system

Abstract

We provide the system. [Solution] A means for receiving input of specific questions from the user, A means for sending the question to the server, A means for generating an answer to the question using generative artificial intelligence, A means for returning the generated response to the user, A means for displaying the returned response to the user, A system that includes this.

Description

Technical Field

[0004] , , ,

[0005] , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 character of the chatbot, 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] Conventional inquiry response systems for business terms and important key performance indicators (KPIs) have difficulty providing quick and appropriate answers to user questions. In particular, in the training of new staff and customer support services, while response speed and quality are required, manual response requires time and effort and is not efficient. Against this background, there is a need for a system that can immediately provide appropriate answers when a user asks questions regarding technical terms and KPIs.

Means for Solving the Problems

[0005] The present invention is a system that includes means for receiving user questions, means for transmitting the questions to a server, means for generating answers to the questions using generative artificial intelligence, means for returning the generated answers to the user, and means for displaying the returned answers to the user. As a result, when a user inputs a question regarding business terminology or KPIs, the system can automatically generate an appropriate answer and provide it to the user quickly. Furthermore, the generated answers are analyzed by a natural language processing engine and formatted into a user-friendly format, allowing the user to understand them intuitively. This can improve the efficiency of training new staff and customer support operations.

[0006] A "user" refers to an individual or organization that uses this system to enter questions.

[0007] "Questions" refer to inquiries that users enter regarding business terminology or key performance indicators (KPIs).

[0008] "Means for receiving input" refers to a function that provides an interface (UI) for users to input questions.

[0009] "Means of transmission" refers to the function for sending question data from the terminal to the server.

[0010] "Generative artificial intelligence" refers to artificial intelligence (AI) technology that generates appropriate answers to input questions.

[0011] "Means for generating answers" refers to a function that uses generative artificial intelligence to construct answers to user questions.

[0012] "Means of returning the answer" refers to the function for sending the generated answer from the server to the terminal.

[0013] "Means of display" refers to a function that visually displays the response sent back to the user's device.

[0014] The "natural language processing engine" refers to the technology used to analyze the input question, understand its meaning, and generate an answer.

[0015] The "formatting means" refers to the function of formatting the generated answer into a user-friendly format.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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), etc.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered 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, etc.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system that allows users to input questions regarding business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. Specific embodiments of the system of this invention are described below.

[0038] System Overview

[0039] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[0040] System components

[0041] User's terminal

[0042] The device provides an interface (UI) for the user to input and submit questions. Examples include browser-based forms and dedicated applications.

[0043] Input interface:

[0044] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[0045] Sending function:

[0046] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[0047] Server side

[0048] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server performs the following processes:

[0049] Question received:

[0050] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[0051] Natural language processing and response generation:

[0052] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4®). For example, it might generate an answer such as, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. In this situation..."

[0053] Format and submit your response:

[0054] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[0055] User's device (display of answers)

[0056] The terminal visually displays the response received from the server to the user.

[0057] Received a response:

[0058] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[0059] Show answers:

[0060] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed in the browser to make them easy for the user to understand.

[0061] Specific example

[0062] For example, suppose a user enters a question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. The question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, who then reviews and deepens their understanding of the answer.

[0063] This system allows users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time. This is expected to lead to increased operational efficiency and improved customer satisfaction.

[0064] The following describes the processing flow.

[0065] Step 1:

[0066] User

[0067] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[0068] Step 2:

[0069] terminal

[0070] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[0071] Step 3:

[0072] terminal

[0073] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[0074] Step 4:

[0075] server

[0076] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[0077] Step 5:

[0078] server

[0079] The extracted question content is passed to a natural language processing engine for analysis. Examples of natural language processing engines include spaCy and NLTK.

[0080] Step 6:

[0081] server

[0082] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[0083] Step 7:

[0084] server

[0085] The generated responses are formatted into a user-friendly format such as HTML or Markdown, and then converted into JSON format.

[0086] Step 8:

[0087] server

[0088] The formatted response is sent to the terminal as an HTTP response.

[0089] Step 9:

[0090] terminal

[0091] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[0092] Step 10:

[0093] terminal

[0094] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. For example, the generated answers are displayed at the bottom of a question form.

[0095] Step 11:

[0096] User

[0097] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[0098] (Example 1)

[0099] 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."

[0100] Providing prompt and appropriate answers to questions regarding business terminology and key performance indicators (KPIs) is crucial for improving operational efficiency and customer satisfaction. However, traditional systems often took too long to analyze questions and generate answers, sometimes failing to provide appropriate responses. Furthermore, the lack of means to provide users with formatted answers sometimes made it difficult for them to understand the information.

[0101] 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.

[0102] In this invention, the server includes means for receiving a specific question from a user, means for sending the question to the server, means for generating an answer to the question using generative artificial intelligence, means for returning the generated answer to the user, means for displaying the returned answer to the user, means for the user to input a question using a browser or dedicated application, means for sending the question to the server using JavaScript's AJAX function or fetch API, means for analyzing the question using a natural language processing engine, means for formatting the generated answer into HTML or Markdown format, means for returning the formatted answer to the terminal in JSON format, and means for parsing the received JSON data, dynamically generating HTML, and displaying it to the user. As a result, users can quickly and appropriately obtain answers regarding technical terms and KPIs, which is expected to improve work efficiency and customer satisfaction.

[0103] A "specific question" is a question that describes information that a user wants to know about business terminology or key performance indicators (KPIs).

[0104] "Means for receiving input" refers to an interface that allows users to input questions and send them to the system.

[0105] "Means of sending to the server" refers to the communication function used to send user-entered questions to the server. Specifically, this involves using JavaScript's AJAX functionality or the fetch API.

[0106] "Generative artificial intelligence" refers to artificial intelligence models that generate appropriate answers to input questions. GPT-4 is an example of this type of system.

[0107] "Means for generating answers" refers to a function that uses generative artificial intelligence to generate appropriate answers to questions.

[0108] "Means of return" refers to the communication function used to send the generated response back to the user's device.

[0109] "Means of display" refers to an interface for visually displaying the response sent back from the server to the user.

[0110] A "browser or dedicated application" is software that a user uses to input and submit a question.

[0111] "AJAX functionality, or fetch API," is a JavaScript communication method for sending queries to a server asynchronously.

[0112] A "natural language processing engine" is a software engine used to analyze input questions. Examples include spaCy and NLTK.

