system

Abstract

We provide the system. [Solution] A means by which the user inputs the model name and keywords using a terminal, The server has means for receiving the model name and keyword from the terminal, A means by which the server queries the artificial intelligence model using the aforementioned model name and keyword, An artificial intelligence model provides means for generating information corresponding to the keyword from descriptive data related to the model name, The server provides means for transmitting the generated information to the terminal, The terminal provides means for displaying the transmitted information to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Modern electronic devices and home appliances are becoming more multifunctional, and accordingly, the number of pages in the operation manuals is increasing. As a result, it is becoming difficult for users to quickly access the information they need. There is a need for a system that solves this problem and allows users to efficiently obtain the necessary information.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that includes means for a user to input a model name and keywords using a terminal, means for a server to receive the model name and keywords from the terminal, means for the server to query an artificial intelligence model using the model name and keywords, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name, means for the server to transmit the generated information to the terminal, and means for the terminal to display the transmitted information to the user. With this system, the user can quickly obtain the necessary information from the vast amount of information in the instruction manual.

[0006] A "terminal" is an electronic device used by users to input information or display received information.

[0007] A "server" is a computer system that receives requests from terminals via a network, processes them, and sends the results back to the terminals.

[0008] A "model name" is a name or model number used to identify a specific electronic device or home appliance.

[0009] A "keyword" is a word or short phrase used by a user to indicate specific information they want to search for.

[0010] An "artificial intelligence model" is software that uses machine learning algorithms to analyze data and generate appropriate information in response to user requests.

[0011] "Description data" refers to information obtained from instruction manuals and other reference materials related to the model name.

[0012] "Information" refers to the content of the responses to user requests generated by the artificial intelligence model.

[0013] A "user" is a person who operates a terminal to access a system and input or retrieve information. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the 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.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0028] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The system of this invention is designed to allow users to quickly obtain necessary information from instruction manuals. Specifically, the user inputs the model name and keywords using a terminal, sends this information to a server, and an artificial intelligence model generates the relevant information, which is then displayed to the user.

[0036] System Configuration

[0037] 1. Terminal

[0038] The terminal serves as the user's input device. The user uses the terminal to input the model name and keywords, and sends them to the server. The terminal has a web browser and a dedicated application installed, which the user uses to access the system.

[0039] 2. Server

[0040] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[0041] 3. Artificial Intelligence Models

[0042] The artificial intelligence model analyzes data from instruction manuals and generates information related to keywords searched by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[0043] Program processing flow

[0044] User input processing

[0045] The user enters the model name (e.g., "Washing Machine ABC123") and a keyword (e.g., "Filter Cleaning") on the device and clicks the submit button. The device sends the entered data to the server. The data is sent in a format such as JSON.

[0046] Server Processing

[0047] The server analyzes the data received from the terminal and extracts the model name and keywords. Next, the server passes this information to an artificial intelligence model and requests the generation of corresponding information.

[0048] Processing of artificial intelligence models

[0049] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts and generates information that matches the keywords. Specifically, it analyzes the text data of the instruction manuals and selects the most relevant information.

[0050] Information formatting and transmission

[0051] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[0052] Display to the user

[0053] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can then quickly obtain the necessary information from the instruction manual.

[0054] Specific example

[0055] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on their device and submits it. The device sends this data to the server. The server receives and analyzes this data, passing the model name and keywords to an artificial intelligence model. The AI ​​model extracts information related to "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this information and sends it to the device, which then displays it to the user. The user can quickly confirm how to set up the remote control.

[0056] The above describes the configuration for implementing the system of the present invention. This system allows users to quickly find the necessary information from a vast number of instruction manuals, significantly improving convenience.

[0057] The following describes the processing flow.

[0058] Step 1:

[0059] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into the input form for searching the instruction manual. After entering the information, the user presses the submit button to send the data.

[0060] Step 2:

[0061] The terminal sends the model name and keywords entered by the user to the server as an HTTP request. This data is sent in JSON format or as HTTP parameters.

[0062] Step 3:

[0063] The server parses the HTTP request received from the terminal and extracts the model name and keywords. The parsed data is stored in variables.

[0064] Step 4:

[0065] The server uses the extracted model name and keywords to send information generation requests to the artificial intelligence model. Specifically, it sends data in the format {"device": "model name", "keyword": "keyword"} using API calls or internal functions.

[0066] Step 5:

[0067] The artificial intelligence model searches a database of instruction manuals related to the model name based on the received request. It extracts information that matches the keywords and generates the most relevant response.

[0068] Step 6:

[0069] The response generated by the artificial intelligence model is returned to the server. The server receives this response and formats it into a user-friendly format, for example, by converting it to HTML.

[0070] Step 7:

[0071] The server sends the formatted information to the terminal as an HTTP response. The data is sent in various formats, such as JSON or HTML, as needed.

[0072] Step 8:

[0073] The terminal analyzes information received from the server and displays it on the user's screen. Specifically, it either inserts the information into the DOM using the browser's JavaScript (registered trademark) or displays the information using a dedicated application.

[0074] Step 9:

[0075] Users can view the information displayed on their device screen and obtain the necessary information. For example, they can view information such as "How to set up the remote control for the XYZ789 air conditioner..." and then perform the actual operation.

[0076] (Example 1)

[0077] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0078] Conventional manual search systems made it difficult to quickly find necessary information from a vast amount of data. Furthermore, users had to enter precise model names or keywords, resulting in usability issues. There is a need to provide a system that solves these problems and allows users to easily and quickly access the information they need.

[0079] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0080] In this invention, the server includes means for a user to input a model name and keywords using an information terminal; means for the server to receive the model name and keywords from the information terminal; means for the server to analyze the model name and keywords and query an artificial intelligence system; means for the artificial intelligence system to generate information corresponding to the keywords from technical literature data related to the model name; means for the server to format the generated information and transmit it to the information terminal; and means for the information terminal to display the formatted information to the user. This makes it possible for the user to easily and quickly obtain the necessary information.

[0081] An "information terminal" is a device used by users to input information and communicate with a server, and includes personal computers, smartphones, tablets, and other similar devices.

[0082] "Model name" refers to a name used to identify a specific product or device, such as a product-specific name like "Air Conditioner XYZ789".

[0083] A "keyword" is a term or phrase that a user uses to search for specific information within an instruction manual.

[0084] A "server" is a computing system that analyzes data received from terminals, queries an artificial intelligence system, and provides appropriate information.

[0085] An "artificial intelligence system" is a model that analyzes and generates information using machine learning algorithms, and its role is to provide the necessary data based on user requests.

[0086] "Technical literature data" refers to a database containing information such as instruction manuals and technical manuals for each model.

[0087] A "machine learning algorithm" is an algorithm used by artificial intelligence systems to learn from data and train models.

[0088] "Formatting" refers to the process of transforming generated information into a format that is easy for users to view, and includes conversion to HTML or JSON format.

[0089] The system of the present invention is designed to allow users to quickly obtain necessary information from instruction manuals using an information terminal. The hardware and software necessary to specifically implement this invention, and the data processing methods using them, are described below.

[0090] terminal

[0091] Users enter the model name and keywords using an information terminal. These terminals can include personal computers, smartphones, and tablets. These terminals also have web browsers and dedicated applications installed, which users use to access the system.

[0092] server

[0093] The server is the central device that receives and analyzes data transmitted from terminals. Server-side programs are often written in programming languages ​​such as Python or Java (registered trademark). The server parses the model name and keywords received from the terminals in JSON format and extracts them appropriately.

[0094] Artificial intelligence system

[0095] The server passes the analyzed model names and keywords to the artificial intelligence (AI) system. The AI ​​system has models trained using machine learning frameworks such as TENSORFLOW® and PyTorch, and analyzes the technical literature data. This AI system is trained using machine learning algorithms and can select information with high relevance.

[0096] Information formatting and transmission

[0097] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format. The formatted information is then converted into HTML or JSON format and finally sent from the server to the terminal.

[0098] Display to the user

[0099] The device displays the received information to the user. Specifically, the information is presented in a visually easy-to-understand format through a web browser or a dedicated app. This allows the user to quickly obtain the necessary information from the instruction manual.

[0100] Specific example

[0101] Let's consider a scenario where a user searches for information about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the information terminal and clicks the submit button. The submitted data is sent to the server, which analyzes it. Then, a request based on the model name and keywords is sent to the artificial intelligence system. The artificial intelligence system searches the technical literature data and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats the generated information and sends it back to the terminal. The terminal displays the received information to the user, allowing the user to easily check how to set up the remote control.

[0102] Example of a prompt

[0103] Model name: Air conditioner XYZ789

[0104] Keywords: Remote control settings

[0105] output:

[0106] How to set up the remote control:

[0107] 1. Insert the batteries.

[0108] 2. Press and hold the settings button for 3 seconds.

[0109] 3. Complete the settings for the receiving unit.

[0110] The above describes the configuration for implementing the invention, and this system allows users to quickly obtain the necessary information from the instruction manual. This significantly improves convenience.

[0111] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0112] Step 1:

[0113] User data entry

[0114] The user enters the model name and keywords using the input form on the information terminal. Specifically, they enter "Air Conditioner XYZ789" (model name) and "Remote Control Settings" (keyword) via a browser or dedicated app, and then click the submit button.

[0115] Input: Model name "Air conditioner XYZ789", Keyword "Remote control settings"

[0116] Output: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[0117] Step 2:

[0118] Data reception by the server

[0119] The server receives data in JSON format sent by the terminal. The server then prepares to parse this data.

[0120] Input: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[0121] Output: Data converted to an internal format for data analysis.

[0122] Step 3:

[0123] Data Analysis

[0124] The server parses the received JSON data and extracts the model name and keywords. It uses parsing programs written in Python or Java.

[0125] Specific operation: Extract the "Model Name" and "Keyword" fields from the JSON data.

[0126] Input: Data in JSON format

[0127] Output: Extracted model name "Air Conditioner XYZ789" and keyword "Remote Control Settings"

[0128] Step 4:

[0129] Inquiries to the artificial intelligence system

[0130] The server uses the analyzed model name and keywords to send an information generation request to the artificial intelligence system. The request is sent via a REST API.

[0131] Specific operation: Send an HTTP request from the server to the artificial intelligence system.

[0132] Input: Extracted model name and keyword

[0133] Output: HTTP request "{"Model name": "Air conditioner XYZ789", "Keyword": "Remote control settings"}"

[0134] Step 5:

[0135] Information generation

[0136] The artificial intelligence system uses machine learning algorithms to extract and generate relevant information from technical literature databases. Specifically, it analyzes text data from instruction manuals and selects information that matches keywords.

[0137] Specific operation: Use natural language processing techniques to extract and generate relevant information.

[0138] Input: Model name "Air conditioner XYZ789" and keyword "Remote control settings"

[0139] Output: Generated information: "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[0140] Step 6:

[0141] Formalization of information

[0142] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format, such as HTML or JSON.

[0143] Specific actions: Convert the generated information into HTML format and arrange the layout.

[0144] Input: Generated information

[0145] Output: Formatted information (HTML or JSON)

[0146] Step 7:

[0147] Information transmission

[0148] The formatted information is sent from the server to the terminal. It is sent quickly so that the user can immediately verify the information.

[0149] Specific operation: Sends formatted information as an HTTP response.

[0150] Input: Formatted information

[0151] Output: Sending information to the user terminal

[0152] Step 8:

[0153] Displaying information

[0154] The device displays the received, formatted information to the user. It presents the information in a visually easy-to-understand format using a browser or dedicated app.

[0155] Specific operation: Renders information in a browser or app and displays it on the screen.

[0156] Input: Information received from the server

[0157] Output: Information visually displayed to the user

[0158] The above outlines the specific processing steps of the system. Each step works in conjunction to create a mechanism that allows users to quickly obtain the information they need.

[0159] (Application Example 1)

[0160] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0161] Maintaining and troubleshooting complex equipment and robots used in factories is time-consuming and labor-intensive, as operators must consult numerous instruction manuals and technical documents. Furthermore, a lack of systems to quickly detect equipment malfunctions and provide appropriate maintenance procedures can hinder efficient factory operations.

[0162] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0163] In this invention, the server includes means for a user to input a model name and keywords using a terminal, means for the server to receive the model name and keywords from the terminal, means for the server to query an artificial intelligence model using the model name and keywords, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name, means for the server to transmit the generated information to the terminal, means for the terminal to display the transmitted information to the user, means for a robot operating in the factory to automatically input the model name and keywords when it detects an abnormality in the equipment, and means for the terminal to display maintenance procedures to the robot operator. This enables rapid and accurate detection of equipment abnormalities and provision of maintenance procedures within the factory, making efficient factory operation possible.

[0164] A "user" is a person who uses a system; they are the entity that performs input and operations through the system interface.

[0165] A "terminal" refers to an input device used by a user to access a system, and includes computers, smartphones, tablets, and other similar devices.

[0166] "Model name" refers to the name that represents a specific piece of equipment or device, and is used as product identification information.

[0167] A "keyword" is a word or phrase that a user enters to specify the information they need.

[0168] A "server" refers to a central computing device that receives and processes requests from users and provides the necessary information.

[0169] An "artificial intelligence model" is a data analysis program that is trained using machine learning algorithms and generates responses based on user input.

[0170] "Explanatory data" refers to information provided in instruction manuals and other documents, including how to operate the equipment and maintenance procedures.

[0171] "Generating information" refers to the process by which an artificial intelligence model extracts and constructs relevant information based on the entered model name and keywords.

[0172] "Detecting an anomaly" means discovering a state in which a robot or piece of equipment deviates from its normal operation.

[0173] "Maintenance procedures" refer to information that outlines the specific steps required for servicing or repairing equipment.

[0174] A "robot operator" is a person who operates and monitors robots within a factory.

[0175] This invention is a system for assisting with the maintenance and troubleshooting of robots used in factories. Specifically, the user inputs the model name and keywords using a terminal, a server receives and analyzes this information, generates relevant information using an artificial intelligence model, and finally displays it to the user.

[0176] System Configuration

[0177] 1. Terminal

[0178] The terminal is a device used by the user as an input device, and includes computers, smartphones, and tablets. The user uses it to input the model name (e.g., "Robot Arm ABC123") and keywords (e.g., "Maintenance Procedure") and sends them to the server.

[0179] 2. Server

[0180] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[0181] Specifically, the server passes the analyzed data to an artificial intelligence model, which then extracts and constructs the most relevant explanatory data.

[0182] 3. Artificial Intelligence Models

[0183] The artificial intelligence model analyzes data from the instruction manual and generates information related to keywords entered by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[0184] The artificial intelligence model uses OpenAI's GPT-3 (registered trademark) (engine: daVinci) and performs natural language processing.

[0185] 4. Formalizing and transmitting information

[0186] The generated information is formatted by the server into HTML or JSON format and sent to the device. This allows the information to be presented in a visually easy-to-understand format on the device.

[0187] Program processing

[0188] The server receives and analyzes the model name and keywords entered by the user from the terminal. After analysis, it passes the information to an artificial intelligence model to create a prompt for generating appropriate information. Using this prompt, the AI ​​model generates data related to the specified model name and keywords. The generated information is formatted by the server, sent to the terminal, and displayed to the user.

[0189] Hardware and software to be used

[0190] Hardware: Robot bodies, control panels, smartphones, tablets, etc., used within factories.

[0191] Software: We use Python and Flask to build the server-side API, and OpenAI's GPT-3 (engine: daVinci) for the artificial intelligence model.

[0192] Specific example

[0193] If a user wants to find out the "initial setup" for the "Robot Arm XYZ789," they enter "Robot Arm XYZ789" and "initial setup" into the input form on the terminal and submit it. The server receives this data and generates a prompt saying, "Please provide the initial setup information for the Robot Arm XYZ789 from the instruction manual," and queries the artificial intelligence model. The artificial intelligence model generates the corresponding initial setup procedure, sends it to the terminal via the server, and the terminal displays it to the user. An example of the prompt text is as follows:

[0194] Prompt message

[0195] "Please provide the initial setup information for the XYZ789 robotic arm from the instruction manual."

[0196] This system enables rapid and accurate detection of equipment malfunctions and provision of maintenance procedures within the factory, leading to more efficient factory operations.

[0197] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0198] Step 1:

[0199] The user enters the model name and keywords using a terminal. In this example, the user enters "Robot Arm XYZ789" and "Initial Setup" and submits the data. The input data is sent to the server in JSON format. Input: Model name and keywords. Output: Data in JSON format.

[0200] Step 2:

[0201] The server parses the received data. The server extracts the model name and keywords from the JSON-formatted data. A Python library is used for data analysis. Input: JSON-formatted data. Output: Model name and keywords.

[0202] Step 3:

[0203] The server generates a prompt to query the artificial intelligence model based on the extracted model name and keywords. An example of a prompt is "Please provide initial setup information for the XYZ789 robot arm from the instruction manual." Input: Model name and keywords. Output: Prompt.

[0204] Step 4:

[0205] The server sends the generated prompt to the artificial intelligence model (GPT-3), which then generates relevant information. The AI ​​model provides appropriate initial setup procedures based on the prompt. Input: Prompt text. Output: Generated initial setup procedures.

[0206] Step 5:

[0207] The server receives the generated information and formats it into the appropriate format (e.g., HTML or JSON). Input: Generated initial setup instructions. Output: Formatted information.

[0208] Step 6:

[0209] The server sends formatted information to the terminal. The terminal parses the received information and displays it to the user. Input: Formatted information. Output: Information displayed to the user.

[0210] Step 7:

[0211] The user reviews the information displayed on the terminal and performs the necessary maintenance or configuration steps. This allows the user to quickly and accurately perform the initial setup of the device. Input: Information displayed on the terminal. Output: Maintenance or configuration steps performed.

[0212] This completes the processing flow.

[0213] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0214] The system of the present invention enables users to quickly obtain necessary information from instruction manuals, and further, by combining it with an emotion engine that recognizes the user's emotions, it achieves the provision of more appropriate information. Specific embodiments of the present invention are described below.

[0215] System Configuration

[0216] 1. Terminal

[0217] The terminal is a user input device, providing a means for the user to input the model name and keywords. The terminal also incorporates an emotion engine, which analyzes the user's facial expressions and voice to recognize emotions.

[0218] 2. Server

[0219] The server receives the device name and keywords sent from the terminal, as well as emotion data sent from the emotion engine. Using this data, it queries the artificial intelligence model to generate appropriate information.

[0220] 3. Artificial Intelligence Models

[0221] The artificial intelligence model is trained using machine learning algorithms to analyze instruction manual data related to model names and generate information corresponding to keywords. It also adjusts the wording of the information based on sentiment data to provide the most appropriate answer to the user.

[0222] Program processing flow

[0223] User input processing

[0224] The user enters the model name (e.g., "washing machine ABC123") and keywords (e.g., "clean the filter") on the device. Simultaneously, the device's emotion engine analyzes the user's facial expressions and voice to acquire emotion data. This emotion data indicates the user's stress level and satisfaction level.

[0225] Sending data

[0226] The device sends the entered model name, keywords, and sentiment data obtained from the sentiment engine to the server. This transmission is performed using HTTP requests or other appropriate communication protocols.

[0227] Server Processing

[0228] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. The analyzed data is stored in variables and provided to the artificial intelligence model.

