated puzzle; and a means for collecting user feedback and adding it to the learning data of the generating AI. This makes it possible to adapt training content in real time to match the emotions of employees.

[0808] "User" refers to a person who uses the system to input information and experience or evaluate the puzzles provided.

[0809] "Situation" refers to the setting, such as the situation, environment, and context in which the puzzle is solved.

[0810] "Purpose of use" refers to the goal or purpose that you intend to achieve by using the system.

[0811] "Tools used" refers to tools and equipment used to solve the puzzle, such as smartphones and robots.

[0812] "Generative artificial intelligence means" refers to a function that uses artificial intelligence technology to generate each element of the puzzle (setting, problem, hint, tool, ending, etc.) based on information entered by the user.

[0813] "Means of provision" refers to the means for presenting and delivering the generated puzzle content to the user.

[0814] An "emotion recognition engine" refers to a technology that has the ability to recognize emotions from a user's facial expressions, voice, actions, etc., and adjust the system's output content based on that.

[0815] "Feedback" refers to information such as impressions, evaluations, and areas for improvement that users provide after using the system.

[0816] "Training data" refers to data that the system uses to generate more accurate results, including, for example, user feedback.

[0817] This invention is a puzzle-solving type education system aimed at operational training and efficiency improvement in a factory. The system is implemented as follows.

[0818] Program processing explanation

[0819] User operations

[0820] The user first inputs information about the situation, purpose of use, and tools used into the system interface. For example, they might enter information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." This information is converted into JSON format by the device and sent to the server.

[0821] Server Processing

[0822] The server first analyzes the information entered by the user. The analyzed information is used by a generative artificial intelligence means to generate a setting, questions, hints, tools, and ending for solving the puzzle. For example, specific questions and hints related to assembly line training are generated.

[0823] Introducing emotion recognition

[0824] The generated puzzles are then adapted using an emotion recognition engine that recognizes the user's emotions, automatically adjusting the difficulty level, lowering it if the user is confused and raising it if the user is enjoying it.

[0825] Submissions and Feedback

[0826] The final puzzle content generated is provided to the user, who can then train based on it. After the user actually trains, they input their feedback into the system. This feedback is collected on the server and added to the learning data of the generating AI.

[0827] Hardware and software used

[0828] Hardware: robots, smartphones, augmented reality devices

[0829] Software: Generative AI method (generative AI model), emotion recognition engine, JSON parser

[0830] Specific examples

[0831] For example, when operation training is carried out for new employees in a factory, the system operates as follows.

[0832] Prompt Sentence Examples

[0833] Situation: Assembly line training

[0834] Purpose of use: To improve work efficiency

[0835] Tools used: Robot, smartphone, augmented reality

[0836] Based on this prompt, a generative artificial intelligence means generates training content, and an emotion recognition engine adjusts the difficulty and content in real time to match the user's emotional state. Specifically, for example, instructions for each step to be performed on an assembly line and hints appropriate to the situation are generated. The generated content is then provided to the user, who can use an augmented reality device to continue training in an actual factory environment. Feedback from the user is used to improve the accuracy of future training content.

[0837] conclusion

[0838] This invention makes it possible to dynamically provide operational training in factories in a format that is tailored to each individual user, which is expected to improve training effectiveness and work efficiency.

[0839] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0840] Step 1:

[0841] The user logs into the system and inputs information about the situation, purpose of use, and tools used into the interface. At this stage, the input is specific information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." The input data is converted into JSON format by the terminal, which prepares the input data in a format that can be processed on the server side.

[0842] Step 2:

[0843] The user's input data, converted into JSON format, is sent from the device to the server. The server parses the received JSON data and understands its contents. The parsed data is sent to a generative AI model, which generates specific puzzle-solving settings, questions, hints, tools, and endings based on the training scenario. The output at this stage is structured data containing each element.

[0844] Step 3:

[0845] The server sends the generated puzzle data to an emotion recognition engine. The emotion recognition engine collects the user's facial expressions, voice data, and other data, and analyzes their emotional state in real time. The obtained emotion data is used to adjust the difficulty and content of the generated puzzle data. For example, if the system recognizes that the user is confused, it lowers the difficulty of the problem, and conversely, if the user is enjoying the problem, it increases the difficulty. The final output is puzzle data optimized according to the user's emotion.

[0846] Step 4:

[0847] The optimized puzzle-solving data is then sent back to the device from the server and provided to the user. The device displays the puzzle content visually or audibly, and the user actually practices using a smartphone or an augmented reality device.

[0848] Step 5:

[0849] Users train by solving puzzles and input feedback on the process and results. This feedback data is then sent from the device to the server. The server analyzes the collected feedback data and stores it as training data for the generative AI model. This improves the quality and accuracy of future puzzle-solving scenarios generated by the system.

[0850] Step 6:

[0851] The server accepts requests to change parts of the generated puzzle as needed. If the user wishes to change the difficulty or content of a specific part, it regenerates only that part. In this case, adjustments are made according to the user's emotional state, and the changed data is provided again.

[0852] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0853] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0854] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0855] [Third embodiment]

[0856] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0857] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0858] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0859] 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.

[0860] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0861] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0862] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0863] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0864] 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.

[0865] 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.

[0866] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0867] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0868] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[0869] User operations

[0870] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0871] Device behavior

[0872] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0873] Server Processing

[0874] When the server receives the input data, it analyzes the information and activates the generative AI engine. The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," or "Ending: An event that allows everyone to share a sense of accomplishment."

[0875] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0876] Provision to users

[0877] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[0878] Collecting feedback

[0879] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator to help improve its accuracy in the future.

[0880] Specific examples

[0881] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0882] Situation: In-house training

[0883] Purpose of use: Team building

[0884] Items used: smartphone, map, QR code

[0885] Once this information is sent to the server, the generative AI engine runs and generates an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the problem, and provides the updated problem. After the event ends, feedback is collected from participants and saved as AF learning data. This allows the accuracy of the generative AI to be improved.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] A user logs into the service and accesses an interface for creating new puzzles.

[0889] Step 2:

[0890] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[0891] Step 3:

[0892] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[0893] Step 4:

[0894] The terminal transmits the converted data to the server.

[0895] Step 5:

[0896] The server receives and analyzes the user's input data and uses that data to issue instructions to the generative AI engine.

[0897] Step 6:

[0898] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates content such as "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[0899] Step 7:

[0900] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[0901] Step 8:

[0902] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[0903] Step 9:

[0904] The server transmits the generated puzzle-solving data package to the terminal.

[0905] Step 10:

[0906] The terminal receives all the data and displays it to the user.

[0907] Step 11:

[0908] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[0909] Step 12:

[0910] The server receives the change request and reparses the affected part.

[0911] Step 13:

[0912] The server's generation AI engine regenerates only the relevant parts, enabling updated content to be provided.

[0913] Step 14:

[0914] The server transmits the regenerated data to the terminal again.

[0915] Step 15:

[0916] The terminal receives the regenerated data and displays it to the user.

[0917] Step 16:

[0918] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[0919] Step 17:

[0920] The server receives the feedback and stores it as learning data for the AI, which helps improve the accuracy of the generating AI.

[0921] Example 1

[0922] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0923] Conventional puzzle creation systems require users to manually create settings, questions, hints, items, and endings, which is both time-consuming and prone to inconsistent quality. Furthermore, when changes are needed to the generated puzzle content, the correction process is cumbersome, making it difficult to respond quickly and efficiently. Furthermore, there is a lack of means to provide the generated puzzle in various formats, such as text, images, and videos, resulting in low user convenience. The present invention aims to solve these problems and provide a system that automatically generates efficient, high-quality puzzles.

[0924] 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.

[0925] In this invention, the server includes: a means for a user to input information about the situation, purpose of use, and items used; a generating AI means for analyzing the input information and generating a puzzle setting, question, hint, item, and ending; a means for converting the input information into an appropriate data format and sending it to the server; a means for providing the generated puzzle content to the user; and a means for collecting user feedback and adding it to the learning data of the generating AI. This enables a system that can automatically generate high-quality puzzles quickly and efficiently and flexibly respond to changes. Furthermore, by including a means for exporting the generated puzzles in text, image files, or video formats, user convenience can be improved.

[0926] text

[0927] "User" refers to a person or organization that uses the system to create and use puzzles.

[0928] "Situation" refers to the specific background or situation in which the puzzle is solved.

[0929] "Purpose of use" refers to the specific purpose or goal for which the puzzle is used.

[0930] "Items used" refers to the objects and tools used by the user while solving the puzzle.

[0931] "Means of input" refers to the method or mechanism by which a user inputs information about the situation, purpose of use, and items used into the system.

[0932] "Means of analysis" refers to the method or mechanism for analyzing the content and characteristics of data based on input information.

[0933] "Generative artificial intelligence means" refers to technologies such as generative AI models that automatically create puzzle settings, questions, hints, items, and endings based on analyzed information.

[0934] "Means for converting into data format" refers to the method or mechanism for converting information entered by the user into a format that is easy for the server to process.

[0935] "Means of sending to the server" refers to the method or mechanism for sending input information or generated data to the server via a network.

[0936] "Means for providing to users" refers to the method or mechanism for providing the content of the generated puzzle so that users can check, download or use it.

[0937] "Means of collecting feedback" refers to the methods and mechanisms for collecting opinions and impressions from users after using the service.