[0113] "Means for formatting into HTML or Markdown format" refers to a function for converting the generated response into a format that is easy for the user to read.

[0114] The "means of returning in JSON format" refer to a function that converts the formatted response into JSON format and sends it back to the user's device.

[0115] "Method for parsing JSON data and dynamically generating HTML" refers to a function that analyzes received JSON data, dynamically generates HTML, and displays it to the user.

[0116] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. The system consists of a terminal for users to input questions, a server that receives and analyzes the questions and generates answers, and a terminal for displaying the generated answers.

[0117] User's terminal

[0118] The terminal provides an interface for users to input and submit questions. Examples include browser-based forms and dedicated applications. Users enter questions in a browser's text area or a dedicated application's input field and submit them by pressing a submit button. The terminal converts the entered questions into a specific format and sends them to the server. JavaScript's AJAX functionality or the fetch API is used for this transmission.

[0119] Server side

[0120] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server uses Node.js or Python frameworks (e.g., Express.js or Flask) to receive HTTP POST requests and parse the request body. The server then uses a natural language processing engine (e.g., spaCy or NLTK) to analyze the question content and generates an appropriate answer using generative artificial intelligence (e.g., the GPT-4 model). The generated answer is formatted into HTML or Markdown for readability. This formatted answer is then sent back to the terminal in JSON format. During the formatting process, readability is considered to ensure the user can easily understand the information.

[0121] User's device (display of answers)

[0122] The terminal is responsible for visually displaying the responses received from the server to the user. The terminal receives the HTTP response sent from the server and parses the received JSON data using JavaScript. Based on the parsed data, it dynamically generates HTML and displays it interactively to the user. This display allows the user to easily check the generated responses and use them to their advantage in their work.

[0123] Specific example

[0124] For example, suppose a user enters the question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. This question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as, "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, allowing the user to review and deepen their understanding.

[0125] Example of a prompt

[0126] "Please explain what it means when sales increase compared to the same period last year."

[0127] "Please tell me about measures to take if the customer satisfaction index declines."

[0128] "Could you tell me what impact an increase in inventory turnover would have?"

[0129] This system will enable users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time, which is expected to improve operational efficiency and customer satisfaction.

[0130] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0131] The processing flow of this system's program is explained by dividing it into the following processing steps.

[0132] Step 1:

[0133] The user enters the question using their device's browser or a dedicated application. For example, they might enter "What are the precautions to take if the KPI is not met?" into the text area. The input in this step is the question entered by the user, and the output is the text of that question.

[0134] Step 2:

[0135] The terminal converts the entered question into a specific format and sends it to the server. Specifically, it uses JavaScript's AJAX functionality or the fetch API to send the input text to the server as an HTTP POST request. In this step, the input is the question text entered by the user, and the output is the HTTP POST request sent to the server.

[0136] Step 3:

[0137] The server receives an HTTP POST request and parses its request body. The server uses Node.js or Python frameworks (such as Express.js or Flask) to achieve this. Specifically, it retrieves the question content through `req.body`. The input for this step is an HTTP POST request sent from the terminal, and the output is the parsed question text.

[0138] Step 4:

[0139] The server uses a natural language processing engine to analyze the question content. For example, it uses spaCy or NLTK to tokenize the text and tag parts of speech. The input for this step is the parsed question text, and the output is the tokenized question data.

[0140] Step 5:

[0141] The server generates appropriate answers to questions using a generative artificial intelligence model. Specifically, it invokes the OpenAI® GPT-4 model, takes the analyzed question as a prompt, and generates an answer. The input for this step is tokenized question data, and the output is the generated answer text.

[0142] Step 6:

[0143] The server formats the generated response into HTML or Markdown format. For example, it encloses the generated response text in HTML tags and converts it into a user-friendly format. The input for this step is the generated response text, and the output is the formatted response HTML or Markdown data.

[0144] Step 7:

[0145] The server returns the formatted response to the terminal in JSON format. Specifically, it uses the res.json() method for output. The input for this step is the formatted response data, and the output is the JSON response sent to the terminal.

[0146] Step 8:

[0147] The terminal receives the HTTP response from the server and parses the JSON data. Specifically, it uses JavaScript to receive the HTTP response and the response.json() method to parse the JSON data. The input for this step is the JSON response sent from the server, and the output is the parsed JSON data.

[0148] Step 9:

[0149] The device dynamically generates HTML based on the parsed data and displays it interactively to the user. Specifically, it uses JavaScript DOM manipulation to generate new HTML elements and display them in the browser. The input for this step is parsed JSON data, and the output is the response text displayed in the browser.

[0150] Based on these steps, users can quickly obtain appropriate answers to questions about business terminology and KPIs, which is expected to improve operational efficiency and customer satisfaction.

[0151] (Application Example 1)

[0152] 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."

[0153] In factory settings, there is a need to quickly acquire information on robot status and key performance indicators (KPIs) so that maintenance staff can take appropriate action in real time. Conventional systems are time-consuming to answer questions, making efficient maintenance difficult. Furthermore, there is a lack of systems that provide accurate and easily understandable answers regarding technical jargon and content.

[0154] 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.

[0155] In this invention, the server includes means for receiving specific questions from a user, means for transmitting the questions to the server, means for generating answers to the questions using generative artificial intelligence, means for returning the generated answers to the user, and means for inputting questions regarding the status of robots and key performance indicators in a factory environment to support on-site maintenance work. As a result, maintenance staff can quickly obtain appropriate answers on-site, enabling efficient maintenance work.

[0156] "Means for receiving specific questions from users" refers to means of providing an interface for receiving questions entered by users.

[0157] "Means for sending the question to the server" refers to means that provide protocols and functions for sending questions entered by the user to the server.

[0158] "Means for generating an answer to the question using generative artificial intelligence" refers to means for generating an appropriate answer to a user's question using generative artificial intelligence.

[0159] "Means for returning the generated response to the user" refers to means of providing communication means or protocols for returning the generated response to the user.

[0160] "Means for displaying the returned response to the user" refers to means for providing a screen or interface for the user to view the received response.

[0161] "A means of inputting questions about the status of robots and key performance indicators in a factory environment to support on-site maintenance work" refers to a means of inputting questions about the status of robots and key performance indicators in a factory setting and obtaining answers to those questions to support maintenance work.

