System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving attribute data input by a user; means for selecting a generative model based on the attribute data; means for optimizing content of an original explanatory material using the selected generative model; and means for sending the optimized explanatory material to a terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] Existing explanatory materials and documents are often created primarily for a specific user demographic (e.g., male managers). This creates a problem in that information is difficult to understand for users with different attributes, such as gender, age, and job title. Furthermore, materials that contain a lot of technical jargon and difficult expressions are particularly difficult for older users to understand. Therefore, a solution is needed to ensure consistent information transmission for different user demographics. [Means for solving the problem]

[0005] The present invention provides a means for receiving attribute data input by a user and selecting a generative model based on the attribute data. It also includes a means for optimizing the content of the original explanatory material using the selected generative model. It also includes a means for transmitting the optimized explanatory material to the user's terminal. Specifically, it includes a means for replacing technical terms with simpler expressions and adding visual elements to the content of the optimized explanatory material. In this way, consistent information transmission is achieved even for users with different attributes.

[0006] A "user" is a general user who uses the system to input attribute data and receive optimized explanatory materials.

[0007] "Attribute data" refers to personal characteristic information such as gender, age, and job title that a user inputs about himself or herself.

[0008] "Terminal" refers to the electronic device through which a user inputs attribute data and receives optimized explanatory materials.

[0009] "Server" refers to a central computer system that selects a generative model based on the received attribute data, optimizes the original explanatory material, and sends it to the terminal.

[0010] "Generative Model" refers to an algorithm or AI model for generating optimized explanatory materials based on received attribute data.

[0011] "Optimization" refers to the process of adjusting the content of the original explanatory materials based on the user's attributes to make them easier to understand.

[0012] "Instructional Materials" refers to documents or content containing information provided to users.

[0013] "Jargon" refers to specialized words and phrases used in a particular field or industry.

[0014] "Simple expressions" refers to replacing technical terms and difficult expressions with easy-to-understand words.

[0015] "Visual elements" refer to visual information such as charts and graphs that are added to materials to aid user understanding. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention is a system for optimizing explanatory materials based on user attribute data, specifically, adjusting the original explanatory materials appropriately according to user attributes such as gender, age, job title, etc. Below, we will explain in detail how the system of the present invention is actually implemented.

[0038] System Overview

[0039] 1. Enter user attributes

[0040] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[0041] 2. Sending attribute data

[0042] The device sends the entered attribute information to the server in an appropriate format, such as JSON.

[0043] 3. Receiving and Processing Attribute Data

[0044] The server receives and analyzes the attribute data sent from the device, and based on this analysis, selects the optimal generative model.

[0045] 4. Acquiring and optimizing source material

[0046] The server retrieves the original explanatory materials from the database and performs optimization processing on the retrieved materials according to the user's attributes. Specifically, it changes the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[0047] 5. Generate and submit optimization materials

[0048] The server generates optimized explanatory materials and sends them to the terminal, allowing the user to receive information that matches their attributes.

[0049] 6. Viewing optimization data

[0050] The terminal receives the optimization data sent from the server and displays it to the user in a format that is easy for the user to understand.

[0051] Specific examples

[0052] A specific scenario will be described below.

[0053] Scenario 1: Optimizing information materials for junior female employees

[0054] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[0055] 2. The terminal sends the entered information to the server.

[0056] 3. Based on the received attribute information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes technical terms like "leadership" to "collaborative work" and replaces difficult expressions with more familiar terms.

[0057] 4. The server sends the optimized explanatory material to the terminal.

[0058] 5. The terminal displays optimized explanatory materials to the user, who is satisfied with the easy-to-understand content.

[0059] Scenario 2: Optimizing instructional materials for older users

[0060] 1. A user (elderly user) enters "Gender: Male", "Age: 65", and "Position: Retired" into the terminal.

[0061] 2. The terminal sends the entered information to the server.

[0062] 3. Based on the received attribute information, the server optimizes the original explanatory materials, which contain a lot of technical terms, for seniors by, for example, replacing technical terms with easier-to-understand language and adding visual elements (diagrams and graphs).

[0063] 4. The server sends the optimized explanatory material to the terminal.

[0064] 5. The terminal displays optimized explanatory materials to the user, making it easier for the user to understand the materials visually intuitively.

[0065] In this way, the system of the present invention allows for flexible optimization of explanatory materials based on different user attributes, thereby enabling effective communication of information.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[0069] Step 2:

[0070] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example:

[0071] json

[0072] {

[0073] "Gender": "Female",

[0074] "age": "25",

[0075] "Position": "Regular employee"

[0076] }

[0077] Step 3:

[0078] The server receives the attribute information sent from the terminal, and then parses the received data appropriately to extract the attribute information.

[0079] Step 4:

[0080] The server selects a generative model based on the received attribute information. For example, if the attributes are "gender: female," "age: 25," and "job title: general employee," the server selects the most suitable generative model.

[0081] Step 5:

[0082] The server retrieves the original explanatory material from the database, which we assume was created for male managers.

[0083] Step 6:

[0084] The server then uses the selected generative model to optimize the original explanatory material, specifically by:

[0085] Changing wording and examples: For example, changing the technical concept of "leadership" to "collaboration."

[0086] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[0087] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[0088] Step 7:

[0089] The server temporarily stores the optimized explanatory materials and then generates the data to be sent to the terminal. The data format for sending can be PDF, HTML, or other formats.

[0090] Step 8:

[0091] The server sends the optimized instruction material to the device. For example:

[0092] json

[0093] {

[0094] "documentation": "optimized documentation content",

[0095] "metadata": {

[0096] "Generation date and time": "2023-10-26T12:00:00Z",

[0097] "User Attributes": {

[0098] "Gender": "Female",

[0099] "age": "25",

[0100] "Position": "Regular employee"

[0101] }

[0102] }

[0103] }

[0104] Step 9:

[0105] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[0106] Example 1

[0107] 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."

[0108] Conventional explanatory materials were not optimized according to the user's attributes, and the same content was provided to all users. As a result, users could not obtain materials that suited their attributes, and it was sometimes difficult to understand the content. For example, there was an issue that general explanatory materials could not provide sufficient information because the information required and the level of understanding of technical terms differ depending on the young person, the elderly, and the type of occupation.

[0109] 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.

[0110] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative AI model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative AI model, means for transmitting the optimized explanatory material to a user terminal, and means for displaying the transmitted optimized material on the user terminal. This makes it possible to flexibly optimize explanatory material based on user attribute information and effectively convey information.

[0111] "User" refers to an individual or corporation that uses the system and is the entity that inputs their attribute information into the system.

[0112] "Attribute data" refers to user-specific characteristics and information such as gender, age, and job title, and serves as the basis for the system to optimize explanatory materials.

[0113] The "means for receiving" refers to a method for the server to receive attribute data input by the user, and includes, for example, an HTTP request or data transfer in JSON format.

[0114] A "generative AI model" is an artificial intelligence model for generating text and data, specifically an advanced natural language processing model such as GPT-3.

[0115] The "means of selection" is a method for selecting the optimal generative AI model based on the received attribute data.

[0116] The "optimization means" is a method for modifying and adjusting the content of the original explanatory materials according to the user's attribute information using the selected generative AI model.

[0117] The "means of transmission" refers to a method for transferring the optimized explanatory material to the user's device, including, for example, a REST API or an HTTP response.

[0118] "Means for displaying" refers to the method of displaying the transmitted optimization materials on the user's device, including rendering a web page using HTML and CSS.

[0119] "Terminology" refers to vocabulary that is specific to a particular field of expertise and difficult for the general public to understand.

[0120] "Simple expressions" refer to expressions that replace technical terms with simple words that are easy for the general public to understand.

[0121] "Visual elements" refers to visual materials such as charts, images, and graphs that are used to support or enhance the content of the explanation.

[0122] The present invention is a system that optimizes explanatory materials based on user attribute data. Specifically, it adjusts the original explanatory materials appropriately according to user attributes such as gender, age, and job title, making them easier to understand.

[0123] System Overview

[0124] Entering User Attributes

[0125] The user enters their own attribute information into the input screen of the device. Attribute information includes gender, age, job title, etc. For example, the user might enter "Gender: Female," "Age: 25," and "Job title: General employee." This allows the system to receive data for optimization processing according to the user's characteristics.

[0126] Sending attribute data

[0127] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example, JavaScript can be used to convert data obtained from a web form into JSON format and send it to the server as an HTTP POST request.

[0128] Receiving and processing attribute data

[0129] The server receives the attribute data sent from the device and analyzes it. The analysis is performed using the Python pandas library. Based on the analysis results, the optimal generative AI model is selected, and this model is used to optimize the data.

[0130] Acquiring and optimizing original material

[0131] The server retrieves the original explanatory materials from a database, such as a MySQL database. The retrieved materials are then optimized based on the user's attributes. This process uses the text generation AI GPT-3. Specifically, the server modifies the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[0132] Generate and submit optimization materials

[0133] The server generates optimized explanatory materials and sends them to the device. Specifically, it formats the generated text into JSON format and returns it to the device as an HTTP response via the REST API.

[0134] View optimization information

[0135] The device receives the optimization data sent from the server and displays it to the user. The data is formatted using HTML and CSS and presented as a web page that is easy for the user to view.

[0136] Hardware and software used

[0137] Terminal: The device (PC, smartphone, etc.) used by the user to enter data and view the optimized materials.

[0138] Server: A computer that receives, analyzes, optimizes, and sends data. For example, it uses Flask to accept HTTP requests.

[0139] Database: The database that stores the original documentation. For example, MySQL.

[0140] Software: Python, pandas library, generative AI model (GPT-3), HTML, CSS, JavaScript.

[0141] Specific examples

[0142] Scenario 1: Optimizing information materials for junior female employees

[0143] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[0144] 2. The device sends the entered information to the server in JSON format.

[0145] 3. Based on the received attribute information, the server sends appropriate prompts to GPT-3 to optimize it, such as changing the term "leadership" to "collaboration."

[0146] 4. The server sends the optimized explanatory materials to the terminal in JSON format.

[0147] 5. The terminal displays the received materials to the user using HTML and CSS.

[0148] Example prompt sentence:

[0149] Original instructional text:

[0150] Leadership is the ability to set direction and motivate team members.

[0151] Example prompts to input to a generative AI model:

[0152] Please optimize the following text for a 25-year-old female general employee.

[0153] Leadership is the ability to set direction and motivate team members.

[0154] Example output from GPT-3:

[0155] Leadership is the ability to decide which direction a team should go and motivate everyone.

[0156] In this way, the system of the present invention can optimize explanatory materials based on user attribute information and effectively communicate information.

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1:

[0159] Entering User Attributes

[0160] The user inputs attribute information into the input screen of the terminal. The input attribute information includes gender, age, job title, etc. Specifically, the user inputs "Gender: Female," "Age: 25," and "Job title: General employee." The input attribute information is temporarily saved in the terminal's memory.

[0161] Input: Attribute information entered by the user (gender, age, job title).

[0162] Output: Attribute information data saved on the device.

[0163] Step 2:

[0164] Sending attribute data

[0165] The device sends the entered attribute information to the server. The data is sent in an appropriate format, such as JSON. Specifically, the data is converted to JSON using JavaScript and sent as an HTTP POST request.

[0166] Input: Attribute information data stored on the device.

[0167] Output: Attribute information data in JSON format sent to the server.

[0168] Step 3:

[0169] Receiving and processing attribute data

[0170] The server receives the attribute data sent from the device and analyzes it using the Python pandas library. Based on the analysis results, the optimal generative AI model (e.g., GPT-3) is selected.

[0171] Input: Attribute information data in JSON format sent to the server.

[0172] Output: Parsed user attribute data and selected generative AI model.

[0173] Step 4:

[0174] Acquiring and optimizing original material

[0175] The server retrieves the original explanatory materials from a database. For example, it retrieves the materials from a MySQL database using an SQL query. It then optimizes the retrieved materials based on user attribute information. For optimization, it uses a generative AI model (GPT-3) to generate appropriate prompts and send them to the API.

[0176] Input: Parsed user attribute data, selected generative AI model, and original explanatory material retrieved from the database.

[0177] Output: Optimized explanatory material.

[0178] Step 5:

[0179] Generate and submit optimization materials

[0180] The server generates optimized explanatory materials, formats them in JSON format, and sends them to the terminal. Specifically, it packages the generated text in JSON format and returns an HTTP response via the REST API.

[0181] Input: Response data from a generative AI model (GPT-3).

[0182] Output: Optimization data formatted in JSON format.

[0183] Step 6:

[0184] View optimization information

[0185] The device receives the optimization data sent from the server and displays it to the user. Specifically, it parses the received JSON data using JavaScript, formats it using HTML and CSS, and displays it as a web page.

[0186] Input: Optimization data in JSON format sent from the server.

[0187] Output: Optimized explanatory material that the user can view on the screen.

[0188] In this way, the system can flexibly optimize explanatory materials based on the user's attribute information, and effectively communicate information.

[0189] (Application example 1)

[0190] 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."

[0191] Uniformly provided explanatory materials and work instructions for workers with different positions and experience within a factory cannot be adapted to the needs and level of understanding of each worker, resulting in the problem of work proceeding without sufficient understanding. Furthermore, for new engineers and older workers in particular, the use of technical terms and complex procedures not only takes time to understand, but also increases the risk of incorrect operation and safety issues. For this reason, a system is needed that provides materials optimally customized to the attributes of each worker.

[0192] 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.

[0193] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative model, means for transmitting the optimized explanatory material to a user's terminal, and means for displaying the optimized explanatory material on the industrial machine. This makes it possible to provide manuals and work instructions that are optimal for each worker's attributes, thereby improving understanding and ensuring safety.

[0194] "User" means a person or representative of an organization who uses the system.

[0195] "Attribute data" is information indicating characteristics of a user, such as gender, age, and job title.

[0196] A "generative model" is an algorithm or computational method used to generate optimal explanatory materials based on a user's attributes.

[0197] "Original explanatory materials" refers to the underlying information materials or manuals before they are optimized.

[0198] "Optimization" is the process of adjusting materials to suit the user's attributes and making them easier to understand.

[0199] "Terminal" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[0200] "Industrial machinery" refers to automated electronic devices and robots used in factories, etc.

[0201] The "receiving means" refers to a function or method for acquiring attribute data from a user.

[0202] The "transmitting means" refers to a function or method for transmitting the generated optimization data to a user's terminal or industrial machine.

[0203] This invention is a system that provides optimized explanatory materials based on user attribute data, and is particularly suitable for use in factories. The system itself is realized using multiple hardware components, including servers, terminals, and industrial machines, as well as appropriate software.

[0204] The server is implemented using a web framework called Flask and has the ability to receive attribute data from users. Users enter their own attribute data (such as job title and years of experience) into an input screen on their device and submit it. This data is sent to the server in a common format such as JSON.

[0205] The server analyzes the received attribute data and selects the optimal generative model based on it. The generative model contains an algorithm that can be customized according to the user's attributes. Specifically, the generative AI model is used to optimize the original explanatory material.

[0206] The generative model adapts language and terminology, adds visual elements, and more based on user attributes. For example, it can be optimized to provide more basic instructions and precautions for new technicians, while providing more advanced operating procedures and troubleshooting for more experienced workers.

[0207] The optimized explanatory materials are sent from the server to the user's device and are also displayed in real time on the displays of industrial machines, helping to ensure smooth operation within the factory.

[0208] This allows users to receive materials appropriate to their individual attributes, improving their understanding, improving work efficiency, and ensuring safety.

[0209] As a concrete example, consider the case where a new engineer enters and submits "job title: new engineer," "years of experience: 1 year," and "department: assembly." The server analyzes this data and selects a generative AI model for new employees. As a result, the generated optimization data will look like the one below.

[0210] Example prompt:

[0211] Basic Operation Instructions for New Technicians:

[0212] 1. Before performing procedure A, be sure to check procedure B.

[0213] 2. As a precaution, be especially careful when handling part X.

[0214] This information is displayed on the display of industrial machinery or on the user's terminal, making it easier for new engineers to understand the operating procedures that are appropriate for them.

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] The user enters their own attribute data into the device's input screen. They enter appropriate information into fields such as "gender," "age," and "job title," and press the "Submit" button. This allows the user's attribute information to be collected.

[0218] Input: Attribute data such as gender, age, and job title

[0219] Output: Converts attribute data to JSON format and sends it to the server

[0220] Step 2:

[0221] The terminal sends the input attribute data to the server, which receives the data in an appropriate format (e.g., JSON format).

[0222] Input: Attribute data (JSON format)

[0223] Output: Stores attribute data in the server-side receive buffer

[0224] Step 3:

[0225] The server receives and analyzes the attribute data sent from the device. In this analysis process, it parses the received JSON data and extracts each field (gender, age, job title).

[0226] Input: Attribute data (JSON format)

[0227] Output: Parsed attribute data (gender, age, job title fields)

[0228] Step 4:

[0229] The server selects the optimal generative model based on the analyzed attribute data, using algorithms and rule-based systems to select the most suitable generative AI model.

[0230] Input: Parsed attribute data

[0231] Output: The selected generative AI model

[0232] Step 5:

[0233] The server retrieves the original explanatory materials from the database, which are then optimized by the generative AI model.

[0234] Input: Original explanatory material, selected generative AI model

[0235] Output: Optimized explanatory material

[0236] Step 6:

[0237] The server uses a generative AI model to optimize the content of the original explanatory materials, customizing them based on user attributes, such as changing wording and terminology, and adding visual elements.

[0238] Input: Original explanatory material, selected generative AI model

[0239] Output: Optimized explanatory material

[0240] Step 7:

[0241] The server transmits the optimized explanatory materials to the user's terminal, which then processes the optimized materials into an appropriate format and sends them to the user's terminal.

[0242] Input: Optimized explanatory material

[0243] Output: Optimization data sent to the user's terminal

[0244] Step 8:

[0245] The terminal receives the optimization data sent from the server and displays it to the user in a visually easy-to-understand format.

[0246] Input: Optimized explanatory material

[0247] Output: Displayed optimization explanation

[0248] Step 9:

[0249] The optimized instruction materials are also displayed on the displays of industrial machines, providing workers in the factory with the information they need in real time.

[0250] Input: Optimized explanatory material

[0251] Output: Optimization instructions displayed on the industrial machine's display

[0252] 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.