[0938] "Means of adding to training data" refers to the method or mechanism for adding collected feedback to the training data of the generative AI.

[0939] "Means for regeneration when a change request is received" refers to the method or mechanism for receiving a change request from a user and regenerating the relevant information.

[0940] "Means for making the solution exportable in text, image file, or video format" refers to a method or mechanism for saving or providing the generated solution in text, image file, or video format.

[0941] text

[0942] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[0943] User operations

[0944] First, users log in to the service and access an interface for creating new puzzles. Next, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[0945] Device behavior

[0946] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[0947] Server Processing

[0948] When the server receives the input data, it analyzes the information and launches a generative AI engine (e.g., GPT-3). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that gives everyone a sense of accomplishment." Each generated element is saved as an individual data object, allowing for later partial modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[0949] Provision to users

[0950] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[0951] Collecting feedback

[0952] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[0953] Specific examples

[0954] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[0955] Situation: In-house training

[0956] Purpose of use: Team building

[0957] Items used: smartphone, map, QR code

[0958] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can submit a change request for that part. The server will accept the change request, regenerate the problem, and provide the updated problem.

[0959] After the event, feedback will be collected from participants and saved as learning data for the AI, which will improve the accuracy of the AI.

[0960] Example prompts for generative AI models

[0961] "I'd like to create a puzzle for team building to be used in our in-house training. The items to be used will be a smartphone, a map, and a QR code. I'd like specific suggestions for the puzzle, the problem, the hints, the setting, and the ending."

[0962] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0963] text

[0964] Step 1: User Login

[0965] A user accesses the system and enters their authentication information (such as user ID and password) into an input form. The entered authentication information is sent from the terminal to the server. The server compares the received authentication information with a database, and if authentication is successful, it redirects the user to the main interface. In this process, the input is the user's authentication information, and the output is whether the authentication was successful or not.

[0966] Step 2: Enter your information

[0967] The user accesses an interface for creating new puzzles and inputs information about the situation, purpose of use, and items used. For example, they might input "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." This information is converted into an appropriate data format (e.g., JSON format) on the device. The input is the user's information, and the output is the converted data format.

[0968] Step 3: Sending data

[0969] The terminal sends the converted information to the server, which receives the information and stores it in a database. The input is the converted data format, and the output is the successful transmission of data to the server.

[0970] Step 4: Data analysis

[0971] The server analyzes the received data and extracts information on the situation, purpose of use, and items used. For example, "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." The input is the data stored on the server, and the output is the analyzed information.

[0972] Step 5: Launching the Generative AI

[0973] The server launches a generative AI engine (for example, GPT-3) based on the analyzed information. A prompt containing the analyzed information is input to the generative AI. For example, a sample prompt is input: "I would like to create a puzzle for team building to be used in in-house training. The items to be used will be a smartphone, a map, and a QR code. Please provide specific suggestions for the puzzle question, hints, setting, and ending." The input is the analyzed information, and the output is the prompt input to the AI.

[0974] Step 6: Generate the puzzle

[0975] The generation AI generates each element of the puzzle (setting, problem, hint, item, ending) based on the input prompt. For example, it generates "Problem 1: Use a QR code to find a hidden place," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment." The input is the prompt to the AI, and the output is each generated element.

[0976] Step 7: Storing and packaging the data

[0977] The server saves each generated element as a separate data object and converts it into the user's desired format (e.g., text, image file, video, etc.) The converted data is then compiled into a data package. The input is each generated element, and the output is the data package.

[0978] Step 8: Provide to users

[0979] The server sends the final puzzle-solving data package to the user's device. The user can check the contents and download them as needed. The input is the data package, and the output is provided to the user.

[0980] Step 9: Change Requests

[0981] If the user has a change request for a specific part, they enter that information into the terminal again, convert it into JSON format, and send it to the server. The server then inputs the prompt into the generation AI again, regenerating the problem. The input is the change request, and the output is the regenerated data.

[0982] Step 10: Gather feedback

[0983] After completing the task, the user inputs feedback. The device sends the feedback to the server, which stores it as training data for the generative AI. The input is feedback, and the output is added to the training data.

[0984] (Application example 1)

[0985] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0986] Traditional in-factory education and training is often monotonous and inefficient, making it difficult to improve worker learning effectiveness and motivation. There is a need for more effective and engaging ways to communicate training content, especially to new employees and transferred employees. Another problem is the difficulty of customizing the training to meet individual needs.

[0987] 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.

[0988] In this invention, the server includes: means for a user to input information on the situation, purpose of use, and items to be used; artificial intelligence generating means for analyzing the input information and generating a setting, question, hint, item, and ending for solving the puzzle; means for providing the generated content of the puzzle to the user; means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means; and means for providing a smartphone application for implementing specialized education and training for factory workers. This makes it possible to conduct education and training in the factory interactively and effectively.

[0989] A "user" is an entity that uses the system to instruct the creation of puzzles and questions.

[0990] "Information" is data relating to the situation, purpose of use, and items used.

[0991] "Situation" is information about the scene or environment in which the puzzle is solved.

[0992] "Purpose of use" refers to the specific purpose or goal when solving the puzzle.

[0993] "Items used" is information about tools and devices used when solving puzzles.

[0994] "Generative artificial intelligence means" is a technology for automatically generating puzzle settings, questions, hints, items, and endings based on information input by the user.

[0995] "Puzzle content" is a general term for the settings, questions, hints, items, and endings of the generated puzzle.

[0996] "Feedback" refers to information provided by users regarding their evaluation of the system and areas for improvement after completing use.

[0997] A "smartphone application for providing specialized education and training for factory workers" is an application used on a specialized smartphone by factory workers to learn knowledge and skills.

[0998] This invention is a specialized education and training system for factory workers that uses generative AI to provide interactive and effective puzzle solving.

[0999] User operations

[1000] First, the user logs in to the smartphone application and accesses the interface for creating a new puzzle. There, they input information about the situation, purpose of use, and items used. For example, they can input information such as "Situation: New employee training in a factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[1001] Device behavior

[1002] When a user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to a backend server.

[1003] Server Processing

[1004] When the server receives the input data, it analyzes the information and activates a generative AI engine (e.g., OpenAI GPT-3). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it generates "Question 1: Use a factory map to find a specific work area," "Hint: Check the location of a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[1005] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[1006] Provision to users

[1007] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can instruct the change to be made to only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle.

[1008] Collecting feedback

[1009] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[1010] Specific examples

[1011] For example, let's say a factory wants to organize an educational event using puzzles as part of new employee training. The employee logs into the system and enters the following information:

[1012] Situation: New employee training in the factory

[1013] Purpose of use: Understanding work procedures and team building

[1014] Items used: Smartphone, factory map

[1015] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server will accept the change request, regenerate the problem, and provide the updated problem. After the event, feedback from participants will be collected and saved as learning data for the generative AI. This will help improve the accuracy of the generative AI.

[1016] Prompt Sentence Examples

[1017] Situation: New employee training in the factory

[1018] Purpose of use: Understanding work procedures and team building

[1019] Items used: Smartphone, factory map

[1020] Generate a puzzle using the following information:

[1021] In this way, factory workers can acquire the necessary knowledge and skills more effectively and in a fun way.

[1022] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1023] Step 1:

[1024] The user inputs information about the situation, purpose of use, and items used. This input data is collected on the smartphone application and converted into JSON format. Specific inputs include "Situation: New employee training in the factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[1025] Step 2:

[1026] The terminal receives input data, converts it to JSON format, and sends it to the server. Network communication is performed to send the input data (JSON format) to the server. The input here is JSON data received from the terminal, and an output is generated to send it to the server.

[1027] Step 3:

[1028] The server receives the JSON-formatted data, analyzes it, and generates a prompt. Here, the server analyzes the JSON data to extract information on the "situation," "purpose of use," and "items used." As a specific example, the following prompt is generated: "Situation: New employee training within the factory. Purpose of use: Understanding work procedures and team building. Items used: Smartphone, factory map. Please generate a solution to the puzzle based on the information below."

[1029] Step 4:

[1030] The server starts a generative AI engine (e.g., OpenAI GPT-3) and provides the prompt as input. The generative AI engine generates appropriate puzzle settings, questions, hints, items, and endings based on the prompt. In this step, the prompt is the input, and the generated puzzle content is the output.

[1031] Step 5:

[1032] The generated puzzles are converted into individual data objects and saved. For example, they might include a problem such as "Problem 1: Use the factory map to find a specific work area" and a hint such as "Check the location of a specific mark on the map." The output obtained through this process is saved in a database.

[1033] Step 6:

[1034] The server sends the generated puzzle-solving data package to the user's device. The user can check the contents and make changes to specific parts as needed. The sent data package is the output here. Meanwhile, the change request from the user is returned to the server as input.

[1035] Step 7:

[1036] The server that receives the change request regenerates the relevant part. It generates a prompt for regeneration and sends it to the AI ​​engine again. The regenerated puzzle content becomes the output and is sent to the user again as a data package.

[1037] Step 8:

[1038] After completing the task, the user enters feedback, which is added to the database and then used as training data for the generative AI. This feedback becomes the final input, which generates an output that contributes to improving the accuracy of the generative AI.

[1039] The above is the flow of processing of the system program that realizes this application example.

[1040] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1041] This invention is a system that uses generative AI and an emotion engine to easily create original puzzles. The emotion engine can recognize the user's emotions and provide appropriate solutions.