[0229] Processing of artificial intelligence models

[0230] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts information that matches the keywords. It also adjusts the wording of the information, taking into account emotional data. For example, if the user is feeling stressed, it will make the explanation more concise.

[0231] Information formatting and transmission

[0232] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[0233] Display to the user

[0234] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can review the displayed information and quickly obtain the necessary details.

[0235] Specific example

[0236] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the terminal and submits it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice to obtain emotion data such as "irritated."

[0237] The terminal sends this data to the server. The server analyzes the data and queries an artificial intelligence model. The AI ​​model extracts information related to "remote control settings" from the instruction manual for the XYZ789 air conditioner and generates information while considering the user's emotions. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[0238] The server formats the generated information and sends it to the terminal. The terminal displays the information to the user, allowing the user to quickly check how to configure the remote control.

[0239] The above describes a specific embodiment for implementing the system of the present invention in combination with an emotion engine. This system enables the provision of optimal information according to the user's emotional state, further improving convenience.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into an input form for searching the instruction manual. Simultaneously, the device's camera and microphone capture the user's facial expressions and voice in real time.

[0243] Step 2:

[0244] The emotion engine analyzes captured facial and voice data to estimate the user's emotional state. For example, it determines whether the user is irritated or calm. This emotional data is expressed as a state such as "irritated" or "calm."

[0245] Step 3:

[0246] The user enters the model name and keywords and presses the send button. The device sends the input data and emotion data to the server in an appropriate format such as JSON. For example, data such as {"device": "Washing machine ABC123", "keyword": "Cleaning the filter", "emotion": "Irritated"} is sent.

[0247] Step 4:

[0248] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. This data is stored in variables on the server and used for subsequent processing.

[0249] Step 5:

[0250] The server provides the extracted model name and keywords to the artificial intelligence model and requests information generation. Specifically, it passes the model name "washing machine ABC123" and the keyword "filter cleaning" to the artificial intelligence model.

[0251] Step 6:

[0252] The artificial intelligence model searches the instruction manual database for relevant information based on the provided data. For example, it extracts paragraphs related to "filter cleaning."

[0253] Step 7:

[0254] The artificial intelligence model further considers emotional data and adjusts the wording of the information. For example, if the user is "frustrated," the explanation will be made more concise and use more approachable language. It will also provide step-by-step instructions as needed.

[0255] Step 8:

[0256] The server receives the information generated by the artificial intelligence model and formats it into a user-friendly format (such as HTML or JSON). The formatted information might look like this: "To clean the filter of washing machine ABC123, first remove the filter cover. Next, take out the filter and wash it with water. Finally, put the filter back in place."

[0257] Step 9:

[0258] The server sends formatted information to the terminal as an HTTP response. The data is transmitted using the appropriate communication protocol.

[0259] Step 10:

[0260] The device analyzes the information received from the server and displays it on the user's screen. For example, a web browser uses JavaScript to insert information into the DOM, while a dedicated app binds the information to UI elements.

[0261] Step 11:

[0262] Users can check the information displayed on their device screen and quickly obtain the necessary information. For example, they can check "How to clean the filter of washing machine ABC123" and then actually perform the cleaning.

[0263] Specific example

[0264] When a user searches for "Air Conditioner XYZ789" and "Remote Control Settings," the process proceeds as follows:

[0265] The user enters the model name "Air Conditioner XYZ789" and the keyword "Remote Control Settings," then presses the submit button. The emotion engine analyzes the user's facial expressions and voice to determine that they are "frustrated." The terminal sends this data to the server, which analyzes the data and passes it to the artificial intelligence model. The AI ​​model extracts information about "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates a concise response, taking into account the user's "frustration." The server sends the formatted information to the terminal, which then displays it to the user. The user can quickly find out how to configure the remote control.

[0266] In this way, a system is realized in which terminals, servers, artificial intelligence models, and emotion engines work together to provide users with the most optimal information.

[0267] (Example 2)

[0268] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0269] In modern information retrieval systems, it is difficult for users to quickly and accurately obtain specific information from instruction manuals. Furthermore, conventional systems provide uniform information without considering the user's emotional state, resulting in a poor user experience. General information delivery methods are particularly insufficient for users experiencing stress or anxiety. To solve these problems, it is necessary to recognize the user's emotional state and provide appropriate information based on that understanding.

[0270] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0271] In this invention, the server includes means for analyzing facial expressions and voice simultaneously with user input and acquiring emotional data from the terminal; means for the server to receive the model name, keywords, and emotional data from the terminal; and means for an artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information based on the emotional data. This makes it possible to provide optimal information according to the user's emotional state.

[0272] A "terminal" is a device operated by a user, which provides a means of inputting the model name and keywords as an input device, and has the function of analyzing facial expressions and voice to acquire emotional data.

[0273] A "server" is a device that receives data sent from a terminal, analyzes it, queries an artificial intelligence model, formats the generated information into an appropriate format, and sends it back to the terminal.

[0274] "Model name" is a name used to identify a specific product or device, and is entered by the user into the terminal.

[0275] A "keyword" is a phrase used when searching for specific information in an instruction manual, and is entered by the user into the device.

[0276] "Emotional data" refers to data indicating the emotional state analyzed from the user's expressions and voices, and reflects psychological states such as stress and anxiety.

[0277] "Artificial intelligence model" refers to a model trained using machine learning algorithms, which generates information corresponding to keywords from explanatory data related to the model name and adjusts the information based on emotional data.

[0278] "Explanatory data" refers to data of operation manuals and technical documents related to specific products or devices, which are the objects analyzed by the artificial intelligence model.

[0279] "Adjustment of information" refers to appropriately changing the text and format of the generated information based on the user's emotional data, for example, making the explanation concise.

[0280] "HTTP request" is one of the Internet protocols and is a means for transmitting data.

[0281] "JSON format" is a format for structuring and expressing data, and is the abbreviation of JavaScript Object Notation.

[0282] "HTML format" is a markup language for creating web pages, and is the abbreviation of HyperText Markup Language.

[0283] The system of this invention aims to enable the user to quickly obtain the necessary information from the operation manual. Furthermore, by combining an emotion engine that recognizes the user's emotions, more appropriate information can be provided. Hereinafter, specific embodiments for implementing this invention will be described.

[0284] Configuration of the System

[0285] Terminal

[0286] The terminal is an input device operated by the user and provides means for the user to input the model name and keywords. In addition, the terminal is equipped with an emotion engine and incorporates a function to analyze the user's expression and voice to obtain emotion data. Specifically, the terminal uses a camera and a microphone to collect the user's expression and voice and analyzes the data.

[0287] Server

[0288] The server has the role of receiving the model name, keywords, and emotion data transmitted from the emotion engine sent from the terminal. It analyzes the received data and makes inquiries to the artificial intelligence model. The server performs data transmission and reception using communication protocols such as HTTP requests and WebSocket.

[0289] Artificial Intelligence Model

[0290] The artificial intelligence model is trained using machine learning algorithms and generates information corresponding to the keywords from the explanatory data related to the model name. Furthermore, it adjusts the information generated based on the emotion data and provides the most appropriate answer to the user. For example, when the user is feeling stressed, it makes adjustments such as making the explanation more concise.

[0291] Flow of Program Processing

[0292] Data Acquisition and Transmission

[0293] The user inputs the model name and keywords into the input form of the terminal and presses the "Send" button. For example, the user inputs "Air conditioner XYZ789" and "Remote control settings". At the same time, the built-in camera and microphone of the terminal collect the user's expression and voice and obtain emotion data. The terminal converts this data into JSON format and sends it to the server as an HTTP request.

[0294] Server Processing

[0295] The server parses the received JSON data and extracts the model name, keywords, and sentiment data. This data is stored in variables, and a prompt message is generated for the artificial intelligence model. For example, the prompt message might be, "Please tell me how to configure the remote control for the XYZ789 air conditioner."

[0296] Processing of artificial intelligence models

[0297] The artificial intelligence model extracts appropriate information from relevant explanatory data based on the provided prompt text. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." It also adjusts the text by taking sentiment data into consideration.

[0298] Shape and display

[0299] The server receives the generated information, formats it into a user-friendly format (e.g., HTML or JSON), and sends it to the terminal. The terminal parses the received information and displays it to the user in a browser or dedicated application. This allows the user to quickly obtain the information they need.

[0300] Specific example

[0301] Let's consider a specific example where a user inquires about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the terminal and sends it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice, obtaining emotion data such as "irritated." The terminal sends this data to the server, which then queries the AI ​​model. The AI ​​model extracts information about "Remote Control Settings" from the instruction manual data and generates a concise explanation considering the emotion data. For example, it might say, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this and sends it to the terminal, which then displays the information to the user.

[0302] In this way, the system enables the user to quickly obtain the optimal information according to the emotional state.

[0303] The flow of the specific process in Example 2 will be described using FIG. 13.

[0304] Step 1:

[0305] The user enters the model name and keyword in the input form of the terminal and presses the "Send" button. The input data is, for example, "Air conditioner XYZ789" and "Remote control settings". At the same time, the camera and microphone of the terminal collect the user's expression and voice to obtain emotional data. The emotional data indicates the psychological state of the user, such as "being irritated". These input data are temporarily stored in the terminal.

[0306] Input: Model name, keyword, user's expression and voice

[0307] Output: Temporarily stored model name, keyword, emotional data

[0308] Step 2:

[0309] The terminal converts the input model name, keyword, and emotional data into JSON format and sends it to the server as an HTTP request. For example, the POST method is used. This request contains the following JSON-formatted data:

[0310] json

[0311] {

[0312] "model": "Air conditioner XYZ789",

[0313] "keyword": "Remote control settings",

[0314] "emotion": "Irritated"

[0315] }

[0316] Input: Temporarily saved model name, keyword, sentiment data

[0317] Output: JSON data, HTTP request

[0318] Step 3:

[0319] The server parses the received JSON data, extracts the model name, keywords, and emotion data, and stores them in their respective variables. For example, the model name is stored in "model_name", the keywords in "keyword", and the emotion data in "emotion".

[0320] Python

[0321] model_name = request_data["model"]

[0322] keyword = request_data["keyword"]

[0323] emotion = request_data["emotion"]

[0324] Input: Data in JSON format

[0325] Output: Model name, keyword, and sentiment data stored in variables

[0326] Step 4:

[0327] The server generates a prompt based on the model name and keywords stored in variables and queries the artificial intelligence model. For example, the prompt might be "Please tell me how to set up the remote control for air conditioner XYZ789." This is sent to the artificial intelligence model, and a response is received. The artificial intelligence model uses a machine learning algorithm to generate the answer from the corresponding instruction manual data.

[0328] Input: Model name, keyword, and sentiment data stored in variables.

[0329] Output: Prompt sentences to the AI ​​model, generated answers

[0330] Step 5:

[0331] Based on the responses received from the artificial intelligence model, the server adjusts the information while taking emotional data into consideration. For example, if the user is "frustrated," the explanation will be made more concise. Specifically, it might generate a response such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[0332] Input: Generated responses, sentiment data

[0333] Output: Adjusted information

[0334] Step 6:

[0335] The server formats the adjusted information into HTML or JSON format and sends it to the terminal. For example, the data will be in HTML format as follows:

[0336] html

[0337] How to set up the remote control:

[0338]

[0339] Insert the batteries.

[0340] Press and hold the settings button for 3 seconds.

[0341] Complete the settings for the receiving unit.

[0342]

[0343] Input: Adjusted information

[0344] Output: HTML and JSON formatted data, HTTP response

[0345] Step 7:

[0346] The device parses the received HTML or JSON data and displays it to the user through a browser or dedicated app. The user can then review the displayed information and quickly take the necessary steps.

[0347] Input: HTML or JSON formatted data

[0348] Output: Information displayed in the browser or app

[0349] (Application Example 2)

[0350] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0351] Conventional systems had challenges in quickly obtaining necessary information from instruction manuals and providing appropriate information that took into account the user's emotional state. In particular, in customer service at physical stores, the provision of operational instructions and product information often involved one-sided information provision that disregarded the customer's emotional state, which contributed to reduced customer satisfaction. Therefore, there was a need for information provision that took the user's emotions into consideration.

[0352] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0353] In this invention, the server includes means for the user to input a model name and keywords using a terminal, means for acquiring emotional data from the user's facial expressions and voice using an emotion engine, means for the server to receive the model name, keywords and emotional data from the terminal, means for the server to query an artificial intelligence model using the model name, keywords and emotional data, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information generated based on the emotional data, means for the server to transmit the generated information to the terminal, and means for the terminal to display the transmitted information to the user. This makes it possible to quickly provide optimal information while taking into account the user's emotional state.

[0354] A "terminal" is a device used by the user to input the model name and keywords, and it is equipped with the function of acquiring emotional data from the user's facial expressions and voice using an emotion engine.

[0355] An "emotion engine" is a combination of software and hardware that analyzes a user's facial expressions and voice to acquire emotional data.

[0356] "Emotional data" refers to data that indicates the user's emotional state, obtained from the user's facial expressions and voice.

[0357] A "server" is a device that analyzes the model name, keywords, and sentiment data received from a terminal and queries an artificial intelligence model for this analysis.

[0358] "Model name" refers to the name of the specific device or product from which the user is seeking information from the instruction manual.

[0359] "Keywords" are related terms that users enter to identify information in the instruction manual.

[0360] An "artificial intelligence model" is a model that uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name and to adjust the information based on sentiment data.

[0361] "Explanatory data" refers to data related to instruction manuals and product information, and includes the information that users need.

[0362] "Information generation" refers to the process where an artificial intelligence model creates appropriate information to provide to the user based on the model name and keywords.

[0363] "Information adjustment" refers to optimizing the wording and expression of generated information to match the user's emotional state, based on emotional data.

[0364] System Configuration

[0365] As a specific embodiment of this invention, the system includes the following hardware and software.

[0366] 1. Terminal

[0367] User input device: Equipped with a touch panel or voice input device for the user to input the model name and keywords.

[0368] Emotion Engine: Equipped with a camera for analyzing the user's facial expressions and a microphone for voice analysis.

[0369] Emotion analysis software: A software module for acquiring emotional data from facial expressions and voice.

[0370] 2. Server

[0371] Data receiving module: Receives model name, keywords, and sentiment data transmitted from the terminal.

[0372] Data analysis module: Analyzes model names, keywords, and sentiment data, and provides this information to an artificial intelligence model.

[0373] Artificial intelligence model: This model uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name, and adjusts the information based on sentiment data.

[0374] Data transmission module: Sends the generated information to the terminal in the appropriate format.

[0375] System operation

[0376] Step 1: User Input

[0377] The user enters the model name and keywords using the terminal. For example, if the user wants to know the "temperature setting method" for the "refrigerator GX300," they enter this information on the touch panel. In addition, the emotion engine analyzes the user's facial expressions (e.g., captured by the camera) and voice (e.g., captured by the microphone) to acquire emotion data.

[0378] Step 2: Data transmission

[0379] After the user completes the input, the device sends the model name, keywords, and sentiment data to the server. This transmission uses communication protocols such as HTTP requests.

[0380] Step 3: Data Analysis and Information Generation

[0381] The server analyzes the received data using a data analysis module and queries an artificial intelligence model. The AI ​​model searches a database of descriptions related to the model name and generates information corresponding to the keywords. In doing so, it adjusts the wording of the information, taking sentiment data into consideration. For example, if the user is feeling stressed, the description will be generated to be concise and easy to understand.

[0382] Step 4: Information Submission and Display

[0383] The generated information is sent to the terminal in an appropriate format by the data transmission module. The terminal then displays the received information to the user in a visually easy-to-understand format (e.g., browser display or dedicated application).

[0384] Examples

[0385] As a practical example, consider a scenario where a customer wants to know how to operate a home appliance. For instance, imagine a customer asking about the "temperature setting method" for a "GX300 refrigerator." The customer enters the model name and keywords into the terminal's touchscreen, an emotion engine captures the customer's facial expression, and voice analysis obtains emotion data indicating "frustrated." This data is sent to a server, where an artificial intelligence model generates a specific and concise answer: "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature." The server sends this information to the terminal, which then displays it to the customer.

[0386] Examples of prompts for a generative AI model:

[0387] text

[0388] A user asked about the "temperature setting method" for the "GX300 refrigerator." The user is also frustrated. Therefore, please provide a clear and concise explanation to the user.

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] The user enters the model name and keywords using the terminal. For example, they might enter "refrigerator GX300" and "temperature setting method". The terminal captures this input and prepares the data for the next processing step. Specifically, voice input is converted to text by speech recognition software, and touch panel input is directly acquired as text data.

[0392] input:

[0393] Model name: "Refrigerator GX300"

[0394] Keywords: "Temperature setting method"

[0395] output:

[0396] The model name and keywords are retrieved in text format.

[0397] Step 2:

[0398] The emotion engine analyzes the user's facial expressions and voice to acquire emotion data. The device's camera captures the user's facial expressions, and the microphone records the tone of the user's voice. Emotion recognition software analyzes this data to generate emotion data. For example, the emotion "irritated" might be recognized.

[0399] input:

[0400] User facial expression data (captured by camera)

[0401] User's voice data (recorded by microphone)

[0402] output:

[0403] Emotional data: "Irritated"

[0404] Step 3:

[0405] The device sends the model name, keywords, and sentiment data entered by the user to the server. This transmission is performed using an appropriate communication protocol, such as an HTTP request. The data is packaged in a format such as JSON.

[0406] input:

[0407] Model name: "Refrigerator GX300"

[0408] Keywords: "Temperature setting method"

[0409] Emotional data: "Irritated"

[0410] output:

[0411] Data sent to the server (model name, keywords, sentiment data)

[0412] Step 4:

[0413] The server analyzes the received data and extracts the model name, keywords, and sentiment data. This data is stored in variables and prepared for the next processing step.

[0414] input:

[0415] Data sent from the device (device name, keywords, sentiment data)

[0416] output:

[0417] Extracted data (model name, keywords, sentiment data)

[0418] Step 5:

[0419] The server's artificial intelligence model searches a description database related to the model name and generates information that matches the keywords. Furthermore, it adjusts the wording of this information by taking sentiment data into consideration. For example, it generates a concise explanation such as, "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature."

[0420] input:

[0421] Extracted data (model name, keywords, sentiment data)

[0422] output:

[0423] Adjusted information (concise explanation)

[0424] Step 6:

[0425] The server sends the processed information to the terminal in an appropriate format (e.g., HTML or JSON). This transmission is also carried out using an appropriate communication protocol.

[0426] input:

[0427] Adjusted information

[0428] output:

[0429] Formatted information

[0430] Step 7:

[0431] The terminal visually displays the received information to the user. This is done using a browser or a dedicated application. The displayed information is provided in a format that the user can easily understand.

[0432] input:

[0433] Formatted information

[0434] output:

[0435] Information displayed to the user

[0436] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0437] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0438] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0439] [Second Embodiment]

[0440] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0441] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0442] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0443] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0444] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0446] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0447] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0448] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0449] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0450] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0451] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0452] The system of this invention is designed to allow users to quickly obtain necessary information from instruction manuals. Specifically, the user inputs the model name and keywords using a terminal, sends this information to a server, and an artificial intelligence model generates the relevant information, which is then displayed to the user.

[0453] System Configuration

[0454] 1. Terminal

[0455] The terminal serves as the user's input device. The user uses the terminal to input the model name and keywords, and sends them to the server. The terminal has a web browser and a dedicated application installed, which the user uses to access the system.