[0253] The present invention is a system that optimizes explanatory materials based on a user's attribute data and emotional state. Specifically, in addition to user attributes such as gender, age, and job title, the system can recognize the user's emotions and adaptively adjust the explanatory materials based on this information. Below, we will explain in detail how the system of the present invention is actually implemented.

[0254] System Overview

[0255] 1. Enter user attributes

[0256] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[0257] 2. Emotion recognition

[0258] The device uses cameras, microphones, and sensors to recognize the user's emotions in real time. For example, it can identify the user's emotional state, such as "happy," "troubled," or "stressed," through facial expression analysis and voice tone analysis.

[0259] 3. Transmission of attribute data and emotion data

[0260] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[0261] json

[0262] {

[0263] "attribute data": {

[0264] "Gender": "Female",

[0265] "age": "25",

[0266] "Position": "Regular employee"

[0267] },

[0268] "Emotion data": "troubled"

[0269] }

[0270] 4. Receipt and processing of data

[0271] The server receives the attribute data and emotion data sent from the device, and then parses the data appropriately to extract attribute information and emotion information.

[0272] 5. Generative Model Selection

[0273] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[0274] 6. Acquiring and optimizing source material

[0275] The server retrieves the original explanatory materials from the database. It then performs optimization processing on the retrieved materials according to the user's attributes and emotions. Specifically, it performs the following processing:

[0276] Changes in wording and examples: For example, changing the technical term "leadership" to "collaboration."

[0277] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[0278] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[0279] Emotion-based adjustments: If the user is struggling, adjustments are made, such as making the explanation more concise and polite, and adding words of encouragement.

[0280] 7. Generate and submit optimization materials

[0281] The server temporarily stores the optimized explanatory materials in memory, and then generates data for transmission to the terminal. The transmission data format can be PDF, HTML, or other formats.

[0282] 8. Viewing optimization data

[0283] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[0284] Specific examples

[0285] A specific scenario will be described below.

[0286] Scenario 1: Optimizing explanatory materials for young female employees in need

[0287] 1. A user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular Employee" into the terminal, and the emotion "troubled" is recognized from her facial expression.

[0288] 2. The device sends the input information and emotion data to the server.

[0289] 3. Based on the received information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes the technical term "leadership" to "collaborative work" and replaces difficult expressions with more familiar language. It also softens the tone of the materials and adds words of encouragement.

[0290] 4. The server sends the optimized explanatory material to the terminal.

[0291] 5. The device displays optimized explanatory materials to the user, who is pleased with the easy-to-understand content and friendly tone.

[0292] The system of the present invention makes it possible to flexibly optimize explanatory materials based on user attributes and emotions, and to effectively communicate information.

[0293] The processing flow will be explained below.

[0294] Step 1:

[0295] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[0296] Step 2:

[0297] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. Through facial expression analysis and voice tone analysis, the device identifies emotions such as "happy," "troubled," or "stressed."

[0298] Step 3:

[0299] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[0300] json

[0301] {

[0302] "attribute data": {

[0303] "Gender": "Female",

[0304] "age": "25",

[0305] "Position": "Regular employee"

[0306] },

[0307] "Emotion data": "troubled"

[0308] }

[0309] Step 4:

[0310] The server receives the attribute data and emotion data sent from the terminal, parses and analyzes them appropriately, and extracts user attribute information and emotion information as analysis results.

[0311] Step 5:

[0312] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[0313] Step 6:

[0314] The server retrieves the original explanatory materials created for male managers from the database and performs optimization processing on the retrieved materials according to the user's attributes and emotions.

[0315] Step 7:

[0316] The server performs the following specific optimizations:

[0317] Changes in wording or examples: For example, changing the word "leadership" to "collaboration."

[0318] Jargon-free: Replace difficult phrases with easy-to-understand terms, e.g., changing "KPI" to "Key Performance Indicator."

[0319] Add visuals: Add charts and graphs where appropriate to help understand the material.

[0320] Emotion-based adjustment: If the user is judged to be "troubled," the explanation will be made more concise and polite, and words of encouragement will be added.

[0321] Step 8:

[0322] The server generates and stores in temporary memory optimized descriptive material, which may also include appropriate metadata.

[0323] Step 9:

[0324] The server sends the optimized explanatory materials to the terminal. The data format can be PDF or HTML. Example:

[0325] json

[0326] {

[0327] "documentation": "optimized documentation content",

[0328] "metadata": {

[0329] "Generation date and time": "2023-10-26T12:00:00Z",

[0330] "User Attributes": {

[0331] "Gender": "Female",

[0332] "age": "25",

[0333] "Position": "Regular employee"

[0334] },

[0335] "Emotion data": "troubled"

[0336] }

[0337] }

[0338] Step 10:

[0339] The terminal receives the optimization data sent from the server and displays it to the user in a format that is most easily understood by the user.

[0340] Example 2

[0341] 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."

[0342] Conventional systems for providing explanatory materials have had difficulty providing materials optimized for users based on their emotional state at any given time, in addition to their attribute information. Therefore, there has been a demand for a means to deepen users' understanding and provide information efficiently. Furthermore, materials containing technical terms and difficult expressions are often difficult for certain users to understand. It is necessary to develop a system that can solve these issues and provide information in the most optimal form for users.

[0343] 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.

[0344] In this invention, the server includes means for receiving attribute data and emotion data input by a user, means for selecting a generative model based on the attribute data and emotion data, and means for optimizing the content of the original explanatory material using the selected generative model, thereby making it possible to provide explanatory material that is appropriately optimized based on the user's attributes and emotions.

[0345] "User" refers to a person who uses the system to input attribute data and emotion data.

[0346] "Attribute data" refers to information related to a user, such as gender, age, and job title.

[0347] "Emotion data" refers to data that recognizes and expresses the user's emotional state in real time.

[0348] "Generative model" refers to an artificial intelligence model for optimizing explanatory materials based on user attribute data and emotional data.

[0349] "Optimized explanatory materials" refers to materials that have been modified and adjusted using a generative model to suit the user's attributes and emotions.

[0350] "Server" refers to a device at the back end of the system that receives data, selects a generative model, performs optimization processing, and sends optimized explanatory materials to the terminal.

[0351] "Terminal" refers to a device through which a user inputs attribute data and emotion data and receives and displays optimized explanatory materials.

[0352] "Jargon" refers to words commonly used in a particular field or industry, but difficult for the general public to understand.

[0353] "Visual elements" refer to elements that visually supplement information, such as diagrams, graphs, and icons, that are added to explanatory materials.

[0354] The present invention is a system for optimizing explanatory materials based on attribute data and emotional state of a user. Specific embodiments of the system will be described below.

[0355] System configuration

[0356] The system of the present invention is mainly composed of a terminal, a server, and a network connecting these.

[0357] Input of user attributes and emotion data

[0358] The user enters attribute data such as gender, age, and job title into the device's input screen. The device provides these data fields and prompts the user to enter accurate data. For example, the user might enter information such as "Gender: Female," "Age: 25," and "Job title: General employee."

[0359] The device uses a camera, microphone, and sensors (for example, facial expression analysis using OpenCV and Dlib, and voice tone analysis) to recognize the user's emotions in real time. It estimates their emotional state, such as "troubled," "happy," or "angry."

[0360] Sending data

[0361] The device sends the entered user attribute information and recognized emotion data in JSON format to the server using an HTTP POST request, with the following data format:

[0362] json

[0363] {

[0364] "attribute data": {

[0365] "Gender": "Female",

[0366] "age": "25",

[0367] "Position": "Regular employee"

[0368] },

[0369] "Emotion data": "troubled"

[0370] }

[0371] Data reception and analysis

[0372] The server receives the data sent from the device, processes the HTTP request using Python or Node.js, and then parses the received data to extract attribute data and emotion data.

[0373] Generative model selection and optimization

[0374] The server selects the optimal generative AI model (e.g., GPT-3 or BERT) based on the received attribute and emotion data. This selection uses a filtering algorithm to select the model that best suits the user's attribute and emotion information.

[0375] The server uses the selected generative AI model to optimize the content of the original explanatory material, specifically:

[0376] Modification of wording and examples: Send prompts to the generative AI model to replace specific jargon or phrases with appropriate modifications.

[0377] Replacing technical terms with plain language: Using pre-prepared dictionaries and algorithms, technical terms are replaced with plain language.

[0378] Add visual elements: Generate and add charts and graphs to your materials to aid comprehension, using image generation APIs such as Matplotlib or D3.js.

[0379] Emotion-based adjustment: If the user is struggling, change the message to an encouraging one or a brief, polite explanation.

[0380] Submitting and viewing optimization materials

[0381] The server uses libraries such as ReportLab and BeautifulSoup to convert the optimized explanatory materials into PDF or HTML format and store them in temporary memory, after which it sends the data to the terminal.

[0382] The terminal receives the documents sent from the server and displays them to the user using a PDF viewer or HTML rendering engine, and the documents are designed to be easy for the user to read.

[0383] Specific scenarios and prompt examples

[0384] Example scenario:

[0385] A young female employee enters "gender: female," "age: 25," and "job title: general employee" into the terminal, and the emotion "troubled" is recognized from her facial expression. The terminal sends the entered information and emotional data to the server, which then uses this information to optimize the original explanatory materials for young female employees. It changes the word "leadership" to "collaborative work" and replaces difficult expressions with more familiar words. It also softens the tone of the materials and adds words of encouragement. The optimized materials are sent to the terminal and displayed to the user. The user is pleased with the easy-to-understand content and gentle tone.

[0386] Example prompt sentence:

[0387] "Female, 25 years old, general employee. Please generate explanatory materials for a difficult situation."

[0388] This allows the present invention to provide optimized explanatory materials based on the user's individual attribute information and emotional state, thereby deepening the user's understanding and maximizing the effectiveness of the information provided.

[0389] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0390] Step 1:

[0391] The user enters attribute data such as gender, age, and job title into the device's input screen. The input data includes information such as "Gender: Female," "Age: 25," and "Job title: General employee." This attribute data specifically indicates the user's background information and plays an important role in subsequent processes. The input data is temporarily stored in the device.

[0392] Step 2:

[0393] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. It receives facial expressions and voice tones as input, and uses facial expression analysis and voice analysis algorithms, specifically OpenCV and Dlib, to determine the emotion. Emotional data, such as "troubled" or "happy," is generated as output. This emotional data is then ready to be sent to the server along with attribute data.

[0394] Step 3:

[0395] The device sends the attribute data entered by the user and the recognized emotion data to the server in JSON format. The data is sent as an HTTP POST request, with the input being the attribute data and emotion data, and the output being a notification of completion of transmission to the server. Specifically, the following JSON data is sent:

[0396] json

[0397] {

[0398] "attribute data": {

[0399] "Gender": "Female",

[0400] "age": "25",

[0401] "Position": "Regular employee"

[0402] },

[0403] "Emotion data": "troubled"

[0404] }

[0405] Step 4:

[0406] The server receives JSON data sent from the device. The input is JSON data containing attribute data and emotion data, and processes HTTP requests using Python and Node.js. Once the data is received, the server parses it to extract the attribute data and emotion data, storing them in variables. The parsed data is obtained as output.

[0407] Step 5:

[0408] The server selects the optimal generative AI model based on the received attribute data and emotion data. The input is attribute data and emotion data, and a filtering algorithm is used to select the most appropriate generative AI model (examples include GPT-3 and BERT). The selected generative AI model is obtained as the output.

[0409] Step 6:

[0410] The server optimizes the content of the original explanatory material using the selected generative AI model. The input is the original explanatory material and the selected generative model, and the following specific data processing is performed:

[0411] Change wording and examples: Send prompts to the generative model to change specific words or phrases.

[0412] Replacing technical terms with plain language: Using dictionaries and algorithms, technical terms are automatically replaced with plain language.

[0413] Add visual elements: Use Matplotlib or D3.js to generate and add charts and graphs appropriate for your presentation.

[0414] Emotion-based adjustment: If the user is struggling, adjust the message to encouragement or a concise, polite explanation.

[0415] The output is optimized explanatory material.

[0416] Step 7:

[0417] The server converts the optimized explanatory materials into PDF or HTML format and stores them in temporary memory. The input is the optimized explanatory materials, and libraries such as ReportLab and BeautifulSoup are used. As output, a savable PDF or HTML formatted document is generated. This document is then sent to the terminal.

[0418] Step 8:

[0419] The terminal receives the optimized documents sent from the server and displays them to the user. The input is the document in PDF or HTML format, and the terminal uses a PDF viewer or HTML rendering engine to render the document on the display screen. The output is the explanatory document displayed in a format that is easy for the user to read.

[0420] This allows the provision of optimal materials according to the user's attributes and emotions, thereby deepening the user's understanding.

[0421] (Application example 2)

[0422] 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."

[0423] Conventional systems for optimizing explanatory materials optimize materials based on user attribute information, but because they do not consider the user's emotional state, they are unable to sufficiently improve the user's understanding or satisfaction. Furthermore, they lack the ability to adaptively change explanatory materials according to the user's needs under specific circumstances or emotions. As a result, users find it difficult to receive appropriate support in difficult situations.

[0424] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user attribute data, means for recognizing emotion data in real time, means for selecting a generative model based on the attribute data and emotion data, means for optimizing the content of the original explanatory material using the selected generative model, and means for transmitting the optimized explanatory material to the user's terminal. This makes it possible to provide optimal explanatory material that takes into account the user's attribute information and emotional state, thereby improving the user's understanding and satisfaction.

[0425] "User" refers to an individual who uses a system or application.

[0426] "Attribute data" refers to data that includes personal information about a user, such as gender, age, and job title.

[0427] "Emotion data" is data that indicates the user's real-time emotional state, and includes emotions such as "happy," "troubled," and "stressed," for example.

[0428] "Generative model" refers to an algorithm or process for generating optimized explanatory materials based on user attribute data and emotion data.

[0429] "Instructional Materials" means any written or digital content containing information or instructions provided to a User.

[0430] "Terminal" refers to an electronic device used by a user, including, for example, a smartphone, a tablet, a personal computer, etc.

[0431] "Server" refers to a remote computer system that performs the central processing of the system, receiving data, processing the data, selecting generative models, and transmitting optimization materials.

[0432] "Optimization" refers to the process of adjusting the content of explanatory materials based on the user's attribute data and emotional data, and changing them into a form that is most easily understandable to the user.

[0433] The following describes the mode for carrying out this invention. The main components of the invention are a system that receives user attribute data, recognizes emotion data in real time, selects a generative model based on that data, and optimizes explanatory materials. This processing is performed by a server and a user's terminal.

[0434] First, the user uses the device to input their attribute data, including basic personal information such as gender, age, and job title. The device is also equipped with sensors such as a camera and microphone, which are used to recognize the user's emotional data in real time. Emotional data is obtained by analyzing the user's facial expressions and tone of voice.

[0435] Next, the user's device sends this attribute data and emotion data to the server in an appropriate data format, such as JSON. The server receives this data, analyzes its contents, and extracts the user's attribute information and emotion information.

[0436] The server selects the optimal generative model based on the extracted information. The generative model is selected from multiple pre-built models to best fit the user's attribute information and emotional state. The generative model is then used to optimize the original explanatory material to make it most understandable for the user. This optimization involves replacing technical terms with simpler language and adding visual elements. The tone of the material is also adjusted based on the user's emotions.

[0437] The optimized explanatory material is temporarily stored in the memory of the server and then sent to the user's terminal, which displays the received optimized material for the user to easily understand.

[0438] The system's main hardware consists of the user's device (smartphone, tablet, PC, etc.) and a server (cloud services such as AWS, GCP, and Azure). The software uses Python and Flask to receive and analyze data, select generative models, optimize explanatory materials, and send and receive data.

[0439] As a specific example, suppose a young female user inputs "gender: female," "age: 25," and "job title: general employee," and the device's camera recognizes the emotion "troubled." In this case, the server selects the optimal generative model, changes the technical term "leadership" to "collaborative work," and generates explanatory materials with more familiar language. The generated materials contain a gentle tone and encouraging words.

[0440] An example prompt is:

[0441] "Gender: Male, Age: 20, Position: Student, Emotion: Troubled"

[0442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0443] Step 1:

[0444] The user enters their own attribute data into the input screen of the terminal. The input attribute data includes gender, age, job title, etc. For example, data such as "Gender: Female," "Age: 25," and "Job title: General employee" are entered.

[0445] Step 2:

[0446] The device uses sensors such as a built-in camera and microphone to recognize the user's emotional data in real time. Specifically, it analyzes facial expressions and voice tones to identify the user's emotional state as "happy," "troubled," "stressed," etc. This emotional data, along with attribute data, is used in the next step.

[0447] Step 3:

[0448] The device sends the input attribute data and recognized emotion data to the server in an appropriate data format, such as JSON. For example, the following JSON format data is sent:

[0449] json

[0450] {

[0451] "attribute data": {

[0452] "Gender": "Female",

[0453] "age": "25",

[0454] "Position": "Regular employee"

[0455] },

[0456] "Emotion data": "troubled"

[0457] }

[0458] Step 4:

[0459] The server receives the attribute data and emotion data sent from the device. It parses (analyzes) the received data and extracts the user's attribute information and emotion information. For example, it can obtain information such as "Gender: Female," "Age: 25," "Position: Regular Employee," and "Emotion: Troubled."

[0460] Step 5:

[0461] The server selects the optimal generative model based on the extracted attribute and emotion information. Multiple generative models are available, and the model that best suits the user's attribute and emotion data is selected. For example, the generative model that best suits the conditions "young female employee" and "in trouble" is selected.

[0462] Step 6:

[0463] The server uses the selected generative model to optimize the content of the original explanatory material retrieved from the database. The optimization process includes the following steps:

[0464] Replacing technical terms with simpler expressions

[0465] Add visual elements (diagrams, graphs, etc.) to your explanations

[0466] Change tone based on user emotion and add words of encouragement

[0467] For example, change the term "leadership" to "collaboration" and add words of encouragement to "struggling" users.

[0468] Step 7:

[0469] The server temporarily stores the optimized explanatory materials and then transmits them to the user's device in a format such as PDF or HTML.

[0470] Step 8:

[0471] The user's device receives the optimization materials sent from the server and displays them to the user. The display screen is designed to be easy for the user to read and is presented in an easy-to-understand format. For example, a simple and easy-to-understand explanatory document is displayed to help users deal with situations where immediate help is needed.

[0472] 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.

[0473] 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.

[0474] 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.

[0475] [Second embodiment]

[0476] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0477] 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.

[0478] 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).

[0479] 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.

[0480] 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.