[1042] User operations

[1043] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[1044] Device behavior

[1045] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[1046] Server Processing

[1047] When the server receives the input data, it analyzes the information and activates the generative AI engine and emotion engine. The generative AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. The emotion engine analyzes the input data and user feedback and recognizes the user's emotions. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[1048] Each generated element is saved as an individual data object, allowing for later partial modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package. Furthermore, the generation AI optimizes the output content based on emotional information recognized by the emotion engine.

[1049] Provision to users

[1050] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle. The emotion engine adjusts the content to reflect the user's emotions even when regenerating.

[1051] Collecting feedback

[1052] After completing the task, the user enters feedback. The server adds the collected feedback to the learning data of the generative AI to help improve its accuracy in the future. The emotion engine also analyzes the feedback and reflects it in optimizing the generative AI.

[1053] Specific examples

[1054] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[1055] Situation: In-house training

[1056] Purpose of use: Team building

[1057] Items used: smartphone, map, QR code

[1058] Once this information is sent to the server, the generative AI engine is activated and generates an appropriate puzzle. The emotion engine recognizes emotions from the input data, the user's facial expressions, voice, etc., and adjusts the generated content based on that information. For example, if the user is enjoying themselves, the difficulty level will be increased, or if they are confused, the difficulty level will be lowered.

[1059] The user checks the generated puzzles, and if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the puzzle, and provides the updated problem. The emotion engine also adjusts the content to reflect the user's emotions when regenerating. After the event, feedback is collected from participants and saved as AI learning data. This improves the accuracy of the generation AI and emotion engine.

[1060] The processing flow will be explained below.

[1061] Step 1:

[1062] A user logs into the service and accesses an interface for creating new puzzles.

[1063] Step 2:

[1064] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[1065] Step 3:

[1066] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[1067] Step 4:

[1068] The terminal transmits the converted data to the server.

[1069] Step 5:

[1070] The server receives and analyzes the user's input data and uses that data to activate the generative AI engine and emotion engine.

[1071] Step 6:

[1072] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[1073] Step 7:

[1074] The server's emotion engine analyzes input data and user feedback to recognize the user's emotions, such as whether the user is enjoying or confused.

[1075] Step 8:

[1076] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[1077] Step 9:

[1078] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[1079] Step 10:

[1080] The server transmits the generated puzzle-solving data package to the terminal.

[1081] Step 11:

[1082] The terminal receives all the data and displays it to the user.

[1083] Step 12:

[1084] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[1085] Step 13:

[1086] The server receives the change request and reparses the affected part.

[1087] Step 14:

[1088] The server's emotion engine analyzes the user's emotions again and provides information to reflect them when regenerating. For example, if the user's emotion is confusion, it will adjust the difficulty level accordingly.

[1089] Step 15:

[1090] The server uses a generation AI engine to regenerate only the relevant parts and provide updated content.

[1091] Step 16:

[1092] The server transmits the regenerated data to the terminal again.

[1093] Step 17:

[1094] The terminal receives the regenerated data and displays it to the user.

[1095] Step 18:

[1096] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[1097] Step 19:

[1098] The server receives the feedback and stores it as learning data for the AI, which improves the accuracy of the generative AI and emotion engine.

[1099] Example 2

[1100] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1101] Conventional puzzle generation systems have difficulty generating adaptive content that takes user emotions into account, making it difficult to increase user engagement and satisfaction. In addition, there are limited ways to effectively utilize feedback on the generated content and improve the accuracy of the system.

[1102] 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.

[1103] In this invention, the server includes: means for the user to input information on the situation, purpose of use, and items used; artificial intelligence generating means for analyzing the input information and generating puzzle settings, questions, hints, items, and endings; emotion analyzing means for analyzing the user's emotions and applying them to the generated puzzle content; means for providing the generated puzzle content to the user; and means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means. This makes it possible to generate adaptive, satisfying puzzle content that responds to the user's emotions.

[1104] "User" refers to the person who operates the system and inputs information such as the situation and purpose of use.

[1105] "Situation" refers to the situation, scene, or specific setting in which the mystery is solved.

[1106] "Purpose of use" refers to the goal or intention that the user wishes to achieve by solving the puzzle.

[1107] "Used items" refers to objects, tools, and devices used to progress through the puzzle.

[1108] "Input means" refers to an interface or tool that allows a user to input information into a system.

[1109] "Analysis means" refers to a function for analyzing input information and extracting necessary data.

[1110] "Generative artificial intelligence means" refers to artificial intelligence for generating puzzle settings, questions, hints, items, and endings based on input information.

[1111] "Emotion analysis means" refers to a function for analyzing the user's emotions and reflecting them in the generated puzzle content.

[1112] "Providing means" refers to a function for presenting the generated puzzle content to the user and making it available for use.

[1113] "Feedback collection means" refers to a function for collecting user feedback and using it as learning data for the system.

[1114] "Data package" refers to a collection of puzzle elements stored as individual data objects.

[1115] "Change instructions" refer to requests made by the user to correct or change part of the generated puzzle content.

[1116] "Regeneration means" refers to a function for regenerating a part of the puzzle content that has already been generated based on a change instruction.

[1117] "Text format" refers to a data format expressed as a character string.

[1118] "Image file" refers to a data format that contains visual information represented in bitmap or vector format.

[1119] "Video" refers to a data format that contains dynamic visual information.

[1120] This invention is a system that can easily create original puzzles that adapt to the user's emotions by combining a generative AI and an emotion analysis engine. This system is characterized by analyzing the information entered by the user, and the generative AI generates appropriate puzzles, while the emotion analysis engine analyzes the user's emotions and adjusts the content accordingly.

[1121] User Action:

[1122] First, the user logs into the system and accesses the interface for creating a new puzzle. Then, the user enters the following information into the input form:

[1123] Situation

[1124] Purpose of use

[1125] Items used

[1126] For example, enter "Situation: In-house training," "Purpose of use: Team building," "Items used: Smartphone, map, QR code," etc.

[1127] Terminal behavior:

[1128] When input data is sent from the device to the server, the device converts the information into an appropriate format, such as JSON, and then sends the converted data to the server.

[1129] Server Action:

[1130] The server analyzes the received data and activates the generation AI engine and emotion analysis engine. The generation AI engine generates the puzzle setting, questions, hints, items, and endings based on the input information. For example, it generates questions such as "use a QR code to find a hidden location," hints such as "there is a specific mark on a map," and endings such as "an event that allows everyone to share a sense of accomplishment." The emotion analysis engine analyzes the user's emotions and optimizes the generated content based on that information.

[1131] Format conversion and storage of generated data:

[1132] Each generated element is saved as an individual data object and can be regenerated later in response to a user request for partial changes. The generated elements are converted into the user's desired format (text, image, video, etc.) and compiled into a data package.

[1133] Provide to users:

[1134] The generated data package is sent from the server to the user's device, where the user can check its contents and download them as necessary. If the user requests changes to specific parts, the server accepts the request and the generation AI engine regenerates the data. When regenerating, the emotion analysis engine also adjusts the content to reflect the user's emotions.

[1135] Collecting feedback:

[1136] After solving the puzzle, users can enter feedback, which the server collects and adds to the learning data of the generative AI. This improves the accuracy of the system. The sentiment analysis engine also analyzes the feedback and uses it to optimize the generative AI.

[1137] Examples:

[1138] For example, if a company uses this system to hold a team-building event as part of its in-house training, the steps would be as follows:

[1139] 1. The person in charge logs in to the system and enters the following information:

[1140] Situation: In-house training

[1141] Purpose of use: Team building

[1142] Items used: smartphone, map, QR code

[1143] 2. The entered information is sent from the terminal to the server, and the server analyzes the received data.

[1144] 3. The generative AI engine and sentiment analysis engine are activated to generate an appropriate puzzle, such as "find a hidden place using a QR code," "there is a specific mark on a map," or "an event that everyone can share a sense of accomplishment in."

[1145] 4. If the user checks the generated puzzle and requests changes to specific parts, the server accepts the request and regenerates it.

[1146] 5. After the event, users enter their feedback, which is then added to the AI ​​training data.

[1147] Example prompt sentence:

[1148] "I want to create a team building puzzle suitable for in-house training. The situation is in-house training, and the purpose is team building. The items used are a smartphone, a map, and a QR code."

[1149] The above is the specific content of the "Mode for Carrying Out the Invention." This system makes it possible to generate adaptive puzzle-solving content that responds to the user's emotions and provides a high level of satisfaction.

[1150] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1151] Step 1:

[1152] User Login

[1153] A user enters a username and password to log in to this system. The server authenticates the user based on the entered authentication information, and if successful, provides the user with access to the system.

[1154] Input and Output:

[1155] Input: Username, Password

[1156] Data processing: The server checks the received authentication information against the information in the database.

[1157] Output: User authentication success or failure

[1158] Step 2:

[1159] Entering input data into a form

[1160] The user accesses an interface for creating a new puzzle and enters the following information:

[1161] Situation

[1162] Purpose of use

[1163] Items used

[1164] Input and Output:

[1165] Input: situation, purpose of use, item used

[1166] Data processing: The terminal converts the input data into an appropriate format (e.g., JSON format).

[1167] Output: The transformed data

[1168] Step 3:

[1169] Sending input data

[1170] The terminal transmits the converted data to the server.