[0456] 2. Server

[0457] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[0458] 3. Artificial Intelligence Models

[0459] The artificial intelligence model analyzes data from instruction manuals and generates information related to keywords searched by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[0460] Program processing flow

[0461] User input processing

[0462] The user enters the model name (e.g., "Washing Machine ABC123") and a keyword (e.g., "Filter Cleaning") on the device and clicks the submit button. The device sends the entered data to the server. The data is sent in a format such as JSON.

[0463] Server Processing

[0464] The server analyzes the data received from the terminal and extracts the model name and keywords. Next, the server passes this information to an artificial intelligence model and requests the generation of corresponding information.

[0465] Processing of artificial intelligence models

[0466] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts and generates information that matches the keywords. Specifically, it analyzes the text data of the instruction manuals and selects the most relevant information.

[0467] Information formatting and transmission

[0468] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[0469] Display to the user

[0470] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can then quickly obtain the necessary information from the instruction manual.

[0471] Specific example

[0472] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on their device and submits it. The device sends this data to the server. The server receives and analyzes this data, passing the model name and keywords to an artificial intelligence model. The AI ​​model extracts information related to "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this information and sends it to the device, which then displays it to the user. The user can quickly confirm how to set up the remote control.

[0473] The above describes the configuration for implementing the system of the present invention. This system allows users to quickly find the necessary information from a vast number of instruction manuals, significantly improving convenience.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into the input form for searching the instruction manual. After entering the information, the user presses the submit button to send the data.

[0477] Step 2:

[0478] The terminal sends the model name and keywords entered by the user to the server as an HTTP request. This data is sent in JSON format or as HTTP parameters.

[0479] Step 3:

[0480] The server parses the HTTP request received from the terminal and extracts the model name and keywords. The parsed data is stored in variables.

[0481] Step 4:

[0482] The server uses the extracted model name and keywords to send information generation requests to the artificial intelligence model. Specifically, it sends data in the format {"device": "model name", "keyword": "keyword"} using API calls or internal functions.

[0483] Step 5:

[0484] The artificial intelligence model searches a database of instruction manuals related to the model name based on the received request. It extracts information that matches the keywords and generates the most relevant response.

[0485] Step 6:

[0486] The response generated by the artificial intelligence model is returned to the server. The server receives this response and formats it into a user-friendly format, for example, by converting it to HTML.

[0487] Step 7:

[0488] The server sends the formatted information to the terminal as an HTTP response. The data is sent in various formats, such as JSON or HTML, as needed.

[0489] Step 8:

[0490] The device analyzes the information received from the server and displays it on the user's screen. Specifically, it either inserts the information into the DOM using JavaScript in the browser or displays it using a dedicated application.

[0491] Step 9:

[0492] Users can view the information displayed on their device screen and obtain the necessary information. For example, they can view information such as "How to set up the remote control for the XYZ789 air conditioner..." and then perform the actual operation.

[0493] (Example 1)

[0494] Next, we will describe Example 1. 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."

[0495] Conventional manual search systems made it difficult to quickly find necessary information from a vast amount of data. Furthermore, users had to enter precise model names or keywords, resulting in usability issues. There is a need to provide a system that solves these problems and allows users to easily and quickly access the information they need.

[0496] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0497] In this invention, the server includes means for a user to input a model name and keywords using an information terminal; means for the server to receive the model name and keywords from the information terminal; means for the server to analyze the model name and keywords and query an artificial intelligence system; means for the artificial intelligence system to generate information corresponding to the keywords from technical literature data related to the model name; means for the server to format the generated information and transmit it to the information terminal; and means for the information terminal to display the formatted information to the user. This makes it possible for the user to easily and quickly obtain the necessary information.

[0498] An "information terminal" is a device used by users to input information and communicate with a server, and includes personal computers, smartphones, tablets, and other similar devices.

[0499] "Model name" refers to a name used to identify a specific product or device, such as a product-specific name like "Air Conditioner XYZ789".

[0500] A "keyword" is a term or phrase that a user uses to search for specific information within an instruction manual.

[0501] A "server" is a computing system that analyzes data received from terminals, queries an artificial intelligence system, and provides appropriate information.

[0502] An "artificial intelligence system" is a model that analyzes and generates information using machine learning algorithms, and its role is to provide the necessary data based on user requests.

[0503] "Technical literature data" refers to a database containing information such as instruction manuals and technical manuals for each model.

[0504] A "machine learning algorithm" is an algorithm used by artificial intelligence systems to learn from data and train models.

[0505] "Formatting" refers to the process of transforming generated information into a format that is easy for users to view, and includes conversion to HTML or JSON format.

[0506] The system of the present invention is designed to allow users to quickly obtain necessary information from instruction manuals using an information terminal. The hardware and software necessary to specifically implement this invention, and the data processing methods using them, are described below.

[0507] terminal

[0508] Users enter the model name and keywords using an information terminal. These terminals can include personal computers, smartphones, and tablets. These terminals also have web browsers and dedicated applications installed, which users use to access the system.

[0509] server

[0510] The server is the central device that receives and analyzes data transmitted from terminals. Server-side programs are often written in programming languages ​​such as Python or Java. The server parses the model name and keywords received from the terminals in JSON format and extracts them appropriately.

[0511] Artificial intelligence system

[0512] The server passes the analyzed model names and keywords to the artificial intelligence (AI) system. The AI ​​system, equipped with models trained using machine learning frameworks such as TensorFlow and PyTorch, analyzes the technical literature data. This AI system, trained using machine learning algorithms, can select highly relevant information.

[0513] Information formatting and transmission

[0514] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format. The formatted information is then converted into HTML or JSON format and finally sent from the server to the terminal.

[0515] Display to the user

[0516] The device displays the received information to the user. Specifically, the information is presented in a visually easy-to-understand format through a web browser or a dedicated app. This allows the user to quickly obtain the necessary information from the instruction manual.

[0517] Specific example

[0518] Let's consider a scenario where a user searches for information about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the information terminal and clicks the submit button. The submitted data is sent to the server, which analyzes it. Then, a request based on the model name and keywords is sent to the artificial intelligence system. The artificial intelligence system searches the technical literature data and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats the generated information and sends it back to the terminal. The terminal displays the received information to the user, allowing the user to easily check how to set up the remote control.

[0519] Example of a prompt

[0520] Model name: Air conditioner XYZ789

[0521] Keywords: Remote control settings

[0522] output:

[0523] How to set up the remote control:

[0524] 1. Insert the batteries.

[0525] 2. Press and hold the settings button for 3 seconds.

[0526] 3. Complete the settings for the receiving unit.

[0527] The above describes the configuration for implementing the invention, and this system allows users to quickly obtain the necessary information from the instruction manual. This significantly improves convenience.

[0528] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0529] Step 1:

[0530] User data entry

[0531] The user enters the model name and keywords using the input form on the information terminal. Specifically, they enter "Air Conditioner XYZ789" (model name) and "Remote Control Settings" (keyword) via a browser or dedicated app, and then click the submit button.

[0532] Input: Model name "Air conditioner XYZ789", Keyword "Remote control settings"

[0533] Output: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[0534] Step 2:

[0535] Data reception by the server

[0536] The server receives data in JSON format sent by the terminal. The server then prepares to parse this data.

[0537] Input: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[0538] Output: Data converted to an internal format for data analysis.

[0539] Step 3:

[0540] Data Analysis

[0541] The server parses the received JSON data and extracts the model name and keywords. It uses parsing programs written in Python or Java.

[0542] Specific operation: Extract the "Model Name" and "Keyword" fields from the JSON data.

[0543] Input: Data in JSON format

[0544] Output: Extracted model name "Air Conditioner XYZ789" and keyword "Remote Control Settings"

[0545] Step 4:

[0546] Inquiries to the artificial intelligence system

[0547] The server uses the analyzed model name and keywords to send an information generation request to the artificial intelligence system. The request is sent via a REST API.

[0548] Specific operation: Send an HTTP request from the server to the artificial intelligence system.

[0549] Input: Extracted model name and keyword

[0550] Output: HTTP request "{"Model name": "Air conditioner XYZ789", "Keyword": "Remote control settings"}"

[0551] Step 5:

[0552] Information generation

[0553] The artificial intelligence system uses machine learning algorithms to extract and generate relevant information from technical literature databases. Specifically, it analyzes text data from instruction manuals and selects information that matches keywords.

[0554] Specific operation: Use natural language processing techniques to extract and generate relevant information.

[0555] Input: Model name "Air conditioner XYZ789" and keyword "Remote control settings"

[0556] Output: Generated information: "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[0557] Step 6:

[0558] Formalization of information

[0559] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format, such as HTML or JSON.

[0560] Specific actions: Convert the generated information into HTML format and arrange the layout.

[0561] Input: Generated information

[0562] Output: Formatted information (HTML or JSON)

[0563] Step 7:

[0564] Information transmission

[0565] The formatted information is sent from the server to the terminal. It is sent quickly so that the user can immediately verify the information.

[0566] Specific operation: Sends formatted information as an HTTP response.

[0567] Input: Formatted information

[0568] Output: Sending information to the user terminal

[0569] Step 8:

[0570] Displaying information

[0571] The device displays the received, formatted information to the user. It presents the information in a visually easy-to-understand format using a browser or dedicated app.

[0572] Specific operation: Renders information in a browser or app and displays it on the screen.

[0573] Input: Information received from the server

[0574] Output: Information visually displayed to the user

[0575] The above outlines the specific processing steps of the system. Each step works in conjunction to create a mechanism that allows users to quickly obtain the information they need.

[0576] (Application Example 1)

[0577] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0578] Maintaining and troubleshooting complex equipment and robots used in factories is time-consuming and labor-intensive, as operators must consult numerous instruction manuals and technical documents. Furthermore, a lack of systems to quickly detect equipment malfunctions and provide appropriate maintenance procedures can hinder efficient factory operations.

[0579] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0580] In this invention, the server includes means for a user to input a model name and keywords using a terminal, means for the server to receive the model name and keywords from the terminal, means for the server to query an artificial intelligence model using the model name and keywords, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name, means for the server to transmit the generated information to the terminal, means for the terminal to display the transmitted information to the user, means for a robot operating in the factory to automatically input the model name and keywords when it detects an abnormality in the equipment, and means for the terminal to display maintenance procedures to the robot operator. This enables rapid and accurate detection of equipment abnormalities and provision of maintenance procedures within the factory, making efficient factory operation possible.

[0581] A "user" is a person who uses a system; they are the entity that performs input and operations through the system interface.

[0582] A "terminal" refers to an input device used by a user to access a system, and includes computers, smartphones, tablets, and other similar devices.

[0583] "Model name" refers to the name that represents a specific piece of equipment or device, and is used as product identification information.

[0584] A "keyword" is a word or phrase that a user enters to specify the information they need.

[0585] A "server" refers to a central computing device that receives and processes requests from users and provides the necessary information.

[0586] An "artificial intelligence model" is a data analysis program that is trained using machine learning algorithms and generates responses based on user input.

[0587] "Explanatory data" refers to information provided in instruction manuals and other documents, including how to operate the equipment and maintenance procedures.

[0588] "Generating information" refers to the process by which an artificial intelligence model extracts and constructs relevant information based on the entered model name and keywords.

[0589] "Detecting an anomaly" means discovering a state in which a robot or piece of equipment deviates from its normal operation.

[0590] "Maintenance procedures" refer to information that outlines the specific steps required for servicing or repairing equipment.

[0591] A "robot operator" is a person who operates and monitors robots within a factory.

[0592] This invention is a system for assisting with the maintenance and troubleshooting of robots used in factories. Specifically, the user inputs the model name and keywords using a terminal, a server receives and analyzes this information, generates relevant information using an artificial intelligence model, and finally displays it to the user.

[0593] System Configuration

[0594] 1. Terminal

[0595] The terminal is a device used by the user as an input device, and includes computers, smartphones, and tablets. The user uses it to input the model name (e.g., "Robot Arm ABC123") and keywords (e.g., "Maintenance Procedure") and sends them to the server.

[0596] 2. Server

[0597] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[0598] Specifically, the server passes the analyzed data to an artificial intelligence model, which then extracts and constructs the most relevant explanatory data.

[0599] 3. Artificial Intelligence Models

[0600] The artificial intelligence model analyzes data from the instruction manual and generates information related to keywords entered by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[0601] The artificial intelligence model uses OpenAI's GPT-3 (engine: daVinci) and performs natural language processing.

[0602] 4. Formalizing and transmitting information

[0603] The generated information is formatted by the server into HTML or JSON format and sent to the device. This allows the information to be presented in a visually easy-to-understand format on the device.

[0604] Program processing

[0605] The server receives and analyzes the model name and keywords entered by the user from the terminal. After analysis, it passes the information to an artificial intelligence model to create a prompt for generating appropriate information. Using this prompt, the AI ​​model generates data related to the specified model name and keywords. The generated information is formatted by the server, sent to the terminal, and displayed to the user.

[0606] Hardware and software to be used

[0607] Hardware: Robot bodies, control panels, smartphones, tablets, etc., used within factories.

[0608] Software: We use Python and Flask to build the server-side API, and OpenAI's GPT-3 (engine: daVinci) for the artificial intelligence model.

[0609] Specific example

[0610] If a user wants to find out the "initial setup" for the "Robot Arm XYZ789," they enter "Robot Arm XYZ789" and "initial setup" into the input form on the terminal and submit it. The server receives this data and generates a prompt saying, "Please provide the initial setup information for the Robot Arm XYZ789 from the instruction manual," and queries the artificial intelligence model. The artificial intelligence model generates the corresponding initial setup procedure, sends it to the terminal via the server, and the terminal displays it to the user. An example of the prompt text is as follows:

[0611] Prompt message

[0612] "Please provide the initial setup information for the XYZ789 robotic arm from the instruction manual."

[0613] This system enables rapid and accurate detection of equipment malfunctions and provision of maintenance procedures within the factory, leading to more efficient factory operations.

[0614] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0615] Step 1:

[0616] The user enters the model name and keywords using a terminal. In this example, the user enters "Robot Arm XYZ789" and "Initial Setup" and submits the data. The input data is sent to the server in JSON format. Input: Model name and keywords. Output: Data in JSON format.

[0617] Step 2:

[0618] The server parses the received data. The server extracts the model name and keywords from the JSON-formatted data. A Python library is used for data analysis. Input: JSON-formatted data. Output: Model name and keywords.

[0619] Step 3:

[0620] The server generates a prompt to query the artificial intelligence model based on the extracted model name and keywords. An example of a prompt is "Please provide initial setup information for the XYZ789 robot arm from the instruction manual." Input: Model name and keywords. Output: Prompt.

[0621] Step 4:

[0622] The server sends the generated prompt to the artificial intelligence model (GPT-3), which then generates relevant information. The AI ​​model provides appropriate initial setup procedures based on the prompt. Input: Prompt text. Output: Generated initial setup procedures.

[0623] Step 5:

[0624] The server receives the generated information and formats it into the appropriate format (e.g., HTML or JSON). Input: Generated initial setup instructions. Output: Formatted information.

[0625] Step 6:

[0626] The server sends formatted information to the terminal. The terminal parses the received information and displays it to the user. Input: Formatted information. Output: Information displayed to the user.

[0627] Step 7:

[0628] The user reviews the information displayed on the terminal and performs the necessary maintenance or configuration steps. This allows the user to quickly and accurately perform the initial setup of the device. Input: Information displayed on the terminal. Output: Maintenance or configuration steps performed.

[0629] This completes the processing flow.

[0630] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0631] The system of the present invention enables users to quickly obtain necessary information from instruction manuals, and further, by combining it with an emotion engine that recognizes the user's emotions, it achieves the provision of more appropriate information. Specific embodiments of the present invention are described below.

[0632] System Configuration

[0633] 1. Terminal

[0634] The terminal is a user input device, providing a means for the user to input the model name and keywords. The terminal also incorporates an emotion engine, which analyzes the user's facial expressions and voice to recognize emotions.

[0635] 2. Server

[0636] The server receives the device name and keywords sent from the terminal, as well as emotion data sent from the emotion engine. Using this data, it queries the artificial intelligence model to generate appropriate information.

[0637] 3. Artificial Intelligence Models

[0638] The artificial intelligence model is trained using machine learning algorithms to analyze instruction manual data related to model names and generate information corresponding to keywords. It also adjusts the wording of the information based on sentiment data to provide the most appropriate answer to the user.

[0639] Program processing flow

[0640] User input processing

[0641] The user enters the model name (e.g., "washing machine ABC123") and keywords (e.g., "clean the filter") on the device. Simultaneously, the device's emotion engine analyzes the user's facial expressions and voice to acquire emotion data. This emotion data indicates the user's stress level and satisfaction level.

[0642] Sending data

[0643] The device sends the entered model name, keywords, and sentiment data obtained from the sentiment engine to the server. This transmission is performed using HTTP requests or other appropriate communication protocols.

[0644] Server Processing

[0645] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. The analyzed data is stored in variables and provided to the artificial intelligence model.

[0646] Processing of artificial intelligence models

[0647] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts information that matches the keywords. It also adjusts the wording of the information, taking into account emotional data. For example, if the user is feeling stressed, it will make the explanation more concise.

[0648] Information formatting and transmission

[0649] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[0650] Display to the user

[0651] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can review the displayed information and quickly obtain the necessary details.

[0652] Specific example

[0653] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the terminal and submits it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice to obtain emotion data such as "irritated."

[0654] The terminal sends this data to the server. The server analyzes the data and queries an artificial intelligence model. The AI ​​model extracts information related to "remote control settings" from the instruction manual for the XYZ789 air conditioner and generates information while considering the user's emotions. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[0655] The server formats the generated information and sends it to the terminal. The terminal displays the information to the user, allowing the user to quickly check how to configure the remote control.

[0656] The above describes a specific embodiment for implementing the system of the present invention in combination with an emotion engine. This system enables the provision of optimal information according to the user's emotional state, further improving convenience.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into an input form for searching the instruction manual. Simultaneously, the device's camera and microphone capture the user's facial expressions and voice in real time.

[0660] Step 2:

[0661] The emotion engine analyzes captured facial and voice data to estimate the user's emotional state. For example, it determines whether the user is irritated or calm. This emotional data is expressed as a state such as "irritated" or "calm."

[0662] Step 3:

[0663] The user enters the model name and keywords and presses the send button. The device sends the input data and emotion data to the server in an appropriate format such as JSON. For example, data such as {"device": "Washing machine ABC123", "keyword": "Cleaning the filter", "emotion": "Irritated"} is sent.

[0664] Step 4:

[0665] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. This data is stored in variables on the server and used for subsequent processing.

[0666] Step 5:

[0667] The server provides the extracted model name and keywords to the artificial intelligence model and requests information generation. Specifically, it passes the model name "washing machine ABC123" and the keyword "filter cleaning" to the artificial intelligence model.

[0668] Step 6:

[0669] The artificial intelligence model searches the instruction manual database for relevant information based on the provided data. For example, it extracts paragraphs related to "filter cleaning."

[0670] Step 7:

[0671] The artificial intelligence model further considers emotional data and adjusts the wording of the information. For example, if the user is "frustrated," the explanation will be made more concise and use more approachable language. It will also provide step-by-step instructions as needed.