[0481] 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).

[0482] 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.

[0483] 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.

[0484] 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.

[0485] 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.

[0486] 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.

[0487] 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."

[0488] The present invention is a system for optimizing explanatory materials based on user attribute data, specifically, adjusting the original explanatory materials appropriately according to user attributes such as gender, age, job title, etc. Below, we will explain in detail how the system of the present invention is actually implemented.

[0489] System Overview

[0490] 1. Enter user attributes

[0491] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[0492] 2. Sending attribute data

[0493] The device sends the entered attribute information to the server in an appropriate format, such as JSON.

[0494] 3. Receiving and Processing Attribute Data

[0495] The server receives and analyzes the attribute data sent from the device, and based on this analysis, selects the optimal generative model.

[0496] 4. Acquiring and optimizing source material

[0497] The server retrieves the original explanatory materials from the database and performs optimization processing on the retrieved materials according to the user's attributes. Specifically, it changes the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[0498] 5. Generate and submit optimization materials

[0499] The server generates optimized explanatory materials and sends them to the terminal, allowing the user to receive information that matches their attributes.

[0500] 6. Viewing optimization data

[0501] The terminal receives the optimization data sent from the server and displays it to the user in a format that is easy for the user to understand.

[0502] Specific examples

[0503] A specific scenario will be described below.

[0504] Scenario 1: Optimizing information materials for junior female employees

[0505] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[0506] 2. The terminal sends the entered information to the server.

[0507] 3. Based on the received attribute information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes technical terms like "leadership" to "collaborative work" and replaces difficult expressions with more familiar terms.

[0508] 4. The server sends the optimized explanatory material to the terminal.

[0509] 5. The terminal displays optimized explanatory materials to the user, who is satisfied with the easy-to-understand content.

[0510] Scenario 2: Optimizing instructional materials for older users

[0511] 1. A user (elderly user) enters "Gender: Male", "Age: 65", and "Position: Retired" into the terminal.

[0512] 2. The terminal sends the entered information to the server.

[0513] 3. Based on the received attribute information, the server optimizes the original explanatory materials, which contain a lot of technical terms, for seniors by, for example, replacing technical terms with easier-to-understand language and adding visual elements (diagrams and graphs).

[0514] 4. The server sends the optimized explanatory material to the terminal.

[0515] 5. The terminal displays optimized explanatory materials to the user, making it easier for the user to understand the materials visually intuitively.

[0516] In this way, the system of the present invention allows for flexible optimization of explanatory materials based on different user attributes, thereby enabling effective communication of information.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[0520] Step 2:

[0521] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example:

[0522] json

[0523] {

[0524] "Gender": "Female",

[0525] "age": "25",

[0526] "Position": "Regular employee"

[0527] }

[0528] Step 3:

[0529] The server receives the attribute information sent from the terminal, and then parses the received data appropriately to extract the attribute information.

[0530] Step 4:

[0531] The server selects a generative model based on the received attribute information. For example, if the attributes are "gender: female," "age: 25," and "job title: general employee," the server selects the most suitable generative model.

[0532] Step 5:

[0533] The server retrieves the original explanatory material from the database, which we assume was created for male managers.

[0534] Step 6:

[0535] The server then uses the selected generative model to optimize the original explanatory material, specifically by:

[0536] Changing wording and examples: For example, changing the technical concept of "leadership" to "collaboration."

[0537] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[0538] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[0539] Step 7:

[0540] The server temporarily stores the optimized explanatory materials and then generates the data to be sent to the terminal. The data format for sending can be PDF, HTML, or other formats.

[0541] Step 8:

[0542] The server sends the optimized instruction material to the device. For example:

[0543] json

[0544] {

[0545] "documentation": "optimized documentation content",

[0546] "metadata": {

[0547] "Generation date and time": "2023-10-26T12:00:00Z",

[0548] "User Attributes": {

[0549] "Gender": "Female",

[0550] "age": "25",

[0551] "Position": "Regular employee"

[0552] }

[0553] }

[0554] }

[0555] Step 9:

[0556] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[0557] Example 1

[0558] 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."

[0559] Conventional explanatory materials were not optimized according to the user's attributes, and the same content was provided to all users. As a result, users could not obtain materials that suited their attributes, and it was sometimes difficult to understand the content. For example, there was an issue that general explanatory materials could not provide sufficient information because the information required and the level of understanding of technical terms differ depending on the young person, the elderly, and the type of occupation.

[0560] 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.

[0561] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative AI model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative AI model, means for transmitting the optimized explanatory material to a user terminal, and means for displaying the transmitted optimized material on the user terminal. This makes it possible to flexibly optimize explanatory material based on user attribute information and effectively convey information.

[0562] "User" refers to an individual or corporation that uses the system and is the entity that inputs their attribute information into the system.

[0563] "Attribute data" refers to user-specific characteristics and information such as gender, age, and job title, and serves as the basis for the system to optimize explanatory materials.

[0564] The "means for receiving" refers to a method for the server to receive attribute data input by the user, and includes, for example, an HTTP request or data transfer in JSON format.

[0565] A "generative AI model" is an artificial intelligence model for generating text and data, specifically an advanced natural language processing model such as GPT-3.

[0566] The "means of selection" is a method for selecting the optimal generative AI model based on the received attribute data.

[0567] The "optimization means" is a method for modifying and adjusting the content of the original explanatory materials according to the user's attribute information using the selected generative AI model.

[0568] The "means of transmission" refers to a method for transferring the optimized explanatory material to the user's device, including, for example, a REST API or an HTTP response.

[0569] "Means for displaying" refers to the method of displaying the transmitted optimization materials on the user's device, including rendering a web page using HTML and CSS.

[0570] "Terminology" refers to vocabulary that is specific to a particular field of expertise and difficult for the general public to understand.

[0571] "Simple expressions" refer to expressions that replace technical terms with simple words that are easy for the general public to understand.

[0572] "Visual elements" refers to visual materials such as charts, images, and graphs that are used to support or enhance the content of the explanation.

[0573] The present invention is a system that optimizes explanatory materials based on user attribute data. Specifically, it adjusts the original explanatory materials appropriately according to user attributes such as gender, age, and job title, making them easier to understand.

[0574] System Overview

[0575] Entering User Attributes

[0576] The user enters their own attribute information into the input screen of the device. Attribute information includes gender, age, job title, etc. For example, the user might enter "Gender: Female," "Age: 25," and "Job title: General employee." This allows the system to receive data for optimization processing according to the user's characteristics.

[0577] Sending attribute data

[0578] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example, JavaScript can be used to convert data obtained from a web form into JSON format and send it to the server as an HTTP POST request.

[0579] Receiving and processing attribute data

[0580] The server receives the attribute data sent from the device and analyzes it. The analysis is performed using the Python pandas library. Based on the analysis results, the optimal generative AI model is selected, and this model is used to optimize the data.

[0581] Acquiring and optimizing original material

[0582] The server retrieves the original explanatory materials from a database, such as a MySQL database. The retrieved materials are then optimized based on the user's attributes. This process uses the text generation AI GPT-3. Specifically, the server modifies the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[0583] Generate and submit optimization materials

[0584] The server generates optimized explanatory materials and sends them to the device. Specifically, it formats the generated text into JSON format and returns it to the device as an HTTP response via the REST API.

[0585] View optimization information

[0586] The device receives the optimization data sent from the server and displays it to the user. The data is formatted using HTML and CSS and presented as a web page that is easy for the user to view.

[0587] Hardware and software used

[0588] Terminal: The device (PC, smartphone, etc.) used by the user to enter data and view the optimized materials.

[0589] Server: A computer that receives, analyzes, optimizes, and sends data. For example, it uses Flask to accept HTTP requests.

[0590] Database: The database that stores the original documentation. For example, MySQL.

[0591] Software: Python, pandas library, generative AI model (GPT-3), HTML, CSS, JavaScript.

[0592] Specific examples

[0593] Scenario 1: Optimizing information materials for junior female employees

[0594] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[0595] 2. The device sends the entered information to the server in JSON format.

[0596] 3. Based on the received attribute information, the server sends appropriate prompts to GPT-3 to optimize it, such as changing the term "leadership" to "collaboration."

[0597] 4. The server sends the optimized explanatory materials to the terminal in JSON format.

[0598] 5. The terminal displays the received materials to the user using HTML and CSS.

[0599] Example prompt sentence:

[0600] Original instructional text:

[0601] Leadership is the ability to set direction and motivate team members.

[0602] Example prompts to input to a generative AI model:

[0603] Please optimize the following text for a 25-year-old female general employee.

[0604] Leadership is the ability to set direction and motivate team members.

[0605] Example output from GPT-3:

[0606] Leadership is the ability to decide which direction a team should go and motivate everyone.

[0607] In this way, the system of the present invention can optimize explanatory materials based on user attribute information and effectively communicate information.

[0608] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0609] Step 1:

[0610] Entering User Attributes

[0611] The user inputs attribute information into the input screen of the terminal. The input attribute information includes gender, age, job title, etc. Specifically, the user inputs "Gender: Female," "Age: 25," and "Job title: General employee." The input attribute information is temporarily saved in the terminal's memory.

[0612] Input: Attribute information entered by the user (gender, age, job title).

[0613] Output: Attribute information data saved on the device.

[0614] Step 2:

[0615] Sending attribute data

[0616] The device sends the entered attribute information to the server. The data is sent in an appropriate format, such as JSON. Specifically, the data is converted to JSON using JavaScript and sent as an HTTP POST request.

[0617] Input: Attribute information data stored on the device.

[0618] Output: Attribute information data in JSON format sent to the server.

[0619] Step 3:

[0620] Receiving and processing attribute data

[0621] The server receives the attribute data sent from the device and analyzes it using the Python pandas library. Based on the analysis results, the optimal generative AI model (e.g., GPT-3) is selected.

[0622] Input: Attribute information data in JSON format sent to the server.

[0623] Output: Parsed user attribute data and selected generative AI model.

[0624] Step 4:

[0625] Acquiring and optimizing original material

[0626] The server retrieves the original explanatory materials from a database. For example, it retrieves the materials from a MySQL database using an SQL query. It then optimizes the retrieved materials based on user attribute information. For optimization, it uses a generative AI model (GPT-3) to generate appropriate prompts and send them to the API.

[0627] Input: Parsed user attribute data, selected generative AI model, and original explanatory material retrieved from the database.

[0628] Output: Optimized explanatory material.

[0629] Step 5:

[0630] Generate and submit optimization materials

[0631] The server generates optimized explanatory materials, formats them in JSON format, and sends them to the terminal. Specifically, it packages the generated text in JSON format and returns an HTTP response via the REST API.

[0632] Input: Response data from a generative AI model (GPT-3).

[0633] Output: Optimization data formatted in JSON format.

[0634] Step 6:

[0635] View optimization information

[0636] The device receives the optimization data sent from the server and displays it to the user. Specifically, it parses the received JSON data using JavaScript, formats it using HTML and CSS, and displays it as a web page.

[0637] Input: Optimization data in JSON format sent from the server.

[0638] Output: Optimized explanatory material that the user can view on the screen.

[0639] In this way, the system can flexibly optimize explanatory materials based on the user's attribute information, and effectively communicate information.

[0640] (Application example 1)

[0641] 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."

[0642] Uniformly provided explanatory materials and work instructions for workers with different positions and experience within a factory cannot be adapted to the needs and level of understanding of each worker, resulting in the problem of work proceeding without sufficient understanding. Furthermore, for new engineers and older workers in particular, the use of technical terms and complex procedures not only takes time to understand, but also increases the risk of incorrect operation and safety issues. For this reason, a system is needed that provides materials optimally customized to the attributes of each worker.

[0643] 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.

[0644] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative model, means for transmitting the optimized explanatory material to a user's terminal, and means for displaying the optimized explanatory material on the industrial machine. This makes it possible to provide manuals and work instructions that are optimal for each worker's attributes, thereby improving understanding and ensuring safety.

[0645] "User" means a person or representative of an organization who uses the system.

[0646] "Attribute data" is information indicating characteristics of a user, such as gender, age, and job title.

[0647] A "generative model" is an algorithm or computational method used to generate optimal explanatory materials based on a user's attributes.

[0648] "Original explanatory materials" refers to the underlying information materials or manuals before they are optimized.

[0649] "Optimization" is the process of adjusting materials to suit the user's attributes and making them easier to understand.

[0650] "Terminal" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[0651] "Industrial machinery" refers to automated electronic devices and robots used in factories, etc.

[0652] The "receiving means" refers to a function or method for acquiring attribute data from a user.

[0653] The "transmitting means" refers to a function or method for transmitting the generated optimization data to a user's terminal or industrial machine.

[0654] This invention is a system that provides optimized explanatory materials based on user attribute data, and is particularly suitable for use in factories. The system itself is realized using multiple hardware components, including servers, terminals, and industrial machines, as well as appropriate software.

[0655] The server is implemented using a web framework called Flask and has the ability to receive attribute data from users. Users enter their own attribute data (such as job title and years of experience) into an input screen on their device and submit it. This data is sent to the server in a common format such as JSON.

[0656] The server analyzes the received attribute data and selects the optimal generative model based on it. The generative model contains an algorithm that can be customized according to the user's attributes. Specifically, the generative AI model is used to optimize the original explanatory material.

[0657] The generative model adapts language and terminology, adds visual elements, and more based on user attributes. For example, it can be optimized to provide more basic instructions and precautions for new technicians, while providing more advanced operating procedures and troubleshooting for more experienced workers.

[0658] The optimized explanatory materials are sent from the server to the user's device and are also displayed in real time on the displays of industrial machines, helping to ensure smooth operation within the factory.

[0659] This allows users to receive materials appropriate to their individual attributes, improving their understanding, improving work efficiency, and ensuring safety.

[0660] As a concrete example, consider the case where a new engineer enters and submits "job title: new engineer," "years of experience: 1 year," and "department: assembly." The server analyzes this data and selects a generative AI model for new employees. As a result, the generated optimization data will look like the one below.

[0661] Example prompt:

[0662] Basic Operation Instructions for New Technicians:

[0663] 1. Before performing procedure A, be sure to check procedure B.

[0664] 2. As a precaution, be especially careful when handling part X.

[0665] This information is displayed on the display of industrial machinery or on the user's terminal, making it easier for new engineers to understand the operating procedures that are appropriate for them.

[0666] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0667] Step 1:

[0668] The user enters their own attribute data into the device's input screen. They enter appropriate information into fields such as "gender," "age," and "job title," and press the "Submit" button. This allows the user's attribute information to be collected.

[0669] Input: Attribute data such as gender, age, and job title

[0670] Output: Converts attribute data to JSON format and sends it to the server

[0671] Step 2:

[0672] The terminal sends the input attribute data to the server, which receives the data in an appropriate format (e.g., JSON format).

[0673] Input: Attribute data (JSON format)

[0674] Output: Stores attribute data in the server-side receive buffer

[0675] Step 3:

[0676] The server receives and analyzes the attribute data sent from the device. In this analysis process, it parses the received JSON data and extracts each field (gender, age, job title).

[0677] Input: Attribute data (JSON format)

[0678] Output: Parsed attribute data (gender, age, job title fields)

[0679] Step 4:

[0680] The server selects the optimal generative model based on the analyzed attribute data, using algorithms and rule-based systems to select the most suitable generative AI model.

[0681] Input: Parsed attribute data

[0682] Output: The selected generative AI model

[0683] Step 5:

[0684] The server retrieves the original explanatory materials from the database, which are then optimized by the generative AI model.

[0685] Input: Original explanatory material, selected generative AI model

[0686] Output: Optimized explanatory material

[0687] Step 6:

[0688] The server uses a generative AI model to optimize the content of the original explanatory materials, customizing them based on user attributes, such as changing wording and terminology, and adding visual elements.

[0689] Input: Original explanatory material, selected generative AI model

[0690] Output: Optimized explanatory material

[0691] Step 7:

[0692] The server transmits the optimized explanatory materials to the user's terminal, which then processes the optimized materials into an appropriate format and sends them to the user's terminal.

[0693] Input: Optimized explanatory material

[0694] Output: Optimization data sent to the user's terminal

[0695] Step 8:

[0696] The terminal receives the optimization data sent from the server and displays it to the user in a visually easy-to-understand format.

[0697] Input: Optimized explanatory material

[0698] Output: Displayed optimization explanation

[0699] Step 9:

[0700] The optimized instruction materials are also displayed on the displays of industrial machines, providing workers in the factory with the information they need in real time.

[0701] Input: Optimized explanatory material

[0702] Output: Optimization instructions displayed on the industrial machine's display

[0703] 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.

[0704] The present invention is a system that optimizes explanatory materials based on a user's attribute data and emotional state. Specifically, in addition to user attributes such as gender, age, and job title, the system can recognize the user's emotions and adaptively adjust the explanatory materials based on this information. Below, we will explain in detail how the system of the present invention is actually implemented.

[0705] System Overview

[0706] 1. Enter user attributes

[0707] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[0708] 2. Emotion recognition

[0709] The device uses cameras, microphones, and sensors to recognize the user's emotions in real time. For example, it can identify the user's emotional state, such as "happy," "troubled," or "stressed," through facial expression analysis and voice tone analysis.

[0710] 3. Transmission of attribute data and emotion data

[0711] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[0712] json

[0713] {

[0714] "attribute data": {

[0715] "Gender": "Female",

[0716] "age": "25",

[0717] "Position": "Regular employee"

[0718] },

[0719] "Emotion data": "troubled"

[0720] }

[0721] 4. Receipt and processing of data

[0722] The server receives the attribute data and emotion data sent from the device, and then parses the data appropriately to extract attribute information and emotion information.

[0723] 5. Generative Model Selection

[0724] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[0725] 6. Acquiring and optimizing source material

[0726] The server retrieves the original explanatory materials from the database. It then performs optimization processing on the retrieved materials according to the user's attributes and emotions. Specifically, it performs the following processing:

[0727] Changes in wording and examples: For example, changing the technical term "leadership" to "collaboration."

[0728] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[0729] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[0730] Emotion-based adjustments: If the user is struggling, adjustments are made, such as making the explanation more concise and polite, and adding words of encouragement.

[0731] 7. Generate and submit optimization materials

[0732] The server temporarily stores the optimized explanatory materials in memory, and then generates data for transmission to the terminal. The transmission data format can be PDF, HTML, or other formats.

[0733] 8. Viewing optimization data

[0734] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[0735] Specific examples

[0736] A specific scenario will be described below.