[1171] Input and Output:

[1172] Input: Formatted data

[1173] Data processing: Preparing and sending data

[1174] Output: Notification of successful data transmission to the server

[1175] Step 4:

[1176] Data analysis and engine startup

[1177] The server analyzes the received data and activates the generative AI engine and sentiment analysis engine based on the content.

[1178] Input and Output:

[1179] Input: Received data (situation, purpose of use, items used)

[1180] Data processing: Extracting information through data analysis and triggering engine activation

[1181] Output: Engine start success notification

[1182] Step 5:

[1183] Puzzle generation and emotion analysis

[1184] The generative AI engine generates puzzle settings, questions, hints, items, and endings based on input data, while the sentiment analysis engine analyzes the user's emotions and uses that information to adjust the generated content.

[1185] Input and Output:

[1186] Input: Parsed data

[1187] Data processing: Data generation by a generative AI engine and adjustment by a sentiment analysis engine

[1188] Output: Generated puzzle content

[1189] Step 6:

[1190] Format conversion and storage of generated data

[1191] The server stores each generated element as a separate data object, converts each element into the format desired by the user (text, image, video, etc.), and assembles them into a data package.

[1192] Input and Output:

[1193] Input: Generated puzzle content

[1194] Data processing: format conversion and data packaging

[1195] Output: Data package

[1196] Step 7:

[1197] Data package offerings

[1198] The server transmits the generated data package to the user's terminal.

[1199] Input and Output:

[1200] Input: Data package

[1201] Data processing: Data preparation and transmission

[1202] Output: Notification of successful data transmission to the user device

[1203] Step 8:

[1204] Change Request Processing

[1205] If a user requests a change to a part of the generated puzzle, the request is sent to the server. The server accepts the request, and the AI ​​generation engine regenerates it. During regeneration, the emotion analysis engine adjusts the content to reflect the user's emotions.

[1206] Input and Output:

[1207] Input: Change Request

[1208] Data processing: Requirement analysis and regeneration process execution

[1209] Output: Regenerated puzzle content

[1210] Step 9:

[1211] Collecting and analyzing feedback

[1212] After solving the puzzle, the user inputs feedback, which the server uses as learning data for the AI ​​generation engine and the emotion analysis engine.

[1213] Input and Output:

[1214] Input: User feedback

[1215] Data processing: analyzing feedback and adding it to the training data

[1216] Output: Improved system accuracy

[1217] (Application example 2)

[1218] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1219] Factory training and operational guidance require flexible content adjustments according to the emotions and stress levels of individual employees. In addition, since it is effective to conduct training in a format that is close to actual operating scenarios, it is necessary for the system to recognize emotions on the spot and optimize the content and difficulty in real time.

[1220] 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.

[1221] In this invention, the server includes: a means for a user to input information on the situation, purpose of use, and tools used; a generating AI means for analyzing the input information and generating puzzle settings, questions, hints, tools, and endings; a means for providing the information to the user; a means including an emotion recognition engine for recognizing the user's emotions and adjusting the difficulty and content of the generated puzzle; and a means for collecting user feedback and adding it to the learning data of the generating AI. This makes it possible to adapt training content in real time to match the emotions of employees.

[1222] "User" refers to a person who uses the system to input information and experience or evaluate the puzzles provided.

[1223] "Situation" refers to the setting, such as the situation, environment, and context in which the puzzle is solved.

[1224] "Purpose of use" refers to the goal or purpose that you intend to achieve by using the system.

[1225] "Tools used" refers to tools and equipment used to solve the puzzle, such as smartphones and robots.

[1226] "Generative artificial intelligence means" refers to a function that uses artificial intelligence technology to generate each element of the puzzle (setting, problem, hint, tool, ending, etc.) based on information entered by the user.

[1227] "Means of provision" refers to the means for presenting and delivering the generated puzzle content to the user.

[1228] An "emotion recognition engine" refers to a technology that has the ability to recognize emotions from a user's facial expressions, voice, actions, etc., and adjust the system's output content based on that.

[1229] "Feedback" refers to information such as impressions, evaluations, and areas for improvement that users provide after using the system.

[1230] "Training data" refers to data that the system uses to generate more accurate results, including, for example, user feedback.

[1231] This invention is a puzzle-solving type education system aimed at operational training and efficiency improvement in a factory. The system is implemented as follows.

[1232] Program processing explanation

[1233] User operations

[1234] The user first inputs information about the situation, purpose of use, and tools used into the system interface. For example, they might enter information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." This information is converted into JSON format by the device and sent to the server.

[1235] Server Processing

[1236] The server first analyzes the information entered by the user. The analyzed information is used by a generative artificial intelligence means to generate a setting, questions, hints, tools, and ending for solving the puzzle. For example, specific questions and hints related to assembly line training are generated.

[1237] Introducing emotion recognition

[1238] The generated puzzles are then adapted using an emotion recognition engine that recognizes the user's emotions, automatically adjusting the difficulty level, lowering it if the user is confused and raising it if the user is enjoying it.

[1239] Submissions and Feedback

[1240] The final puzzle content generated is provided to the user, who can then train based on it. After the user actually trains, they input their feedback into the system. This feedback is collected on the server and added to the learning data of the generating AI.

[1241] Hardware and software used

[1242] Hardware: robots, smartphones, augmented reality devices

[1243] Software: Generative AI method (generative AI model), emotion recognition engine, JSON parser

[1244] Specific examples

[1245] For example, when operation training is carried out for new employees in a factory, the system operates as follows.

[1246] Prompt Sentence Examples

[1247] Situation: Assembly line training

[1248] Purpose of use: To improve work efficiency

[1249] Tools used: Robot, smartphone, augmented reality

[1250] Based on this prompt, a generative artificial intelligence means generates training content, and an emotion recognition engine adjusts the difficulty and content in real time to match the user's emotional state. Specifically, for example, instructions for each step to be performed on an assembly line and hints appropriate to the situation are generated. The generated content is then provided to the user, who can use an augmented reality device to continue training in an actual factory environment. Feedback from the user is used to improve the accuracy of future training content.

[1251] conclusion

[1252] This invention makes it possible to dynamically provide operational training in factories in a format that is tailored to each individual user, which is expected to improve training effectiveness and work efficiency.

[1253] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1254] Step 1:

[1255] The user logs into the system and inputs information about the situation, purpose of use, and tools used into the interface. At this stage, the input is specific information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." The input data is converted into JSON format by the terminal, which prepares the input data in a format that can be processed on the server side.

[1256] Step 2:

[1257] The user's input data, converted into JSON format, is sent from the device to the server. The server parses the received JSON data and understands its contents. The parsed data is sent to a generative AI model, which generates specific puzzle-solving settings, questions, hints, tools, and endings based on the training scenario. The output at this stage is structured data containing each element.

[1258] Step 3:

[1259] The server sends the generated puzzle data to an emotion recognition engine. The emotion recognition engine collects the user's facial expressions, voice data, and other data, and analyzes their emotional state in real time. The obtained emotion data is used to adjust the difficulty and content of the generated puzzle data. For example, if the system recognizes that the user is confused, it lowers the difficulty of the problem, and conversely, if the user is enjoying the problem, it increases the difficulty. The final output is puzzle data optimized according to the user's emotion.

[1260] Step 4:

[1261] The optimized puzzle-solving data is then sent back to the device from the server and provided to the user. The device displays the puzzle content visually or audibly, and the user actually practices using a smartphone or an augmented reality device.

[1262] Step 5:

[1263] Users train by solving puzzles and input feedback on the process and results. This feedback data is then sent from the device to the server. The server analyzes the collected feedback data and stores it as training data for the generative AI model. This improves the quality and accuracy of future puzzle-solving scenarios generated by the system.

[1264] Step 6:

[1265] The server accepts requests to change parts of the generated puzzle as needed. If the user wishes to change the difficulty or content of a specific part, it regenerates only that part. In this case, adjustments are made according to the user's emotional state, and the changed data is provided again.

[1266] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1267] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1268] 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.

[1269] [Fourth embodiment]

[1270] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1271] 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.

[1272] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1273] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1274] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1275] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1276] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1277] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1278] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1279] 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.

[1280] 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.

[1281] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1282] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1283] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[1284] User operations

[1285] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[1286] Device behavior

[1287] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[1288] Server Processing

[1289] When the server receives the input data, it analyzes the information and activates the generative AI engine. The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," or "Ending: An event that allows everyone to share a sense of accomplishment."

[1290] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[1291] Provision to users

[1292] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[1293] Collecting feedback

[1294] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator to help improve its accuracy in the future.

[1295] Specific examples

[1296] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[1297] Situation: In-house training

[1298] Purpose of use: Team building

[1299] Items used: smartphone, map, QR code

[1300] Once this information is sent to the server, the generative AI engine runs and generates an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the problem, and provides the updated problem. After the event ends, feedback is collected from participants and saved as AF learning data. This allows the accuracy of the generative AI to be improved.

[1301] The processing flow will be explained below.

[1302] Step 1:

[1303] A user logs into the service and accesses an interface for creating new puzzles.

[1304] Step 2:

[1305] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[1306] Step 3:

[1307] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[1308] Step 4:

[1309] The terminal transmits the converted data to the server.

[1310] Step 5:

[1311] The server receives and analyzes the user's input data and uses that data to issue instructions to the generative AI engine.