[0162] Modes for carrying out the invention

[0163] This invention is a system that supports on-site maintenance work in a factory environment by inputting questions regarding the status of robots and key performance indicators (KPIs). The embodiments of this system will be described in detail below.

[0164] System Overview

[0165] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[0166] System components

[0167] User's terminal

[0168] The device provides an interface (UI) for the user to input and submit questions. For example, a dedicated application installed on a smartphone or tablet falls into this category.

[0169] Input interface:

[0170] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "What are some ways to improve the robot's utilization rate?"

[0171] Sending function:

[0172] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[0173] Server side

[0174] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The following describes the processes performed by the server.

[0175] Question received:

[0176] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[0177] Natural language processing and response generation:

[0178] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4). For example, it might generate an answer such as, "If the robot's operating rate is low, the possible causes are as follows..."

[0179] Format and submit your response:

[0180] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[0181] User's device (display of answers)

[0182] The user's device then visually displays the response received from the server to the user.

[0183] Received a response:

[0184] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[0185] Show answers:

[0186] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed on a smartphone screen to make them easy for the user to understand.

[0187] Specific example

[0188] For example, suppose a user enters a question, "What are some ways to improve the robot's utilization rate?" and presses the send button. The question is sent to the server via a dedicated application on the smartphone. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. The server generates an answer such as, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." This answer is formatted on the server and sent back to the user's smartphone. Finally, the received answer is displayed on the smartphone screen, and the user can review and deepen their understanding of the answer.

[0189] Example of a prompt:

[0190] User question: What are some ways to improve the low utilization rate of robots?

[0191] answer:

[0192] This system allows factory maintenance staff to immediately obtain appropriate solutions on-site and carry out maintenance more efficiently.

[0193] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0194] Step 1:

[0195] Users enter questions using a dedicated application on their smartphone or tablet. The questions are in a format such as, "What are some ways to improve the robot's utilization rate?" The entered questions are captured as text data.

[0196] Step 2:

[0197] The terminal sends the entered question to the server. Specifically, it sends an HTTP POST request to the server using AJAX functionality or the fetch API. This request contains the text data of the question.

[0198] Step 3:

[0199] The server receives an HTTP POST request and extracts the question content from the request body. This process can be performed using frameworks such as Node.js or Python. The input obtained is the text data of the question.

[0200] Step 4:

[0201] The server analyzes the question using a natural language processing engine (e.g., spaCy or NLTK). The purpose of the analysis is to understand the meaning of the question and extract keywords and entities contained within it. For example, entities such as "robot," "operating rate," and "improvement measures" may be extracted.

[0202] Step 5:

[0203] The server uses generative artificial intelligence (e.g., GPT-4) to generate an appropriate answer. It creates a prompt based on the extracted entities and the context of the question, and inputs it into the generative AI. An example of a generated prompt is: "User question: What can I do to improve the robot's utilization rate? Answer: ".

[0204] Step 6:

[0205] A generative artificial intelligence generates a response based on the prompt text. This response might be something like, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." The generated response is returned to the server as text data.

[0206] Step 7:

[0207] The server formats the generated response into a readable format. It uses HTML, Markdown, or other formats to make it easy for the user to understand. This formatted response is then converted to JSON format and sent to the device.

[0208] Step 8:

[0209] The terminal receives an HTTP response from the server. The received response is parsed as JSON data, and the content of the response is retrieved.

[0210] Step 9:

[0211] The system visually displays the answers obtained by the device to the user. JavaScript is used to dynamically generate HTML, which is then displayed on the smartphone or tablet screen. For example, formatted answers are displayed on the screen, making them easy for the user to understand. As a result, maintenance staff can quickly take appropriate action on-site.

[0212] The above steps enable the creation of a system that allows for the rapid acquisition of answers to questions regarding the status of robots and key performance indicators (KPIs) in a factory environment.

[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] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by incorporating an emotion engine that recognizes the user's emotions, it becomes possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[0215] System Overview

[0216] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[0217] System components

[0218] User's terminal

[0219] The device provides an interface (UI) for the user to input questions. Specifically, it includes the following features:

[0220] Input interface:

[0221] Provide a text field and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[0222] Sending function:

[0223] The entered questions are converted into a specific format (e.g., JSON format) and sent to the server. Specifically, JavaScript's AJAX functionality or the fetch API is used.

[0224] Server side

[0225] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. Furthermore, it has a function where an emotion engine analyzes the user's emotions and adjusts the answers accordingly. Specifically, it performs the following processes:

[0226] Question received:

[0227] The server receives an HTTP POST request and extracts the question content from the request body. Examples of frameworks used include Node.js and Python.

[0228] Emotional analysis using an emotion engine:

[0229] The system analyzes user input and other emotional data (e.g., voice, facial expressions) to recognize the user's emotional state. For example, natural language processing engines (such as spaCy and NLTK) and machine learning algorithms are used.

[0230] Natural language processing and response generation:

[0231] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (e.g., GPT-4) is used to generate an appropriate answer. For example, it might say, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. This indicates better-than-expected results."

[0232] Adjusting the answer:

[0233] The emotion engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is feeling dissatisfied, the response will be changed to a more polite and encouraging tone.

[0234] Format and submit your response:

[0235] The adjusted response is formatted into an easy-to-read format (HTML or Markdown), converted to JSON format, and sent back to the device.

[0236] User's device (display of answers)

[0237] The terminal visually displays the response received from the server to the user.

[0238] Received a response:

[0239] The system receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[0240] Show answers:

[0241] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[0242] Specific example

[0243] For example, a user, feeling emotionally frustrated, might type "What should I be careful about if I don't meet my KPIs?" and press the send button. The terminal sends the question to the server. The server receives the question and uses an emotion engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. An answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." is generated. The server adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, and the user reviews it to deepen their understanding.

[0244] This system allows users to quickly receive appropriate responses that are tailored to their emotions, which is expected to improve work efficiency and customer satisfaction.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] User

[0248] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[0249] Step 2:

[0250] terminal

[0251] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[0252] Step 3:

[0253] terminal

[0254] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[0255] Step 4:

[0256] server

[0257] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[0258] Step 5:

[0259] server

[0260] The extracted question content is passed to the emotion engine for analysis. The emotion engine uses natural language processing technology and machine learning algorithms to analyze emotional data from the user's input.

[0261] Step 6:

[0262] server

[0263] The emotion data analyzed by the emotion engine is stored, and the question content is passed to a natural language processing engine for analysis. Examples of such engines include spaCy and NLTK.