[0737] Scenario 1: Optimizing explanatory materials for young female employees in need

[0738] 1. A user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular Employee" into the terminal, and the emotion "troubled" is recognized from her facial expression.

[0739] 2. The device sends the input information and emotion data to the server.

[0740] 3. Based on the received information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes the technical term "leadership" to "collaborative work" and replaces difficult expressions with more familiar language. It also softens the tone of the materials and adds words of encouragement.

[0741] 4. The server sends the optimized explanatory material to the terminal.

[0742] 5. The device displays optimized explanatory materials to the user, who is pleased with the easy-to-understand content and friendly tone.

[0743] The system of the present invention makes it possible to flexibly optimize explanatory materials based on user attributes and emotions, and to effectively communicate information.

[0744] The processing flow will be explained below.

[0745] Step 1:

[0746] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[0747] Step 2:

[0748] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. Through facial expression analysis and voice tone analysis, the device identifies emotions such as "happy," "troubled," or "stressed."

[0749] Step 3:

[0750] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[0751] json

[0752] {

[0753] "attribute data": {

[0754] "Gender": "Female",

[0755] "age": "25",

[0756] "Position": "Regular employee"

[0757] },

[0758] "Emotion data": "troubled"

[0759] }

[0760] Step 4:

[0761] The server receives the attribute data and emotion data sent from the terminal, parses and analyzes them appropriately, and extracts user attribute information and emotion information as analysis results.

[0762] Step 5:

[0763] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[0764] Step 6:

[0765] The server retrieves the original explanatory materials created for male managers from the database and performs optimization processing on the retrieved materials according to the user's attributes and emotions.

[0766] Step 7:

[0767] The server performs the following specific optimizations:

[0768] Changes in wording or examples: For example, changing the word "leadership" to "collaboration."

[0769] Jargon-free: Replace difficult phrases with easy-to-understand terms, e.g., changing "KPI" to "Key Performance Indicator."

[0770] Add visuals: Add charts and graphs where appropriate to help understand the material.

[0771] Emotion-based adjustment: If the user is judged to be "troubled," the explanation will be made more concise and polite, and words of encouragement will be added.

[0772] Step 8:

[0773] The server generates and stores in temporary memory optimized descriptive material, which may also include appropriate metadata.

[0774] Step 9:

[0775] The server sends the optimized explanatory materials to the terminal. The data format can be PDF or HTML. Example:

[0776] json

[0777] {

[0778] "documentation": "optimized documentation content",

[0779] "metadata": {

[0780] "Generation date and time": "2023-10-26T12:00:00Z",

[0781] "User Attributes": {

[0782] "Gender": "Female",

[0783] "age": "25",

[0784] "Position": "Regular employee"

[0785] },

[0786] "Emotion data": "troubled"

[0787] }

[0788] }

[0789] Step 10:

[0790] The terminal receives the optimization data sent from the server and displays it to the user in a format that is most easily understood by the user.

[0791] Example 2

[0792] 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."

[0793] Conventional systems for providing explanatory materials have had difficulty providing materials optimized for users based on their emotional state at any given time, in addition to their attribute information. Therefore, there has been a demand for a means to deepen users' understanding and provide information efficiently. Furthermore, materials containing technical terms and difficult expressions are often difficult for certain users to understand. It is necessary to develop a system that can solve these issues and provide information in the most optimal form for users.

[0794] 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.

[0795] In this invention, the server includes means for receiving attribute data and emotion data input by a user, means for selecting a generative model based on the attribute data and emotion data, and means for optimizing the content of the original explanatory material using the selected generative model, thereby making it possible to provide explanatory material that is appropriately optimized based on the user's attributes and emotions.

[0796] "User" refers to a person who uses the system to input attribute data and emotion data.

[0797] "Attribute data" refers to information related to a user, such as gender, age, and job title.

[0798] "Emotion data" refers to data that recognizes and expresses the user's emotional state in real time.

[0799] "Generative model" refers to an artificial intelligence model for optimizing explanatory materials based on user attribute data and emotional data.

[0800] "Optimized explanatory materials" refers to materials that have been modified and adjusted using a generative model to suit the user's attributes and emotions.

[0801] "Server" refers to a device at the back end of the system that receives data, selects a generative model, performs optimization processing, and sends optimized explanatory materials to the terminal.

[0802] "Terminal" refers to a device through which a user inputs attribute data and emotion data and receives and displays optimized explanatory materials.

[0803] "Jargon" refers to words commonly used in a particular field or industry, but difficult for the general public to understand.

[0804] "Visual elements" refer to elements that visually supplement information, such as diagrams, graphs, and icons, that are added to explanatory materials.

[0805] The present invention is a system for optimizing explanatory materials based on attribute data and emotional state of a user. Specific embodiments of the system will be described below.

[0806] System configuration

[0807] The system of the present invention is mainly composed of a terminal, a server, and a network connecting these.

[0808] Input of user attributes and emotion data

[0809] The user enters attribute data such as gender, age, and job title into the device's input screen. The device provides these data fields and prompts the user to enter accurate data. For example, the user might enter information such as "Gender: Female," "Age: 25," and "Job title: General employee."

[0810] The device uses a camera, microphone, and sensors (for example, facial expression analysis using OpenCV and Dlib, and voice tone analysis) to recognize the user's emotions in real time. It estimates their emotional state, such as "troubled," "happy," or "angry."

[0811] Sending data

[0812] The device sends the entered user attribute information and recognized emotion data in JSON format to the server using an HTTP POST request, with the following data format:

[0813] json

[0814] {

[0815] "attribute data": {

[0816] "Gender": "Female",

[0817] "age": "25",

[0818] "Position": "Regular employee"

[0819] },

[0820] "Emotion data": "troubled"

[0821] }

[0822] Data reception and analysis

[0823] The server receives the data sent from the device, processes the HTTP request using Python or Node.js, and then parses the received data to extract attribute data and emotion data.

[0824] Generative model selection and optimization

[0825] The server selects the optimal generative AI model (e.g., GPT-3 or BERT) based on the received attribute and emotion data. This selection uses a filtering algorithm to select the model that best suits the user's attribute and emotion information.

[0826] The server uses the selected generative AI model to optimize the content of the original explanatory material, specifically:

[0827] Modification of wording and examples: Send prompts to the generative AI model to replace specific jargon or phrases with appropriate modifications.

[0828] Replacing technical terms with plain language: Using pre-prepared dictionaries and algorithms, technical terms are replaced with plain language.

[0829] Add visual elements: Generate and add charts and graphs to your materials to aid comprehension, using image generation APIs such as Matplotlib or D3.js.

[0830] Emotion-based adjustment: If the user is struggling, change the message to an encouraging one or a brief, polite explanation.

[0831] Submitting and viewing optimization materials

[0832] The server uses libraries such as ReportLab and BeautifulSoup to convert the optimized explanatory materials into PDF or HTML format and store them in temporary memory, after which it sends the data to the terminal.

[0833] The terminal receives the documents sent from the server and displays them to the user using a PDF viewer or HTML rendering engine, and the documents are designed to be easy for the user to read.

[0834] Specific scenarios and prompt examples

[0835] Example scenario:

[0836] A young female employee enters "gender: female," "age: 25," and "job title: general employee" into the terminal, and the emotion "troubled" is recognized from her facial expression. The terminal sends the entered information and emotional data to the server, which then uses this information to optimize the original explanatory materials for young female employees. It changes the word "leadership" to "collaborative work" and replaces difficult expressions with more familiar words. It also softens the tone of the materials and adds words of encouragement. The optimized materials are sent to the terminal and displayed to the user. The user is pleased with the easy-to-understand content and gentle tone.

[0837] Example prompt sentence:

[0838] "Female, 25 years old, general employee. Please generate explanatory materials for a difficult situation."

[0839] This allows the present invention to provide optimized explanatory materials based on the user's individual attribute information and emotional state, thereby deepening the user's understanding and maximizing the effectiveness of the information provided.

[0840] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0841] Step 1:

[0842] The user enters attribute data such as gender, age, and job title into the device's input screen. The input data includes information such as "Gender: Female," "Age: 25," and "Job title: General employee." This attribute data specifically indicates the user's background information and plays an important role in subsequent processes. The input data is temporarily stored in the device.

[0843] Step 2:

[0844] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. It receives facial expressions and voice tones as input, and uses facial expression analysis and voice analysis algorithms, specifically OpenCV and Dlib, to determine the emotion. Emotional data, such as "troubled" or "happy," is generated as output. This emotional data is then ready to be sent to the server along with attribute data.

[0845] Step 3:

[0846] The device sends the attribute data entered by the user and the recognized emotion data to the server in JSON format. The data is sent as an HTTP POST request, with the input being the attribute data and emotion data, and the output being a notification of completion of transmission to the server. Specifically, the following JSON data is sent:

[0847] json

[0848] {

[0849] "attribute data": {

[0850] "Gender": "Female",

[0851] "age": "25",

[0852] "Position": "Regular employee"

[0853] },

[0854] "Emotion data": "troubled"

[0855] }

[0856] Step 4:

[0857] The server receives JSON data sent from the device. The input is JSON data containing attribute data and emotion data, and processes HTTP requests using Python and Node.js. Once the data is received, the server parses it to extract the attribute data and emotion data, storing them in variables. The parsed data is obtained as output.

[0858] Step 5:

[0859] The server selects the optimal generative AI model based on the received attribute data and emotion data. The input is attribute data and emotion data, and a filtering algorithm is used to select the most appropriate generative AI model (examples include GPT-3 and BERT). The selected generative AI model is obtained as the output.

[0860] Step 6:

[0861] The server optimizes the content of the original explanatory material using the selected generative AI model. The input is the original explanatory material and the selected generative model, and the following specific data processing is performed:

[0862] Change wording and examples: Send prompts to the generative model to change specific words or phrases.

[0863] Replacing technical terms with plain language: Using dictionaries and algorithms, technical terms are automatically replaced with plain language.

[0864] Add visual elements: Use Matplotlib or D3.js to generate and add charts and graphs appropriate for your presentation.

[0865] Emotion-based adjustment: If the user is struggling, adjust the message to encouragement or a concise, polite explanation.

[0866] The output is optimized explanatory material.

[0867] Step 7:

[0868] The server converts the optimized explanatory materials into PDF or HTML format and stores them in temporary memory. The input is the optimized explanatory materials, and libraries such as ReportLab and BeautifulSoup are used. As output, a savable PDF or HTML formatted document is generated. This document is then sent to the terminal.

[0869] Step 8:

[0870] The terminal receives the optimized documents sent from the server and displays them to the user. The input is the document in PDF or HTML format, and the terminal uses a PDF viewer or HTML rendering engine to render the document on the display screen. The output is the explanatory document displayed in a format that is easy for the user to read.

[0871] This allows the provision of optimal materials according to the user's attributes and emotions, thereby deepening the user's understanding.

[0872] (Application example 2)

[0873] 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."

[0874] Conventional systems for optimizing explanatory materials optimize materials based on user attribute information, but because they do not consider the user's emotional state, they are unable to sufficiently improve the user's understanding or satisfaction. Furthermore, they lack the ability to adaptively change explanatory materials according to the user's needs under specific circumstances or emotions. As a result, users find it difficult to receive appropriate support in difficult situations.

[0875] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user attribute data, means for recognizing emotion data in real time, means for selecting a generative model based on the attribute data and emotion data, means for optimizing the content of the original explanatory material using the selected generative model, and means for transmitting the optimized explanatory material to the user's terminal. This makes it possible to provide optimal explanatory material that takes into account the user's attribute information and emotional state, thereby improving the user's understanding and satisfaction.

[0876] "User" refers to an individual who uses a system or application.

[0877] "Attribute data" refers to data that includes personal information about a user, such as gender, age, and job title.

[0878] "Emotion data" is data that indicates the user's real-time emotional state, and includes emotions such as "happy," "troubled," and "stressed," for example.

[0879] "Generative model" refers to an algorithm or process for generating optimized explanatory materials based on user attribute data and emotion data.

[0880] "Instructional Materials" means any written or digital content containing information or instructions provided to a User.

[0881] "Terminal" refers to an electronic device used by a user, including, for example, a smartphone, a tablet, a personal computer, etc.

[0882] "Server" refers to a remote computer system that performs the central processing of the system, receiving data, processing the data, selecting generative models, and transmitting optimization materials.

[0883] "Optimization" refers to the process of adjusting the content of explanatory materials based on the user's attribute data and emotional data, and changing them into a form that is most easily understandable to the user.

[0884] The following describes the mode for carrying out this invention. The main components of the invention are a system that receives user attribute data, recognizes emotion data in real time, selects a generative model based on that data, and optimizes explanatory materials. This processing is performed by a server and a user's terminal.

[0885] First, the user uses the device to input their attribute data, including basic personal information such as gender, age, and job title. The device is also equipped with sensors such as a camera and microphone, which are used to recognize the user's emotional data in real time. Emotional data is obtained by analyzing the user's facial expressions and tone of voice.

[0886] Next, the user's device sends this attribute data and emotion data to the server in an appropriate data format, such as JSON. The server receives this data, analyzes its contents, and extracts the user's attribute information and emotion information.

[0887] The server selects the optimal generative model based on the extracted information. The generative model is selected from multiple pre-built models to best fit the user's attribute information and emotional state. The generative model is then used to optimize the original explanatory material to make it most understandable for the user. This optimization involves replacing technical terms with simpler language and adding visual elements. The tone of the material is also adjusted based on the user's emotions.

[0888] The optimized explanatory material is temporarily stored in the memory of the server and then sent to the user's terminal, which displays the received optimized material for the user to easily understand.

[0889] The system's main hardware consists of the user's device (smartphone, tablet, PC, etc.) and a server (cloud services such as AWS, GCP, and Azure). The software uses Python and Flask to receive and analyze data, select generative models, optimize explanatory materials, and send and receive data.

[0890] As a specific example, suppose a young female user inputs "gender: female," "age: 25," and "job title: general employee," and the device's camera recognizes the emotion "troubled." In this case, the server selects the optimal generative model, changes the technical term "leadership" to "collaborative work," and generates explanatory materials with more familiar language. The generated materials contain a gentle tone and encouraging words.

[0891] An example prompt is:

[0892] "Gender: Male, Age: 20, Position: Student, Emotion: Troubled"

[0893] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0894] Step 1:

[0895] The user enters their own attribute data into the input screen of the terminal. The input attribute data includes gender, age, job title, etc. For example, data such as "Gender: Female," "Age: 25," and "Job title: General employee" are entered.

[0896] Step 2:

[0897] The device uses sensors such as a built-in camera and microphone to recognize the user's emotional data in real time. Specifically, it analyzes facial expressions and voice tones to identify the user's emotional state as "happy," "troubled," "stressed," etc. This emotional data, along with attribute data, is used in the next step.

[0898] Step 3:

[0899] The device sends the input attribute data and recognized emotion data to the server in an appropriate data format, such as JSON. For example, the following JSON format data is sent:

[0900] json

[0901] {

[0902] "attribute data": {

[0903] "Gender": "Female",

[0904] "age": "25",

[0905] "Position": "Regular employee"

[0906] },

[0907] "Emotion data": "troubled"

[0908] }

[0909] Step 4:

[0910] The server receives the attribute data and emotion data sent from the device. It parses (analyzes) the received data and extracts the user's attribute information and emotion information. For example, it can obtain information such as "Gender: Female," "Age: 25," "Position: Regular Employee," and "Emotion: Troubled."

[0911] Step 5:

[0912] The server selects the optimal generative model based on the extracted attribute and emotion information. Multiple generative models are available, and the model that best suits the user's attribute and emotion data is selected. For example, the generative model that best suits the conditions "young female employee" and "in trouble" is selected.

[0913] Step 6:

[0914] The server uses the selected generative model to optimize the content of the original explanatory material retrieved from the database. The optimization process includes the following steps:

[0915] Replacing technical terms with simpler expressions

[0916] Add visual elements (diagrams, graphs, etc.) to your explanations

[0917] Change tone based on user emotion and add words of encouragement

[0918] For example, change the term "leadership" to "collaboration" and add words of encouragement to "struggling" users.

[0919] Step 7:

[0920] The server temporarily stores the optimized explanatory materials and then transmits them to the user's device in a format such as PDF or HTML.

[0921] Step 8:

[0922] The user's device receives the optimization materials sent from the server and displays them to the user. The display screen is designed to be easy for the user to read and is presented in an easy-to-understand format. For example, a simple and easy-to-understand explanatory document is displayed to help users deal with situations where immediate help is needed.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] [Third embodiment]

[0927] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0928] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0929] 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).

[0930] 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.

[0931] 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.

[0932] 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).

[0933] 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.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] 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."

[0939] The present invention is a system for optimizing explanatory materials based on user attribute data, specifically, adjusting the original explanatory materials appropriately according to user attributes such as gender, age, job title, etc. Below, we will explain in detail how the system of the present invention is actually implemented.

[0940] System Overview

[0941] 1. Enter user attributes

[0942] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[0943] 2. Sending attribute data

[0944] The device sends the entered attribute information to the server in an appropriate format, such as JSON.

[0945] 3. Receiving and Processing Attribute Data

[0946] The server receives and analyzes the attribute data sent from the device, and based on this analysis, selects the optimal generative model.

[0947] 4. Acquiring and optimizing source material

[0948] The server retrieves the original explanatory materials from the database and performs optimization processing on the retrieved materials according to the user's attributes. Specifically, it changes the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[0949] 5. Generate and submit optimization materials

[0950] The server generates optimized explanatory materials and sends them to the terminal, allowing the user to receive information that matches their attributes.

[0951] 6. Viewing optimization data

[0952] The terminal receives the optimization data sent from the server and displays it to the user in a format that is easy for the user to understand.

[0953] Specific examples

[0954] A specific scenario will be described below.

[0955] Scenario 1: Optimizing information materials for junior female employees

[0956] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[0957] 2. The terminal sends the entered information to the server.

[0958] 3. Based on the received attribute information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes technical terms like "leadership" to "collaborative work" and replaces difficult expressions with more familiar terms.

[0959] 4. The server sends the optimized explanatory material to the terminal.

[0960] 5. The terminal displays optimized explanatory materials to the user, who is satisfied with the easy-to-understand content.

[0961] Scenario 2: Optimizing instructional materials for older users

[0962] 1. A user (elderly user) enters "Gender: Male", "Age: 65", and "Position: Retired" into the terminal.

[0963] 2. The terminal sends the entered information to the server.