[1312] Step 6:

[1313] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates content such as "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[1314] Step 7:

[1315] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[1316] Step 8:

[1317] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[1318] Step 9:

[1319] The server transmits the generated puzzle-solving data package to the terminal.

[1320] Step 10:

[1321] The terminal receives all the data and displays it to the user.

[1322] Step 11:

[1323] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[1324] Step 12:

[1325] The server receives the change request and reparses the affected part.

[1326] Step 13:

[1327] The server's generation AI engine regenerates only the relevant parts, enabling updated content to be provided.

[1328] Step 14:

[1329] The server transmits the regenerated data to the terminal again.

[1330] Step 15:

[1331] The terminal receives the regenerated data and displays it to the user.

[1332] Step 16:

[1333] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[1334] Step 17:

[1335] The server receives the feedback and stores it as learning data for the AI, which helps improve the accuracy of the generating AI.

[1336] Example 1

[1337] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1338] Conventional puzzle creation systems require users to manually create settings, questions, hints, items, and endings, which is both time-consuming and prone to inconsistent quality. Furthermore, when changes are needed to the generated puzzle content, the correction process is cumbersome, making it difficult to respond quickly and efficiently. Furthermore, there is a lack of means to provide the generated puzzle in various formats, such as text, images, and videos, resulting in low user convenience. The present invention aims to solve these problems and provide a system that automatically generates efficient, high-quality puzzles.

[1339] 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.

[1340] In this invention, the server includes: a means for a user to input information about the situation, purpose of use, and items used; a generating AI means for analyzing the input information and generating a puzzle setting, question, hint, item, and ending; a means for converting the input information into an appropriate data format and sending it to the server; a means for providing the generated puzzle content to the user; and a means for collecting user feedback and adding it to the learning data of the generating AI. This enables a system that can automatically generate high-quality puzzles quickly and efficiently and flexibly respond to changes. Furthermore, by including a means for exporting the generated puzzles in text, image files, or video formats, user convenience can be improved.

[1341] text

[1342] "User" refers to a person or organization that uses the system to create and use puzzles.

[1343] "Situation" refers to the specific background or situation in which the puzzle is solved.

[1344] "Purpose of use" refers to the specific purpose or goal for which the puzzle is used.

[1345] "Items used" refers to the objects and tools used by the user while solving the puzzle.

[1346] "Means of input" refers to the method or mechanism by which a user inputs information about the situation, purpose of use, and items used into the system.

[1347] "Means of analysis" refers to the method or mechanism for analyzing the content and characteristics of data based on input information.

[1348] "Generative artificial intelligence means" refers to technologies such as generative AI models that automatically create puzzle settings, questions, hints, items, and endings based on analyzed information.

[1349] "Means for converting into data format" refers to the method or mechanism for converting information entered by the user into a format that is easy for the server to process.

[1350] "Means of sending to the server" refers to the method or mechanism for sending input information or generated data to the server via a network.

[1351] "Means for providing to users" refers to the method or mechanism for providing the content of the generated puzzle so that users can check, download or use it.

[1352] "Means of collecting feedback" refers to the methods and mechanisms for collecting opinions and impressions from users after using the service.

[1353] "Means of adding to training data" refers to the method or mechanism for adding collected feedback to the training data of the generative AI.

[1354] "Means for regeneration when a change request is received" refers to the method or mechanism for receiving a change request from a user and regenerating the relevant information.

[1355] "Means for making the solution exportable in text, image file, or video format" refers to a method or mechanism for saving or providing the generated solution in text, image file, or video format.

[1356] text

[1357] This invention is a system that allows users to easily create original puzzles using a generation AI. In this system, users input information about the situation, purpose, and items used, and the generation AI generates the setting, questions, hints, items, and endings for the puzzle based on that information.

[1358] User operations

[1359] First, users log in to the service and access an interface for creating new puzzles. Next, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[1360] Device behavior

[1361] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[1362] Server Processing

[1363] When the server receives the input data, it analyzes the information and launches a generative AI engine (e.g., GPT-3). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it might generate "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that gives everyone a sense of accomplishment." Each generated element is saved as an individual data object, allowing for later partial modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[1364] Provision to users

[1365] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests a change to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates it.

[1366] Collecting feedback

[1367] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[1368] Specific examples

[1369] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[1370] Situation: In-house training

[1371] Purpose of use: Team building

[1372] Items used: smartphone, map, QR code

[1373] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can submit a change request for that part. The server will accept the change request, regenerate the problem, and provide the updated problem.

[1374] After the event, feedback will be collected from participants and saved as learning data for the AI, which will improve the accuracy of the AI.

[1375] Example prompts for generative AI models

[1376] "I'd like to create a puzzle for team building to be used in our in-house training. The items to be used will be a smartphone, a map, and a QR code. I'd like specific suggestions for the puzzle, the problem, the hints, the setting, and the ending."

[1377] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1378] text

[1379] Step 1: User Login

[1380] A user accesses the system and enters their authentication information (such as user ID and password) into an input form. The entered authentication information is sent from the terminal to the server. The server compares the received authentication information with a database, and if authentication is successful, it redirects the user to the main interface. In this process, the input is the user's authentication information, and the output is whether the authentication was successful or not.

[1381] Step 2: Enter your information

[1382] The user accesses an interface for creating new puzzles and inputs information about the situation, purpose of use, and items used. For example, they might input "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." This information is converted into an appropriate data format (e.g., JSON format) on the device. The input is the user's information, and the output is the converted data format.

[1383] Step 3: Sending data

[1384] The terminal sends the converted information to the server, which receives the information and stores it in a database. The input is the converted data format, and the output is the successful transmission of data to the server.

[1385] Step 4: Data analysis

[1386] The server analyzes the received data and extracts information on the situation, purpose of use, and items used. For example, "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code." The input is the data stored on the server, and the output is the analyzed information.

[1387] Step 5: Launching the Generative AI

[1388] The server launches a generative AI engine (for example, GPT-3) based on the analyzed information. A prompt containing the analyzed information is input to the generative AI. For example, a sample prompt is input: "I would like to create a puzzle for team building to be used in in-house training. The items to be used will be a smartphone, a map, and a QR code. Please provide specific suggestions for the puzzle question, hints, setting, and ending." The input is the analyzed information, and the output is the prompt input to the AI.

[1389] Step 6: Generate the puzzle

[1390] The generation AI generates each element of the puzzle (setting, problem, hint, item, ending) based on the input prompt. For example, it generates "Problem 1: Use a QR code to find a hidden place," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment." The input is the prompt to the AI, and the output is each generated element.

[1391] Step 7: Storing and packaging the data

[1392] The server saves each generated element as a separate data object and converts it into the user's desired format (e.g., text, image file, video, etc.) The converted data is then compiled into a data package. The input is each generated element, and the output is the data package.

[1393] Step 8: Provide to users

[1394] The server sends the final puzzle-solving data package to the user's device. The user can check the contents and download them as needed. The input is the data package, and the output is provided to the user.

[1395] Step 9: Change Requests

[1396] If the user has a change request for a specific part, they enter that information into the terminal again, convert it into JSON format, and send it to the server. The server then inputs the prompt into the generation AI again, regenerating the problem. The input is the change request, and the output is the regenerated data.

[1397] Step 10: Gather feedback

[1398] After completing the task, the user inputs feedback. The device sends the feedback to the server, which stores it as training data for the generative AI. The input is feedback, and the output is added to the training data.

[1399] (Application example 1)

[1400] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1401] Traditional in-factory education and training is often monotonous and inefficient, making it difficult to improve worker learning effectiveness and motivation. There is a need for more effective and engaging ways to communicate training content, especially to new employees and transferred employees. Another problem is the difficulty of customizing the training to meet individual needs.

[1402] 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.

[1403] In this invention, the server includes: means for a user to input information on the situation, purpose of use, and items to be used; artificial intelligence generating means for analyzing the input information and generating a setting, question, hint, item, and ending for solving the puzzle; means for providing the generated content of the puzzle to the user; means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means; and means for providing a smartphone application for implementing specialized education and training for factory workers. This makes it possible to conduct education and training in the factory interactively and effectively.

[1404] A "user" is an entity that uses the system to instruct the creation of puzzles and questions.

[1405] "Information" is data relating to the situation, purpose of use, and items used.

[1406] "Situation" is information about the scene or environment in which the puzzle is solved.

[1407] "Purpose of use" refers to the specific purpose or goal when solving the puzzle.

[1408] "Items used" is information about tools and devices used when solving puzzles.

[1409] "Generative artificial intelligence means" is a technology for automatically generating puzzle settings, questions, hints, items, and endings based on information input by the user.

[1410] "Puzzle content" is a general term for the settings, questions, hints, items, and endings of the generated puzzle.

[1411] "Feedback" refers to information provided by users regarding their evaluation of the system and areas for improvement after completing use.

[1412] A "smartphone application for providing specialized education and training for factory workers" is an application used on a specialized smartphone by factory workers to learn knowledge and skills.

[1413] This invention is a specialized education and training system for factory workers that uses generative AI to provide interactive and effective puzzle solving.

[1414] User operations

[1415] First, the user logs in to the smartphone application and accesses the interface for creating a new puzzle. There, they input information about the situation, purpose of use, and items used. For example, they can input information such as "Situation: New employee training in a factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[1416] Device behavior

[1417] When a user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to a backend server.