[0264] Step 7:

[0265] server

[0266] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[0267] Step 8:

[0268] server

[0269] The generated responses are compared with sentiment data from the sentiment engine, and the tone and content of the responses are adjusted accordingly. For example, if the user is dissatisfied, the tone of the response is changed to be more kind and polite.

[0270] Step 9:

[0271] server

[0272] The adjusted responses are formatted into user-friendly formats such as HTML or Markdown, and then converted into JSON format.

[0273] Step 10:

[0274] server

[0275] The formatted response is sent to the terminal as an HTTP response.

[0276] Step 11:

[0277] terminal

[0278] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[0279] Step 12:

[0280] terminal

[0281] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. Specifically, the generated answers are displayed at the bottom of the question form.

[0282] Step 13:

[0283] User

[0284] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[0285] (Example 2)

[0286] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0287] In a conventional system, the answers generated for the questions input by the user are uniform and do not take into account the emotional state of the user, so the tone of the answers may not be appropriate. In addition, there is also a lack of a method for providing the generated answers in a more friendly and understandable form to the user. Such limitations of the system become factors that hinder the improvement of customer satisfaction and business efficiency.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the emotional state of the user using an emotion analysis engine, means for generating an answer to the question using a generative artificial intelligence, and means for adjusting the generated answer based on the emotional state of the user. Thereby, an answer with an appropriate tone that conforms to the user's emotion can be generated, and it becomes possible to convey the content of the answer to the user more effectively.

[0289] The "user" refers to a person who inputs a question using the system and receives the answer thereto.

[0290] The "means for accepting input" refers to the function of providing an interface for the user to input a question as text.

[0291] The "server" refers to a computer system that receives a question sent from a user and performs analysis and answer generation.

[0292] The "means for transmitting" refers to the communication function of transmitting the question input by the user to the server.

[0293] An "emotion analysis engine" refers to software that analyzes user input and emotional data to recognize the user's emotional state.

[0294] "Generative artificial intelligence" refers to artificial intelligence that analyzes the content of a user's question and generates an appropriate answer based on that analysis.

[0295] "Means of adjustment" refers to a function that modifies the tone and content of the generated response according to the user's emotional state.

[0296] "Methods for formatting into an easy-to-read format" refers to a function that converts the generated and adjusted answers into a format that is easy for users to understand (such as HTML or Markdown).

[0297] "Means of display" refers to functions that visually display formatted answers to the user.

[0298] This invention provides a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[0299] System Overview

[0300] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion analysis engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[0301] System components

[0302] User's terminal

[0303] The terminal provides an interface for the user to input questions. Specifically, the following functions are included:

[0304] Input interface:

[0305] It provides a text field and a send button for the user to input questions. For example, the user can input "Please tell me the countermeasures when the KPI cannot be achieved."

[0306] Sending function:

[0307] It converts the input question into a certain format (e.g., JSON format) and sends it to the server. This function is implemented using AJAX or the fetch API.

[0308] Server side

[0309] The server receives the question sent by the user and is responsible for analyzing and generating an answer. Furthermore, the sentiment analysis engine has the function of analyzing the user's sentiment and adjusting the answer based on it. Specifically, the following processes are carried out:

[0310] Receiving the question:

[0311] The server receives an HTTP POST request and extracts the question content from the request body. Node.js or a Python framework is used for this process.

[0312] Sentiment analysis by the sentiment analysis engine:

[0313] To analyze the user's input content and other sentiment data (e.g., text, expressions, etc.) and recognize the user's sentiment state, a natural language processing engine (e.g., spaCy or NLTK) is used.

[0314] Natural language processing and answer generation:

[0315] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (such as GPT-4) generates an appropriate answer. For example, in response to the question, "What are the countermeasures to take if the KPIs are not achieved?", the answer generated would be, "If the KPIs are not achieved, it is important to first identify the cause and then take appropriate countermeasures."

[0316] Adjusting the answer:

[0317] The sentiment analysis engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is irritated, the tone will be changed to be more polite and encouraging.

[0318] Format and submit your response:

[0319] The adjusted response is formatted into an easy-to-read format (e.g., HTML or Markdown), converted to JSON format, and sent back to the device.

[0320] User's device (display of answers)

[0321] The terminal has the function of visually displaying the response received from the server to the user.

[0322] Received a response:

[0323] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[0324] Show answers:

[0325] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[0326] Specific example

[0327] For example, a user, frustrated, might type, "What should I be careful about if I don't meet my KPIs?" and press the submit button. The terminal sends the question to the server. The server receives the question and uses an emotion analysis engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. The server might generate an answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." The server then adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, allowing the user to review and deepen their understanding.

[0328] This system will not only provide factual answers but also respond in a way that is sensitive to the user's emotions, which is expected to improve operational efficiency and customer satisfaction.

[0329] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0330] Step 1:

[0331] The user enters a question into the terminal's input interface and presses the submit button. The input interface includes a text field and a submit button. The data entered is the user's question text, such as, "Please tell me what to do if the KPI is not achieved."

[0332] Input: User's question text (e.g., "What are the countermeasures to take if the KPI is not met?")

[0333] Output: None

[0334] Step 2:

[0335] The terminal converts the entered question text into a specific format (e.g., JSON format) and sends it to the server. JavaScript's AJAX or fetch API is used for this conversion.

[0336] Input: User's question text

[0337] Data processing: Convert the question text to JSON format (e.g., {"question": "Please tell me what measures to take if the KPI is not achieved"})

[0338] Output: Question data in JSON format

[0339] Step 3:

[0340] The server receives the question as an HTTP POST request. Node.js or Python frameworks are used to extract the question content from the request body.

[0341] Input: Question data in JSON format (Example: {"question": "Please tell us what measures to take if the KPI is not achieved"})

[0342] Data processing: Extracting question text from JSON data

[0343] Output: Question text

[0344] Step 4:

[0345] The server uses an emotion analysis engine (e.g., spaCy or NLTK) to analyze the user's emotional state from the question text. The emotional state identifies conditions such as frustration, joy, and anxiety.

[0346] Input: Question text

[0347] Data processing: Analyzing emotional states using natural language processing algorithms.

[0348] Output: Emotional state (e.g., irritation)

[0349] Step 5:

[0350] The server analyzes the question text using a natural language processing engine (e.g., spaCy) and generates an answer using generative artificial intelligence (e.g., GPT-4).