[0964] 3. Based on the received attribute information, the server optimizes the original explanatory materials, which contain a lot of technical terms, for seniors by, for example, replacing technical terms with easier-to-understand language and adding visual elements (diagrams and graphs).

[0965] 4. The server sends the optimized explanatory material to the terminal.

[0966] 5. The terminal displays optimized explanatory materials to the user, making it easier for the user to understand the materials visually intuitively.

[0967] In this way, the system of the present invention allows for flexible optimization of explanatory materials based on different user attributes, thereby enabling effective communication of information.

[0968] The processing flow will be explained below.

[0969] Step 1:

[0970] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[0971] Step 2:

[0972] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example:

[0973] json

[0974] {

[0975] "Gender": "Female",

[0976] "age": "25",

[0977] "Position": "Regular employee"

[0978] }

[0979] Step 3:

[0980] The server receives the attribute information sent from the terminal, and then parses the received data appropriately to extract the attribute information.

[0981] Step 4:

[0982] The server selects a generative model based on the received attribute information. For example, if the attributes are "gender: female," "age: 25," and "job title: general employee," the server selects the most suitable generative model.

[0983] Step 5:

[0984] The server retrieves the original explanatory material from the database, which we assume was created for male managers.

[0985] Step 6:

[0986] The server then uses the selected generative model to optimize the original explanatory material, specifically by:

[0987] Changing wording and examples: For example, changing the technical concept of "leadership" to "collaboration."

[0988] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[0989] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[0990] Step 7:

[0991] The server temporarily stores the optimized explanatory materials and then generates the data to be sent to the terminal. The data format for sending can be PDF, HTML, or other formats.

[0992] Step 8:

[0993] The server sends the optimized instruction material to the device. For example:

[0994] json

[0995] {

[0996] "documentation": "optimized documentation content",

[0997] "metadata": {

[0998] "Generation date and time": "2023-10-26T12:00:00Z",

[0999] "User Attributes": {

[1000] "Gender": "Female",

[1001] "age": "25",

[1002] "Position": "Regular employee"

[1003] }

[1004] }

[1005] }

[1006] Step 9:

[1007] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[1008] Example 1

[1009] 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."

[1010] Conventional explanatory materials were not optimized according to the user's attributes, and the same content was provided to all users. As a result, users could not obtain materials that suited their attributes, and it was sometimes difficult to understand the content. For example, there was an issue that general explanatory materials could not provide sufficient information because the information required and the level of understanding of technical terms differ depending on the young person, the elderly, and the type of occupation.

[1011] 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.

[1012] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative AI model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative AI model, means for transmitting the optimized explanatory material to a user terminal, and means for displaying the transmitted optimized material on the user terminal. This makes it possible to flexibly optimize explanatory material based on user attribute information and effectively convey information.

[1013] "User" refers to an individual or corporation that uses the system and is the entity that inputs their attribute information into the system.

[1014] "Attribute data" refers to user-specific characteristics and information such as gender, age, and job title, and serves as the basis for the system to optimize explanatory materials.

[1015] The "means for receiving" refers to a method for the server to receive attribute data input by the user, and includes, for example, an HTTP request or data transfer in JSON format.

[1016] A "generative AI model" is an artificial intelligence model for generating text and data, specifically an advanced natural language processing model such as GPT-3.

[1017] The "means of selection" is a method for selecting the optimal generative AI model based on the received attribute data.

[1018] The "optimization means" is a method for modifying and adjusting the content of the original explanatory materials according to the user's attribute information using the selected generative AI model.

[1019] The "means of transmission" refers to a method for transferring the optimized explanatory material to the user's device, including, for example, a REST API or an HTTP response.

[1020] "Means for displaying" refers to the method of displaying the transmitted optimization materials on the user's device, including rendering a web page using HTML and CSS.

[1021] "Terminology" refers to vocabulary that is specific to a particular field of expertise and difficult for the general public to understand.

[1022] "Simple expressions" refer to expressions that replace technical terms with simple words that are easy for the general public to understand.

[1023] "Visual elements" refers to visual materials such as charts, images, and graphs that are used to support or enhance the content of the explanation.

[1024] The present invention is a system that optimizes explanatory materials based on user attribute data. Specifically, it adjusts the original explanatory materials appropriately according to user attributes such as gender, age, and job title, making them easier to understand.

[1025] System Overview

[1026] Entering User Attributes

[1027] The user enters their own attribute information into the input screen of the device. Attribute information includes gender, age, job title, etc. For example, the user might enter "Gender: Female," "Age: 25," and "Job title: General employee." This allows the system to receive data for optimization processing according to the user's characteristics.

[1028] Sending attribute data

[1029] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example, JavaScript can be used to convert data obtained from a web form into JSON format and send it to the server as an HTTP POST request.

[1030] Receiving and processing attribute data

[1031] The server receives the attribute data sent from the device and analyzes it. The analysis is performed using the Python pandas library. Based on the analysis results, the optimal generative AI model is selected, and this model is used to optimize the data.

[1032] Acquiring and optimizing original material

[1033] The server retrieves the original explanatory materials from a database, such as a MySQL database. The retrieved materials are then optimized based on the user's attributes. This process uses the text generation AI GPT-3. Specifically, the server modifies the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[1034] Generate and submit optimization materials

[1035] The server generates optimized explanatory materials and sends them to the device. Specifically, it formats the generated text into JSON format and returns it to the device as an HTTP response via the REST API.

[1036] View optimization information

[1037] The device receives the optimization data sent from the server and displays it to the user. The data is formatted using HTML and CSS and presented as a web page that is easy for the user to view.

[1038] Hardware and software used

[1039] Terminal: The device (PC, smartphone, etc.) used by the user to enter data and view the optimized materials.

[1040] Server: A computer that receives, analyzes, optimizes, and sends data. For example, it uses Flask to accept HTTP requests.

[1041] Database: The database that stores the original documentation. For example, MySQL.

[1042] Software: Python, pandas library, generative AI model (GPT-3), HTML, CSS, JavaScript.

[1043] Specific examples

[1044] Scenario 1: Optimizing information materials for junior female employees

[1045] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[1046] 2. The device sends the entered information to the server in JSON format.

[1047] 3. Based on the received attribute information, the server sends appropriate prompts to GPT-3 to optimize it, such as changing the term "leadership" to "collaboration."

[1048] 4. The server sends the optimized explanatory materials to the terminal in JSON format.

[1049] 5. The terminal displays the received materials to the user using HTML and CSS.

[1050] Example prompt sentence:

[1051] Original instructional text:

[1052] Leadership is the ability to set direction and motivate team members.

[1053] Example prompts to input to a generative AI model:

[1054] Please optimize the following text for a 25-year-old female general employee.

[1055] Leadership is the ability to set direction and motivate team members.

[1056] Example output from GPT-3:

[1057] Leadership is the ability to decide which direction a team should go and motivate everyone.

[1058] In this way, the system of the present invention can optimize explanatory materials based on user attribute information and effectively communicate information.

[1059] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1060] Step 1:

[1061] Entering User Attributes

[1062] The user inputs attribute information into the input screen of the terminal. The input attribute information includes gender, age, job title, etc. Specifically, the user inputs "Gender: Female," "Age: 25," and "Job title: General employee." The input attribute information is temporarily saved in the terminal's memory.

[1063] Input: Attribute information entered by the user (gender, age, job title).

[1064] Output: Attribute information data saved on the device.

[1065] Step 2:

[1066] Sending attribute data

[1067] The device sends the entered attribute information to the server. The data is sent in an appropriate format, such as JSON. Specifically, the data is converted to JSON using JavaScript and sent as an HTTP POST request.

[1068] Input: Attribute information data stored on the device.

[1069] Output: Attribute information data in JSON format sent to the server.

[1070] Step 3:

[1071] Receiving and processing attribute data

[1072] The server receives the attribute data sent from the device and analyzes it using the Python pandas library. Based on the analysis results, the optimal generative AI model (e.g., GPT-3) is selected.

[1073] Input: Attribute information data in JSON format sent to the server.

[1074] Output: Parsed user attribute data and selected generative AI model.

[1075] Step 4:

[1076] Acquiring and optimizing original material

[1077] The server retrieves the original explanatory materials from a database. For example, it retrieves the materials from a MySQL database using an SQL query. It then optimizes the retrieved materials based on user attribute information. For optimization, it uses a generative AI model (GPT-3) to generate appropriate prompts and send them to the API.

[1078] Input: Parsed user attribute data, selected generative AI model, and original explanatory material retrieved from the database.

[1079] Output: Optimized explanatory material.

[1080] Step 5:

[1081] Generate and submit optimization materials

[1082] The server generates optimized explanatory materials, formats them in JSON format, and sends them to the terminal. Specifically, it packages the generated text in JSON format and returns an HTTP response via the REST API.

[1083] Input: Response data from a generative AI model (GPT-3).

[1084] Output: Optimization data formatted in JSON format.

[1085] Step 6:

[1086] View optimization information

[1087] The device receives the optimization data sent from the server and displays it to the user. Specifically, it parses the received JSON data using JavaScript, formats it using HTML and CSS, and displays it as a web page.

[1088] Input: Optimization data in JSON format sent from the server.

[1089] Output: Optimized explanatory material that the user can view on the screen.

[1090] In this way, the system can flexibly optimize explanatory materials based on the user's attribute information, and effectively communicate information.

[1091] (Application example 1)

[1092] 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."

[1093] Uniformly provided explanatory materials and work instructions for workers with different positions and experience within a factory cannot be adapted to the needs and level of understanding of each worker, resulting in the problem of work proceeding without sufficient understanding. Furthermore, for new engineers and older workers in particular, the use of technical terms and complex procedures not only takes time to understand, but also increases the risk of incorrect operation and safety issues. For this reason, a system is needed that provides materials optimally customized to the attributes of each worker.

[1094] 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.

[1095] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative model, means for transmitting the optimized explanatory material to a user's terminal, and means for displaying the optimized explanatory material on the industrial machine. This makes it possible to provide manuals and work instructions that are optimal for each worker's attributes, thereby improving understanding and ensuring safety.

[1096] "User" means a person or representative of an organization who uses the system.

[1097] "Attribute data" is information indicating characteristics of a user, such as gender, age, and job title.

[1098] A "generative model" is an algorithm or computational method used to generate optimal explanatory materials based on a user's attributes.

[1099] "Original explanatory materials" refers to the underlying information materials or manuals before they are optimized.

[1100] "Optimization" is the process of adjusting materials to suit the user's attributes and making them easier to understand.

[1101] "Terminal" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[1102] "Industrial machinery" refers to automated electronic devices and robots used in factories, etc.

[1103] The "receiving means" refers to a function or method for acquiring attribute data from a user.

[1104] The "transmitting means" refers to a function or method for transmitting the generated optimization data to a user's terminal or industrial machine.

[1105] This invention is a system that provides optimized explanatory materials based on user attribute data, and is particularly suitable for use in factories. The system itself is realized using multiple hardware components, including servers, terminals, and industrial machines, as well as appropriate software.

[1106] The server is implemented using a web framework called Flask and has the ability to receive attribute data from users. Users enter their own attribute data (such as job title and years of experience) into an input screen on their device and submit it. This data is sent to the server in a common format such as JSON.

[1107] The server analyzes the received attribute data and selects the optimal generative model based on it. The generative model contains an algorithm that can be customized according to the user's attributes. Specifically, the generative AI model is used to optimize the original explanatory material.

[1108] The generative model adapts language and terminology, adds visual elements, and more based on user attributes. For example, it can be optimized to provide more basic instructions and precautions for new technicians, while providing more advanced operating procedures and troubleshooting for more experienced workers.

[1109] The optimized explanatory materials are sent from the server to the user's device and are also displayed in real time on the displays of industrial machines, helping to ensure smooth operation within the factory.

[1110] This allows users to receive materials appropriate to their individual attributes, improving their understanding, improving work efficiency, and ensuring safety.

[1111] As a concrete example, consider the case where a new engineer enters and submits "job title: new engineer," "years of experience: 1 year," and "department: assembly." The server analyzes this data and selects a generative AI model for new employees. As a result, the generated optimization data will look like the one below.

[1112] Example prompt:

[1113] Basic Operation Instructions for New Technicians:

[1114] 1. Before performing procedure A, be sure to check procedure B.

[1115] 2. As a precaution, be especially careful when handling part X.

[1116] This information is displayed on the display of industrial machinery or on the user's terminal, making it easier for new engineers to understand the operating procedures that are appropriate for them.

[1117] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1118] Step 1:

[1119] The user enters their own attribute data into the device's input screen. They enter appropriate information into fields such as "gender," "age," and "job title," and press the "Submit" button. This allows the user's attribute information to be collected.

[1120] Input: Attribute data such as gender, age, and job title

[1121] Output: Converts attribute data to JSON format and sends it to the server

[1122] Step 2:

[1123] The terminal sends the input attribute data to the server, which receives the data in an appropriate format (e.g., JSON format).

[1124] Input: Attribute data (JSON format)

[1125] Output: Stores attribute data in the server-side receive buffer

[1126] Step 3:

[1127] The server receives and analyzes the attribute data sent from the device. In this analysis process, it parses the received JSON data and extracts each field (gender, age, job title).

[1128] Input: Attribute data (JSON format)

[1129] Output: Parsed attribute data (gender, age, job title fields)

[1130] Step 4:

[1131] The server selects the optimal generative model based on the analyzed attribute data, using algorithms and rule-based systems to select the most suitable generative AI model.

[1132] Input: Parsed attribute data

[1133] Output: The selected generative AI model

[1134] Step 5:

[1135] The server retrieves the original explanatory materials from the database, which are then optimized by the generative AI model.

[1136] Input: Original explanatory material, selected generative AI model

[1137] Output: Optimized explanatory material

[1138] Step 6:

[1139] The server uses a generative AI model to optimize the content of the original explanatory materials, customizing them based on user attributes, such as changing wording and terminology, and adding visual elements.

[1140] Input: Original explanatory material, selected generative AI model

[1141] Output: Optimized explanatory material

[1142] Step 7:

[1143] The server transmits the optimized explanatory materials to the user's terminal, which then processes the optimized materials into an appropriate format and sends them to the user's terminal.

[1144] Input: Optimized explanatory material

[1145] Output: Optimization data sent to the user's terminal

[1146] Step 8:

[1147] The terminal receives the optimization data sent from the server and displays it to the user in a visually easy-to-understand format.

[1148] Input: Optimized explanatory material

[1149] Output: Displayed optimization explanation

[1150] Step 9:

[1151] The optimized instruction materials are also displayed on the displays of industrial machines, providing workers in the factory with the information they need in real time.

[1152] Input: Optimized explanatory material

[1153] Output: Optimization instructions displayed on the industrial machine's display

[1154] 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.

[1155] The present invention is a system that optimizes explanatory materials based on a user's attribute data and emotional state. Specifically, in addition to user attributes such as gender, age, and job title, the system can recognize the user's emotions and adaptively adjust the explanatory materials based on this information. Below, we will explain in detail how the system of the present invention is actually implemented.

[1156] System Overview

[1157] 1. Enter user attributes

[1158] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[1159] 2. Emotion recognition

[1160] The device uses cameras, microphones, and sensors to recognize the user's emotions in real time. For example, it can identify the user's emotional state, such as "happy," "troubled," or "stressed," through facial expression analysis and voice tone analysis.

[1161] 3. Transmission of attribute data and emotion data

[1162] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[1163] json

[1164] {

[1165] "attribute data": {

[1166] "Gender": "Female",

[1167] "age": "25",

[1168] "Position": "Regular employee"

[1169] },

[1170] "Emotion data": "troubled"

[1171] }

[1172] 4. Receipt and processing of data

[1173] The server receives the attribute data and emotion data sent from the device, and then parses the data appropriately to extract attribute information and emotion information.

[1174] 5. Generative Model Selection

[1175] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[1176] 6. Acquiring and optimizing source material

[1177] The server retrieves the original explanatory materials from the database. It then performs optimization processing on the retrieved materials according to the user's attributes and emotions. Specifically, it performs the following processing:

[1178] Changes in wording and examples: For example, changing the technical term "leadership" to "collaboration."

[1179] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[1180] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[1181] Emotion-based adjustments: If the user is struggling, adjustments are made, such as making the explanation more concise and polite, and adding words of encouragement.

[1182] 7. Generate and submit optimization materials

[1183] The server temporarily stores the optimized explanatory materials in memory, and then generates data for transmission to the terminal. The transmission data format can be PDF, HTML, or other formats.

[1184] 8. Viewing optimization data

[1185] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[1186] Specific examples

[1187] A specific scenario will be described below.

[1188] Scenario 1: Optimizing explanatory materials for young female employees in need

[1189] 1. A user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular Employee" into the terminal, and the emotion "troubled" is recognized from her facial expression.

[1190] 2. The device sends the input information and emotion data to the server.

[1191] 3. Based on the received information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes the technical term "leadership" to "collaborative work" and replaces difficult expressions with more familiar language. It also softens the tone of the materials and adds words of encouragement.

[1192] 4. The server sends the optimized explanatory material to the terminal.

[1193] 5. The device displays optimized explanatory materials to the user, who is pleased with the easy-to-understand content and friendly tone.

[1194] The system of the present invention makes it possible to flexibly optimize explanatory materials based on user attributes and emotions, and to effectively communicate information.

[1195] The processing flow will be explained below.

[1196] Step 1:

[1197] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[1198] Step 2:

[1199] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. Through facial expression analysis and voice tone analysis, the device identifies emotions such as "happy," "troubled," or "stressed."

[1200] Step 3:

[1201] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[1202] json

[1203] {

[1204] "attribute data": {

[1205] "Gender": "Female",

[1206] "age": "25",

[1207] "Position": "Regular employee"

[1208] },

[1209] "Emotion data": "troubled"

[1210] }

[1211] Step 4:

[1212] The server receives the attribute data and emotion data sent from the terminal, parses and analyzes them appropriately, and extracts user attribute information and emotion information as analysis results.

[1213] Step 5:

[1214] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[1215] Step 6:

[1216] The server retrieves the original explanatory materials created for male managers from the database and performs optimization processing on the retrieved materials according to the user's attributes and emotions.

[1217] Step 7:

[1218] The server performs the following specific optimizations:

[1219] Changes in wording or examples: For example, changing the word "leadership" to "collaboration."

[1220] Jargon-free: Replace difficult phrases with easy-to-understand terms, e.g., changing "KPI" to "Key Performance Indicator."