[1418] Server Processing

[1419] When the server receives the input data, it analyzes the information and activates a generative AI engine (e.g., OpenAI GPT-3). The generative AI engine generates the puzzle setting, questions, hints, items, and ending based on the input data. For example, it generates "Question 1: Use a factory map to find a specific work area," "Hint: Check the location of a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[1420] Each generated element is saved as an individual data object, allowing for subsequent modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package.

[1421] Provision to users

[1422] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can instruct the change to be made to only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle.

[1423] Collecting feedback

[1424] After completing the task, the user enters feedback, which the server then adds to the learning data of the AI ​​generator, helping to improve its accuracy in the future.

[1425] Specific examples

[1426] For example, let's say a factory wants to organize an educational event using puzzles as part of new employee training. The employee logs into the system and enters the following information:

[1427] Situation: New employee training in the factory

[1428] Purpose of use: Understanding work procedures and team building

[1429] Items used: Smartphone, factory map

[1430] Once this information is sent to the server, the generative AI engine will run and generate an appropriate solution to the puzzle. The user can review the generated solution and, if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server will accept the change request, regenerate the problem, and provide the updated problem. After the event, feedback from participants will be collected and saved as learning data for the generative AI. This will help improve the accuracy of the generative AI.

[1431] Prompt Sentence Examples

[1432] Situation: New employee training in the factory

[1433] Purpose of use: Understanding work procedures and team building

[1434] Items used: Smartphone, factory map

[1435] Generate a puzzle using the following information:

[1436] In this way, factory workers can acquire the necessary knowledge and skills more effectively and in a fun way.

[1437] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1438] Step 1:

[1439] The user inputs information about the situation, purpose of use, and items used. This input data is collected on the smartphone application and converted into JSON format. Specific inputs include "Situation: New employee training in the factory," "Purpose of use: Understanding work procedures and team building," and "Items used: Smartphone, factory map."

[1440] Step 2:

[1441] The terminal receives input data, converts it to JSON format, and sends it to the server. Network communication is performed to send the input data (JSON format) to the server. The input here is JSON data received from the terminal, and an output is generated to send it to the server.

[1442] Step 3:

[1443] The server receives the JSON-formatted data, analyzes it, and generates a prompt. Here, the server analyzes the JSON data to extract information on the "situation," "purpose of use," and "items used." As a specific example, the following prompt is generated: "Situation: New employee training within the factory. Purpose of use: Understanding work procedures and team building. Items used: Smartphone, factory map. Please generate a solution to the puzzle based on the information below."

[1444] Step 4:

[1445] The server starts a generative AI engine (e.g., OpenAI GPT-3) and provides the prompt as input. The generative AI engine generates appropriate puzzle settings, questions, hints, items, and endings based on the prompt. In this step, the prompt is the input, and the generated puzzle content is the output.

[1446] Step 5:

[1447] The generated puzzles are converted into individual data objects and saved. For example, they might include a problem such as "Problem 1: Use the factory map to find a specific work area" and a hint such as "Check the location of a specific mark on the map." The output obtained through this process is saved in a database.

[1448] Step 6:

[1449] The server sends the generated puzzle-solving data package to the user's device. The user can check the contents and make changes to specific parts as needed. The sent data package is the output here. Meanwhile, the change request from the user is returned to the server as input.

[1450] Step 7:

[1451] The server that receives the change request regenerates the relevant part. It generates a prompt for regeneration and sends it to the AI ​​engine again. The regenerated puzzle content becomes the output and is sent to the user again as a data package.

[1452] Step 8:

[1453] After completing the task, the user enters feedback, which is added to the database and then used as training data for the generative AI. This feedback becomes the final input, which generates an output that contributes to improving the accuracy of the generative AI.

[1454] The above is the flow of processing of the system program that realizes this application example.

[1455] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1456] This invention is a system that uses generative AI and an emotion engine to easily create original puzzles. The emotion engine can recognize the user's emotions and provide appropriate solutions.

[1457] User operations

[1458] Users first log in to the service and access an interface for creating new puzzles. After that, they enter information about the situation, purpose of use, and items used into an input form. For example, they can enter information such as "Situation: In-house training," "Purpose of use: Team building," and "Items used: Smartphone, map, QR code."

[1459] Device behavior

[1460] When the user submits input data, the device converts the information into an appropriate format, such as JSON, and sends it to the server.

[1461] Server Processing

[1462] When the server receives the input data, it analyzes the information and activates the generative AI engine and emotion engine. The generative AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. The emotion engine analyzes the input data and user feedback and recognizes the user's emotions. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[1463] Each generated element is saved as an individual data object, allowing for later partial modification requests from the user. Each element is converted into the user's desired format (text, image file, video, etc.) and compiled into a data package. Furthermore, the generation AI optimizes the output content based on emotional information recognized by the emotion engine.

[1464] Provision to users

[1465] The server sends the generated puzzle-solving data package to the user's device, where the user can confirm and download the contents. If the user requests changes to a specific part, they can edit or change only that part. This change request is also sent to the server, and the generation AI engine regenerates the puzzle. The emotion engine adjusts the content to reflect the user's emotions even when regenerating.

[1466] Collecting feedback

[1467] After completing the task, the user enters feedback. The server adds the collected feedback to the learning data of the generative AI to help improve its accuracy in the future. The emotion engine also analyzes the feedback and reflects it in optimizing the generative AI.

[1468] Specific examples

[1469] For example, let's say a company wants to organize a team-building event using puzzle solving as part of their internal training. The person in charge logs into the system and enters the following information:

[1470] Situation: In-house training

[1471] Purpose of use: Team building

[1472] Items used: smartphone, map, QR code

[1473] Once this information is sent to the server, the generative AI engine is activated and generates an appropriate puzzle. The emotion engine recognizes emotions from the input data, the user's facial expressions, voice, etc., and adjusts the generated content based on that information. For example, if the user is enjoying themselves, the difficulty level will be increased, or if they are confused, the difficulty level will be lowered.

[1474] The user checks the generated puzzles, and if they want to make "Problem 1" a little more difficult, for example, they can request a change to that part. The server accepts the change request, regenerates the puzzle, and provides the updated problem. The emotion engine also adjusts the content to reflect the user's emotions when regenerating. After the event, feedback is collected from participants and saved as AI learning data. This improves the accuracy of the generation AI and emotion engine.

[1475] The processing flow will be explained below.

[1476] Step 1:

[1477] A user logs into the service and accesses an interface for creating new puzzles.

[1478] Step 2:

[1479] The user enters information such as "situation," "purpose of use," and "items used" into the input form. For example, the user might enter "situation: in-house training," "purpose of use: team building," and "items used: smartphone, map, QR code."

[1480] Step 3:

[1481] The terminal receives the input data and converts it into an appropriate format, such as JSON.

[1482] Step 4:

[1483] The terminal transmits the converted data to the server.

[1484] Step 5:

[1485] The server receives and analyzes the user's input data and uses that data to activate the generative AI engine and emotion engine.

[1486] Step 6:

[1487] The server's AI engine generates the puzzle setting, questions, hints, items, and endings based on the input data. For example, it generates "Question 1: Use a QR code to find a hidden location," "Hint: There is a specific mark on the map," and "Ending: An event that allows everyone to share a sense of accomplishment."

[1488] Step 7:

[1489] The server's emotion engine analyzes input data and user feedback to recognize the user's emotions, such as whether the user is enjoying or confused.

[1490] Step 8:

[1491] The server stores each generated element as a separate data object, allowing for subsequent partial modification requests from the user.

[1492] Step 9:

[1493] The server converts each element into the user's desired format (e.g., text, image file, video, etc.) and combines them into a single data package.

[1494] Step 10:

[1495] The server transmits the generated puzzle-solving data package to the terminal.

[1496] Step 11:

[1497] The terminal receives all the data and displays it to the user.

[1498] Step 12:

[1499] The user checks the generated puzzle. If there are any changes required for a specific part, the user inputs the specific change request for that part and submits it again.

[1500] Step 13:

[1501] The server receives the change request and reparses the affected part.

[1502] Step 14:

[1503] The server's emotion engine analyzes the user's emotions again and provides information to reflect them when regenerating. For example, if the user's emotion is confusion, it will adjust the difficulty level accordingly.

[1504] Step 15:

[1505] The server uses a generation AI engine to regenerate only the relevant parts and provide updated content.

[1506] Step 16:

[1507] The server transmits the regenerated data to the terminal again.

[1508] Step 17:

[1509] The terminal receives the regenerated data and displays it to the user.

[1510] Step 18:

[1511] The user performs a final check and completes the puzzle. After use, the user enters feedback.

[1512] Step 19:

[1513] The server receives the feedback and stores it as learning data for the AI, which improves the accuracy of the generative AI and emotion engine.

[1514] Example 2

[1515] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1516] Conventional puzzle generation systems have difficulty generating adaptive content that takes user emotions into account, making it difficult to increase user engagement and satisfaction. In addition, there are limited ways to effectively utilize feedback on the generated content and improve the accuracy of the system.

[1517] 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.

[1518] In this invention, the server includes: means for the user to input information on the situation, purpose of use, and items used; artificial intelligence generating means for analyzing the input information and generating puzzle settings, questions, hints, items, and endings; emotion analyzing means for analyzing the user's emotions and applying them to the generated puzzle content; means for providing the generated puzzle content to the user; and means for collecting user feedback and adding it to the learning data of the artificial intelligence generating means. This makes it possible to generate adaptive, satisfying puzzle content that responds to the user's emotions.