[0672] Step 8:

[0673] The server receives the information generated by the artificial intelligence model and formats it into a user-friendly format (such as HTML or JSON). The formatted information might look like this: "To clean the filter of washing machine ABC123, first remove the filter cover. Next, take out the filter and wash it with water. Finally, put the filter back in place."

[0674] Step 9:

[0675] The server sends formatted information to the terminal as an HTTP response. The data is transmitted using the appropriate communication protocol.

[0676] Step 10:

[0677] The device analyzes the information received from the server and displays it on the user's screen. For example, a web browser uses JavaScript to insert information into the DOM, while a dedicated app binds the information to UI elements.

[0678] Step 11:

[0679] Users can check the information displayed on their device screen and quickly obtain the necessary information. For example, they can check "How to clean the filter of washing machine ABC123" and then actually perform the cleaning.

[0680] Specific example

[0681] When a user searches for "Air Conditioner XYZ789" and "Remote Control Settings," the process proceeds as follows:

[0682] The user enters the model name "Air Conditioner XYZ789" and the keyword "Remote Control Settings," then presses the submit button. The emotion engine analyzes the user's facial expressions and voice to determine that they are "frustrated." The terminal sends this data to the server, which analyzes the data and passes it to the artificial intelligence model. The AI ​​model extracts information about "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates a concise response, taking into account the user's "frustration." The server sends the formatted information to the terminal, which then displays it to the user. The user can quickly find out how to configure the remote control.

[0683] In this way, a system is realized in which terminals, servers, artificial intelligence models, and emotion engines work together to provide users with the most optimal information.

[0684] (Example 2)

[0685] Next, we will describe Example 2. 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".

[0686] In modern information retrieval systems, it is difficult for users to quickly and accurately obtain specific information from instruction manuals. Furthermore, conventional systems provide uniform information without considering the user's emotional state, resulting in a poor user experience. General information delivery methods are particularly insufficient for users experiencing stress or anxiety. To solve these problems, it is necessary to recognize the user's emotional state and provide appropriate information based on that understanding.

[0687] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0688] In this invention, the server includes means for analyzing facial expressions and voice simultaneously with user input and acquiring emotional data from the terminal; means for the server to receive the model name, keywords, and emotional data from the terminal; and means for an artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information based on the emotional data. This makes it possible to provide optimal information according to the user's emotional state.

[0689] A "terminal" is a device operated by a user, which provides a means of inputting the model name and keywords as an input device, and has the function of analyzing facial expressions and voice to acquire emotional data.

[0690] A "server" is a device that receives data sent from a terminal, analyzes it, queries an artificial intelligence model, formats the generated information into an appropriate format, and sends it back to the terminal.

[0691] "Model name" is a name used to identify a specific product or device, and is entered by the user into the terminal.

[0692] A "keyword" is a phrase used when searching for specific information in an instruction manual, and is entered by the user into the device.

[0693] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from their facial expressions and voice, and reflects psychological states such as stress and anxiety.

[0694] An "artificial intelligence model" is a model trained using machine learning algorithms that generates information corresponding to keywords from descriptive data related to model names and adjusts the information based on sentiment data.

[0695] "Explanatory data" refers to instruction manuals and technical documents related to specific products or equipment, which are the data that artificial intelligence models analyze.

[0696] "Information adjustment" refers to appropriately modifying the wording and format of generated information based on user sentiment data, such as making explanations more concise.

[0697] An "HTTP request" is one of the Internet protocols and a means of sending data.

[0698] "JSON format" is a format for representing data in a structured way, and it is an abbreviation for JavaScript Object Notation.

[0699] "HTML format" is a markup language used to create web pages, and is an abbreviation for HyperText Markup Language.

[0700] The system of this invention aims to enable users to quickly obtain necessary information from instruction manuals. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to provide more appropriate information. The following describes specific embodiments for carrying out this invention.

[0701] System Configuration

[0702] terminal

[0703] The terminal is an input device operated by the user, providing a means for the user to input the model name and keywords. The terminal also incorporates an emotion engine, which analyzes the user's facial expressions and voice to acquire emotional data. Specifically, the terminal uses a camera and microphone to collect the user's facial expressions and voice, and then analyzes that data.

[0704] server

[0705] The server's role is to receive the device name, keywords, and emotion data sent from the terminal, as well as emotion data sent from the emotion engine. It analyzes the received data and queries the artificial intelligence model. The server uses communication protocols such as HTTP requests and WebSockets to send and receive data.

[0706] Artificial intelligence model

[0707] The artificial intelligence model is trained using machine learning algorithms to generate information corresponding to keywords from descriptive data related to model names. Furthermore, it adjusts the generated information based on sentiment data to provide the most appropriate answer to the user. For example, if the user is feeling stressed, it will make the explanation more concise.

[0708] Program processing flow

[0709] Data acquisition and transmission

[0710] The user enters the model name and keywords into the input form on the device and presses the "Submit" button. For example, the user enters "Air conditioner XYZ789" and "Remote control settings". Simultaneously, the device's built-in camera and microphone collect the user's facial expressions and voice, acquiring emotion data. The device converts this data into JSON format and sends it to the server as an HTTP request.

[0711] Server Processing

[0712] The server parses the received JSON data and extracts the model name, keywords, and sentiment data. This data is stored in variables, and a prompt message is generated for the artificial intelligence model. For example, the prompt message might be, "Please tell me how to configure the remote control for the XYZ789 air conditioner."

[0713] Processing of artificial intelligence models

[0714] The artificial intelligence model extracts appropriate information from relevant explanatory data based on the provided prompt text. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." It also adjusts the text by taking sentiment data into consideration.

[0715] Shape and display

[0716] The server receives the generated information, formats it into a user-friendly format (e.g., HTML or JSON), and sends it to the terminal. The terminal parses the received information and displays it to the user in a browser or dedicated application. This allows the user to quickly obtain the information they need.

[0717] Specific example

[0718] Let's consider a specific example where a user inquires about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the terminal and sends it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice, obtaining emotion data such as "irritated." The terminal sends this data to the server, which then queries the AI ​​model. The AI ​​model extracts information about "Remote Control Settings" from the instruction manual data and generates a concise explanation considering the emotion data. For example, it might say, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this and sends it to the terminal, which then displays the information to the user.

[0719] In this way, this system allows users to quickly obtain optimal information tailored to their emotional state.

[0720] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0721] Step 1:

[0722] The user enters the model name and keywords into the terminal's input form and presses the "Submit" button. The entered data might be, for example, "Air Conditioner XYZ789" and "Remote Control Settings." Simultaneously, the terminal's camera and microphone collect the user's facial expressions and voice, acquiring emotional data. This emotional data indicates the user's psychological state, such as "Irritated." This input data is temporarily stored within the terminal.

[0723] Input: Model name, keywords, user's facial expression and voice

[0724] Output: Temporarily saved model name, keyword, sentiment data

[0725] Step 2:

[0726] The terminal converts the entered model name, keywords, and sentiment data into JSON format and sends it to the server as an HTTP request. For example, it uses the POST method. This request contains JSON data such as the following:

[0727] json

[0728] {

[0729] "model": "Air conditioner XYZ789",

[0730] "keyword": "remote control settings",

[0731] "emotion": "irritation"

[0732] }

[0733] Input: Temporarily saved model name, keyword, sentiment data

[0734] Output: JSON data, HTTP request

[0735] Step 3:

[0736] The server parses the received JSON data, extracts the model name, keywords, and emotion data, and stores them in their respective variables. For example, the model name is stored in "model_name", the keywords in "keyword", and the emotion data in "emotion".

[0737] Python

[0738] model_name = request_data["model"]

[0739] keyword = request_data["keyword"]

[0740] emotion = request_data["emotion"]

[0741] Input: Data in JSON format

[0742] Output: Model name, keyword, and sentiment data stored in variables

[0743] Step 4:

[0744] The server generates a prompt based on the model name and keywords stored in variables and queries the artificial intelligence model. For example, the prompt might be "Please tell me how to set up the remote control for air conditioner XYZ789." This is sent to the artificial intelligence model, and a response is received. The artificial intelligence model uses a machine learning algorithm to generate the answer from the corresponding instruction manual data.

[0745] Input: Model name, keyword, and sentiment data stored in variables.

[0746] Output: Prompt sentences to the AI ​​model, generated answers

[0747] Step 5:

[0748] Based on the responses received from the artificial intelligence model, the server adjusts the information while taking emotional data into consideration. For example, if the user is "frustrated," the explanation will be made more concise. Specifically, it might generate a response such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[0749] Input: Generated responses, sentiment data

[0750] Output: Adjusted information

[0751] Step 6:

[0752] The server formats the adjusted information into HTML or JSON format and sends it to the terminal. For example, the data will be in HTML format as follows:

[0753] html

[0754] How to set up the remote control:

[0755]

[0756] Insert the batteries.

[0757] Press and hold the settings button for 3 seconds.

[0758] Complete the settings for the receiving unit.

[0759]

[0760] Input: Adjusted information

[0761] Output: HTML and JSON formatted data, HTTP response

[0762] Step 7:

[0763] The device parses the received HTML or JSON data and displays it to the user through a browser or dedicated app. The user can then review the displayed information and quickly take the necessary steps.

[0764] Input: HTML or JSON formatted data

[0765] Output: Information displayed in the browser or app

[0766] (Application Example 2)

[0767] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0768] Conventional systems had challenges in quickly obtaining necessary information from instruction manuals and providing appropriate information that took into account the user's emotional state. In particular, in customer service at physical stores, the provision of operational instructions and product information often involved one-sided information provision that disregarded the customer's emotional state, which contributed to reduced customer satisfaction. Therefore, there was a need for information provision that took the user's emotions into consideration.

[0769] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0770] In this invention, the server includes means for the user to input a model name and keywords using a terminal, means for acquiring emotional data from the user's facial expressions and voice using an emotion engine, means for the server to receive the model name, keywords and emotional data from the terminal, means for the server to query an artificial intelligence model using the model name, keywords and emotional data, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information generated based on the emotional data, means for the server to transmit the generated information to the terminal, and means for the terminal to display the transmitted information to the user. This makes it possible to quickly provide optimal information while taking into account the user's emotional state.

[0771] A "terminal" is a device used by the user to input the model name and keywords, and it is equipped with the function of acquiring emotional data from the user's facial expressions and voice using an emotion engine.

[0772] An "emotion engine" is a combination of software and hardware that analyzes a user's facial expressions and voice to acquire emotional data.

[0773] "Emotional data" refers to data that indicates the user's emotional state, obtained from the user's facial expressions and voice.

[0774] A "server" is a device that analyzes the model name, keywords, and sentiment data received from a terminal and queries an artificial intelligence model for this analysis.

[0775] "Model name" refers to the name of the specific device or product from which the user is seeking information from the instruction manual.

[0776] "Keywords" are related terms that users enter to identify information in the instruction manual.

[0777] An "artificial intelligence model" is a model that uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name and to adjust the information based on sentiment data.

[0778] "Explanatory data" refers to data related to instruction manuals and product information, and includes the information that users need.

[0779] "Information generation" refers to the process where an artificial intelligence model creates appropriate information to provide to the user based on the model name and keywords.

[0780] "Information adjustment" refers to optimizing the wording and expression of generated information to match the user's emotional state, based on emotional data.

[0781] System Configuration

[0782] As a specific embodiment of this invention, the system includes the following hardware and software.

[0783] 1. Terminal

[0784] User input device: Equipped with a touch panel or voice input device for the user to input the model name and keywords.

[0785] Emotion Engine: Equipped with a camera for analyzing the user's facial expressions and a microphone for voice analysis.

[0786] Emotion analysis software: A software module for acquiring emotional data from facial expressions and voice.

[0787] 2. Server

[0788] Data receiving module: Receives model name, keywords, and sentiment data transmitted from the terminal.

[0789] Data analysis module: Analyzes model names, keywords, and sentiment data, and provides this information to an artificial intelligence model.

[0790] Artificial intelligence model: This model uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name, and adjusts the information based on sentiment data.

[0791] Data transmission module: Sends the generated information to the terminal in the appropriate format.

[0792] System operation

[0793] Step 1: User Input

[0794] The user enters the model name and keywords using the terminal. For example, if the user wants to know the "temperature setting method" for the "refrigerator GX300," they enter this information on the touch panel. In addition, the emotion engine analyzes the user's facial expressions (e.g., captured by the camera) and voice (e.g., captured by the microphone) to acquire emotion data.

[0795] Step 2: Data transmission

[0796] After the user completes the input, the device sends the model name, keywords, and sentiment data to the server. This transmission uses communication protocols such as HTTP requests.

[0797] Step 3: Data Analysis and Information Generation

[0798] The server analyzes the received data using a data analysis module and queries an artificial intelligence model. The AI ​​model searches a database of descriptions related to the model name and generates information corresponding to the keywords. In doing so, it adjusts the wording of the information, taking sentiment data into consideration. For example, if the user is feeling stressed, the description will be generated to be concise and easy to understand.

[0799] Step 4: Information Submission and Display

[0800] The generated information is sent to the terminal in an appropriate format by the data transmission module. The terminal then displays the received information to the user in a visually easy-to-understand format (e.g., browser display or dedicated application).

[0801] Examples

[0802] As a practical example, consider a scenario where a customer wants to know how to operate a home appliance. For instance, imagine a customer asking about the "temperature setting method" for a "GX300 refrigerator." The customer enters the model name and keywords into the terminal's touchscreen, an emotion engine captures the customer's facial expression, and voice analysis obtains emotion data indicating "frustrated." This data is sent to a server, where an artificial intelligence model generates a specific and concise answer: "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature." The server sends this information to the terminal, which then displays it to the customer.

[0803] Examples of prompts for a generative AI model:

[0804] text

[0805] A user asked about the "temperature setting method" for the "GX300 refrigerator." The user is also frustrated. Therefore, please provide a clear and concise explanation to the user.

[0806] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0807] Step 1:

[0808] The user enters the model name and keywords using the terminal. For example, they might enter "refrigerator GX300" and "temperature setting method". The terminal captures this input and prepares the data for the next processing step. Specifically, voice input is converted to text by speech recognition software, and touch panel input is directly acquired as text data.

[0809] input:

[0810] Model name: "Refrigerator GX300"

[0811] Keywords: "Temperature setting method"

[0812] output:

[0813] The model name and keywords are retrieved in text format.

[0814] Step 2:

[0815] The emotion engine analyzes the user's facial expressions and voice to acquire emotion data. The device's camera captures the user's facial expressions, and the microphone records the tone of the user's voice. Emotion recognition software analyzes this data to generate emotion data. For example, the emotion "irritated" might be recognized.

[0816] input:

[0817] User facial expression data (captured by camera)

[0818] User's voice data (recorded by microphone)

[0819] output:

[0820] Emotional data: "Irritated"

[0821] Step 3:

[0822] The device sends the model name, keywords, and sentiment data entered by the user to the server. This transmission is performed using an appropriate communication protocol, such as an HTTP request. The data is packaged in a format such as JSON.

[0823] input:

[0824] Model name: "Refrigerator GX300"

[0825] Keywords: "Temperature setting method"

[0826] Emotional data: "Irritated"

[0827] output:

[0828] Data sent to the server (model name, keywords, sentiment data)

[0829] Step 4:

[0830] The server analyzes the received data and extracts the model name, keywords, and sentiment data. This data is stored in variables and prepared for the next processing step.

[0831] input:

[0832] Data sent from the device (device name, keywords, sentiment data)

[0833] output:

[0834] Extracted data (model name, keywords, sentiment data)

[0835] Step 5:

[0836] The server's artificial intelligence model searches a description database related to the model name and generates information that matches the keywords. Furthermore, it adjusts the wording of this information by taking sentiment data into consideration. For example, it generates a concise explanation such as, "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature."

[0837] input:

[0838] Extracted data (model name, keywords, sentiment data)

[0839] output:

[0840] Adjusted information (concise explanation)

[0841] Step 6:

[0842] The server sends the processed information to the terminal in an appropriate format (e.g., HTML or JSON). This transmission is also carried out using an appropriate communication protocol.

[0843] input:

[0844] Adjusted information

[0845] output:

[0846] Formatted information

[0847] Step 7:

[0848] The terminal visually displays the received information to the user. This is done using a browser or a dedicated application. The displayed information is provided in a format that the user can easily understand.

[0849] input:

[0850] Formatted information

[0851] output:

[0852] Information displayed to the user

[0853] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0854] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0855] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0856] [Third Embodiment]

[0857] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0858] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0859] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0860] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0861] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0862] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0863] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0864] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0865] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0866] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0867] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0868] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0869] The system of this invention is designed to allow users to quickly obtain necessary information from instruction manuals. Specifically, the user inputs the model name and keywords using a terminal, sends this information to a server, and an artificial intelligence model generates the relevant information, which is then displayed to the user.

[0870] System Configuration

[0871] 1. Terminal

[0872] The terminal serves as the user's input device. The user uses the terminal to input the model name and keywords, and sends them to the server. The terminal has a web browser and a dedicated application installed, which the user uses to access the system.

[0873] 2. Server

[0874] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[0875] 3. Artificial Intelligence Models

[0876] The artificial intelligence model analyzes data from instruction manuals and generates information related to keywords searched by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[0877] Program processing flow

[0878] User input processing

[0879] The user enters the model name (e.g., "Washing Machine ABC123") and a keyword (e.g., "Filter Cleaning") on the device and clicks the submit button. The device sends the entered data to the server. The data is sent in a format such as JSON.

[0880] Server Processing

[0881] The server analyzes the data received from the terminal and extracts the model name and keywords. Next, the server passes this information to an artificial intelligence model and requests the generation of corresponding information.

[0882] Processing of artificial intelligence models

[0883] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts and generates information that matches the keywords. Specifically, it analyzes the text data of the instruction manuals and selects the most relevant information.

[0884] Information formatting and transmission

[0885] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[0886] Display to the user

[0887] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can then quickly obtain the necessary information from the instruction manual.

[0888] Specific example

[0889] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on their device and submits it. The device sends this data to the server. The server receives and analyzes this data, passing the model name and keywords to an artificial intelligence model. The AI ​​model extracts information related to "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this information and sends it to the device, which then displays it to the user. The user can quickly confirm how to set up the remote control.

[0890] The above describes the configuration for implementing the system of the present invention. This system allows users to quickly find the necessary information from a vast number of instruction manuals, significantly improving convenience.

[0891] The following describes the processing flow.

[0892] Step 1:

[0893] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into the input form for searching the instruction manual. After entering the information, the user presses the submit button to send the data.

[0894] Step 2:

[0895] The terminal sends the model name and keywords entered by the user to the server as an HTTP request. This data is sent in JSON format or as HTTP parameters.

[0896] Step 3:

[0897] The server parses the HTTP request received from the terminal and extracts the model name and keywords. The parsed data is stored in variables.

[0898] Step 4:

[0899] The server uses the extracted model name and keywords to send information generation requests to the artificial intelligence model. Specifically, it sends data in the format {"device": "model name", "keyword": "keyword"} using API calls or internal functions.

[0900] Step 5:

[0901] The artificial intelligence model searches a database of instruction manuals related to the model name based on the received request. It extracts information that matches the keywords and generates the most relevant response.

[0902] Step 6:

[0903] The response generated by the artificial intelligence model is returned to the server. The server receives this response and formats it into a user-friendly format, for example, by converting it to HTML.