[1221] Add visuals: Add charts and graphs where appropriate to help understand the material.

[1222] Emotion-based adjustment: If the user is judged to be "troubled," the explanation will be made more concise and polite, and words of encouragement will be added.

[1223] Step 8:

[1224] The server generates and stores in temporary memory optimized descriptive material, which may also include appropriate metadata.

[1225] Step 9:

[1226] The server sends the optimized explanatory materials to the terminal. The data format can be PDF or HTML. Example:

[1227] json

[1228] {

[1229] "documentation": "optimized documentation content",

[1230] "metadata": {

[1231] "Generation date and time": "2023-10-26T12:00:00Z",

[1232] "User Attributes": {

[1233] "Gender": "Female",

[1234] "age": "25",

[1235] "Position": "Regular employee"

[1236] },

[1237] "Emotion data": "troubled"

[1238] }

[1239] }

[1240] Step 10:

[1241] The terminal receives the optimization data sent from the server and displays it to the user in a format that is most easily understood by the user.

[1242] Example 2

[1243] 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."

[1244] Conventional systems for providing explanatory materials have had difficulty providing materials optimized for users based on their emotional state at any given time, in addition to their attribute information. Therefore, there has been a demand for a means to deepen users' understanding and provide information efficiently. Furthermore, materials containing technical terms and difficult expressions are often difficult for certain users to understand. It is necessary to develop a system that can solve these issues and provide information in the most optimal form for users.

[1245] 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.

[1246] In this invention, the server includes means for receiving attribute data and emotion data input by a user, means for selecting a generative model based on the attribute data and emotion data, and means for optimizing the content of the original explanatory material using the selected generative model, thereby making it possible to provide explanatory material that is appropriately optimized based on the user's attributes and emotions.

[1247] "User" refers to a person who uses the system to input attribute data and emotion data.

[1248] "Attribute data" refers to information related to a user, such as gender, age, and job title.

[1249] "Emotion data" refers to data that recognizes and expresses the user's emotional state in real time.

[1250] "Generative model" refers to an artificial intelligence model for optimizing explanatory materials based on user attribute data and emotional data.

[1251] "Optimized explanatory materials" refers to materials that have been modified and adjusted using a generative model to suit the user's attributes and emotions.

[1252] "Server" refers to a device at the back end of the system that receives data, selects a generative model, performs optimization processing, and sends optimized explanatory materials to the terminal.

[1253] "Terminal" refers to a device through which a user inputs attribute data and emotion data and receives and displays optimized explanatory materials.

[1254] "Jargon" refers to words commonly used in a particular field or industry, but difficult for the general public to understand.

[1255] "Visual elements" refer to elements that visually supplement information, such as diagrams, graphs, and icons, that are added to explanatory materials.

[1256] The present invention is a system for optimizing explanatory materials based on attribute data and emotional state of a user. Specific embodiments of the system will be described below.

[1257] System configuration

[1258] The system of the present invention is mainly composed of a terminal, a server, and a network connecting these.

[1259] Input of user attributes and emotion data

[1260] The user enters attribute data such as gender, age, and job title into the device's input screen. The device provides these data fields and prompts the user to enter accurate data. For example, the user might enter information such as "Gender: Female," "Age: 25," and "Job title: General employee."

[1261] The device uses a camera, microphone, and sensors (for example, facial expression analysis using OpenCV and Dlib, and voice tone analysis) to recognize the user's emotions in real time. It estimates their emotional state, such as "troubled," "happy," or "angry."

[1262] Sending data

[1263] The device sends the entered user attribute information and recognized emotion data in JSON format to the server using an HTTP POST request, with the following data format:

[1264] json

[1265] {

[1266] "attribute data": {

[1267] "Gender": "Female",

[1268] "age": "25",

[1269] "Position": "Regular employee"

[1270] },

[1271] "Emotion data": "troubled"

[1272] }

[1273] Data reception and analysis

[1274] The server receives the data sent from the device, processes the HTTP request using Python or Node.js, and then parses the received data to extract attribute data and emotion data.

[1275] Generative model selection and optimization

[1276] The server selects the optimal generative AI model (e.g., GPT-3 or BERT) based on the received attribute and emotion data. This selection uses a filtering algorithm to select the model that best suits the user's attribute and emotion information.

[1277] The server uses the selected generative AI model to optimize the content of the original explanatory material, specifically:

[1278] Modification of wording and examples: Send prompts to the generative AI model to replace specific jargon or phrases with appropriate modifications.

[1279] Replacing technical terms with plain language: Using pre-prepared dictionaries and algorithms, technical terms are replaced with plain language.

[1280] Add visual elements: Generate and add charts and graphs to your materials to aid comprehension, using image generation APIs such as Matplotlib or D3.js.

[1281] Emotion-based adjustment: If the user is struggling, change the message to an encouraging one or a brief, polite explanation.

[1282] Submitting and viewing optimization materials

[1283] The server uses libraries such as ReportLab and BeautifulSoup to convert the optimized explanatory materials into PDF or HTML format and store them in temporary memory, after which it sends the data to the terminal.

[1284] The terminal receives the documents sent from the server and displays them to the user using a PDF viewer or HTML rendering engine, and the documents are designed to be easy for the user to read.

[1285] Specific scenarios and prompt examples

[1286] Example scenario:

[1287] A young female employee enters "gender: female," "age: 25," and "job title: general employee" into the terminal, and the emotion "troubled" is recognized from her facial expression. The terminal sends the entered information and emotional data to the server, which then uses this information to optimize the original explanatory materials for young female employees. It changes the word "leadership" to "collaborative work" and replaces difficult expressions with more familiar words. It also softens the tone of the materials and adds words of encouragement. The optimized materials are sent to the terminal and displayed to the user. The user is pleased with the easy-to-understand content and gentle tone.

[1288] Example prompt sentence:

[1289] "Female, 25 years old, general employee. Please generate explanatory materials for a difficult situation."

[1290] This allows the present invention to provide optimized explanatory materials based on the user's individual attribute information and emotional state, thereby deepening the user's understanding and maximizing the effectiveness of the information provided.

[1291] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1292] Step 1:

[1293] The user enters attribute data such as gender, age, and job title into the device's input screen. The input data includes information such as "Gender: Female," "Age: 25," and "Job title: General employee." This attribute data specifically indicates the user's background information and plays an important role in subsequent processes. The input data is temporarily stored in the device.

[1294] Step 2:

[1295] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. It receives facial expressions and voice tones as input, and uses facial expression analysis and voice analysis algorithms, specifically OpenCV and Dlib, to determine the emotion. Emotional data, such as "troubled" or "happy," is generated as output. This emotional data is then ready to be sent to the server along with attribute data.

[1296] Step 3:

[1297] The device sends the attribute data entered by the user and the recognized emotion data to the server in JSON format. The data is sent as an HTTP POST request, with the input being the attribute data and emotion data, and the output being a notification of completion of transmission to the server. Specifically, the following JSON data is sent:

[1298] json

[1299] {

[1300] "attribute data": {

[1301] "Gender": "Female",

[1302] "age": "25",

[1303] "Position": "Regular employee"

[1304] },

[1305] "Emotion data": "troubled"

[1306] }

[1307] Step 4:

[1308] The server receives JSON data sent from the device. The input is JSON data containing attribute data and emotion data, and processes HTTP requests using Python and Node.js. Once the data is received, the server parses it to extract the attribute data and emotion data, storing them in variables. The parsed data is obtained as output.

[1309] Step 5:

[1310] The server selects the optimal generative AI model based on the received attribute data and emotion data. The input is attribute data and emotion data, and a filtering algorithm is used to select the most appropriate generative AI model (examples include GPT-3 and BERT). The selected generative AI model is obtained as the output.

[1311] Step 6:

[1312] The server optimizes the content of the original explanatory material using the selected generative AI model. The input is the original explanatory material and the selected generative model, and the following specific data processing is performed:

[1313] Change wording and examples: Send prompts to the generative model to change specific words or phrases.

[1314] Replacing technical terms with plain language: Using dictionaries and algorithms, technical terms are automatically replaced with plain language.

[1315] Add visual elements: Use Matplotlib or D3.js to generate and add charts and graphs appropriate for your presentation.

[1316] Emotion-based adjustment: If the user is struggling, adjust the message to encouragement or a concise, polite explanation.

[1317] The output is optimized explanatory material.

[1318] Step 7:

[1319] The server converts the optimized explanatory materials into PDF or HTML format and stores them in temporary memory. The input is the optimized explanatory materials, and libraries such as ReportLab and BeautifulSoup are used. As output, a savable PDF or HTML formatted document is generated. This document is then sent to the terminal.

[1320] Step 8:

[1321] The terminal receives the optimized documents sent from the server and displays them to the user. The input is the document in PDF or HTML format, and the terminal uses a PDF viewer or HTML rendering engine to render the document on the display screen. The output is the explanatory document displayed in a format that is easy for the user to read.

[1322] This allows the provision of optimal materials according to the user's attributes and emotions, thereby deepening the user's understanding.

[1323] (Application example 2)

[1324] 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."

[1325] Conventional systems for optimizing explanatory materials optimize materials based on user attribute information, but because they do not consider the user's emotional state, they are unable to sufficiently improve the user's understanding or satisfaction. Furthermore, they lack the ability to adaptively change explanatory materials according to the user's needs under specific circumstances or emotions. As a result, users find it difficult to receive appropriate support in difficult situations.

[1326] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user attribute data, means for recognizing emotion data in real time, means for selecting a generative model based on the attribute data and emotion data, means for optimizing the content of the original explanatory material using the selected generative model, and means for transmitting the optimized explanatory material to the user's terminal. This makes it possible to provide optimal explanatory material that takes into account the user's attribute information and emotional state, thereby improving the user's understanding and satisfaction.

[1327] "User" refers to an individual who uses a system or application.

[1328] "Attribute data" refers to data that includes personal information about a user, such as gender, age, and job title.

[1329] "Emotion data" is data that indicates the user's real-time emotional state, and includes emotions such as "happy," "troubled," and "stressed," for example.

[1330] "Generative model" refers to an algorithm or process for generating optimized explanatory materials based on user attribute data and emotion data.

[1331] "Instructional Materials" means any written or digital content containing information or instructions provided to a User.

[1332] "Terminal" refers to an electronic device used by a user, including, for example, a smartphone, a tablet, a personal computer, etc.

[1333] "Server" refers to a remote computer system that performs the central processing of the system, receiving data, processing the data, selecting generative models, and transmitting optimization materials.

[1334] "Optimization" refers to the process of adjusting the content of explanatory materials based on the user's attribute data and emotional data, and changing them into a form that is most easily understandable to the user.

[1335] The following describes the mode for carrying out this invention. The main components of the invention are a system that receives user attribute data, recognizes emotion data in real time, selects a generative model based on that data, and optimizes explanatory materials. This processing is performed by a server and a user's terminal.

[1336] First, the user uses the device to input their attribute data, including basic personal information such as gender, age, and job title. The device is also equipped with sensors such as a camera and microphone, which are used to recognize the user's emotional data in real time. Emotional data is obtained by analyzing the user's facial expressions and tone of voice.

[1337] Next, the user's device sends this attribute data and emotion data to the server in an appropriate data format, such as JSON. The server receives this data, analyzes its contents, and extracts the user's attribute information and emotion information.

[1338] The server selects the optimal generative model based on the extracted information. The generative model is selected from multiple pre-built models to best fit the user's attribute information and emotional state. The generative model is then used to optimize the original explanatory material to make it most understandable for the user. This optimization involves replacing technical terms with simpler language and adding visual elements. The tone of the material is also adjusted based on the user's emotions.

[1339] The optimized explanatory material is temporarily stored in the memory of the server and then sent to the user's terminal, which displays the received optimized material for the user to easily understand.

[1340] The system's main hardware consists of the user's device (smartphone, tablet, PC, etc.) and a server (cloud services such as AWS, GCP, and Azure). The software uses Python and Flask to receive and analyze data, select generative models, optimize explanatory materials, and send and receive data.

[1341] As a specific example, suppose a young female user inputs "gender: female," "age: 25," and "job title: general employee," and the device's camera recognizes the emotion "troubled." In this case, the server selects the optimal generative model, changes the technical term "leadership" to "collaborative work," and generates explanatory materials with more familiar language. The generated materials contain a gentle tone and encouraging words.

[1342] An example prompt is:

[1343] "Gender: Male, Age: 20, Position: Student, Emotion: Troubled"

[1344] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1345] Step 1:

[1346] The user enters their own attribute data into the input screen of the terminal. The input attribute data includes gender, age, job title, etc. For example, data such as "Gender: Female," "Age: 25," and "Job title: General employee" are entered.

[1347] Step 2:

[1348] The device uses sensors such as a built-in camera and microphone to recognize the user's emotional data in real time. Specifically, it analyzes facial expressions and voice tones to identify the user's emotional state as "happy," "troubled," "stressed," etc. This emotional data, along with attribute data, is used in the next step.

[1349] Step 3:

[1350] The device sends the input attribute data and recognized emotion data to the server in an appropriate data format, such as JSON. For example, the following JSON format data is sent:

[1351] json

[1352] {

[1353] "attribute data": {

[1354] "Gender": "Female",

[1355] "age": "25",

[1356] "Position": "Regular employee"

[1357] },

[1358] "Emotion data": "troubled"

[1359] }

[1360] Step 4:

[1361] The server receives the attribute data and emotion data sent from the device. It parses (analyzes) the received data and extracts the user's attribute information and emotion information. For example, it can obtain information such as "Gender: Female," "Age: 25," "Position: Regular Employee," and "Emotion: Troubled."

[1362] Step 5:

[1363] The server selects the optimal generative model based on the extracted attribute and emotion information. Multiple generative models are available, and the model that best suits the user's attribute and emotion data is selected. For example, the generative model that best suits the conditions "young female employee" and "in trouble" is selected.

[1364] Step 6:

[1365] The server uses the selected generative model to optimize the content of the original explanatory material retrieved from the database. The optimization process includes the following steps:

[1366] Replacing technical terms with simpler expressions

[1367] Add visual elements (diagrams, graphs, etc.) to your explanations

[1368] Change tone based on user emotion and add words of encouragement

[1369] For example, change the term "leadership" to "collaboration" and add words of encouragement to "struggling" users.

[1370] Step 7:

[1371] The server temporarily stores the optimized explanatory materials and then transmits them to the user's device in a format such as PDF or HTML.

[1372] Step 8:

[1373] The user's device receives the optimization materials sent from the server and displays them to the user. The display screen is designed to be easy for the user to read and is presented in an easy-to-understand format. For example, a simple and easy-to-understand explanatory document is displayed to help users deal with situations where immediate help is needed.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] [Fourth embodiment]

[1378] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1379] 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.

[1380] 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).

[1381] 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.

[1382] 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.

[1383] 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).

[1384] 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.

[1385] 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.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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."

[1391] The present invention is a system for optimizing explanatory materials based on user attribute data, specifically, adjusting the original explanatory materials appropriately according to user attributes such as gender, age, job title, etc. Below, we will explain in detail how the system of the present invention is actually implemented.

[1392] System Overview

[1393] 1. Enter user attributes

[1394] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[1395] 2. Sending attribute data

[1396] The device sends the entered attribute information to the server in an appropriate format, such as JSON.

[1397] 3. Receiving and Processing Attribute Data

[1398] The server receives and analyzes the attribute data sent from the device, and based on this analysis, selects the optimal generative model.

[1399] 4. Acquiring and optimizing source material

[1400] The server retrieves the original explanatory materials from the database and performs optimization processing on the retrieved materials according to the user's attributes. Specifically, it changes the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[1401] 5. Generate and submit optimization materials

[1402] The server generates optimized explanatory materials and sends them to the terminal, allowing the user to receive information that matches their attributes.

[1403] 6. Viewing optimization data

[1404] The terminal receives the optimization data sent from the server and displays it to the user in a format that is easy for the user to understand.

[1405] Specific examples

[1406] A specific scenario will be described below.

[1407] Scenario 1: Optimizing information materials for junior female employees

[1408] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[1409] 2. The terminal sends the entered information to the server.

[1410] 3. Based on the received attribute information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes technical terms like "leadership" to "collaborative work" and replaces difficult expressions with more familiar terms.

[1411] 4. The server sends the optimized explanatory material to the terminal.

[1412] 5. The terminal displays optimized explanatory materials to the user, who is satisfied with the easy-to-understand content.

[1413] Scenario 2: Optimizing instructional materials for older users

[1414] 1. A user (elderly user) enters "Gender: Male", "Age: 65", and "Position: Retired" into the terminal.

[1415] 2. The terminal sends the entered information to the server.

[1416] 3. Based on the received attribute information, the server optimizes the original explanatory materials, which contain a lot of technical terms, for seniors by, for example, replacing technical terms with easier-to-understand language and adding visual elements (diagrams and graphs).

[1417] 4. The server sends the optimized explanatory material to the terminal.

[1418] 5. The terminal displays optimized explanatory materials to the user, making it easier for the user to understand the materials visually intuitively.

[1419] In this way, the system of the present invention allows for flexible optimization of explanatory materials based on different user attributes, thereby enabling effective communication of information.

[1420] The processing flow will be explained below.

[1421] Step 1:

[1422] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[1423] Step 2:

[1424] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example:

[1425] json

[1426] {

[1427] "Gender": "Female",

[1428] "age": "25",

[1429] "Position": "Regular employee"

[1430] }

[1431] Step 3:

[1432] The server receives the attribute information sent from the terminal, and then parses the received data appropriately to extract the attribute information.

[1433] Step 4:

[1434] The server selects a generative model based on the received attribute information. For example, if the attributes are "gender: female," "age: 25," and "job title: general employee," the server selects the most suitable generative model.

[1435] Step 5:

[1436] The server retrieves the original explanatory material from the database, which we assume was created for male managers.

[1437] Step 6:

[1438] The server then uses the selected generative model to optimize the original explanatory material, specifically by:

[1439] Changing wording and examples: For example, changing the technical concept of "leadership" to "collaboration."

[1440] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[1441] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[1442] Step 7:

[1443] The server temporarily stores the optimized explanatory materials and then generates the data to be sent to the terminal. The data format for sending can be PDF, HTML, or other formats.