[1519] "User" refers to the person who operates the system and inputs information such as the situation and purpose of use.

[1520] "Situation" refers to the situation, scene, or specific setting in which the mystery is solved.

[1521] "Purpose of use" refers to the goal or intention that the user wishes to achieve by solving the puzzle.

[1522] "Used items" refers to objects, tools, and devices used to progress through the puzzle.

[1523] "Input means" refers to an interface or tool that allows a user to input information into a system.

[1524] "Analysis means" refers to a function for analyzing input information and extracting necessary data.

[1525] "Generative artificial intelligence means" refers to artificial intelligence for generating puzzle settings, questions, hints, items, and endings based on input information.

[1526] "Emotion analysis means" refers to a function for analyzing the user's emotions and reflecting them in the generated puzzle content.

[1527] "Providing means" refers to a function for presenting the generated puzzle content to the user and making it available for use.

[1528] "Feedback collection means" refers to a function for collecting user feedback and using it as learning data for the system.

[1529] "Data package" refers to a collection of puzzle elements stored as individual data objects.

[1530] "Change instructions" refer to requests made by the user to correct or change part of the generated puzzle content.

[1531] "Regeneration means" refers to a function for regenerating a part of the puzzle content that has already been generated based on a change instruction.

[1532] "Text format" refers to a data format expressed as a character string.

[1533] "Image file" refers to a data format that contains visual information represented in bitmap or vector format.

[1534] "Video" refers to a data format that contains dynamic visual information.

[1535] This invention is a system that can easily create original puzzles that adapt to the user's emotions by combining a generative AI and an emotion analysis engine. This system is characterized by analyzing the information entered by the user, and the generative AI generates appropriate puzzles, while the emotion analysis engine analyzes the user's emotions and adjusts the content accordingly.

[1536] User Action:

[1537] First, the user logs into the system and accesses the interface for creating a new puzzle. Then, the user enters the following information into the input form:

[1538] Situation

[1539] Purpose of use

[1540] Items used

[1541] For example, enter "Situation: In-house training," "Purpose of use: Team building," "Items used: Smartphone, map, QR code," etc.

[1542] Terminal behavior:

[1543] When input data is sent from the device to the server, the device converts the information into an appropriate format, such as JSON, and then sends the converted data to the server.

[1544] Server Action:

[1545] The server analyzes the received data and activates the generation AI engine and emotion analysis engine. The generation AI engine generates the puzzle setting, questions, hints, items, and endings based on the input information. For example, it generates questions such as "use a QR code to find a hidden location," hints such as "there is a specific mark on a map," and endings such as "an event that allows everyone to share a sense of accomplishment." The emotion analysis engine analyzes the user's emotions and optimizes the generated content based on that information.

[1546] Format conversion and storage of generated data:

[1547] Each generated element is saved as an individual data object and can be regenerated later in response to a user request for partial changes. The generated elements are converted into the user's desired format (text, image, video, etc.) and compiled into a data package.

[1548] Provide to users:

[1549] The generated data package is sent from the server to the user's device, where the user can check its contents and download them as necessary. If the user requests changes to specific parts, the server accepts the request and the generation AI engine regenerates the data. When regenerating, the emotion analysis engine also adjusts the content to reflect the user's emotions.

[1550] Collecting feedback:

[1551] After solving the puzzle, users can enter feedback, which the server collects and adds to the learning data of the generative AI. This improves the accuracy of the system. The sentiment analysis engine also analyzes the feedback and uses it to optimize the generative AI.

[1552] Examples:

[1553] For example, if a company uses this system to hold a team-building event as part of its in-house training, the steps would be as follows:

[1554] 1. The person in charge logs in to the system and enters the following information:

[1555] Situation: In-house training

[1556] Purpose of use: Team building

[1557] Items used: smartphone, map, QR code

[1558] 2. The entered information is sent from the terminal to the server, and the server analyzes the received data.

[1559] 3. The generative AI engine and sentiment analysis engine are activated to generate an appropriate puzzle, such as "find a hidden place using a QR code," "there is a specific mark on a map," or "an event that everyone can share a sense of accomplishment in."

[1560] 4. If the user checks the generated puzzle and requests changes to specific parts, the server accepts the request and regenerates it.

[1561] 5. After the event, users enter their feedback, which is then added to the AI ​​training data.

[1562] Example prompt sentence:

[1563] "I want to create a team building puzzle suitable for in-house training. The situation is in-house training, and the purpose is team building. The items used are a smartphone, a map, and a QR code."

[1564] The above is the specific content of the "Mode for Carrying Out the Invention." This system makes it possible to generate adaptive puzzle-solving content that responds to the user's emotions and provides a high level of satisfaction.

[1565] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1566] Step 1:

[1567] User Login

[1568] A user enters a username and password to log in to this system. The server authenticates the user based on the entered authentication information, and if successful, provides the user with access to the system.

[1569] Input and Output:

[1570] Input: Username, Password

[1571] Data processing: The server checks the received authentication information against the information in the database.

[1572] Output: User authentication success or failure

[1573] Step 2:

[1574] Entering input data into a form

[1575] The user accesses an interface for creating a new puzzle and enters the following information:

[1576] Situation

[1577] Purpose of use

[1578] Items used

[1579] Input and Output:

[1580] Input: situation, purpose of use, item used

[1581] Data processing: The terminal converts the input data into an appropriate format (e.g., JSON format).

[1582] Output: The transformed data

[1583] Step 3:

[1584] Sending input data

[1585] The terminal transmits the converted data to the server.

[1586] Input and Output:

[1587] Input: Formatted data

[1588] Data processing: Preparing and sending data

[1589] Output: Notification of successful data transmission to the server

[1590] Step 4:

[1591] Data analysis and engine startup

[1592] The server analyzes the received data and activates the generative AI engine and sentiment analysis engine based on the content.

[1593] Input and Output:

[1594] Input: Received data (situation, purpose of use, items used)

[1595] Data processing: Extracting information through data analysis and triggering engine activation

[1596] Output: Engine start success notification

[1597] Step 5:

[1598] Puzzle generation and emotion analysis

[1599] The generative AI engine generates puzzle settings, questions, hints, items, and endings based on input data, while the sentiment analysis engine analyzes the user's emotions and uses that information to adjust the generated content.

[1600] Input and Output:

[1601] Input: Parsed data

[1602] Data processing: Data generation by a generative AI engine and adjustment by a sentiment analysis engine

[1603] Output: Generated puzzle content

[1604] Step 6:

[1605] Format conversion and storage of generated data

[1606] The server stores each generated element as a separate data object, converts each element into the format desired by the user (text, image, video, etc.), and assembles them into a data package.

[1607] Input and Output:

[1608] Input: Generated puzzle content

[1609] Data processing: format conversion and data packaging

[1610] Output: Data package

[1611] Step 7:

[1612] Data package offerings

[1613] The server transmits the generated data package to the user's terminal.

[1614] Input and Output:

[1615] Input: Data package

[1616] Data processing: Data preparation and transmission

[1617] Output: Notification of successful data transmission to the user device

[1618] Step 8:

[1619] Change Request Processing

[1620] If a user requests a change to a part of the generated puzzle, the request is sent to the server. The server accepts the request, and the AI ​​generation engine regenerates it. During regeneration, the emotion analysis engine adjusts the content to reflect the user's emotions.

[1621] Input and Output:

[1622] Input: Change Request

[1623] Data processing: Requirement analysis and regeneration process execution

[1624] Output: Regenerated puzzle content

[1625] Step 9:

[1626] Collecting and analyzing feedback

[1627] After solving the puzzle, the user inputs feedback, which the server uses as learning data for the AI ​​generation engine and the emotion analysis engine.

[1628] Input and Output:

[1629] Input: User feedback

[1630] Data processing: analyzing feedback and adding it to the training data

[1631] Output: Improved system accuracy

[1632] (Application example 2)

[1633] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1634] Factory training and operational guidance require flexible content adjustments according to the emotions and stress levels of individual employees. In addition, since it is effective to conduct training in a format that is close to actual operating scenarios, it is necessary for the system to recognize emotions on the spot and optimize the content and difficulty in real time.

[1635] 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.

[1636] In this invention, the server includes: a means for a user to input information on the situation, purpose of use, and tools used; a generating AI means for analyzing the input information and generating puzzle settings, questions, hints, tools, and endings; a means for providing the information to the user; a means including an emotion recognition engine for recognizing the user's emotions and adjusting the difficulty and content of the generated puzzle; and a means for collecting user feedback and adding it to the learning data of the generating AI. This makes it possible to adapt training content in real time to match the emotions of employees.

[1637] "User" refers to a person who uses the system to input information and experience or evaluate the puzzles provided.

[1638] "Situation" refers to the setting, such as the situation, environment, and context in which the puzzle is solved.

[1639] "Purpose of use" refers to the goal or purpose that you intend to achieve by using the system.

[1640] "Tools used" refers to tools and equipment used to solve the puzzle, such as smartphones and robots.

[1641] "Generative artificial intelligence means" refers to a function that uses artificial intelligence technology to generate each element of the puzzle (setting, problem, hint, tool, ending, etc.) based on information entered by the user.

[1642] "Means of provision" refers to the means for presenting and delivering the generated puzzle content to the user.