[0351] Input: Question text

[0352] Data processing: Generate answers using natural language processing and generative artificial intelligence.

[0353] Output: Generated response text (Example: "If KPIs are not met, it is important to identify the cause and take corrective action.")

[0354] Step 6:

[0355] The server adjusts the tone and content of the generated response text based on the user's emotional state recognized by the sentiment analysis engine. For example, if the user is irritated, the response tone will be changed to something more encouraging.

[0356] Input: Generated response text and user's emotional state

[0357] Data processing: Adjust the tone of the response text (e.g., "Don't worry. Even if you don't meet the KPI, you can find the cause and make improvements to succeed next time.")

[0358] Output: Adjusted response text

[0359] Step 7:

[0360] The server formats the adjusted response text into a readable format (e.g., HTML or Markdown), converts it to JSON format, and sends it back to the terminal.

[0361] Input: Adjusted response text

[0362] Data processing: Format the response text into HTML or Markdown format, then convert it to JSON format (e.g., {"response": " Don't worry. Even if you don't meet your KPIs, you can find the cause and make improvements, and you'll succeed next time. "})

[0363] Output: Adjusted response data in JSON format

[0364] Step 8:

[0365] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the answer.

[0366] Input: Adjusted response data in JSON format

[0367] Data processing: Parse the JSON data and extract the response text.

[0368] Output: Adjusted response text

[0369] Step 9:

[0370] The device uses JavaScript to dynamically generate HTML based on the extracted response text and displays it interactively to the user. Specifically, the generated response is displayed at the bottom of the question form.

[0371] Input: Adjusted response text

[0372] Data processing: Dynamically generate HTML and display the answers.

[0373] Output: Displayed answer text

[0374] (Application Example 2)

[0375] 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".

[0376] Conventional question-answering systems failed to consider the user's emotional state when providing answers to their questions. As a result, users often experienced dissatisfaction and anxiety. Furthermore, these systems were insufficient as a means of reducing stress in the work environment, and there was a particular need for a rapid and emotionally empathetic response, especially in workplaces such as factories.

[0377] 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. In this invention, the server includes means including an emotion engine for analyzing the user's emotional state, means for generating an answer to the question using generative artificial intelligence, and means for adjusting the generated answer according to the user's emotional state. This makes it possible to provide an answer that matches the user's emotional state.

[0378] "User emotional state" refers to the psychological state or emotions a user exhibits when entering questions or receiving answers.

[0379] An "emotion engine" refers to a system that analyzes user input and other emotional data to recognize their emotional state.

[0380] "Generative artificial intelligence" refers to artificial intelligence models that generate answers to input questions.

[0381] A "natural language processing engine" refers to the technologies and algorithms used to analyze input natural language text and make its meaning easier to understand.

[0382] "Means of adjustment" refers to functions that modify the tone and content of generated responses based on the user's emotional state.

[0383] A "server" refers to a device or system that receives questions submitted by users, analyzes and generates answers, and performs sentiment analysis using an emotion engine.

[0384] "Means of display" refers to devices or interfaces that visually provide users with the responses returned from the server.

[0385] This invention is a system that allows users to input questions related to business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion engine equipped with emotion analysis capabilities, it becomes possible to adjust the tone and content according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and means for displaying those answers.

[0386] System Overview

[0387] This system includes means for receiving user questions as input, means for sending said questions to a server, means for generating answers to said questions using generative artificial intelligence (e.g., GPT-4), an emotion engine for analyzing the user's emotional state, means for adjusting the generated answers according to the user's emotional state, and means for returning and displaying the adjusted answers to the user.

[0388] Hardware and software to use

[0389] 1. Hardware

[0390] Robots installed inside the factory

[0391] Cloud server (for hosting Flask applications)

[0392] 2. Software

[0393] Flask (a Python web framework for receiving and providing responses to questions)

[0394] TextBlob (emotional analysis)

[0395] OpenAI API (natural language processing and response generation, specifically GPT-4)

[0396] Data flow and calculations

[0397] 1. The user inputs a question to the robot in the factory. For example, "What is causing the production line to be behind schedule?"

[0398] 2. The robot sends this question to the server using Flask. The server receives the HTTP request and extracts the question content from the request body.

[0399] 3. The server uses TextBlob to analyze the question and calculate the emotional polarity. This analysis classifies the user's emotional state as positive, negative, or neutral.

[0400] 4. The server uses the OpenAI API to generate an initial answer to the question.

[0401] 5. Next, adjust the tone of your response based on their emotional state. For example, if they are feeling negative emotions, add comforting words such as, "Don't worry."

[0402] 6. The adjusted response is sent back to the robot and displayed to the user.

[0403] Specific example

[0404] A worker in a factory asks a robot, "What is causing the production line to be delayed?" This question is sent to a server, which uses an emotion engine to recognize that the questioner's emotions are negative. The server generates an initial response, "The production line delay may be due to machine maintenance," and the emotion engine adjusts it by adding, "Don't worry." Ultimately, the response "Don't worry. The production line delay may be due to machine maintenance" is sent back to the user.

[0405] Example of a prompt

[0406] Please answer the following question: "What is causing the production line to be delayed?"

[0407] In this way, it becomes possible to provide responses that are tailored to the user's emotional state, contributing to improvements in the factory's working environment and increased operational efficiency.

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] A user inputs a question into a robot in the factory. For example, they might ask, "What is causing the production line to be behind schedule?" At this stage, the input is text data entered by the user, and the robot receives this text data.

[0411] Step 2:

[0412] The terminal (robot) converts the received question text into JSON format and sends it to the server via an HTTP request. This transmission operation is performed using JavaScript, with the input being the question text and the output being JSON formatted data.

[0413] Step 3:

[0414] The server receives an HTTP request and extracts the question content from the request body. At this stage, the input is in JSON format, from which the question text is extracted. For example, the Flask framework in Python can be used to process the request.

[0415] Step 4:

[0416] The server uses the TextBlob library to analyze the question text and calculate the emotional polarity. The input is the question text, and the output is the emotional state (positive, negative, or neutral). Through this analysis, the server recognizes the user's emotional state.

[0417] Step 5:

[0418] The server uses the OpenAI API to generate an initial answer to a question. The input is the question text, and the output is the generated answer text. Specifically, a generative AI model (e.g., GPT-4) is used to generate the answer.