[0904] Step 7:

[0905] The server sends the formatted information to the terminal as an HTTP response. The data is sent in various formats, such as JSON or HTML, as needed.

[0906] Step 8:

[0907] The device analyzes the information received from the server and displays it on the user's screen. Specifically, it either inserts the information into the DOM using JavaScript in the browser or displays it using a dedicated application.

[0908] Step 9:

[0909] Users can view the information displayed on their device screen and obtain the necessary information. For example, they can view information such as "How to set up the remote control for the XYZ789 air conditioner..." and then perform the actual operation.

[0910] (Example 1)

[0911] Next, we will describe Example 1. 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."

[0912] Conventional manual search systems made it difficult to quickly find necessary information from a vast amount of data. Furthermore, users had to enter precise model names or keywords, resulting in usability issues. There is a need to provide a system that solves these problems and allows users to easily and quickly access the information they need.

[0913] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0914] In this invention, the server includes means for a user to input a model name and keywords using an information terminal; means for the server to receive the model name and keywords from the information terminal; means for the server to analyze the model name and keywords and query an artificial intelligence system; means for the artificial intelligence system to generate information corresponding to the keywords from technical literature data related to the model name; means for the server to format the generated information and transmit it to the information terminal; and means for the information terminal to display the formatted information to the user. This makes it possible for the user to easily and quickly obtain the necessary information.

[0915] An "information terminal" is a device used by users to input information and communicate with a server, and includes personal computers, smartphones, tablets, and other similar devices.

[0916] "Model name" refers to a name used to identify a specific product or device, such as a product-specific name like "Air Conditioner XYZ789".

[0917] A "keyword" is a term or phrase that a user uses to search for specific information within an instruction manual.

[0918] A "server" is a computing system that analyzes data received from terminals, queries an artificial intelligence system, and provides appropriate information.

[0919] An "artificial intelligence system" is a model that analyzes and generates information using machine learning algorithms, and its role is to provide the necessary data based on user requests.

[0920] "Technical literature data" refers to a database containing information such as instruction manuals and technical manuals for each model.

[0921] A "machine learning algorithm" is an algorithm used by artificial intelligence systems to learn from data and train models.

[0922] "Formatting" refers to the process of transforming generated information into a format that is easy for users to view, and includes conversion to HTML or JSON format.

[0923] The system of the present invention is designed to allow users to quickly obtain necessary information from instruction manuals using an information terminal. The hardware and software necessary to specifically implement this invention, and the data processing methods using them, are described below.

[0924] terminal

[0925] Users enter the model name and keywords using an information terminal. These terminals can include personal computers, smartphones, and tablets. These terminals also have web browsers and dedicated applications installed, which users use to access the system.

[0926] server

[0927] The server is the central device that receives and analyzes data transmitted from terminals. Server-side programs are often written in programming languages ​​such as Python or Java. The server parses the model name and keywords received from the terminals in JSON format and extracts them appropriately.

[0928] Artificial intelligence system

[0929] The server passes the analyzed model names and keywords to the artificial intelligence (AI) system. The AI ​​system, equipped with models trained using machine learning frameworks such as TensorFlow and PyTorch, analyzes the technical literature data. This AI system, trained using machine learning algorithms, can select highly relevant information.

[0930] Information formatting and transmission

[0931] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format. The formatted information is then converted into HTML or JSON format and finally sent from the server to the terminal.

[0932] Display to the user

[0933] The device displays the received information to the user. Specifically, the information is presented in a visually easy-to-understand format through a web browser or a dedicated app. This allows the user to quickly obtain the necessary information from the instruction manual.

[0934] Specific example

[0935] Let's consider a scenario where a user searches for information about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the information terminal and clicks the submit button. The submitted data is sent to the server, which analyzes it. Then, a request based on the model name and keywords is sent to the artificial intelligence system. The artificial intelligence system searches the technical literature data and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats the generated information and sends it back to the terminal. The terminal displays the received information to the user, allowing the user to easily check how to set up the remote control.

[0936] Example of a prompt

[0937] Model name: Air conditioner XYZ789

[0938] Keywords: Remote control settings

[0939] output:

[0940] How to set up the remote control:

[0941] 1. Insert the batteries.

[0942] 2. Press and hold the settings button for 3 seconds.

[0943] 3. Complete the settings for the receiving unit.

[0944] The above describes the configuration for implementing the invention, and this system allows users to quickly obtain the necessary information from the instruction manual. This significantly improves convenience.

[0945] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0946] Step 1:

[0947] User data entry

[0948] The user enters the model name and keywords using the input form on the information terminal. Specifically, they enter "Air Conditioner XYZ789" (model name) and "Remote Control Settings" (keyword) via a browser or dedicated app, and then click the submit button.

[0949] Input: Model name "Air conditioner XYZ789", Keyword "Remote control settings"

[0950] Output: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[0951] Step 2:

[0952] Data reception by the server

[0953] The server receives data in JSON format sent by the terminal. The server then prepares to parse this data.

[0954] Input: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[0955] Output: Data converted to an internal format for data analysis.

[0956] Step 3:

[0957] Data Analysis

[0958] The server parses the received JSON data and extracts the model name and keywords. It uses parsing programs written in Python or Java.

[0959] Specific operation: Extract the "Model Name" and "Keyword" fields from the JSON data.

[0960] Input: Data in JSON format

[0961] Output: Extracted model name "Air Conditioner XYZ789" and keyword "Remote Control Settings"

[0962] Step 4:

[0963] Inquiries to the artificial intelligence system

[0964] The server uses the analyzed model name and keywords to send an information generation request to the artificial intelligence system. The request is sent via a REST API.

[0965] Specific operation: Send an HTTP request from the server to the artificial intelligence system.

[0966] Input: Extracted model name and keyword

[0967] Output: HTTP request "{"Model name": "Air conditioner XYZ789", "Keyword": "Remote control settings"}"

[0968] Step 5:

[0969] Information generation

[0970] The artificial intelligence system uses machine learning algorithms to extract and generate relevant information from technical literature databases. Specifically, it analyzes text data from instruction manuals and selects information that matches keywords.

[0971] Specific operation: Use natural language processing techniques to extract and generate relevant information.

[0972] Input: Model name "Air conditioner XYZ789" and keyword "Remote control settings"

[0973] Output: Generated information: "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[0974] Step 6:

[0975] Formalization of information

[0976] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format, such as HTML or JSON.

[0977] Specific actions: Convert the generated information into HTML format and arrange the layout.

[0978] Input: Generated information

[0979] Output: Formatted information (HTML or JSON)

[0980] Step 7:

[0981] Information transmission

[0982] The formatted information is sent from the server to the terminal. It is sent quickly so that the user can immediately verify the information.

[0983] Specific operation: Sends formatted information as an HTTP response.

[0984] Input: Formatted information

[0985] Output: Sending information to the user terminal

[0986] Step 8:

[0987] Displaying information

[0988] The device displays the received, formatted information to the user. It presents the information in a visually easy-to-understand format using a browser or dedicated app.

[0989] Specific operation: Renders information in a browser or app and displays it on the screen.

[0990] Input: Information received from the server

[0991] Output: Information visually displayed to the user

[0992] The above outlines the specific processing steps of the system. Each step works in conjunction to create a mechanism that allows users to quickly obtain the information they need.

[0993] (Application Example 1)

[0994] Next, we will explain Application Example 1. In the following explanation, 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."

[0995] Maintaining and troubleshooting complex equipment and robots used in factories is time-consuming and labor-intensive, as operators must consult numerous instruction manuals and technical documents. Furthermore, a lack of systems to quickly detect equipment malfunctions and provide appropriate maintenance procedures can hinder efficient factory operations.

[0996] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0997] In this invention, the server includes means for a user to input a model name and keywords using a terminal, means for the server to receive the model name and keywords from the terminal, means for the server to query an artificial intelligence model using the model name and keywords, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name, means for the server to transmit the generated information to the terminal, means for the terminal to display the transmitted information to the user, means for a robot operating in the factory to automatically input the model name and keywords when it detects an abnormality in the equipment, and means for the terminal to display maintenance procedures to the robot operator. This enables rapid and accurate detection of equipment abnormalities and provision of maintenance procedures within the factory, making efficient factory operation possible.

[0998] A "user" is a person who uses a system; they are the entity that performs input and operations through the system interface.

[0999] A "terminal" refers to an input device used by a user to access a system, and includes computers, smartphones, tablets, and other similar devices.

[1000] "Model name" refers to the name that represents a specific piece of equipment or device, and is used as product identification information.

[1001] A "keyword" is a word or phrase that a user enters to specify the information they need.

[1002] A "server" refers to a central computing device that receives and processes requests from users and provides the necessary information.

[1003] An "artificial intelligence model" is a data analysis program that is trained using machine learning algorithms and generates responses based on user input.

[1004] "Explanatory data" refers to information provided in instruction manuals and other documents, including how to operate the equipment and maintenance procedures.

[1005] "Generating information" refers to the process by which an artificial intelligence model extracts and constructs relevant information based on the entered model name and keywords.

[1006] "Detecting an anomaly" means discovering a state in which a robot or piece of equipment deviates from its normal operation.

[1007] "Maintenance procedures" refer to information that outlines the specific steps required for servicing or repairing equipment.

[1008] A "robot operator" is a person who operates and monitors robots within a factory.

[1009] This invention is a system for assisting with the maintenance and troubleshooting of robots used in factories. Specifically, the user inputs the model name and keywords using a terminal, a server receives and analyzes this information, generates relevant information using an artificial intelligence model, and finally displays it to the user.

[1010] System Configuration

[1011] 1. Terminal

[1012] The terminal is a device used by the user as an input device, and includes computers, smartphones, and tablets. The user uses it to input the model name (e.g., "Robot Arm ABC123") and keywords (e.g., "Maintenance Procedure") and sends them to the server.

[1013] 2. Server

[1014] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[1015] Specifically, the server passes the analyzed data to an artificial intelligence model, which then extracts and constructs the most relevant explanatory data.

[1016] 3. Artificial Intelligence Models

[1017] The artificial intelligence model analyzes data from the instruction manual and generates information related to keywords entered by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[1018] The artificial intelligence model uses OpenAI's GPT-3 (engine: daVinci) and performs natural language processing.

[1019] 4. Formalizing and transmitting information

[1020] The generated information is formatted by the server into HTML or JSON format and sent to the device. This allows the information to be presented in a visually easy-to-understand format on the device.

[1021] Program processing

[1022] The server receives and analyzes the model name and keywords entered by the user from the terminal. After analysis, it passes the information to an artificial intelligence model to create a prompt for generating appropriate information. Using this prompt, the AI ​​model generates data related to the specified model name and keywords. The generated information is formatted by the server, sent to the terminal, and displayed to the user.

[1023] Hardware and software to be used

[1024] Hardware: Robot bodies, control panels, smartphones, tablets, etc., used within factories.

[1025] Software: We use Python and Flask to build the server-side API, and OpenAI's GPT-3 (engine: daVinci) for the artificial intelligence model.

[1026] Specific example

[1027] If a user wants to find out the "initial setup" for the "Robot Arm XYZ789," they enter "Robot Arm XYZ789" and "initial setup" into the input form on the terminal and submit it. The server receives this data and generates a prompt saying, "Please provide the initial setup information for the Robot Arm XYZ789 from the instruction manual," and queries the artificial intelligence model. The artificial intelligence model generates the corresponding initial setup procedure, sends it to the terminal via the server, and the terminal displays it to the user. An example of the prompt text is as follows:

[1028] Prompt message

[1029] "Please provide the initial setup information for the XYZ789 robotic arm from the instruction manual."

[1030] This system enables rapid and accurate detection of equipment malfunctions and provision of maintenance procedures within the factory, leading to more efficient factory operations.

[1031] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1032] Step 1:

[1033] The user enters the model name and keywords using a terminal. In this example, the user enters "Robot Arm XYZ789" and "Initial Setup" and submits the data. The input data is sent to the server in JSON format. Input: Model name and keywords. Output: Data in JSON format.

[1034] Step 2:

[1035] The server parses the received data. The server extracts the model name and keywords from the JSON-formatted data. A Python library is used for data analysis. Input: JSON-formatted data. Output: Model name and keywords.

[1036] Step 3:

[1037] The server generates a prompt to query the artificial intelligence model based on the extracted model name and keywords. An example of a prompt is "Please provide initial setup information for the XYZ789 robot arm from the instruction manual." Input: Model name and keywords. Output: Prompt.

[1038] Step 4:

[1039] The server sends the generated prompt to the artificial intelligence model (GPT-3), which then generates relevant information. The AI ​​model provides appropriate initial setup procedures based on the prompt. Input: Prompt text. Output: Generated initial setup procedures.

[1040] Step 5:

[1041] The server receives the generated information and formats it into the appropriate format (e.g., HTML or JSON). Input: Generated initial setup instructions. Output: Formatted information.

[1042] Step 6:

[1043] The server sends formatted information to the terminal. The terminal parses the received information and displays it to the user. Input: Formatted information. Output: Information displayed to the user.

[1044] Step 7:

[1045] The user reviews the information displayed on the terminal and performs the necessary maintenance or configuration steps. This allows the user to quickly and accurately perform the initial setup of the device. Input: Information displayed on the terminal. Output: Maintenance or configuration steps performed.

[1046] This completes the processing flow.

[1047] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1048] The system of the present invention enables users to quickly obtain necessary information from instruction manuals, and further, by combining it with an emotion engine that recognizes the user's emotions, it achieves the provision of more appropriate information. Specific embodiments of the present invention are described below.

[1049] System Configuration

[1050] 1. Terminal

[1051] The terminal is a user input device, providing a means for the user to input the model name and keywords. The terminal also incorporates an emotion engine, which analyzes the user's facial expressions and voice to recognize emotions.

[1052] 2. Server

[1053] The server receives the device name and keywords sent from the terminal, as well as emotion data sent from the emotion engine. Using this data, it queries the artificial intelligence model to generate appropriate information.

[1054] 3. Artificial Intelligence Models

[1055] The artificial intelligence model is trained using machine learning algorithms to analyze instruction manual data related to model names and generate information corresponding to keywords. It also adjusts the wording of the information based on sentiment data to provide the most appropriate answer to the user.

[1056] Program processing flow

[1057] User input processing

[1058] The user enters the model name (e.g., "washing machine ABC123") and keywords (e.g., "clean the filter") on the device. Simultaneously, the device's emotion engine analyzes the user's facial expressions and voice to acquire emotion data. This emotion data indicates the user's stress level and satisfaction level.

[1059] Sending data

[1060] The device sends the entered model name, keywords, and sentiment data obtained from the sentiment engine to the server. This transmission is performed using HTTP requests or other appropriate communication protocols.

[1061] Server Processing

[1062] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. The analyzed data is stored in variables and provided to the artificial intelligence model.

[1063] Processing of artificial intelligence models

[1064] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts information that matches the keywords. It also adjusts the wording of the information, taking into account emotional data. For example, if the user is feeling stressed, it will make the explanation more concise.

[1065] Information formatting and transmission

[1066] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[1067] Display to the user

[1068] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can review the displayed information and quickly obtain the necessary details.

[1069] Specific example

[1070] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the terminal and submits it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice to obtain emotion data such as "irritated."

[1071] The terminal sends this data to the server. The server analyzes the data and queries an artificial intelligence model. The AI ​​model extracts information related to "remote control settings" from the instruction manual for the XYZ789 air conditioner and generates information while considering the user's emotions. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[1072] The server formats the generated information and sends it to the terminal. The terminal displays the information to the user, allowing the user to quickly check how to configure the remote control.

[1073] The above describes a specific embodiment for implementing the system of the present invention in combination with an emotion engine. This system enables the provision of optimal information according to the user's emotional state, further improving convenience.

[1074] The following describes the processing flow.

[1075] Step 1:

[1076] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into an input form for searching the instruction manual. Simultaneously, the device's camera and microphone capture the user's facial expressions and voice in real time.

[1077] Step 2:

[1078] The emotion engine analyzes captured facial and voice data to estimate the user's emotional state. For example, it determines whether the user is irritated or calm. This emotional data is expressed as a state such as "irritated" or "calm."

[1079] Step 3:

[1080] The user enters the model name and keywords and presses the send button. The device sends the input data and emotion data to the server in an appropriate format such as JSON. For example, data such as {"device": "Washing machine ABC123", "keyword": "Cleaning the filter", "emotion": "Irritated"} is sent.

[1081] Step 4:

[1082] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. This data is stored in variables on the server and used for subsequent processing.

[1083] Step 5:

[1084] The server provides the extracted model name and keywords to the artificial intelligence model and requests information generation. Specifically, it passes the model name "washing machine ABC123" and the keyword "filter cleaning" to the artificial intelligence model.

[1085] Step 6:

[1086] The artificial intelligence model searches the instruction manual database for relevant information based on the provided data. For example, it extracts paragraphs related to "filter cleaning."

[1087] Step 7:

[1088] The artificial intelligence model further considers emotional data and adjusts the wording of the information. For example, if the user is "frustrated," the explanation will be made more concise and use more approachable language. It will also provide step-by-step instructions as needed.

[1089] Step 8:

[1090] The server receives the information generated by the artificial intelligence model and formats it into a user-friendly format (such as HTML or JSON). The formatted information might look like this: "To clean the filter of washing machine ABC123, first remove the filter cover. Next, take out the filter and wash it with water. Finally, put the filter back in place."

[1091] Step 9:

[1092] The server sends formatted information to the terminal as an HTTP response. The data is transmitted using the appropriate communication protocol.

[1093] Step 10:

[1094] The device analyzes the information received from the server and displays it on the user's screen. For example, a web browser uses JavaScript to insert information into the DOM, while a dedicated app binds the information to UI elements.

[1095] Step 11:

[1096] Users can check the information displayed on their device screen and quickly obtain the necessary information. For example, they can check "How to clean the filter of washing machine ABC123" and then actually perform the cleaning.

[1097] Specific example

[1098] When a user searches for "Air Conditioner XYZ789" and "Remote Control Settings," the process proceeds as follows:

[1099] The user enters the model name "Air Conditioner XYZ789" and the keyword "Remote Control Settings," then presses the submit button. The emotion engine analyzes the user's facial expressions and voice to determine that they are "frustrated." The terminal sends this data to the server, which analyzes the data and passes it to the artificial intelligence model. The AI ​​model extracts information about "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates a concise response, taking into account the user's "frustration." The server sends the formatted information to the terminal, which then displays it to the user. The user can quickly find out how to configure the remote control.

[1100] In this way, a system is realized in which terminals, servers, artificial intelligence models, and emotion engines work together to provide users with the most optimal information.

[1101] (Example 2)

[1102] Next, we will describe Example 2. 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."

[1103] In modern information retrieval systems, it is difficult for users to quickly and accurately obtain specific information from instruction manuals. Furthermore, conventional systems provide uniform information without considering the user's emotional state, resulting in a poor user experience. General information delivery methods are particularly insufficient for users experiencing stress or anxiety. To solve these problems, it is necessary to recognize the user's emotional state and provide appropriate information based on that understanding.

[1104] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1105] In this invention, the server includes means for analyzing facial expressions and voice simultaneously with user input and acquiring emotional data from the terminal; means for the server to receive the model name, keywords, and emotional data from the terminal; and means for an artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information based on the emotional data. This makes it possible to provide optimal information according to the user's emotional state.