[1444] Step 8:

[1445] The server sends the optimized instruction material to the device. For example:

[1446] json

[1447] {

[1448] "documentation": "optimized documentation content",

[1449] "metadata": {

[1450] "Generation date and time": "2023-10-26T12:00:00Z",

[1451] "User Attributes": {

[1452] "Gender": "Female",

[1453] "age": "25",

[1454] "Position": "Regular employee"

[1455] }

[1456] }

[1457] }

[1458] Step 9:

[1459] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[1460] Example 1

[1461] 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."

[1462] Conventional explanatory materials were not optimized according to the user's attributes, and the same content was provided to all users. As a result, users could not obtain materials that suited their attributes, and it was sometimes difficult to understand the content. For example, there was an issue that general explanatory materials could not provide sufficient information because the information required and the level of understanding of technical terms differ depending on the young person, the elderly, and the type of occupation.

[1463] 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.

[1464] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative AI model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative AI model, means for transmitting the optimized explanatory material to a user terminal, and means for displaying the transmitted optimized material on the user terminal. This makes it possible to flexibly optimize explanatory material based on user attribute information and effectively convey information.

[1465] "User" refers to an individual or corporation that uses the system and is the entity that inputs their attribute information into the system.

[1466] "Attribute data" refers to user-specific characteristics and information such as gender, age, and job title, and serves as the basis for the system to optimize explanatory materials.

[1467] The "means for receiving" refers to a method for the server to receive attribute data input by the user, and includes, for example, an HTTP request or data transfer in JSON format.

[1468] A "generative AI model" is an artificial intelligence model for generating text and data, specifically an advanced natural language processing model such as GPT-3.

[1469] The "means of selection" is a method for selecting the optimal generative AI model based on the received attribute data.

[1470] The "optimization means" is a method for modifying and adjusting the content of the original explanatory materials according to the user's attribute information using the selected generative AI model.

[1471] The "means of transmission" refers to a method for transferring the optimized explanatory material to the user's device, including, for example, a REST API or an HTTP response.

[1472] "Means for displaying" refers to the method of displaying the transmitted optimization materials on the user's device, including rendering a web page using HTML and CSS.

[1473] "Terminology" refers to vocabulary that is specific to a particular field of expertise and difficult for the general public to understand.

[1474] "Simple expressions" refer to expressions that replace technical terms with simple words that are easy for the general public to understand.

[1475] "Visual elements" refers to visual materials such as charts, images, and graphs that are used to support or enhance the content of the explanation.

[1476] The present invention is a system that optimizes explanatory materials based on user attribute data. Specifically, it adjusts the original explanatory materials appropriately according to user attributes such as gender, age, and job title, making them easier to understand.

[1477] System Overview

[1478] Entering User Attributes

[1479] The user enters their own attribute information into the input screen of the device. Attribute information includes gender, age, job title, etc. For example, the user might enter "Gender: Female," "Age: 25," and "Job title: General employee." This allows the system to receive data for optimization processing according to the user's characteristics.

[1480] Sending attribute data

[1481] The device sends the entered attribute information to the server in an appropriate format, such as JSON. For example, JavaScript can be used to convert data obtained from a web form into JSON format and send it to the server as an HTTP POST request.

[1482] Receiving and processing attribute data

[1483] The server receives the attribute data sent from the device and analyzes it. The analysis is performed using the Python pandas library. Based on the analysis results, the optimal generative AI model is selected, and this model is used to optimize the data.

[1484] Acquiring and optimizing original material

[1485] The server retrieves the original explanatory materials from a database, such as a MySQL database. The retrieved materials are then optimized based on the user's attributes. This process uses the text generation AI GPT-3. Specifically, the server modifies the wording and examples, replaces technical terms with simpler expressions, and adds visual elements.

[1486] Generate and submit optimization materials

[1487] The server generates optimized explanatory materials and sends them to the device. Specifically, it formats the generated text into JSON format and returns it to the device as an HTTP response via the REST API.

[1488] View optimization information

[1489] The device receives the optimization data sent from the server and displays it to the user. The data is formatted using HTML and CSS and presented as a web page that is easy for the user to view.

[1490] Hardware and software used

[1491] Terminal: The device (PC, smartphone, etc.) used by the user to enter data and view the optimized materials.

[1492] Server: A computer that receives, analyzes, optimizes, and sends data. For example, it uses Flask to accept HTTP requests.

[1493] Database: The database that stores the original documentation. For example, MySQL.

[1494] Software: Python, pandas library, generative AI model (GPT-3), HTML, CSS, JavaScript.

[1495] Specific examples

[1496] Scenario 1: Optimizing information materials for junior female employees

[1497] 1. The user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular employee" into the terminal.

[1498] 2. The device sends the entered information to the server in JSON format.

[1499] 3. Based on the received attribute information, the server sends appropriate prompts to GPT-3 to optimize it, such as changing the term "leadership" to "collaboration."

[1500] 4. The server sends the optimized explanatory materials to the terminal in JSON format.

[1501] 5. The terminal displays the received materials to the user using HTML and CSS.

[1502] Example prompt sentence:

[1503] Original instructional text:

[1504] Leadership is the ability to set direction and motivate team members.

[1505] Example prompts to input to a generative AI model:

[1506] Please optimize the following text for a 25-year-old female general employee.

[1507] Leadership is the ability to set direction and motivate team members.

[1508] Example output from GPT-3:

[1509] Leadership is the ability to decide which direction a team should go and motivate everyone.

[1510] In this way, the system of the present invention can optimize explanatory materials based on user attribute information and effectively communicate information.

[1511] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1512] Step 1:

[1513] Entering User Attributes

[1514] The user inputs attribute information into the input screen of the terminal. The input attribute information includes gender, age, job title, etc. Specifically, the user inputs "Gender: Female," "Age: 25," and "Job title: General employee." The input attribute information is temporarily saved in the terminal's memory.

[1515] Input: Attribute information entered by the user (gender, age, job title).

[1516] Output: Attribute information data saved on the device.

[1517] Step 2:

[1518] Sending attribute data

[1519] The device sends the entered attribute information to the server. The data is sent in an appropriate format, such as JSON. Specifically, the data is converted to JSON using JavaScript and sent as an HTTP POST request.

[1520] Input: Attribute information data stored on the device.

[1521] Output: Attribute information data in JSON format sent to the server.

[1522] Step 3:

[1523] Receiving and processing attribute data

[1524] The server receives the attribute data sent from the device and analyzes it using the Python pandas library. Based on the analysis results, the optimal generative AI model (e.g., GPT-3) is selected.

[1525] Input: Attribute information data in JSON format sent to the server.

[1526] Output: Parsed user attribute data and selected generative AI model.

[1527] Step 4:

[1528] Acquiring and optimizing original material

[1529] The server retrieves the original explanatory materials from a database. For example, it retrieves the materials from a MySQL database using an SQL query. It then optimizes the retrieved materials based on user attribute information. For optimization, it uses a generative AI model (GPT-3) to generate appropriate prompts and send them to the API.

[1530] Input: Parsed user attribute data, selected generative AI model, and original explanatory material retrieved from the database.

[1531] Output: Optimized explanatory material.

[1532] Step 5:

[1533] Generate and submit optimization materials

[1534] The server generates optimized explanatory materials, formats them in JSON format, and sends them to the terminal. Specifically, it packages the generated text in JSON format and returns an HTTP response via the REST API.

[1535] Input: Response data from a generative AI model (GPT-3).

[1536] Output: Optimization data formatted in JSON format.

[1537] Step 6:

[1538] View optimization information

[1539] The device receives the optimization data sent from the server and displays it to the user. Specifically, it parses the received JSON data using JavaScript, formats it using HTML and CSS, and displays it as a web page.

[1540] Input: Optimization data in JSON format sent from the server.

[1541] Output: Optimized explanatory material that the user can view on the screen.

[1542] In this way, the system can flexibly optimize explanatory materials based on the user's attribute information, and effectively communicate information.

[1543] (Application example 1)

[1544] 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."

[1545] Uniformly provided explanatory materials and work instructions for workers with different positions and experience within a factory cannot be adapted to the needs and level of understanding of each worker, resulting in the problem of work proceeding without sufficient understanding. Furthermore, for new engineers and older workers in particular, the use of technical terms and complex procedures not only takes time to understand, but also increases the risk of incorrect operation and safety issues. For this reason, a system is needed that provides materials optimally customized to the attributes of each worker.

[1546] 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.

[1547] In this invention, the server includes means for receiving attribute data input by a user, means for selecting a generative model based on the attribute data, means for optimizing the content of the original explanatory material using the selected generative model, means for transmitting the optimized explanatory material to a user's terminal, and means for displaying the optimized explanatory material on the industrial machine. This makes it possible to provide manuals and work instructions that are optimal for each worker's attributes, thereby improving understanding and ensuring safety.

[1548] "User" means a person or representative of an organization who uses the system.

[1549] "Attribute data" is information indicating characteristics of a user, such as gender, age, and job title.

[1550] A "generative model" is an algorithm or computational method used to generate optimal explanatory materials based on a user's attributes.

[1551] "Original explanatory materials" refers to the underlying information materials or manuals before they are optimized.

[1552] "Optimization" is the process of adjusting materials to suit the user's attributes and making them easier to understand.

[1553] "Terminal" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[1554] "Industrial machinery" refers to automated electronic devices and robots used in factories, etc.

[1555] The "receiving means" refers to a function or method for acquiring attribute data from a user.

[1556] The "transmitting means" refers to a function or method for transmitting the generated optimization data to a user's terminal or industrial machine.

[1557] This invention is a system that provides optimized explanatory materials based on user attribute data, and is particularly suitable for use in factories. The system itself is realized using multiple hardware components, including servers, terminals, and industrial machines, as well as appropriate software.

[1558] The server is implemented using a web framework called Flask and has the ability to receive attribute data from users. Users enter their own attribute data (such as job title and years of experience) into an input screen on their device and submit it. This data is sent to the server in a common format such as JSON.

[1559] The server analyzes the received attribute data and selects the optimal generative model based on it. The generative model contains an algorithm that can be customized according to the user's attributes. Specifically, the generative AI model is used to optimize the original explanatory material.

[1560] The generative model adapts language and terminology, adds visual elements, and more based on user attributes. For example, it can be optimized to provide more basic instructions and precautions for new technicians, while providing more advanced operating procedures and troubleshooting for more experienced workers.

[1561] The optimized explanatory materials are sent from the server to the user's device and are also displayed in real time on the displays of industrial machines, helping to ensure smooth operation within the factory.

[1562] This allows users to receive materials appropriate to their individual attributes, improving their understanding, improving work efficiency, and ensuring safety.

[1563] As a concrete example, consider the case where a new engineer enters and submits "job title: new engineer," "years of experience: 1 year," and "department: assembly." The server analyzes this data and selects a generative AI model for new employees. As a result, the generated optimization data will look like the one below.

[1564] Example prompt:

[1565] Basic Operation Instructions for New Technicians:

[1566] 1. Before performing procedure A, be sure to check procedure B.

[1567] 2. As a precaution, be especially careful when handling part X.

[1568] This information is displayed on the display of industrial machinery or on the user's terminal, making it easier for new engineers to understand the operating procedures that are appropriate for them.

[1569] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1570] Step 1:

[1571] The user enters their own attribute data into the device's input screen. They enter appropriate information into fields such as "gender," "age," and "job title," and press the "Submit" button. This allows the user's attribute information to be collected.

[1572] Input: Attribute data such as gender, age, and job title

[1573] Output: Converts attribute data to JSON format and sends it to the server

[1574] Step 2:

[1575] The terminal sends the input attribute data to the server, which receives the data in an appropriate format (e.g., JSON format).

[1576] Input: Attribute data (JSON format)

[1577] Output: Stores attribute data in the server-side receive buffer

[1578] Step 3:

[1579] The server receives and analyzes the attribute data sent from the device. In this analysis process, it parses the received JSON data and extracts each field (gender, age, job title).

[1580] Input: Attribute data (JSON format)

[1581] Output: Parsed attribute data (gender, age, job title fields)

[1582] Step 4:

[1583] The server selects the optimal generative model based on the analyzed attribute data, using algorithms and rule-based systems to select the most suitable generative AI model.

[1584] Input: Parsed attribute data

[1585] Output: The selected generative AI model

[1586] Step 5:

[1587] The server retrieves the original explanatory materials from the database, which are then optimized by the generative AI model.

[1588] Input: Original explanatory material, selected generative AI model

[1589] Output: Optimized explanatory material

[1590] Step 6:

[1591] The server uses a generative AI model to optimize the content of the original explanatory materials, customizing them based on user attributes, such as changing wording and terminology, and adding visual elements.

[1592] Input: Original explanatory material, selected generative AI model

[1593] Output: Optimized explanatory material

[1594] Step 7:

[1595] The server transmits the optimized explanatory materials to the user's terminal, which then processes the optimized materials into an appropriate format and sends them to the user's terminal.

[1596] Input: Optimized explanatory material

[1597] Output: Optimization data sent to the user's terminal

[1598] Step 8:

[1599] The terminal receives the optimization data sent from the server and displays it to the user in a visually easy-to-understand format.

[1600] Input: Optimized explanatory material

[1601] Output: Displayed optimization explanation

[1602] Step 9:

[1603] The optimized instruction materials are also displayed on the displays of industrial machines, providing workers in the factory with the information they need in real time.

[1604] Input: Optimized explanatory material

[1605] Output: Optimization instructions displayed on the industrial machine's display

[1606] 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.

[1607] The present invention is a system that optimizes explanatory materials based on a user's attribute data and emotional state. Specifically, in addition to user attributes such as gender, age, and job title, the system can recognize the user's emotions and adaptively adjust the explanatory materials based on this information. Below, we will explain in detail how the system of the present invention is actually implemented.

[1608] System Overview

[1609] 1. Enter user attributes

[1610] The user enters attribute information into the input screen of the terminal. The attribute information includes fields such as gender, age, and job title. For example, the user enters "Gender: Female," "Age: 25," and "Job title: General employee."

[1611] 2. Emotion recognition

[1612] The device uses cameras, microphones, and sensors to recognize the user's emotions in real time. For example, it can identify the user's emotional state, such as "happy," "troubled," or "stressed," through facial expression analysis and voice tone analysis.

[1613] 3. Transmission of attribute data and emotion data

[1614] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[1615] json

[1616] {

[1617] "attribute data": {

[1618] "Gender": "Female",

[1619] "age": "25",

[1620] "Position": "Regular employee"

[1621] },

[1622] "Emotion data": "troubled"

[1623] }

[1624] 4. Receipt and processing of data

[1625] The server receives the attribute data and emotion data sent from the device, and then parses the data appropriately to extract attribute information and emotion information.

[1626] 5. Generative Model Selection

[1627] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[1628] 6. Acquiring and optimizing source material

[1629] The server retrieves the original explanatory materials from the database. It then performs optimization processing on the retrieved materials according to the user's attributes and emotions. Specifically, it performs the following processing:

[1630] Changes in wording and examples: For example, changing the technical term "leadership" to "collaboration."

[1631] Replace technical terms with simpler terms: Replace technical terms and difficult phrases with easier-to-understand terms.

[1632] Add visual elements: Add charts and graphs where appropriate to aid comprehension.

[1633] Emotion-based adjustments: If the user is struggling, adjustments are made, such as making the explanation more concise and polite, and adding words of encouragement.

[1634] 7. Generate and submit optimization materials

[1635] The server temporarily stores the optimized explanatory materials in memory, and then generates data for transmission to the terminal. The transmission data format can be PDF, HTML, or other formats.

[1636] 8. Viewing optimization data

[1637] The terminal receives the optimization data sent from the server and displays it to the user. The display screen is designed to be easy for the user to read.

[1638] Specific examples

[1639] A specific scenario will be described below.

[1640] Scenario 1: Optimizing explanatory materials for young female employees in need

[1641] 1. A user (young female employee) enters "Gender: Female," "Age: 25," and "Position: Regular Employee" into the terminal, and the emotion "troubled" is recognized from her facial expression.

[1642] 2. The device sends the input information and emotion data to the server.

[1643] 3. Based on the received information, the server optimizes the original explanatory materials, originally written for male managers, for junior female employees. For example, it changes the technical term "leadership" to "collaborative work" and replaces difficult expressions with more familiar language. It also softens the tone of the materials and adds words of encouragement.

[1644] 4. The server sends the optimized explanatory material to the terminal.

[1645] 5. The device displays optimized explanatory materials to the user, who is pleased with the easy-to-understand content and friendly tone.

[1646] The system of the present invention makes it possible to flexibly optimize explanatory materials based on user attributes and emotions, and to effectively communicate information.

[1647] The processing flow will be explained below.

[1648] Step 1:

[1649] The user enters their attribute information (gender, age, job title, etc.) into the input screen of the terminal. The input data is formatted as "gender: female," "age: 25," and "job title: general employee."

[1650] Step 2:

[1651] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. Through facial expression analysis and voice tone analysis, the device identifies emotions such as "happy," "troubled," or "stressed."

[1652] Step 3:

[1653] The device sends the user's attribute information and the recognized emotion data to the server in an appropriate format, such as JSON. For example:

[1654] json

[1655] {

[1656] "attribute data": {

[1657] "Gender": "Female",

[1658] "age": "25",

[1659] "Position": "Regular employee"

[1660] },

[1661] "Emotion data": "troubled"

[1662] }

[1663] Step 4:

[1664] The server receives the attribute data and emotion data sent from the terminal, parses and analyzes them appropriately, and extracts user attribute information and emotion information as analysis results.

[1665] Step 5:

[1666] The server selects the optimal generative model based on the received attribute information and emotion information. For example, if the user's gender is female, age is 25, job title is regular employee, and emotion is troubled, the most appropriate generative model will be selected.

[1667] Step 6:

[1668] The server retrieves the original explanatory materials created for male managers from the database and performs optimization processing on the retrieved materials according to the user's attributes and emotions.

[1669] Step 7:

[1670] The server performs the following specific optimizations:

[1671] Changes in wording or examples: For example, changing the word "leadership" to "collaboration."

[1672] Jargon-free: Replace difficult phrases with easy-to-understand terms, e.g., changing "KPI" to "Key Performance Indicator."

[1673] Add visuals: Add charts and graphs where appropriate to help understand the material.

[1674] Emotion-based adjustment: If the user is judged to be "troubled," the explanation will be made more concise and polite, and words of encouragement will be added.

[1675] Step 8:

[1676] The server generates and stores in temporary memory optimized descriptive material, which may also include appropriate metadata.