[0419] Step 6:

[0420] The server uses an emotion engine to generate responses, adjusting their tone and content according to the user's emotional state. The input is the generated response and the emotional state, and the output is the adjusted response. For example, in the case of a negative emotion, comforting words such as "Don't worry" are added before the response.

[0421] Step 7:

[0422] The server converts the formatted response into JSON format and sends it back to the robot (terminal) via an HTTP response. The input is the formatted response text, and the output is data in JSON format.

[0423] Step 8:

[0424] The robot (terminal) receives JSON data sent back from the server, parses the data, and obtains the answer. The input is data in JSON format, and the output is the answer text.

[0425] Step 9:

[0426] The robot (terminal) displays the acquired answer text to the user. Specifically, it displays the generated answer at the bottom of the user's question form. The input is the answer text, and the output is the answer displayed on the user's screen.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] [Second Embodiment]

[0431] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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".

[0443] This invention is a system that allows users to input questions regarding business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. Specific embodiments of the system of this invention are described below.

[0444] System Overview

[0445] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[0446] System components

[0447] User's terminal

[0448] The device provides an interface (UI) for the user to input and submit questions. Examples include browser-based forms and dedicated applications.

[0449] Input interface:

[0450] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[0451] Sending function:

[0452] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[0453] Server side

[0454] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server performs the following processes:

[0455] Question received:

[0456] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[0457] Natural language processing and response generation:

[0458] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4). For example, it might generate an answer such as, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. In this situation..."

[0459] Format and submit your response:

[0460] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[0461] User's device (display of answers)

[0462] The terminal visually displays the response received from the server to the user.

[0463] Received a response:

[0464] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[0465] Show answers:

[0466] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed in the browser to make them easy for the user to understand.

[0467] Specific example

[0468] For example, suppose a user enters a question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. The question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, who then reviews and deepens their understanding of the answer.

[0469] This system allows users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time. This is expected to lead to increased operational efficiency and improved customer satisfaction.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] User

[0473] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[0474] Step 2:

[0475] terminal

[0476] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[0477] Step 3:

[0478] terminal

[0479] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[0480] Step 4:

[0481] server

[0482] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[0483] Step 5:

[0484] server

[0485] The extracted question content is passed to a natural language processing engine for analysis. Examples of natural language processing engines include spaCy and NLTK.

[0486] Step 6:

[0487] server

[0488] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[0489] Step 7:

[0490] server

[0491] The generated responses are formatted into a user-friendly format such as HTML or Markdown, and then converted into JSON format.

[0492] Step 8:

[0493] server

[0494] The formatted response is sent to the terminal as an HTTP response.

[0495] Step 9:

[0496] terminal

[0497] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[0498] Step 10:

[0499] terminal

[0500] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. For example, the generated answers are displayed at the bottom of a question form.

[0501] Step 11:

[0502] User

[0503] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[0504] (Example 1)

[0505] 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."

[0506] Providing prompt and appropriate answers to questions regarding business terminology and key performance indicators (KPIs) is crucial for improving operational efficiency and customer satisfaction. However, traditional systems often took too long to analyze questions and generate answers, sometimes failing to provide appropriate responses. Furthermore, the lack of means to provide users with formatted answers sometimes made it difficult for them to understand the information.

[0507] 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.

[0508] In this invention, the server includes means for receiving a specific question from a user, means for sending the question to the server, means for generating an answer to the question using generative artificial intelligence, means for returning the generated answer to the user, means for displaying the returned answer to the user, means for the user to input a question using a browser or dedicated application, means for sending the question to the server using JavaScript's AJAX function or fetch API, means for analyzing the question using a natural language processing engine, means for formatting the generated answer into HTML or Markdown format, means for returning the formatted answer to the terminal in JSON format, and means for parsing the received JSON data, dynamically generating HTML, and displaying it to the user. As a result, users can quickly and appropriately obtain answers regarding technical terms and KPIs, which is expected to improve work efficiency and customer satisfaction.

[0509] A "specific question" is a question that describes information that a user wants to know about business terminology or key performance indicators (KPIs).

[0510] "Means for receiving input" refers to an interface that allows users to input questions and send them to the system.

[0511] "Means of sending to the server" refers to the communication function used to send user-entered questions to the server. Specifically, this involves using JavaScript's AJAX functionality or the fetch API.

[0512] "Generative artificial intelligence" refers to artificial intelligence models that generate appropriate answers to input questions. GPT-4 is an example of this type of system.

[0513] "Means for generating answers" refers to a function that uses generative artificial intelligence to generate appropriate answers to questions.

[0514] "Means of return" refers to the communication function used to send the generated response back to the user's device.

[0515] "Means of display" refers to an interface for visually displaying the response sent back from the server to the user.

[0516] A "browser or dedicated application" is software that a user uses to input and submit a question.

[0517] "AJAX functionality, or fetch API," is a JavaScript communication method for sending queries to a server asynchronously.

[0518] A "natural language processing engine" is a software engine used to analyze input questions. Examples include spaCy and NLTK.

[0519] "Means for formatting into HTML or Markdown format" refers to a function for converting the generated response into a format that is easy for the user to read.

[0520] The "means of returning in JSON format" refer to a function that converts the formatted response into JSON format and sends it back to the user's device.

[0521] "Method for parsing JSON data and dynamically generating HTML" refers to a function that analyzes received JSON data, dynamically generates HTML, and displays it to the user.

[0522] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. The system consists of a terminal for users to input questions, a server that receives and analyzes the questions and generates answers, and a terminal for displaying the generated answers.

[0523] User's terminal

[0524] The terminal provides an interface for users to input and submit questions. Examples include browser-based forms and dedicated applications. Users enter questions in a browser's text area or a dedicated application's input field and submit them by pressing a submit button. The terminal converts the entered questions into a specific format and sends them to the server. JavaScript's AJAX functionality or the fetch API is used for this transmission.

[0525] Server side

[0526] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server uses Node.js or Python frameworks (e.g., Express.js or Flask) to receive HTTP POST requests and parse the request body. The server then uses a natural language processing engine (e.g., spaCy or NLTK) to analyze the question content and generates an appropriate answer using generative artificial intelligence (e.g., the GPT-4 model). The generated answer is formatted into HTML or Markdown for readability. This formatted answer is then sent back to the terminal in JSON format. During the formatting process, readability is considered to ensure the user can easily understand the information.