[1106] A "terminal" is a device operated by a user, which provides a means of inputting the model name and keywords as an input device, and has the function of analyzing facial expressions and voice to acquire emotional data.

[1107] A "server" is a device that receives data sent from a terminal, analyzes it, queries an artificial intelligence model, formats the generated information into an appropriate format, and sends it back to the terminal.

[1108] "Model name" is a name used to identify a specific product or device, and is entered by the user into the terminal.

[1109] A "keyword" is a phrase used when searching for specific information in an instruction manual, and is entered by the user into the device.

[1110] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from their facial expressions and voice, and reflects psychological states such as stress and anxiety.

[1111] An "artificial intelligence model" is a model trained using machine learning algorithms that generates information corresponding to keywords from descriptive data related to model names and adjusts the information based on sentiment data.

[1112] "Explanatory data" refers to instruction manuals and technical documents related to specific products or equipment, which are the data that artificial intelligence models analyze.

[1113] "Information adjustment" refers to appropriately modifying the wording and format of generated information based on user sentiment data, such as making explanations more concise.

[1114] An "HTTP request" is one of the Internet protocols and a means of sending data.

[1115] "JSON format" is a format for representing data in a structured way, and it is an abbreviation for JavaScript Object Notation.

[1116] "HTML format" is a markup language used to create web pages, and is an abbreviation for HyperText Markup Language.

[1117] The system of this invention aims to enable users to quickly obtain necessary information from instruction manuals. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to provide more appropriate information. The following describes specific embodiments for carrying out this invention.

[1118] System Configuration

[1119] terminal

[1120] The terminal is an input device operated by the user, providing a means for the user to input the model name and keywords. The terminal also incorporates an emotion engine, which analyzes the user's facial expressions and voice to acquire emotional data. Specifically, the terminal uses a camera and microphone to collect the user's facial expressions and voice, and then analyzes that data.

[1121] server

[1122] The server's role is to receive the device name, keywords, and emotion data sent from the terminal, as well as emotion data sent from the emotion engine. It analyzes the received data and queries the artificial intelligence model. The server uses communication protocols such as HTTP requests and WebSockets to send and receive data.

[1123] Artificial intelligence model

[1124] The artificial intelligence model is trained using machine learning algorithms to generate information corresponding to keywords from descriptive data related to model names. Furthermore, it adjusts the generated information based on sentiment data to provide the most appropriate answer to the user. For example, if the user is feeling stressed, it will make the explanation more concise.

[1125] Program processing flow

[1126] Data acquisition and transmission

[1127] The user enters the model name and keywords into the input form on the device and presses the "Submit" button. For example, the user enters "Air conditioner XYZ789" and "Remote control settings". Simultaneously, the device's built-in camera and microphone collect the user's facial expressions and voice, acquiring emotion data. The device converts this data into JSON format and sends it to the server as an HTTP request.

[1128] Server Processing

[1129] The server parses the received JSON data and extracts the model name, keywords, and sentiment data. This data is stored in variables, and a prompt message is generated for the artificial intelligence model. For example, the prompt message might be, "Please tell me how to configure the remote control for the XYZ789 air conditioner."

[1130] Processing of artificial intelligence models

[1131] The artificial intelligence model extracts appropriate information from relevant explanatory data based on the provided prompt text. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." It also adjusts the text by taking sentiment data into consideration.

[1132] Shape and display

[1133] The server receives the generated information, formats it into a user-friendly format (e.g., HTML or JSON), and sends it to the terminal. The terminal parses the received information and displays it to the user in a browser or dedicated application. This allows the user to quickly obtain the information they need.

[1134] Specific example

[1135] Let's consider a specific example where a user inquires about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the terminal and sends it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice, obtaining emotion data such as "irritated." The terminal sends this data to the server, which then queries the AI ​​model. The AI ​​model extracts information about "Remote Control Settings" from the instruction manual data and generates a concise explanation considering the emotion data. For example, it might say, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this and sends it to the terminal, which then displays the information to the user.

[1136] In this way, this system allows users to quickly obtain optimal information tailored to their emotional state.

[1137] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1138] Step 1:

[1139] The user enters the model name and keywords into the terminal's input form and presses the "Submit" button. The entered data might be, for example, "Air Conditioner XYZ789" and "Remote Control Settings." Simultaneously, the terminal's camera and microphone collect the user's facial expressions and voice, acquiring emotional data. This emotional data indicates the user's psychological state, such as "Irritated." This input data is temporarily stored within the terminal.

[1140] Input: Model name, keywords, user's facial expression and voice

[1141] Output: Temporarily saved model name, keyword, sentiment data

[1142] Step 2:

[1143] The terminal converts the entered model name, keywords, and sentiment data into JSON format and sends it to the server as an HTTP request. For example, it uses the POST method. This request contains JSON data such as the following:

[1144] json

[1145] {

[1146] "model": "Air conditioner XYZ789",

[1147] "keyword": "remote control settings",

[1148] "emotion": "irritation"

[1149] }

[1150] Input: Temporarily saved model name, keyword, sentiment data

[1151] Output: JSON data, HTTP request

[1152] Step 3:

[1153] The server parses the received JSON data, extracts the model name, keywords, and emotion data, and stores them in their respective variables. For example, the model name is stored in "model_name", the keywords in "keyword", and the emotion data in "emotion".

[1154] Python

[1155] model_name = request_data["model"]

[1156] keyword = request_data["keyword"]

[1157] emotion = request_data["emotion"]

[1158] Input: Data in JSON format

[1159] Output: Model name, keyword, and sentiment data stored in variables

[1160] Step 4:

[1161] The server generates a prompt based on the model name and keywords stored in variables and queries the artificial intelligence model. For example, the prompt might be "Please tell me how to set up the remote control for air conditioner XYZ789." This is sent to the artificial intelligence model, and a response is received. The artificial intelligence model uses a machine learning algorithm to generate the answer from the corresponding instruction manual data.

[1162] Input: Model name, keyword, and sentiment data stored in variables.

[1163] Output: Prompt sentences to the AI ​​model, generated answers

[1164] Step 5:

[1165] Based on the responses received from the artificial intelligence model, the server adjusts the information while taking emotional data into consideration. For example, if the user is "frustrated," the explanation will be made more concise. Specifically, it might generate a response such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[1166] Input: Generated responses, sentiment data

[1167] Output: Adjusted information

[1168] Step 6:

[1169] The server formats the adjusted information into HTML or JSON format and sends it to the terminal. For example, the data will be in HTML format as follows:

[1170] html

[1171] How to set up the remote control:

[1172]

[1173] Insert the batteries.

[1174] Press and hold the settings button for 3 seconds.

[1175] Complete the settings for the receiving unit.

[1176]

[1177] Input: Adjusted information

[1178] Output: HTML and JSON formatted data, HTTP response

[1179] Step 7:

[1180] The device parses the received HTML or JSON data and displays it to the user through a browser or dedicated app. The user can then review the displayed information and quickly take the necessary steps.

[1181] Input: HTML or JSON formatted data

[1182] Output: Information displayed in the browser or app

[1183] (Application Example 2)

[1184] Next, we will explain application example 2. In the following explanation, 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."

[1185] Conventional systems had challenges in quickly obtaining necessary information from instruction manuals and providing appropriate information that took into account the user's emotional state. In particular, in customer service at physical stores, the provision of operational instructions and product information often involved one-sided information provision that disregarded the customer's emotional state, which contributed to reduced customer satisfaction. Therefore, there was a need for information provision that took the user's emotions into consideration.

[1186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1187] In this invention, the server includes means for the user to input a model name and keywords using a terminal, means for acquiring emotional data from the user's facial expressions and voice using an emotion engine, means for the server to receive the model name, keywords and emotional data from the terminal, means for the server to query an artificial intelligence model using the model name, keywords and emotional data, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information generated based on the emotional data, means for the server to transmit the generated information to the terminal, and means for the terminal to display the transmitted information to the user. This makes it possible to quickly provide optimal information while taking into account the user's emotional state.

[1188] A "terminal" is a device used by the user to input the model name and keywords, and it is equipped with the function of acquiring emotional data from the user's facial expressions and voice using an emotion engine.

[1189] An "emotion engine" is a combination of software and hardware that analyzes a user's facial expressions and voice to acquire emotional data.

[1190] "Emotional data" refers to data that indicates the user's emotional state, obtained from the user's facial expressions and voice.

[1191] A "server" is a device that analyzes the model name, keywords, and sentiment data received from a terminal and queries an artificial intelligence model for this analysis.

[1192] "Model name" refers to the name of the specific device or product from which the user is seeking information from the instruction manual.

[1193] "Keywords" are related terms that users enter to identify information in the instruction manual.

[1194] An "artificial intelligence model" is a model that uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name and to adjust the information based on sentiment data.

[1195] "Explanatory data" refers to data related to instruction manuals and product information, and includes the information that users need.

[1196] "Information generation" refers to the process where an artificial intelligence model creates appropriate information to provide to the user based on the model name and keywords.

[1197] "Information adjustment" refers to optimizing the wording and expression of generated information to match the user's emotional state, based on emotional data.

[1198] System Configuration

[1199] As a specific embodiment of this invention, the system includes the following hardware and software.

[1200] 1. Terminal

[1201] User input device: Equipped with a touch panel or voice input device for the user to input the model name and keywords.

[1202] Emotion Engine: Equipped with a camera for analyzing the user's facial expressions and a microphone for voice analysis.

[1203] Emotion analysis software: A software module for acquiring emotional data from facial expressions and voice.

[1204] 2. Server

[1205] Data receiving module: Receives model name, keywords, and sentiment data transmitted from the terminal.

[1206] Data analysis module: Analyzes model names, keywords, and sentiment data, and provides this information to an artificial intelligence model.

[1207] Artificial intelligence model: This model uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name, and adjusts the information based on sentiment data.

[1208] Data transmission module: Sends the generated information to the terminal in the appropriate format.

[1209] System operation

[1210] Step 1: User Input

[1211] The user enters the model name and keywords using the terminal. For example, if the user wants to know the "temperature setting method" for the "refrigerator GX300," they enter this information on the touch panel. In addition, the emotion engine analyzes the user's facial expressions (e.g., captured by the camera) and voice (e.g., captured by the microphone) to acquire emotion data.

[1212] Step 2: Data transmission

[1213] After the user completes the input, the device sends the model name, keywords, and sentiment data to the server. This transmission uses communication protocols such as HTTP requests.

[1214] Step 3: Data Analysis and Information Generation

[1215] The server analyzes the received data using a data analysis module and queries an artificial intelligence model. The AI ​​model searches a database of descriptions related to the model name and generates information corresponding to the keywords. In doing so, it adjusts the wording of the information, taking sentiment data into consideration. For example, if the user is feeling stressed, the description will be generated to be concise and easy to understand.

[1216] Step 4: Information Submission and Display

[1217] The generated information is sent to the terminal in an appropriate format by the data transmission module. The terminal then displays the received information to the user in a visually easy-to-understand format (e.g., browser display or dedicated application).

[1218] Examples

[1219] As a practical example, consider a scenario where a customer wants to know how to operate a home appliance. For instance, imagine a customer asking about the "temperature setting method" for a "GX300 refrigerator." The customer enters the model name and keywords into the terminal's touchscreen, an emotion engine captures the customer's facial expression, and voice analysis obtains emotion data indicating "frustrated." This data is sent to a server, where an artificial intelligence model generates a specific and concise answer: "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature." The server sends this information to the terminal, which then displays it to the customer.

[1220] Examples of prompts for a generative AI model:

[1221] text

[1222] A user asked about the "temperature setting method" for the "GX300 refrigerator." The user is also frustrated. Therefore, please provide a clear and concise explanation to the user.

[1223] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1224] Step 1:

[1225] The user enters the model name and keywords using the terminal. For example, they might enter "refrigerator GX300" and "temperature setting method". The terminal captures this input and prepares the data for the next processing step. Specifically, voice input is converted to text by speech recognition software, and touch panel input is directly acquired as text data.

[1226] input:

[1227] Model name: "Refrigerator GX300"

[1228] Keywords: "Temperature setting method"

[1229] output:

[1230] The model name and keywords are retrieved in text format.

[1231] Step 2:

[1232] The emotion engine analyzes the user's facial expressions and voice to acquire emotion data. The device's camera captures the user's facial expressions, and the microphone records the tone of the user's voice. Emotion recognition software analyzes this data to generate emotion data. For example, the emotion "irritated" might be recognized.

[1233] input:

[1234] User facial expression data (captured by camera)

[1235] User's voice data (recorded by microphone)

[1236] output:

[1237] Emotional data: "Irritated"

[1238] Step 3:

[1239] The device sends the model name, keywords, and sentiment data entered by the user to the server. This transmission is performed using an appropriate communication protocol, such as an HTTP request. The data is packaged in a format such as JSON.

[1240] input:

[1241] Model name: "Refrigerator GX300"

[1242] Keywords: "Temperature setting method"

[1243] Emotional data: "Irritated"

[1244] output:

[1245] Data sent to the server (model name, keywords, sentiment data)

[1246] Step 4:

[1247] The server analyzes the received data and extracts the model name, keywords, and sentiment data. This data is stored in variables and prepared for the next processing step.

[1248] input:

[1249] Data sent from the device (device name, keywords, sentiment data)

[1250] output:

[1251] Extracted data (model name, keywords, sentiment data)

[1252] Step 5:

[1253] The server's artificial intelligence model searches a description database related to the model name and generates information that matches the keywords. Furthermore, it adjusts the wording of this information by taking sentiment data into consideration. For example, it generates a concise explanation such as, "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature."

[1254] input:

[1255] Extracted data (model name, keywords, sentiment data)

[1256] output:

[1257] Adjusted information (concise explanation)

[1258] Step 6:

[1259] The server sends the processed information to the terminal in an appropriate format (e.g., HTML or JSON). This transmission is also carried out using an appropriate communication protocol.

[1260] input:

[1261] Adjusted information

[1262] output:

[1263] Formatted information

[1264] Step 7:

[1265] The terminal visually displays the received information to the user. This is done using a browser or a dedicated application. The displayed information is provided in a format that the user can easily understand.

[1266] input:

[1267] Formatted information

[1268] output:

[1269] Information displayed to the user

[1270] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1271] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1272] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1273] [Fourth Embodiment]

[1274] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1275] As shown in Figure 7, the 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.

[1276] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1277] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1278] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1279] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1280] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1281] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1282] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1283] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1284] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1285] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1286] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1287] The system of this invention is designed to allow users to quickly obtain necessary information from instruction manuals. Specifically, the user inputs the model name and keywords using a terminal, sends this information to a server, and an artificial intelligence model generates the relevant information, which is then displayed to the user.

[1288] System Configuration

[1289] 1. Terminal

[1290] The terminal serves as the user's input device. The user uses the terminal to input the model name and keywords, and sends them to the server. The terminal has a web browser and a dedicated application installed, which the user uses to access the system.

[1291] 2. Server

[1292] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[1293] 3. Artificial Intelligence Models

[1294] The artificial intelligence model analyzes data from instruction manuals and generates information related to keywords searched by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[1295] Program processing flow

[1296] User input processing

[1297] The user enters the model name (e.g., "Washing Machine ABC123") and a keyword (e.g., "Filter Cleaning") on the device and clicks the submit button. The device sends the entered data to the server. The data is sent in a format such as JSON.

[1298] Server Processing

[1299] The server analyzes the data received from the terminal and extracts the model name and keywords. Next, the server passes this information to an artificial intelligence model and requests the generation of corresponding information.

[1300] Processing of artificial intelligence models

[1301] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts and generates information that matches the keywords. Specifically, it analyzes the text data of the instruction manuals and selects the most relevant information.

[1302] Information formatting and transmission

[1303] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[1304] Display to the user

[1305] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can then quickly obtain the necessary information from the instruction manual.

[1306] Specific example

[1307] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on their device and submits it. The device sends this data to the server. The server receives and analyzes this data, passing the model name and keywords to an artificial intelligence model. The AI ​​model extracts information related to "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this information and sends it to the device, which then displays it to the user. The user can quickly confirm how to set up the remote control.

[1308] The above describes the configuration for implementing the system of the present invention. This system allows users to quickly find the necessary information from a vast number of instruction manuals, significantly improving convenience.

[1309] The following describes the processing flow.

[1310] Step 1:

[1311] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into the input form for searching the instruction manual. After entering the information, the user presses the submit button to send the data.

[1312] Step 2:

[1313] The terminal sends the model name and keywords entered by the user to the server as an HTTP request. This data is sent in JSON format or as HTTP parameters.

[1314] Step 3:

[1315] The server parses the HTTP request received from the terminal and extracts the model name and keywords. The parsed data is stored in variables.

[1316] Step 4:

[1317] The server uses the extracted model name and keywords to send information generation requests to the artificial intelligence model. Specifically, it sends data in the format {"device": "model name", "keyword": "keyword"} using API calls or internal functions.

[1318] Step 5:

[1319] The artificial intelligence model searches a database of instruction manuals related to the model name based on the received request. It extracts information that matches the keywords and generates the most relevant response.

[1320] Step 6:

[1321] The response generated by the artificial intelligence model is returned to the server. The server receives this response and formats it into a user-friendly format, for example, by converting it to HTML.

[1322] Step 7:

[1323] The server sends the formatted information to the terminal as an HTTP response. The data is sent in various formats, such as JSON or HTML, as needed.

[1324] Step 8:

[1325] The device analyzes the information received from the server and displays it on the user's screen. Specifically, it either inserts the information into the DOM using JavaScript in the browser or displays it using a dedicated application.

[1326] Step 9:

[1327] Users can view the information displayed on their device screen and obtain the necessary information. For example, they can view information such as "How to set up the remote control for the XYZ789 air conditioner..." and then perform the actual operation.

[1328] (Example 1)

[1329] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1330] Conventional manual search systems made it difficult to quickly find necessary information from a vast amount of data. Furthermore, users had to enter precise model names or keywords, resulting in usability issues. There is a need to provide a system that solves these problems and allows users to easily and quickly access the information they need.

[1331] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1332] In this invention, the server includes means for a user to input a model name and keywords using an information terminal; means for the server to receive the model name and keywords from the information terminal; means for the server to analyze the model name and keywords and query an artificial intelligence system; means for the artificial intelligence system to generate information corresponding to the keywords from technical literature data related to the model name; means for the server to format the generated information and transmit it to the information terminal; and means for the information terminal to display the formatted information to the user. This makes it possible for the user to easily and quickly obtain the necessary information.

[1333] An "information terminal" is a device used by users to input information and communicate with a server, and includes personal computers, smartphones, tablets, and other similar devices.

[1334] "Model name" refers to a name used to identify a specific product or device, such as a product-specific name like "Air Conditioner XYZ789".

[1335] A "keyword" is a term or phrase that a user uses to search for specific information within an instruction manual.

[1336] A "server" is a computing system that analyzes data received from terminals, queries an artificial intelligence system, and provides appropriate information.

[1337] An "artificial intelligence system" is a model that analyzes and generates information using machine learning algorithms, and its role is to provide the necessary data based on user requests.

[1338] "Technical literature data" refers to a database containing information such as instruction manuals and technical manuals for each model.

[1339] A "machine learning algorithm" is an algorithm used by artificial intelligence systems to learn from data and train models.