[1643] An "emotion recognition engine" refers to a technology that has the ability to recognize emotions from a user's facial expressions, voice, actions, etc., and adjust the system's output content based on that.

[1644] "Feedback" refers to information such as impressions, evaluations, and areas for improvement that users provide after using the system.

[1645] "Training data" refers to data that the system uses to generate more accurate results, including, for example, user feedback.

[1646] This invention is a puzzle-solving type education system aimed at operational training and efficiency improvement in a factory. The system is implemented as follows.

[1647] Program processing explanation

[1648] User operations

[1649] The user first inputs information about the situation, purpose of use, and tools used into the system interface. For example, they might enter information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." This information is converted into JSON format by the device and sent to the server.

[1650] Server Processing

[1651] The server first analyzes the information entered by the user. The analyzed information is used by a generative artificial intelligence means to generate a setting, questions, hints, tools, and ending for solving the puzzle. For example, specific questions and hints related to assembly line training are generated.

[1652] Introducing emotion recognition

[1653] The generated puzzles are then adapted using an emotion recognition engine that recognizes the user's emotions, automatically adjusting the difficulty level, lowering it if the user is confused and raising it if the user is enjoying it.

[1654] Submissions and Feedback

[1655] The final puzzle content generated is provided to the user, who can then train based on it. After the user actually trains, they input their feedback into the system. This feedback is collected on the server and added to the learning data of the generating AI.

[1656] Hardware and software used

[1657] Hardware: robots, smartphones, augmented reality devices

[1658] Software: Generative AI method (generative AI model), emotion recognition engine, JSON parser

[1659] Specific examples

[1660] For example, when operation training is carried out for new employees in a factory, the system operates as follows.

[1661] Prompt Sentence Examples

[1662] Situation: Assembly line training

[1663] Purpose of use: To improve work efficiency

[1664] Tools used: Robot, smartphone, augmented reality

[1665] Based on this prompt, a generative artificial intelligence means generates training content, and an emotion recognition engine adjusts the difficulty and content in real time to match the user's emotional state. Specifically, for example, instructions for each step to be performed on an assembly line and hints appropriate to the situation are generated. The generated content is then provided to the user, who can use an augmented reality device to continue training in an actual factory environment. Feedback from the user is used to improve the accuracy of future training content.

[1666] conclusion

[1667] This invention makes it possible to dynamically provide operational training in factories in a format that is tailored to each individual user, which is expected to improve training effectiveness and work efficiency.

[1668] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1669] Step 1:

[1670] The user logs into the system and inputs information about the situation, purpose of use, and tools used into the interface. At this stage, the input is specific information such as "Situation: Assembly line training," "Purpose of use: Improving work efficiency," and "Tools used: Robot, smartphone, augmented reality." The input data is converted into JSON format by the terminal, which prepares the input data in a format that can be processed on the server side.

[1671] Step 2:

[1672] The user's input data, converted into JSON format, is sent from the device to the server. The server parses the received JSON data and understands its contents. The parsed data is sent to a generative AI model, which generates specific puzzle-solving settings, questions, hints, tools, and endings based on the training scenario. The output at this stage is structured data containing each element.

[1673] Step 3:

[1674] The server sends the generated puzzle data to an emotion recognition engine. The emotion recognition engine collects the user's facial expressions, voice data, and other data, and analyzes their emotional state in real time. The obtained emotion data is used to adjust the difficulty and content of the generated puzzle data. For example, if the system recognizes that the user is confused, it lowers the difficulty of the problem, and conversely, if the user is enjoying the problem, it increases the difficulty. The final output is puzzle data optimized according to the user's emotion.

[1675] Step 4:

[1676] The optimized puzzle-solving data is then sent back to the device from the server and provided to the user. The device displays the puzzle content visually or audibly, and the user actually practices using a smartphone or an augmented reality device.

[1677] Step 5:

[1678] Users train by solving puzzles and input feedback on the process and results. This feedback data is then sent from the device to the server. The server analyzes the collected feedback data and stores it as training data for the generative AI model. This improves the quality and accuracy of future puzzle-solving scenarios generated by the system.

[1679] Step 6:

[1680] The server accepts requests to change parts of the generated puzzle as needed. If the user wishes to change the difficulty or content of a specific part, it regenerates only that part. In this case, adjustments are made according to the user's emotional state, and the changed data is provided again.

[1681] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1682] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1683] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1684] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1685] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1686] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1687] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1688] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1689] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1690] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1691] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1692] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1693] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1694] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1695] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1696] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1697] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1698] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1699] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1700] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1701] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1702] The following is further disclosed regarding the above embodiment.

[1703] (Claim 1)

[1704] A means for a user to input information on a situation, a purpose of use, and an item to be used;

[1705] A generating artificial intelligence means for analyzing the input information and generating a setting, a question, a hint, an item, and an ending for solving a puzzle;

[1706] A means for providing the generated puzzle content to a user;

[1707] A means for collecting user feedback and adding it to the training data of the generative artificial intelligence;

[1708] A system including:

[1709] (Claim 2)

[1710] 2. The system according to claim 1, further comprising means for regenerating a part of the generated puzzle content when an instruction to change the part is given.

[1711] (Claim 3)

[1712] 2. The system of claim 1, further comprising means for enabling the generated puzzle content to be exported in the form of text, an image file, or a video.

[1713] "Example 1"

[1714] text

[1715] (Claim 1)

[1716] A means for a user to input information on a situation, a purpose of use, and an item to be used;

[1717] A generating artificial intelligence means for analyzing the input information and generating a setting, a question, a hint, an item, and an ending for solving a puzzle;

[1718] means for converting the input information into an appropriate data format and transmitting the converted information to a server;

[1719] A means for providing the generated puzzle content to a user;

[1720] A means for collecting user feedback and adding it to the training data of the generative artificial intelligence;

[1721] A system including:

[1722] (Claim 2)

[1723] 2. The system according to claim 1, further comprising means for regenerating a part of the generated puzzle content when an instruction to change the part is given.

[1724] (Claim 3)

[1725] 2. The system of claim 1, further comprising means for enabling the generated puzzle content to be exported in the form of text, an image file, or a video.

[1726] "Application Example 1"

[1727] (Claim 1)

[1728] A means for a user to input information on a situation, a purpose of use, and an item to be used;

[1729] A generating artificial intelligence means for analyzing the input information and generating a setting, a question, a hint, an item, and an ending for solving a puzzle;

[1730] A means for providing the generated puzzle content to a user;

[1731] A means for collecting user feedback and adding it to the training data of the generative artificial intelligence;

[1732] A means for providing a smartphone application for providing specialized education and training for workers in a factory;

[1733] A system including:

[1734] (Claim 2)

[1735] 2. The system according to claim 1, further comprising means for regenerating a part of the generated puzzle content when an instruction to change the part is given.

[1736] (Claim 3)

[1737] 2. The system of claim 1, further comprising means for enabling the generated puzzle content to be exported in the form of text, an image file, or a video.

[1738] "Example 2: Combining Emotion Engines"

[1739] (Claim 1)

[1740] A means for a user to input information on a situation, a purpose of use, and an item to be used;

[1741] A generating artificial intelligence means for analyzing the input information and generating a setting, a question, a hint, an item, and an ending for solving a puzzle;

[1742] emotion analysis means for analyzing the emotions of the user and applying the results to the generated puzzle content;

[1743] A means for providing the generated puzzle content to a user;

[1744] A means for collecting user feedback and adding it to the training data of the generative artificial intelligence;

[1745] A system including:

[1746] (Claim 2)

[1747] 2. The system according to claim 1, further comprising means for, when an instruction to change a part of the generated puzzle content is received, regenerating the part and optimizing it again using emotion analysis means.

[1748] (Claim 3)

[1749] 2. The system of claim 1, further comprising means for enabling the generated puzzle content to be exported in the form of text, an image file, or a video.

[1750] "Application example 2 when combining emotion engines"

[1751] Rewritten claims:

[1752] (Claim 1)

[1753] A means for a user to input information on a situation, purpose of use, and tools used;

[1754] a generating artificial intelligence means for analyzing the input information and generating a setting, a question, a hint, a tool, and an ending for solving a puzzle;

[1755] A means for providing the generated puzzle content to a user;

[1756] a means including an emotion recognition engine that recognizes the emotion of a user and adjusts the difficulty and content of the generated puzzle;

[1757] A means for collecting user feedback and adding it to the training data of the generative artificial intelligence;

[1758] A system including:

[1759] (Claim 2)

[1760] 2. The system according to claim 1, further comprising means for regenerating a part of the generated puzzle content when an instruction to change the part is given.

[1761] (Claim 3)

[1762] 2. The system according to claim 1, further comprising means for outputting the generated puzzle content in the form of text, an image file, or a video. [Explanation of symbols]

[1763] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for a user to input information on a situation, a purpose of use, and an item to be used; A generating artificial intelligence means for analyzing the input information and generating a setting, a question, a hint, an item, and an ending for solving a puzzle; A means for providing the generated puzzle content to a user; A means for collecting user feedback and adding it to the training data of the generative artificial intelligence; A system including:

2. 2. The system according to claim 1, further comprising means for regenerating a part of the generated puzzle content when an instruction to change the part is given.

3. The system according to claim 1 , further comprising means for enabling the generated puzzle content to be exported in the form of text, an image file, or a video.

Images