[0527] User's device (display of answers)

[0528] The terminal is responsible for visually displaying the responses received from the server to the user. The terminal receives the HTTP response sent from the server and parses the received JSON data using JavaScript. Based on the parsed data, it dynamically generates HTML and displays it interactively to the user. This display allows the user to easily check the generated responses and use them to their advantage in their work.

[0529] Specific example

[0530] For example, suppose a user enters the question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. This question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as, "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, allowing the user to review and deepen their understanding.

[0531] Example of a prompt

[0532] "Please explain what it means when sales increase compared to the same period last year."

[0533] "Please tell me about measures to take if the customer satisfaction index declines."

[0534] "Could you tell me what impact an increase in inventory turnover would have?"

[0535] This system will enable users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time, which is expected to improve operational efficiency and customer satisfaction.

[0536] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0537] The processing flow of this system's program is explained by dividing it into the following processing steps.

[0538] Step 1:

[0539] The user enters the question using their device's browser or a dedicated application. For example, they might enter "What are the precautions to take if the KPI is not met?" into the text area. The input in this step is the question entered by the user, and the output is the text of that question.

[0540] Step 2:

[0541] The terminal converts the entered question into a specific format and sends it to the server. Specifically, it uses JavaScript's AJAX functionality or the fetch API to send the input text to the server as an HTTP POST request. In this step, the input is the question text entered by the user, and the output is the HTTP POST request sent to the server.

[0542] Step 3:

[0543] The server receives an HTTP POST request and parses its request body. The server uses Node.js or Python frameworks (such as Express.js or Flask) to achieve this. Specifically, it retrieves the question content through `req.body`. The input for this step is an HTTP POST request sent from the terminal, and the output is the parsed question text.

[0544] Step 4:

[0545] The server uses a natural language processing engine to analyze the question content. For example, it uses spaCy or NLTK to tokenize the text and tag parts of speech. The input for this step is the parsed question text, and the output is the tokenized question data.

[0546] Step 5:

[0547] The server generates appropriate answers to questions using a generative artificial intelligence model. Specifically, it invokes OpenAI's GPT-4 model, takes the analyzed question as a prompt, and generates an answer. The input for this step is tokenized question data, and the output is the generated answer text.

[0548] Step 6:

[0549] The server formats the generated response into HTML or Markdown format. For example, it encloses the generated response text in HTML tags and converts it into a user-friendly format. The input for this step is the generated response text, and the output is the formatted response HTML or Markdown data.

[0550] Step 7:

[0551] The server returns the formatted response to the terminal in JSON format. Specifically, it uses the res.json() method for output. The input for this step is the formatted response data, and the output is the JSON response sent to the terminal.

[0552] Step 8:

[0553] The terminal receives the HTTP response from the server and parses the JSON data. Specifically, it uses JavaScript to receive the HTTP response and the response.json() method to parse the JSON data. The input for this step is the JSON response sent from the server, and the output is the parsed JSON data.

[0554] Step 9:

[0555] The device dynamically generates HTML based on the parsed data and displays it interactively to the user. Specifically, it uses JavaScript DOM manipulation to generate new HTML elements and display them in the browser. The input for this step is parsed JSON data, and the output is the response text displayed in the browser.

[0556] Based on these steps, users can quickly obtain appropriate answers to questions about business terminology and KPIs, which is expected to improve operational efficiency and customer satisfaction.

[0557] (Application Example 1)

[0558] 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."

[0559] In factory settings, there is a need to quickly acquire information on robot status and key performance indicators (KPIs) so that maintenance staff can take appropriate action in real time. Conventional systems are time-consuming to answer questions, making efficient maintenance difficult. Furthermore, there is a lack of systems that provide accurate and easily understandable answers regarding technical jargon and content.

[0560] 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.

[0561] In this invention, the server includes means for receiving specific questions from a user, means for transmitting the questions to the server, means for generating answers to the questions using generative artificial intelligence, means for returning the generated answers to the user, and means for inputting questions regarding the status of robots and key performance indicators in a factory environment to support on-site maintenance work. As a result, maintenance staff can quickly obtain appropriate answers on-site, enabling efficient maintenance work.

[0562] "Means for receiving specific questions from users" refers to means of providing an interface for receiving questions entered by users.

[0563] "Means for sending the question to the server" refers to means that provide protocols and functions for sending questions entered by the user to the server.

[0564] "Means for generating an answer to the question using generative artificial intelligence" refers to means for generating an appropriate answer to a user's question using generative artificial intelligence.

[0565] "Means for returning the generated response to the user" refers to means of providing communication means or protocols for returning the generated response to the user.

[0566] "Means for displaying the returned response to the user" refers to means for providing a screen or interface for the user to view the received response.

[0567] "A means of inputting questions about the status of robots and key performance indicators in a factory environment to support on-site maintenance work" refers to a means of inputting questions about the status of robots and key performance indicators in a factory setting and obtaining answers to those questions to support maintenance work.

[0568] Modes for carrying out the invention

[0569] This invention is a system that supports on-site maintenance work in a factory environment by inputting questions regarding the status of robots and key performance indicators (KPIs). The embodiments of this system will be described in detail below.

[0570] System Overview

[0571] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[0572] System components

[0573] User's terminal

[0574] The device provides an interface (UI) for the user to input and submit questions. For example, a dedicated application installed on a smartphone or tablet falls into this category.

[0575] Input interface:

[0576] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "What are some ways to improve the robot's utilization rate?"

[0577] Sending function:

[0578] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[0579] Server side

[0580] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The following describes the processes performed by the server.

[0581] Question received:

[0582] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[0583] Natural language processing and response generation:

[0584] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4). For example, it might generate an answer such as, "If the robot's operating rate is low, the possible causes are as follows..."

[0585] Format and submit your response:

[0586] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[0587] User's device (display of answers)

[0588] The user's device then visually displays the response received from the server to the user.

[0589] Received a response:

[0590] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[0591] Show answers:

[0592] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed on a smartphone screen to make them easy for the user to understand.

[0593] Specific example

[0594] For example, suppose a user enters a question, "What are some ways to improve the robot's utilization rate?" and presses the send button. The question is sent to the server via a dedicated application on the smartphone. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. The server generates an answer such as, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." This answer is formatted on the server and sent back to the user's smartphone. Finally, the received answer is displayed on the smartphone screen, and the user can review and deepen their understanding of the answer.