[1340] "Formatting" refers to the process of transforming generated information into a format that is easy for users to view, and includes conversion to HTML or JSON format.

[1341] The system of the present invention is designed to allow users to quickly obtain necessary information from instruction manuals using an information terminal. The hardware and software necessary to specifically implement this invention, and the data processing methods using them, are described below.

[1342] terminal

[1343] Users enter the model name and keywords using an information terminal. These terminals can include personal computers, smartphones, and tablets. These terminals also have web browsers and dedicated applications installed, which users use to access the system.

[1344] server

[1345] The server is the central device that receives and analyzes data transmitted from terminals. Server-side programs are often written in programming languages ​​such as Python or Java. The server parses the model name and keywords received from the terminals in JSON format and extracts them appropriately.

[1346] Artificial intelligence system

[1347] The server passes the analyzed model names and keywords to the artificial intelligence (AI) system. The AI ​​system, equipped with models trained using machine learning frameworks such as TensorFlow and PyTorch, analyzes the technical literature data. This AI system, trained using machine learning algorithms, can select highly relevant information.

[1348] Information formatting and transmission

[1349] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format. The formatted information is then converted into HTML or JSON format and finally sent from the server to the terminal.

[1350] Display to the user

[1351] The device displays the received information to the user. Specifically, the information is presented in a visually easy-to-understand format through a web browser or a dedicated app. This allows the user to quickly obtain the necessary information from the instruction manual.

[1352] Specific example

[1353] Let's consider a scenario where a user searches for information about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the information terminal and clicks the submit button. The submitted data is sent to the server, which analyzes it. Then, a request based on the model name and keywords is sent to the artificial intelligence system. The artificial intelligence system searches the technical literature data and generates information such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats the generated information and sends it back to the terminal. The terminal displays the received information to the user, allowing the user to easily check how to set up the remote control.

[1354] Example of a prompt

[1355] Model name: Air conditioner XYZ789

[1356] Keywords: Remote control settings

[1357] output:

[1358] How to set up the remote control:

[1359] 1. Insert the batteries.

[1360] 2. Press and hold the settings button for 3 seconds.

[1361] 3. Complete the settings for the receiving unit.

[1362] The above describes the configuration for implementing the invention, and this system allows users to quickly obtain the necessary information from the instruction manual. This significantly improves convenience.

[1363] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1364] Step 1:

[1365] User data entry

[1366] The user enters the model name and keywords using the input form on the information terminal. Specifically, they enter "Air Conditioner XYZ789" (model name) and "Remote Control Settings" (keyword) via a browser or dedicated app, and then click the submit button.

[1367] Input: Model name "Air conditioner XYZ789", Keyword "Remote control settings"

[1368] Output: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[1369] Step 2:

[1370] Data reception by the server

[1371] The server receives data in JSON format sent by the terminal. The server then prepares to parse this data.

[1372] Input: JSON data "{"Model Name": "Air Conditioner XYZ789", "Keyword": "Remote Control Settings"}"

[1373] Output: Data converted to an internal format for data analysis.

[1374] Step 3:

[1375] Data Analysis

[1376] The server parses the received JSON data and extracts the model name and keywords. It uses parsing programs written in Python or Java.

[1377] Specific operation: Extract the "Model Name" and "Keyword" fields from the JSON data.

[1378] Input: Data in JSON format

[1379] Output: Extracted model name "Air Conditioner XYZ789" and keyword "Remote Control Settings"

[1380] Step 4:

[1381] Inquiries to the artificial intelligence system

[1382] The server uses the analyzed model name and keywords to send an information generation request to the artificial intelligence system. The request is sent via a REST API.

[1383] Specific operation: Send an HTTP request from the server to the artificial intelligence system.

[1384] Input: Extracted model name and keyword

[1385] Output: HTTP request "{"Model name": "Air conditioner XYZ789", "Keyword": "Remote control settings"}"

[1386] Step 5:

[1387] Information generation

[1388] The artificial intelligence system uses machine learning algorithms to extract and generate relevant information from technical literature databases. Specifically, it analyzes text data from instruction manuals and selects information that matches keywords.

[1389] Specific operation: Use natural language processing techniques to extract and generate relevant information.

[1390] Input: Model name "Air conditioner XYZ789" and keyword "Remote control settings"

[1391] Output: Generated information: "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[1392] Step 6:

[1393] Formalization of information

[1394] The server receives information generated by the artificial intelligence system and formats it into a user-friendly format, such as HTML or JSON.

[1395] Specific actions: Convert the generated information into HTML format and arrange the layout.

[1396] Input: Generated information

[1397] Output: Formatted information (HTML or JSON)

[1398] Step 7:

[1399] Information transmission

[1400] The formatted information is sent from the server to the terminal. It is sent quickly so that the user can immediately verify the information.

[1401] Specific operation: Sends formatted information as an HTTP response.

[1402] Input: Formatted information

[1403] Output: Sending information to the user terminal

[1404] Step 8:

[1405] Displaying information

[1406] The device displays the received, formatted information to the user. It presents the information in a visually easy-to-understand format using a browser or dedicated app.

[1407] Specific operation: Renders information in a browser or app and displays it on the screen.

[1408] Input: Information received from the server

[1409] Output: Information visually displayed to the user

[1410] The above outlines the specific processing steps of the system. Each step works in conjunction to create a mechanism that allows users to quickly obtain the information they need.

[1411] (Application Example 1)

[1412] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1413] Maintaining and troubleshooting complex equipment and robots used in factories is time-consuming and labor-intensive, as operators must consult numerous instruction manuals and technical documents. Furthermore, a lack of systems to quickly detect equipment malfunctions and provide appropriate maintenance procedures can hinder efficient factory operations.

[1414] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1415] In this invention, the server includes means for a user to input a model name and keywords using a terminal, means for the server to receive the model name and keywords from the terminal, means for the server to query an artificial intelligence model using the model name and keywords, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name, means for the server to transmit the generated information to the terminal, means for the terminal to display the transmitted information to the user, means for a robot operating in the factory to automatically input the model name and keywords when it detects an abnormality in the equipment, and means for the terminal to display maintenance procedures to the robot operator. This enables rapid and accurate detection of equipment abnormalities and provision of maintenance procedures within the factory, making efficient factory operation possible.

[1416] A "user" is a person who uses a system; they are the entity that performs input and operations through the system interface.

[1417] A "terminal" refers to an input device used by a user to access a system, and includes computers, smartphones, tablets, and other similar devices.

[1418] "Model name" refers to the name that represents a specific piece of equipment or device, and is used as product identification information.

[1419] A "keyword" is a word or phrase that a user enters to specify the information they need.

[1420] A "server" refers to a central computing device that receives and processes requests from users and provides the necessary information.

[1421] An "artificial intelligence model" is a data analysis program that is trained using machine learning algorithms and generates responses based on user input.

[1422] "Explanatory data" refers to information provided in instruction manuals and other documents, including how to operate the equipment and maintenance procedures.

[1423] "Generating information" refers to the process by which an artificial intelligence model extracts and constructs relevant information based on the entered model name and keywords.

[1424] "Detecting an anomaly" means discovering a state in which a robot or piece of equipment deviates from its normal operation.

[1425] "Maintenance procedures" refer to information that outlines the specific steps required for servicing or repairing equipment.

[1426] A "robot operator" is a person who operates and monitors robots within a factory.

[1427] This invention is a system for assisting with the maintenance and troubleshooting of robots used in factories. Specifically, the user inputs the model name and keywords using a terminal, a server receives and analyzes this information, generates relevant information using an artificial intelligence model, and finally displays it to the user.

[1428] System Configuration

[1429] 1. Terminal

[1430] The terminal is a device used by the user as an input device, and includes computers, smartphones, and tablets. The user uses it to input the model name (e.g., "Robot Arm ABC123") and keywords (e.g., "Maintenance Procedure") and sends them to the server.

[1431] 2. Server

[1432] The server is a central device that analyzes the model name and keywords received from the terminal and queries the artificial intelligence model. The server has an artificial intelligence model trained using machine learning algorithms, and uses this to generate appropriate information.

[1433] Specifically, the server passes the analyzed data to an artificial intelligence model, which then extracts and constructs the most relevant explanatory data.

[1434] 3. Artificial Intelligence Models

[1435] The artificial intelligence model analyzes data from the instruction manual and generates information related to keywords entered by the user. The AI ​​model is located on a server and generates information in response to queries from the server.

[1436] The artificial intelligence model uses OpenAI's GPT-3 (engine: daVinci) and performs natural language processing.

[1437] 4. Formalizing and transmitting information

[1438] The generated information is formatted by the server into HTML or JSON format and sent to the device. This allows the information to be presented in a visually easy-to-understand format on the device.

[1439] Program processing

[1440] The server receives and analyzes the model name and keywords entered by the user from the terminal. After analysis, it passes the information to an artificial intelligence model to create a prompt for generating appropriate information. Using this prompt, the AI ​​model generates data related to the specified model name and keywords. The generated information is formatted by the server, sent to the terminal, and displayed to the user.

[1441] Hardware and software to be used

[1442] Hardware: Robot bodies, control panels, smartphones, tablets, etc., used within factories.

[1443] Software: We use Python and Flask to build the server-side API, and OpenAI's GPT-3 (engine: daVinci) for the artificial intelligence model.

[1444] Specific example

[1445] If a user wants to find out the "initial setup" for the "Robot Arm XYZ789," they enter "Robot Arm XYZ789" and "initial setup" into the input form on the terminal and submit it. The server receives this data and generates a prompt saying, "Please provide the initial setup information for the Robot Arm XYZ789 from the instruction manual," and queries the artificial intelligence model. The artificial intelligence model generates the corresponding initial setup procedure, sends it to the terminal via the server, and the terminal displays it to the user. An example of the prompt text is as follows:

[1446] Prompt message

[1447] "Please provide the initial setup information for the XYZ789 robotic arm from the instruction manual."

[1448] This system enables rapid and accurate detection of equipment malfunctions and provision of maintenance procedures within the factory, leading to more efficient factory operations.

[1449] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1450] Step 1:

[1451] The user enters the model name and keywords using a terminal. In this example, the user enters "Robot Arm XYZ789" and "Initial Setup" and submits the data. The input data is sent to the server in JSON format. Input: Model name and keywords. Output: Data in JSON format.

[1452] Step 2:

[1453] The server parses the received data. The server extracts the model name and keywords from the JSON-formatted data. A Python library is used for data analysis. Input: JSON-formatted data. Output: Model name and keywords.

[1454] Step 3:

[1455] The server generates a prompt to query the artificial intelligence model based on the extracted model name and keywords. An example of a prompt is "Please provide initial setup information for the XYZ789 robot arm from the instruction manual." Input: Model name and keywords. Output: Prompt.

[1456] Step 4:

[1457] The server sends the generated prompt to the artificial intelligence model (GPT-3), which then generates relevant information. The AI ​​model provides appropriate initial setup procedures based on the prompt. Input: Prompt text. Output: Generated initial setup procedures.

[1458] Step 5:

[1459] The server receives the generated information and formats it into the appropriate format (e.g., HTML or JSON). Input: Generated initial setup instructions. Output: Formatted information.

[1460] Step 6:

[1461] The server sends formatted information to the terminal. The terminal parses the received information and displays it to the user. Input: Formatted information. Output: Information displayed to the user.

[1462] Step 7:

[1463] The user reviews the information displayed on the terminal and performs the necessary maintenance or configuration steps. This allows the user to quickly and accurately perform the initial setup of the device. Input: Information displayed on the terminal. Output: Maintenance or configuration steps performed.

[1464] This completes the processing flow.

[1465] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1466] The system of the present invention enables users to quickly obtain necessary information from instruction manuals, and further, by combining it with an emotion engine that recognizes the user's emotions, it achieves the provision of more appropriate information. Specific embodiments of the present invention are described below.

[1467] System Configuration

[1468] 1. Terminal

[1469] The terminal is a user input device, providing a means for the user to input the model name and keywords. The terminal also incorporates an emotion engine, which analyzes the user's facial expressions and voice to recognize emotions.

[1470] 2. Server

[1471] The server receives the device name and keywords sent from the terminal, as well as emotion data sent from the emotion engine. Using this data, it queries the artificial intelligence model to generate appropriate information.

[1472] 3. Artificial Intelligence Models

[1473] The artificial intelligence model is trained using machine learning algorithms to analyze instruction manual data related to model names and generate information corresponding to keywords. It also adjusts the wording of the information based on sentiment data to provide the most appropriate answer to the user.

[1474] Program processing flow

[1475] User input processing

[1476] The user enters the model name (e.g., "washing machine ABC123") and keywords (e.g., "clean the filter") on the device. Simultaneously, the device's emotion engine analyzes the user's facial expressions and voice to acquire emotion data. This emotion data indicates the user's stress level and satisfaction level.

[1477] Sending data

[1478] The device sends the entered model name, keywords, and sentiment data obtained from the sentiment engine to the server. This transmission is performed using HTTP requests or other appropriate communication protocols.

[1479] Server Processing

[1480] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. The analyzed data is stored in variables and provided to the artificial intelligence model.

[1481] Processing of artificial intelligence models

[1482] The artificial intelligence model searches a database of instruction manuals related to the model name and extracts information that matches the keywords. It also adjusts the wording of the information, taking into account emotional data. For example, if the user is feeling stressed, it will make the explanation more concise.

[1483] Information formatting and transmission

[1484] The generated information is formatted by the server and transformed into a user-friendly format. For example, it may be formatted in HTML or JSON format. The formatted information is then sent from the server to the terminal.

[1485] Display to the user

[1486] The terminal displays the received information to the user. In a browser or dedicated application, the information is presented in a visually easy-to-understand format. The user can review the displayed information and quickly obtain the necessary details.

[1487] Specific example

[1488] Let's consider a scenario where a user searches for "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the input form on the terminal and submits it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice to obtain emotion data such as "irritated."

[1489] The terminal sends this data to the server. The server analyzes the data and queries an artificial intelligence model. The AI ​​model extracts information related to "remote control settings" from the instruction manual for the XYZ789 air conditioner and generates information while considering the user's emotions. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[1490] The server formats the generated information and sends it to the terminal. The terminal displays the information to the user, allowing the user to quickly check how to configure the remote control.

[1491] The above describes a specific embodiment for implementing the system of the present invention in combination with an emotion engine. This system enables the provision of optimal information according to the user's emotional state, further improving convenience.

[1492] The following describes the processing flow.

[1493] Step 1:

[1494] The user accesses a web browser or dedicated app using their device and enters the model name and keywords into an input form for searching the instruction manual. Simultaneously, the device's camera and microphone capture the user's facial expressions and voice in real time.

[1495] Step 2:

[1496] The emotion engine analyzes captured facial and voice data to estimate the user's emotional state. For example, it determines whether the user is irritated or calm. This emotional data is expressed as a state such as "irritated" or "calm."

[1497] Step 3:

[1498] The user enters the model name and keywords and presses the send button. The device sends the input data and emotion data to the server in an appropriate format such as JSON. For example, data such as {"device": "Washing machine ABC123", "keyword": "Cleaning the filter", "emotion": "Irritated"} is sent.

[1499] Step 4:

[1500] The server analyzes the data received from the terminal and extracts the model name, keywords, and sentiment data. This data is stored in variables on the server and used for subsequent processing.

[1501] Step 5:

[1502] The server provides the extracted model name and keywords to the artificial intelligence model and requests information generation. Specifically, it passes the model name "washing machine ABC123" and the keyword "filter cleaning" to the artificial intelligence model.

[1503] Step 6:

[1504] The artificial intelligence model searches the instruction manual database for relevant information based on the provided data. For example, it extracts paragraphs related to "filter cleaning."

[1505] Step 7:

[1506] The artificial intelligence model further considers emotional data and adjusts the wording of the information. For example, if the user is "frustrated," the explanation will be made more concise and use more approachable language. It will also provide step-by-step instructions as needed.

[1507] Step 8:

[1508] The server receives the information generated by the artificial intelligence model and formats it into a user-friendly format (such as HTML or JSON). The formatted information might look like this: "To clean the filter of washing machine ABC123, first remove the filter cover. Next, take out the filter and wash it with water. Finally, put the filter back in place."

[1509] Step 9:

[1510] The server sends formatted information to the terminal as an HTTP response. The data is transmitted using the appropriate communication protocol.

[1511] Step 10:

[1512] The device analyzes the information received from the server and displays it on the user's screen. For example, a web browser uses JavaScript to insert information into the DOM, while a dedicated app binds the information to UI elements.

[1513] Step 11:

[1514] Users can check the information displayed on their device screen and quickly obtain the necessary information. For example, they can check "How to clean the filter of washing machine ABC123" and then actually perform the cleaning.

[1515] Specific example

[1516] When a user searches for "Air Conditioner XYZ789" and "Remote Control Settings," the process proceeds as follows:

[1517] The user enters the model name "Air Conditioner XYZ789" and the keyword "Remote Control Settings," then presses the submit button. The emotion engine analyzes the user's facial expressions and voice to determine that they are "frustrated." The terminal sends this data to the server, which analyzes the data and passes it to the artificial intelligence model. The AI ​​model extracts information about "Remote Control Settings" from the Air Conditioner XYZ789 instruction manual and generates a concise response, taking into account the user's "frustration." The server sends the formatted information to the terminal, which then displays it to the user. The user can quickly find out how to configure the remote control.

[1518] In this way, a system is realized in which terminals, servers, artificial intelligence models, and emotion engines work together to provide users with the most optimal information.

[1519] (Example 2)

[1520] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1521] In modern information retrieval systems, it is difficult for users to quickly and accurately obtain specific information from instruction manuals. Furthermore, conventional systems provide uniform information without considering the user's emotional state, resulting in a poor user experience. General information delivery methods are particularly insufficient for users experiencing stress or anxiety. To solve these problems, it is necessary to recognize the user's emotional state and provide appropriate information based on that understanding.

[1522] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1523] In this invention, the server includes means for analyzing facial expressions and voice simultaneously with user input and acquiring emotional data from the terminal; means for the server to receive the model name, keywords, and emotional data from the terminal; and means for an artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information based on the emotional data. This makes it possible to provide optimal information according to the user's emotional state.

[1524] A "terminal" is a device operated by a user, which provides a means of inputting the model name and keywords as an input device, and has the function of analyzing facial expressions and voice to acquire emotional data.

[1525] A "server" is a device that receives data sent from a terminal, analyzes it, queries an artificial intelligence model, formats the generated information into an appropriate format, and sends it back to the terminal.

[1526] "Model name" is a name used to identify a specific product or device, and is entered by the user into the terminal.

[1527] A "keyword" is a phrase used when searching for specific information in an instruction manual, and is entered by the user into the device.

[1528] "Emotional data" refers to data that indicates the emotional state of a user, analyzed from their facial expressions and voice, and reflects psychological states such as stress and anxiety.

[1529] An "artificial intelligence model" is a model trained using machine learning algorithms that generates information corresponding to keywords from descriptive data related to model names and adjusts the information based on sentiment data.

[1530] "Explanatory data" refers to instruction manuals and technical documents related to specific products or equipment, which are the data that artificial intelligence models analyze.

[1531] "Information adjustment" refers to appropriately modifying the wording and format of generated information based on user sentiment data, such as making explanations more concise.

[1532] An "HTTP request" is one of the Internet protocols and a means of sending data.