[1677] Step 9:

[1678] The server sends the optimized explanatory materials to the terminal. The data format can be PDF or HTML. Example:

[1679] json

[1680] {

[1681] "documentation": "optimized documentation content",

[1682] "metadata": {

[1683] "Generation date and time": "2023-10-26T12:00:00Z",

[1684] "User Attributes": {

[1685] "Gender": "Female",

[1686] "age": "25",

[1687] "Position": "Regular employee"

[1688] },

[1689] "Emotion data": "troubled"

[1690] }

[1691] }

[1692] Step 10:

[1693] The terminal receives the optimization data sent from the server and displays it to the user in a format that is most easily understood by the user.

[1694] Example 2

[1695] 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."

[1696] Conventional systems for providing explanatory materials have had difficulty providing materials optimized for users based on their emotional state at any given time, in addition to their attribute information. Therefore, there has been a demand for a means to deepen users' understanding and provide information efficiently. Furthermore, materials containing technical terms and difficult expressions are often difficult for certain users to understand. It is necessary to develop a system that can solve these issues and provide information in the most optimal form for users.

[1697] 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.

[1698] In this invention, the server includes means for receiving attribute data and emotion data input by a user, means for selecting a generative model based on the attribute data and emotion data, and means for optimizing the content of the original explanatory material using the selected generative model, thereby making it possible to provide explanatory material that is appropriately optimized based on the user's attributes and emotions.

[1699] "User" refers to a person who uses the system to input attribute data and emotion data.

[1700] "Attribute data" refers to information related to a user, such as gender, age, and job title.

[1701] "Emotion data" refers to data that recognizes and expresses the user's emotional state in real time.

[1702] "Generative model" refers to an artificial intelligence model for optimizing explanatory materials based on user attribute data and emotional data.

[1703] "Optimized explanatory materials" refers to materials that have been modified and adjusted using a generative model to suit the user's attributes and emotions.

[1704] "Server" refers to a device at the back end of the system that receives data, selects a generative model, performs optimization processing, and sends optimized explanatory materials to the terminal.

[1705] "Terminal" refers to a device through which a user inputs attribute data and emotion data and receives and displays optimized explanatory materials.

[1706] "Jargon" refers to words commonly used in a particular field or industry, but difficult for the general public to understand.

[1707] "Visual elements" refer to elements that visually supplement information, such as diagrams, graphs, and icons, that are added to explanatory materials.

[1708] The present invention is a system for optimizing explanatory materials based on attribute data and emotional state of a user. Specific embodiments of the system will be described below.

[1709] System configuration

[1710] The system of the present invention is mainly composed of a terminal, a server, and a network connecting these.

[1711] Input of user attributes and emotion data

[1712] The user enters attribute data such as gender, age, and job title into the device's input screen. The device provides these data fields and prompts the user to enter accurate data. For example, the user might enter information such as "Gender: Female," "Age: 25," and "Job title: General employee."

[1713] The device uses a camera, microphone, and sensors (for example, facial expression analysis using OpenCV and Dlib, and voice tone analysis) to recognize the user's emotions in real time. It estimates their emotional state, such as "troubled," "happy," or "angry."

[1714] Sending data

[1715] The device sends the entered user attribute information and recognized emotion data in JSON format to the server using an HTTP POST request, with the following data format:

[1716] json

[1717] {

[1718] "attribute data": {

[1719] "Gender": "Female",

[1720] "age": "25",

[1721] "Position": "Regular employee"

[1722] },

[1723] "Emotion data": "troubled"

[1724] }

[1725] Data reception and analysis

[1726] The server receives the data sent from the device, processes the HTTP request using Python or Node.js, and then parses the received data to extract attribute data and emotion data.

[1727] Generative model selection and optimization

[1728] The server selects the optimal generative AI model (e.g., GPT-3 or BERT) based on the received attribute and emotion data. This selection uses a filtering algorithm to select the model that best suits the user's attribute and emotion information.

[1729] The server uses the selected generative AI model to optimize the content of the original explanatory material, specifically:

[1730] Modification of wording and examples: Send prompts to the generative AI model to replace specific jargon or phrases with appropriate modifications.

[1731] Replacing technical terms with plain language: Using pre-prepared dictionaries and algorithms, technical terms are replaced with plain language.

[1732] Add visual elements: Generate and add charts and graphs to your materials to aid comprehension, using image generation APIs such as Matplotlib or D3.js.

[1733] Emotion-based adjustment: If the user is struggling, change the message to an encouraging one or a brief, polite explanation.

[1734] Submitting and viewing optimization materials

[1735] The server uses libraries such as ReportLab and BeautifulSoup to convert the optimized explanatory materials into PDF or HTML format and store them in temporary memory, after which it sends the data to the terminal.

[1736] The terminal receives the documents sent from the server and displays them to the user using a PDF viewer or HTML rendering engine, and the documents are designed to be easy for the user to read.

[1737] Specific scenarios and prompt examples

[1738] Example scenario:

[1739] A young female employee enters "gender: female," "age: 25," and "job title: general employee" into the terminal, and the emotion "troubled" is recognized from her facial expression. The terminal sends the entered information and emotional data to the server, which then uses this information to optimize the original explanatory materials for young female employees. It changes the word "leadership" to "collaborative work" and replaces difficult expressions with more familiar words. It also softens the tone of the materials and adds words of encouragement. The optimized materials are sent to the terminal and displayed to the user. The user is pleased with the easy-to-understand content and gentle tone.

[1740] Example prompt sentence:

[1741] "Female, 25 years old, general employee. Please generate explanatory materials for a difficult situation."

[1742] This allows the present invention to provide optimized explanatory materials based on the user's individual attribute information and emotional state, thereby deepening the user's understanding and maximizing the effectiveness of the information provided.

[1743] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1744] Step 1:

[1745] The user enters attribute data such as gender, age, and job title into the device's input screen. The input data includes information such as "Gender: Female," "Age: 25," and "Job title: General employee." This attribute data specifically indicates the user's background information and plays an important role in subsequent processes. The input data is temporarily stored in the device.

[1746] Step 2:

[1747] The device uses a camera, microphone, and sensors to recognize the user's emotions in real time. It receives facial expressions and voice tones as input, and uses facial expression analysis and voice analysis algorithms, specifically OpenCV and Dlib, to determine the emotion. Emotional data, such as "troubled" or "happy," is generated as output. This emotional data is then ready to be sent to the server along with attribute data.

[1748] Step 3:

[1749] The device sends the attribute data entered by the user and the recognized emotion data to the server in JSON format. The data is sent as an HTTP POST request, with the input being the attribute data and emotion data, and the output being a notification of completion of transmission to the server. Specifically, the following JSON data is sent:

[1750] json

[1751] {

[1752] "attribute data": {

[1753] "Gender": "Female",

[1754] "age": "25",

[1755] "Position": "Regular employee"

[1756] },

[1757] "Emotion data": "troubled"

[1758] }

[1759] Step 4:

[1760] The server receives JSON data sent from the device. The input is JSON data containing attribute data and emotion data, and processes HTTP requests using Python and Node.js. Once the data is received, the server parses it to extract the attribute data and emotion data, storing them in variables. The parsed data is obtained as output.

[1761] Step 5:

[1762] The server selects the optimal generative AI model based on the received attribute data and emotion data. The input is attribute data and emotion data, and a filtering algorithm is used to select the most appropriate generative AI model (examples include GPT-3 and BERT). The selected generative AI model is obtained as the output.

[1763] Step 6:

[1764] The server optimizes the content of the original explanatory material using the selected generative AI model. The input is the original explanatory material and the selected generative model, and the following specific data processing is performed:

[1765] Change wording and examples: Send prompts to the generative model to change specific words or phrases.

[1766] Replacing technical terms with plain language: Using dictionaries and algorithms, technical terms are automatically replaced with plain language.

[1767] Add visual elements: Use Matplotlib or D3.js to generate and add charts and graphs appropriate for your presentation.

[1768] Emotion-based adjustment: If the user is struggling, adjust the message to encouragement or a concise, polite explanation.

[1769] The output is optimized explanatory material.

[1770] Step 7:

[1771] The server converts the optimized explanatory materials into PDF or HTML format and stores them in temporary memory. The input is the optimized explanatory materials, and libraries such as ReportLab and BeautifulSoup are used. As output, a savable PDF or HTML formatted document is generated. This document is then sent to the terminal.

[1772] Step 8:

[1773] The terminal receives the optimized documents sent from the server and displays them to the user. The input is the document in PDF or HTML format, and the terminal uses a PDF viewer or HTML rendering engine to render the document on the display screen. The output is the explanatory document displayed in a format that is easy for the user to read.

[1774] This allows the provision of optimal materials according to the user's attributes and emotions, thereby deepening the user's understanding.

[1775] (Application example 2)

[1776] 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."

[1777] Conventional systems for optimizing explanatory materials optimize materials based on user attribute information, but because they do not consider the user's emotional state, they are unable to sufficiently improve the user's understanding or satisfaction. Furthermore, they lack the ability to adaptively change explanatory materials according to the user's needs under specific circumstances or emotions. As a result, users find it difficult to receive appropriate support in difficult situations.

[1778] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving user attribute data, means for recognizing emotion data in real time, means for selecting a generative model based on the attribute data and emotion data, means for optimizing the content of the original explanatory material using the selected generative model, and means for transmitting the optimized explanatory material to the user's terminal. This makes it possible to provide optimal explanatory material that takes into account the user's attribute information and emotional state, thereby improving the user's understanding and satisfaction.

[1779] "User" refers to an individual who uses a system or application.

[1780] "Attribute data" refers to data that includes personal information about a user, such as gender, age, and job title.

[1781] "Emotion data" is data that indicates the user's real-time emotional state, and includes emotions such as "happy," "troubled," and "stressed," for example.

[1782] "Generative model" refers to an algorithm or process for generating optimized explanatory materials based on user attribute data and emotion data.

[1783] "Instructional Materials" means any written or digital content containing information or instructions provided to a User.

[1784] "Terminal" refers to an electronic device used by a user, including, for example, a smartphone, a tablet, a personal computer, etc.

[1785] "Server" refers to a remote computer system that performs the central processing of the system, receiving data, processing the data, selecting generative models, and transmitting optimization materials.

[1786] "Optimization" refers to the process of adjusting the content of explanatory materials based on the user's attribute data and emotional data, and changing them into a form that is most easily understandable to the user.

[1787] The following describes the mode for carrying out this invention. The main components of the invention are a system that receives user attribute data, recognizes emotion data in real time, selects a generative model based on that data, and optimizes explanatory materials. This processing is performed by a server and a user's terminal.

[1788] First, the user uses the device to input their attribute data, including basic personal information such as gender, age, and job title. The device is also equipped with sensors such as a camera and microphone, which are used to recognize the user's emotional data in real time. Emotional data is obtained by analyzing the user's facial expressions and tone of voice.

[1789] Next, the user's device sends this attribute data and emotion data to the server in an appropriate data format, such as JSON. The server receives this data, analyzes its contents, and extracts the user's attribute information and emotion information.

[1790] The server selects the optimal generative model based on the extracted information. The generative model is selected from multiple pre-built models to best fit the user's attribute information and emotional state. The generative model is then used to optimize the original explanatory material to make it most understandable for the user. This optimization involves replacing technical terms with simpler language and adding visual elements. The tone of the material is also adjusted based on the user's emotions.

[1791] The optimized explanatory material is temporarily stored in the memory of the server and then sent to the user's terminal, which displays the received optimized material for the user to easily understand.

[1792] The system's main hardware consists of the user's device (smartphone, tablet, PC, etc.) and a server (cloud services such as AWS, GCP, and Azure). The software uses Python and Flask to receive and analyze data, select generative models, optimize explanatory materials, and send and receive data.

[1793] As a specific example, suppose a young female user inputs "gender: female," "age: 25," and "job title: general employee," and the device's camera recognizes the emotion "troubled." In this case, the server selects the optimal generative model, changes the technical term "leadership" to "collaborative work," and generates explanatory materials with more familiar language. The generated materials contain a gentle tone and encouraging words.

[1794] An example prompt is:

[1795] "Gender: Male, Age: 20, Position: Student, Emotion: Troubled"

[1796] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1797] Step 1:

[1798] The user enters their own attribute data into the input screen of the terminal. The input attribute data includes gender, age, job title, etc. For example, data such as "Gender: Female," "Age: 25," and "Job title: General employee" are entered.

[1799] Step 2:

[1800] The device uses sensors such as a built-in camera and microphone to recognize the user's emotional data in real time. Specifically, it analyzes facial expressions and voice tones to identify the user's emotional state as "happy," "troubled," "stressed," etc. This emotional data, along with attribute data, is used in the next step.

[1801] Step 3:

[1802] The device sends the input attribute data and recognized emotion data to the server in an appropriate data format, such as JSON. For example, the following JSON format data is sent:

[1803] json

[1804] {

[1805] "attribute data": {

[1806] "Gender": "Female",

[1807] "age": "25",

[1808] "Position": "Regular employee"

[1809] },

[1810] "Emotion data": "troubled"

[1811] }

[1812] Step 4:

[1813] The server receives the attribute data and emotion data sent from the device. It parses (analyzes) the received data and extracts the user's attribute information and emotion information. For example, it can obtain information such as "Gender: Female," "Age: 25," "Position: Regular Employee," and "Emotion: Troubled."

[1814] Step 5:

[1815] The server selects the optimal generative model based on the extracted attribute and emotion information. Multiple generative models are available, and the model that best suits the user's attribute and emotion data is selected. For example, the generative model that best suits the conditions "young female employee" and "in trouble" is selected.

[1816] Step 6:

[1817] The server uses the selected generative model to optimize the content of the original explanatory material retrieved from the database. The optimization process includes the following steps:

[1818] Replacing technical terms with simpler expressions

[1819] Add visual elements (diagrams, graphs, etc.) to your explanations

[1820] Change tone based on user emotion and add words of encouragement

[1821] For example, change the term "leadership" to "collaboration" and add words of encouragement to "struggling" users.

[1822] Step 7:

[1823] The server temporarily stores the optimized explanatory materials and then transmits them to the user's device in a format such as PDF or HTML.

[1824] Step 8:

[1825] The user's device receives the optimization materials sent from the server and displays them to the user. The display screen is designed to be easy for the user to read and is presented in an easy-to-understand format. For example, a simple and easy-to-understand explanatory document is displayed to help users deal with situations where immediate help is needed.

[1826] 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.

[1827] 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.

[1828] 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.

[1829] 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.

[1830] 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.

[1831] 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.

[1832] 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).

[1833] 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.

[1834] 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."

[1835] 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.

[1836] 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).

[1837] 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.

[1838] 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.

[1839] 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.

[1840] 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.

[1841] 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.

[1842] 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.

[1843] 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.

[1844] 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.

[1845] 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.

[1846] 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.

[1847] The following is further disclosed regarding the above embodiment.

[1848] (Claim 1)

[1849] means for receiving attribute data input by a user;

[1850] means for selecting a generative model based on the attribute data;

[1851] A means for optimizing the content of the original explanatory material using the selected generative model;

[1852] means for transmitting the optimized explanatory material to a user's terminal;

[1853] A system including:

[1854] (Claim 2)

[1855] 2. The system according to claim 1, further comprising means for replacing technical terms with plain language in the content of the optimized explanatory material.

[1856] (Claim 3)

[1857] 10. The system of claim 1, further comprising means for adding visual elements within the content of the optimized instructional material.

[1858] "Example 1"

[1859] (Claim 1)

[1860] means for receiving attribute data input by a user;

[1861] A means for selecting a generative AI model based on the attribute data;

[1862] a means for optimizing the content of the original explanatory material using the selected generative AI model; and

[1863] means for transmitting the optimized explanatory material to a user's terminal;

[1864] means for displaying the transmitted optimization data on a user's terminal;

[1865] A system including:

[1866] (Claim 2)

[1867] 2. The system according to claim 1, further comprising means for replacing technical terms with plain language in the content of the optimized explanatory material.

[1868] (Claim 3)

[1869] 10. The system of claim 1, further comprising means for adding visual elements within the content of the optimized instructional material.

[1870] "Application Example 1"

[1871] (Claim 1)

[1872] means for receiving attribute data input by a user;

[1873] means for selecting a generative model based on the attribute data;

[1874] A means for optimizing the content of the original explanatory material using the selected generative model;

[1875] means for transmitting the optimized explanatory material to a user terminal;

[1876] means for displaying the optimized instructional material on the industrial machine;

[1877] A system including:

[1878] (Claim 2)

[1879] 2. The system according to claim 1, further comprising means for replacing technical terms with plain language in the content of the optimized explanatory material.

[1880] (Claim 3)

[1881] 10. The system of claim 1, further comprising means for adding visual elements within the content of the optimized instructional material.

[1882] "Example 2: Combining Emotion Engines"

[1883] (Claim 1)

[1884] means for receiving attribute data and emotion data input by a user;

[1885] means for selecting a generative model based on the attribute data and emotion data;

[1886] A means for optimizing the content of the original explanatory material using the selected generative model;

[1887] means for transmitting the optimized explanatory material to a user's terminal;

[1888] A system including:

[1889] (Claim 2)

[1890] 2. The system according to claim 1, further comprising means for replacing technical terms with plain language in the content of the optimized explanatory material.

[1891] (Claim 3)

[1892] 10. The system of claim 1, further comprising means for adding visual elements within the content of the optimized instructional material.

[1893] "Application example 2 when combining emotion engines"

[1894] (Claim 1)

[1895] means for receiving attribute data input by a user;

[1896] a means for recognizing emotion data in real time;

[1897] means for selecting a generative model based on the attribute data and emotion data;

[1898] A means for optimizing the content of the original explanatory material using the selected generative model;

[1899] means for transmitting the optimized explanatory material to a user terminal;

[1900] A system including:

[1901] (Claim 2)

[1902] 10. The system of claim 1, further comprising means for replacing technical terms with plain language in the content of the optimized explanatory material.

[1903] (Claim 3)

[1904] 10. The system of claim 1, further comprising means for adding visual elements within the content of the optimized instructional material. [Explanation of symbols]

[1905] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving attribute data input by a user; means for selecting a generative model based on the attribute data; A means for optimizing the content of the original explanatory material using the selected generative model; means for transmitting the optimized explanatory material to a user's terminal; A system including:

2. 2. The system according to claim 1, further comprising means for replacing technical terms with simple expressions in the content of the optimized explanatory material.

3. The system of claim 1 , further comprising means for adding visual elements within the content of the optimized instructional material.

Images