[1533] "JSON format" is a format for representing data in a structured way, and it is an abbreviation for JavaScript Object Notation.

[1534] "HTML format" is a markup language used to create web pages, and is an abbreviation for HyperText Markup Language.

[1535] The system of this invention aims to enable users to quickly obtain necessary information from instruction manuals. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to provide more appropriate information. The following describes specific embodiments for carrying out this invention.

[1536] System Configuration

[1537] terminal

[1538] The terminal is an input device operated by the user, providing a means for the user to input the model name and keywords. The terminal also incorporates an emotion engine, which analyzes the user's facial expressions and voice to acquire emotional data. Specifically, the terminal uses a camera and microphone to collect the user's facial expressions and voice, and then analyzes that data.

[1539] server

[1540] The server's role is to receive the device name, keywords, and emotion data sent from the terminal, as well as emotion data sent from the emotion engine. It analyzes the received data and queries the artificial intelligence model. The server uses communication protocols such as HTTP requests and WebSockets to send and receive data.

[1541] Artificial intelligence model

[1542] The artificial intelligence model is trained using machine learning algorithms to generate information corresponding to keywords from descriptive data related to model names. Furthermore, it adjusts the generated information based on sentiment data to provide the most appropriate answer to the user. For example, if the user is feeling stressed, it will make the explanation more concise.

[1543] Program processing flow

[1544] Data acquisition and transmission

[1545] The user enters the model name and keywords into the input form on the device and presses the "Submit" button. For example, the user enters "Air conditioner XYZ789" and "Remote control settings". Simultaneously, the device's built-in camera and microphone collect the user's facial expressions and voice, acquiring emotion data. The device converts this data into JSON format and sends it to the server as an HTTP request.

[1546] Server Processing

[1547] The server parses the received JSON data and extracts the model name, keywords, and sentiment data. This data is stored in variables, and a prompt message is generated for the artificial intelligence model. For example, the prompt message might be, "Please tell me how to configure the remote control for the XYZ789 air conditioner."

[1548] Processing of artificial intelligence models

[1549] The artificial intelligence model extracts appropriate information from relevant explanatory data based on the provided prompt text. For example, it generates a concise explanation such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." It also adjusts the text by taking sentiment data into consideration.

[1550] Shape and display

[1551] The server receives the generated information, formats it into a user-friendly format (e.g., HTML or JSON), and sends it to the terminal. The terminal parses the received information and displays it to the user in a browser or dedicated application. This allows the user to quickly obtain the information they need.

[1552] Specific example

[1553] Let's consider a specific example where a user inquires about "Air Conditioner XYZ789" and "Remote Control Settings." The user enters "Air Conditioner XYZ789" and "Remote Control Settings" into the terminal and sends it. Simultaneously, the emotion engine analyzes the user's facial expressions and voice, obtaining emotion data such as "irritated." The terminal sends this data to the server, which then queries the AI ​​model. The AI ​​model extracts information about "Remote Control Settings" from the instruction manual data and generates a concise explanation considering the emotion data. For example, it might say, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup." The server formats this and sends it to the terminal, which then displays the information to the user.

[1554] In this way, this system allows users to quickly obtain optimal information tailored to their emotional state.

[1555] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1556] Step 1:

[1557] The user enters the model name and keywords into the terminal's input form and presses the "Submit" button. The entered data might be, for example, "Air Conditioner XYZ789" and "Remote Control Settings." Simultaneously, the terminal's camera and microphone collect the user's facial expressions and voice, acquiring emotional data. This emotional data indicates the user's psychological state, such as "Irritated." This input data is temporarily stored within the terminal.

[1558] Input: Model name, keywords, user's facial expression and voice

[1559] Output: Temporarily saved model name, keyword, sentiment data

[1560] Step 2:

[1561] The terminal converts the entered model name, keywords, and sentiment data into JSON format and sends it to the server as an HTTP request. For example, it uses the POST method. This request contains JSON data such as the following:

[1562] json

[1563] {

[1564] "model": "Air conditioner XYZ789",

[1565] "keyword": "remote control settings",

[1566] "emotion": "irritation"

[1567] }

[1568] Input: Temporarily saved model name, keyword, sentiment data

[1569] Output: JSON data, HTTP request

[1570] Step 3:

[1571] The server parses the received JSON data, extracts the model name, keywords, and emotion data, and stores them in their respective variables. For example, the model name is stored in "model_name", the keywords in "keyword", and the emotion data in "emotion".

[1572] Python

[1573] model_name = request_data["model"]

[1574] keyword = request_data["keyword"]

[1575] emotion = request_data["emotion"]

[1576] Input: Data in JSON format

[1577] Output: Model name, keyword, and sentiment data stored in variables

[1578] Step 4:

[1579] The server generates a prompt based on the model name and keywords stored in variables and queries the artificial intelligence model. For example, the prompt might be "Please tell me how to set up the remote control for air conditioner XYZ789." This is sent to the artificial intelligence model, and a response is received. The artificial intelligence model uses a machine learning algorithm to generate the answer from the corresponding instruction manual data.

[1580] Input: Model name, keyword, and sentiment data stored in variables.

[1581] Output: Prompt sentences to the AI ​​model, generated answers

[1582] Step 5:

[1583] Based on the responses received from the artificial intelligence model, the server adjusts the information while taking emotional data into consideration. For example, if the user is "frustrated," the explanation will be made more concise. Specifically, it might generate a response such as, "To set up the remote control, 1. Insert the batteries. 2. Press and hold the setting button for 3 seconds. 3. Point it towards the receiver to complete the setup."

[1584] Input: Generated responses, sentiment data

[1585] Output: Adjusted information

[1586] Step 6:

[1587] The server formats the adjusted information into HTML or JSON format and sends it to the terminal. For example, the data will be in HTML format as follows:

[1588] html

[1589] How to set up the remote control:

[1590]

[1591] Insert the batteries.

[1592] Press and hold the settings button for 3 seconds.

[1593] Complete the settings for the receiving unit.

[1594]

[1595] Input: Adjusted information

[1596] Output: HTML and JSON formatted data, HTTP response

[1597] Step 7:

[1598] The device parses the received HTML or JSON data and displays it to the user through a browser or dedicated app. The user can then review the displayed information and quickly take the necessary steps.

[1599] Input: HTML or JSON formatted data

[1600] Output: Information displayed in the browser or app

[1601] (Application Example 2)

[1602] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1603] Conventional systems had challenges in quickly obtaining necessary information from instruction manuals and providing appropriate information that took into account the user's emotional state. In particular, in customer service at physical stores, the provision of operational instructions and product information often involved one-sided information provision that disregarded the customer's emotional state, which contributed to reduced customer satisfaction. Therefore, there was a need for information provision that took the user's emotions into consideration.

[1604] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1605] In this invention, the server includes means for the user to input a model name and keywords using a terminal, means for acquiring emotional data from the user's facial expressions and voice using an emotion engine, means for the server to receive the model name, keywords and emotional data from the terminal, means for the server to query an artificial intelligence model using the model name, keywords and emotional data, means for the artificial intelligence model to generate information corresponding to the keywords from descriptive data related to the model name and adjust the information generated based on the emotional data, means for the server to transmit the generated information to the terminal, and means for the terminal to display the transmitted information to the user. This makes it possible to quickly provide optimal information while taking into account the user's emotional state.

[1606] A "terminal" is a device used by the user to input the model name and keywords, and it is equipped with the function of acquiring emotional data from the user's facial expressions and voice using an emotion engine.

[1607] An "emotion engine" is a combination of software and hardware that analyzes a user's facial expressions and voice to acquire emotional data.

[1608] "Emotional data" refers to data that indicates the user's emotional state, obtained from the user's facial expressions and voice.

[1609] A "server" is a device that analyzes the model name, keywords, and sentiment data received from a terminal and queries an artificial intelligence model for this analysis.

[1610] "Model name" refers to the name of the specific device or product from which the user is seeking information from the instruction manual.

[1611] "Keywords" are related terms that users enter to identify information in the instruction manual.

[1612] An "artificial intelligence model" is a model that uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name and to adjust the information based on sentiment data.

[1613] "Explanatory data" refers to data related to instruction manuals and product information, and includes the information that users need.

[1614] "Information generation" refers to the process where an artificial intelligence model creates appropriate information to provide to the user based on the model name and keywords.

[1615] "Information adjustment" refers to optimizing the wording and expression of generated information to match the user's emotional state, based on emotional data.

[1616] System Configuration

[1617] As a specific embodiment of this invention, the system includes the following hardware and software.

[1618] 1. Terminal

[1619] User input device: Equipped with a touch panel or voice input device for the user to input the model name and keywords.

[1620] Emotion Engine: Equipped with a camera for analyzing the user's facial expressions and a microphone for voice analysis.

[1621] Emotion analysis software: A software module for acquiring emotional data from facial expressions and voice.

[1622] 2. Server

[1623] Data receiving module: Receives model name, keywords, and sentiment data transmitted from the terminal.

[1624] Data analysis module: Analyzes model names, keywords, and sentiment data, and provides this information to an artificial intelligence model.

[1625] Artificial intelligence model: This model uses machine learning algorithms to generate information corresponding to keywords from descriptive data related to the model name, and adjusts the information based on sentiment data.

[1626] Data transmission module: Sends the generated information to the terminal in the appropriate format.

[1627] System operation

[1628] Step 1: User Input

[1629] The user enters the model name and keywords using the terminal. For example, if the user wants to know the "temperature setting method" for the "refrigerator GX300," they enter this information on the touch panel. In addition, the emotion engine analyzes the user's facial expressions (e.g., captured by the camera) and voice (e.g., captured by the microphone) to acquire emotion data.

[1630] Step 2: Data transmission

[1631] After the user completes the input, the device sends the model name, keywords, and sentiment data to the server. This transmission uses communication protocols such as HTTP requests.

[1632] Step 3: Data Analysis and Information Generation

[1633] The server analyzes the received data using a data analysis module and queries an artificial intelligence model. The AI ​​model searches a database of descriptions related to the model name and generates information corresponding to the keywords. In doing so, it adjusts the wording of the information, taking sentiment data into consideration. For example, if the user is feeling stressed, the description will be generated to be concise and easy to understand.

[1634] Step 4: Information Submission and Display

[1635] The generated information is sent to the terminal in an appropriate format by the data transmission module. The terminal then displays the received information to the user in a visually easy-to-understand format (e.g., browser display or dedicated application).

[1636] Examples

[1637] As a practical example, consider a scenario where a customer wants to know how to operate a home appliance. For instance, imagine a customer asking about the "temperature setting method" for a "GX300 refrigerator." The customer enters the model name and keywords into the terminal's touchscreen, an emotion engine captures the customer's facial expression, and voice analysis obtains emotion data indicating "frustrated." This data is sent to a server, where an artificial intelligence model generates a specific and concise answer: "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature." The server sends this information to the terminal, which then displays it to the customer.

[1638] Examples of prompts for a generative AI model:

[1639] text

[1640] A user asked about the "temperature setting method" for the "GX300 refrigerator." The user is also frustrated. Therefore, please provide a clear and concise explanation to the user.

[1641] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1642] Step 1:

[1643] The user enters the model name and keywords using the terminal. For example, they might enter "refrigerator GX300" and "temperature setting method". The terminal captures this input and prepares the data for the next processing step. Specifically, voice input is converted to text by speech recognition software, and touch panel input is directly acquired as text data.

[1644] input:

[1645] Model name: "Refrigerator GX300"

[1646] Keywords: "Temperature setting method"

[1647] output:

[1648] The model name and keywords are retrieved in text format.

[1649] Step 2:

[1650] The emotion engine analyzes the user's facial expressions and voice to acquire emotion data. The device's camera captures the user's facial expressions, and the microphone records the tone of the user's voice. Emotion recognition software analyzes this data to generate emotion data. For example, the emotion "irritated" might be recognized.

[1651] input:

[1652] User facial expression data (captured by camera)

[1653] User's voice data (recorded by microphone)

[1654] output:

[1655] Emotional data: "Irritated"

[1656] Step 3:

[1657] The device sends the model name, keywords, and sentiment data entered by the user to the server. This transmission is performed using an appropriate communication protocol, such as an HTTP request. The data is packaged in a format such as JSON.

[1658] input:

[1659] Model name: "Refrigerator GX300"

[1660] Keywords: "Temperature setting method"

[1661] Emotional data: "Irritated"

[1662] output:

[1663] Data sent to the server (model name, keywords, sentiment data)

[1664] Step 4:

[1665] The server analyzes the received data and extracts the model name, keywords, and sentiment data. This data is stored in variables and prepared for the next processing step.

[1666] input:

[1667] Data sent from the device (device name, keywords, sentiment data)

[1668] output:

[1669] Extracted data (model name, keywords, sentiment data)

[1670] Step 5:

[1671] The server's artificial intelligence model searches a description database related to the model name and generates information that matches the keywords. Furthermore, it adjusts the wording of this information by taking sentiment data into consideration. For example, it generates a concise explanation such as, "To set the temperature, 1. Open the main menu. 2. Select Settings. 3. Adjust the temperature."

[1672] input:

[1673] Extracted data (model name, keywords, sentiment data)

[1674] output:

[1675] Adjusted information (concise explanation)

[1676] Step 6:

[1677] The server sends the processed information to the terminal in an appropriate format (e.g., HTML or JSON). This transmission is also carried out using an appropriate communication protocol.

[1678] input:

[1679] Adjusted information

[1680] output:

[1681] Formatted information

[1682] Step 7:

[1683] The terminal visually displays the received information to the user. This is done using a browser or a dedicated application. The displayed information is provided in a format that the user can easily understand.

[1684] input:

[1685] Formatted information

[1686] output:

[1687] Information displayed to the user

[1688] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1689] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1690] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1691] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1692] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1693] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1694] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1695] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1696] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1697] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1698] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1699] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1700] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1701] 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.

[1702] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1703] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1704] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1705] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1706] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1707] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1708] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1709] The following is further disclosed regarding the embodiments described above.

[1710] (Claim 1)

[1711] A means for the user to input the model name and keywords using a device,

[1712] The server has means for receiving the model name and keyword from the terminal,

[1713] A means by which the server queries the artificial intelligence model using the aforementioned model name and keyword,

[1714] An artificial intelligence model provides means for generating information corresponding to the keyword from descriptive data related to the model name,

[1715] The server provides means for transmitting the generated information to the terminal,

[1716] The terminal provides means for displaying the transmitted information to the user,

[1717] A system that includes this.

[1718] (Claim 2)

[1719] The system according to claim 1, wherein the artificial intelligence model uses a machine learning algorithm.

[1720] (Claim 3)

[1721] The system according to claim 1, wherein the server analyzes the model name and the keywords and provides the information in an optimized format so that the artificial intelligence model can generate optimal information.

[1722] "Example 1"

[1723] (Claim 1)

[1724] A means by which the user enters the model name and keywords using an information terminal,

[1725] The server has means for receiving the model name and keyword from the information terminal,

[1726] A means by which the server analyzes the aforementioned model name and keywords and queries the artificial intelligence system,

[1727] An artificial intelligence system provides means for generating information corresponding to the keyword from technical literature data related to the model name,

[1728] A server provides means for formatting the generated information and transmitting it to the information terminal,

[1729] The information terminal includes means for displaying the formatted information to the user,

[1730] A system that includes this.

[1731] (Claim 2)

[1732] The system according to claim 1, in which the artificial intelligence system uses a machine learning algorithm.

[1733] (Claim 3)

[1734] The system according to claim 1, wherein the server analyzes the model name and the keywords and provides the information in an optimized format so that the artificial intelligence system can generate the most appropriate information.

[1735] "Application Example 1"

[1736] (Claim 1)

[1737] A means for the user to input the model name and keywords using a device,

[1738] The server has means for receiving the model name and keyword from the terminal,

[1739] A means by which the server queries the artificial intelligence model using the aforementioned model name and keyword,

[1740] An artificial intelligence model provides means for generating information corresponding to the keyword from descriptive data related to the model name,

[1741] The server provides means for transmitting the generated information to the terminal,

[1742] The terminal provides means for displaying the transmitted information to the user,

[1743] A means for automatically inputting the model name and keywords when a robot operating in the factory detects an abnormality in equipment,

[1744] The terminal includes means for displaying maintenance procedures to the robot operator,

[1745] A system that includes this.

[1746] (Claim 2)

[1747] The system according to claim 1, wherein the artificial intelligence model uses a machine learning algorithm.

[1748] (Claim 3)

[1749] The system according to claim 1, wherein the server analyzes the model name and the keywords and provides the information in an optimized format so that the artificial intelligence model can generate optimal information.

[1750] "Example 2 of combining an emotion engine"

[1751] (Claim 1)

[1752] A means for the user to input the model name and keywords using a device,

[1753] A means by which the terminal analyzes facial expressions and voice simultaneously with user input to acquire emotional data,

[1754] The server has means for receiving the model name, keyword, and emotion data from the terminal,

[1755] A means by which the server queries an artificial intelligence model using the aforementioned model name, the aforementioned keyword, and the aforementioned emotion data,

[1756] An artificial intelligence model generates information corresponding to the keyword from descriptive data related to the model name, and means for adjusting the information based on the sentiment data,

[1757] The server provides means for formatting the generated information into a user-friendly format and transmitting it to the terminal,

[1758] The terminal provides means for displaying the transmitted information to the user,

[1759] A system that includes this.

[1760] (Claim 2)

[1761] The system according to claim 1, wherein the artificial intelligence model uses a machine learning algorithm.

[1762] (Claim 3)

[1763] The system according to claim 1, wherein the server analyzes the model name and the keywords, and further considers the sentiment data to provide the information in an optimized format so that the artificial intelligence model can generate optimal information.

[1764] "Application example 2 when combining with an emotional engine"

[1765] (Claim 1)

[1766] A means for the user to input the model name and keywords using a device,

[1767] A means of acquiring emotional data from a user's facial expressions and voice using an emotion engine,

[1768] The server has means for receiving the model name, keyword, and emotion data from the terminal,

[1769] A means by which the server queries an artificial intelligence model using the aforementioned model name, the aforementioned keyword, and the aforementioned emotion data,

[1770] An artificial intelligence model generates information corresponding to the keyword from descriptive data related to the model name, and means for adjusting the information generated based on the sentiment data,

[1771] The server provides means for transmitting the generated information to the terminal,

[1772] The terminal provides means for displaying the transmitted information to the user,

[1773] A system that includes this.

[1774] (Claim 2)

[1775] The system according to claim 1, wherein the artificial intelligence model uses a machine learning algorithm.

[1776] (Claim 3)

[1777] The system according to claim 1, wherein the server analyzes the model name, the keyword, and the emotion data, and provides the information in an optimized format so that the artificial intelligence model can generate optimal information. [Explanation of symbols]

[1778] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for the user to input the model name and keywords using a device, The server has means for receiving the model name and keyword from the terminal, A means by which the server queries the artificial intelligence model using the aforementioned model name and keyword, An artificial intelligence model provides means for generating information corresponding to the keyword from descriptive data related to the model name, The server provides means for transmitting the generated information to the terminal, The terminal provides means for displaying the transmitted information to the user, A system that includes this.

2. The system according to claim 1, wherein the artificial intelligence model uses a machine learning algorithm.

3. The system according to claim 1, wherein the server analyzes the model name and the keywords and provides the information in an optimized format so that the artificial intelligence model can generate optimal information.

Images