[0595] Example of a prompt:

[0596] User question: What are some ways to improve the low utilization rate of robots?

[0597] answer:

[0598] This system allows factory maintenance staff to immediately obtain appropriate solutions on-site and carry out maintenance more efficiently.

[0599] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0600] Step 1:

[0601] Users enter questions using a dedicated application on their smartphone or tablet. The questions are in a format such as, "What are some ways to improve the robot's utilization rate?" The entered questions are captured as text data.

[0602] Step 2:

[0603] The terminal sends the entered question to the server. Specifically, it sends an HTTP POST request to the server using AJAX functionality or the fetch API. This request contains the text data of the question.

[0604] Step 3:

[0605] The server receives an HTTP POST request and extracts the question content from the request body. This process can be performed using frameworks such as Node.js or Python. The input obtained is the text data of the question.

[0606] Step 4:

[0607] The server analyzes the question using a natural language processing engine (e.g., spaCy or NLTK). The purpose of the analysis is to understand the meaning of the question and extract keywords and entities contained within it. For example, entities such as "robot," "operating rate," and "improvement measures" may be extracted.

[0608] Step 5:

[0609] The server uses generative artificial intelligence (e.g., GPT-4) to generate an appropriate answer. It creates a prompt based on the extracted entities and the context of the question, and inputs it into the generative AI. An example of a generated prompt is: "User question: What can I do to improve the robot's utilization rate? Answer: ".

[0610] Step 6:

[0611] A generative artificial intelligence generates a response based on the prompt text. This response might be something like, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." The generated response is returned to the server as text data.

[0612] Step 7:

[0613] The server formats the generated response into a readable format. It uses HTML, Markdown, or other formats to make it easy for the user to understand. This formatted response is then converted to JSON format and sent to the device.

[0614] Step 8:

[0615] The terminal receives an HTTP response from the server. The received response is parsed as JSON data, and the content of the response is retrieved.

[0616] Step 9:

[0617] The system visually displays the answers obtained by the device to the user. JavaScript is used to dynamically generate HTML, which is then displayed on the smartphone or tablet screen. For example, formatted answers are displayed on the screen, making them easy for the user to understand. As a result, maintenance staff can quickly take appropriate action on-site.

[0618] The above steps enable the creation of a system that allows for the rapid acquisition of answers to questions regarding the status of robots and key performance indicators (KPIs) in a factory environment.

[0619] 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.

[0620] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by incorporating an emotion engine that recognizes the user's emotions, it becomes possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[0621] System Overview

[0622] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[0623] System components

[0624] User's terminal

[0625] The device provides an interface (UI) for the user to input questions. Specifically, it includes the following features:

[0626] Input interface:

[0627] Provide a text field and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[0628] Sending function:

[0629] The entered questions are converted into a specific format (e.g., JSON format) and sent to the server. Specifically, JavaScript's AJAX functionality or the fetch API is used.

[0630] Server side

[0631] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. Furthermore, it has a function where an emotion engine analyzes the user's emotions and adjusts the answers accordingly. Specifically, it performs the following processes:

[0632] Question received:

[0633] The server receives an HTTP POST request and extracts the question content from the request body. Examples of frameworks used include Node.js and Python.

[0634] Emotional analysis using an emotion engine:

[0635] The system analyzes user input and other emotional data (e.g., voice, facial expressions) to recognize the user's emotional state. For example, natural language processing engines (such as spaCy and NLTK) and machine learning algorithms are used.

[0636] Natural language processing and response generation:

[0637] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (e.g., GPT-4) is used to generate an appropriate answer. For example, it might say, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. This indicates better-than-expected results."

[0638] Adjusting the answer:

[0639] The emotion engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is feeling dissatisfied, the response will be changed to a more polite and encouraging tone.

[0640] Format and submit your response:

[0641] The adjusted response is formatted into an easy-to-read format (HTML or Markdown), converted to JSON format, and sent back to the device.

[0642] User's device (display of answers)

[0643] The terminal visually displays the response received from the server to the user.

[0644] Received a response:

[0645] The system receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[0646] Show answers:

[0647] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[0648] Specific example

[0649] For example, a user, feeling emotionally frustrated, might type "What should I be careful about if I don't meet my KPIs?" and press the send button. The terminal sends the question to the server. The server receives the question and uses an emotion engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. An answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." is generated. The server adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, and the user reviews it to deepen their understanding.

[0650] This system allows users to quickly receive appropriate responses that are tailored to their emotions, which is expected to improve work efficiency and customer satisfaction.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] User

[0654] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[0655] Step 2:

[0656] terminal

[0657] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[0658] Step 3:

[0659] terminal

[0660] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[0661] Step 4:

[0662] server

[0663] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[0664] Step 5:

[0665] server

[0666] The extracted question content is passed to the emotion engine for analysis. The emotion engine uses natural language processing technology and machine learning algorithms to analyze emotional data from the user's input.

[0667] Step 6:

[0668] server

[0669] The emotion data analyzed by the emotion engine is stored, and the question content is passed to a natural language processing engine for analysis. Examples of such engines include spaCy and NLTK.

[0670] Step 7:

[0671] server

[0672] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[0673] Step 8:

[0674] server

[0675] The generated responses are compared with sentiment data from the sentiment engine, and the tone and content of the responses are adjusted accordingly. For example, if the user is dissatisfied, the tone of the response is changed to be more kind and polite.

[0676] Step 9:

[0677] server

[0678] The adjusted responses are formatted into user-friendly formats such as HTML or Markdown, and then converted into JSON format.

[0679] Step 10:

[0680] server

[0681] The formatted response is sent to the terminal as an HTTP response.

[0682] Step 11:

[0683] terminal

[0684] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[0685] Step 12:

[0686] terminal

[0687] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. Specifically, the generated answers are displayed at the bottom of the question form.

[0688] Step 13:

[0689] User

[0690] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[0691] (Example 2)

[0692] 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".

[0693] Traditional systems generate uniform answers to user-inputted questions, failing to consider the user's emotional state, resulting in inappropriate tone in the responses. Furthermore, there is a lack of methods to present generated answers in a more user-friendly and easily understandable format. These system limitations hinder improvements in customer satisfaction and operational efficiency.

[0694] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state using an emotion analysis engine, means for generating an answer to the question using generative artificial intelligence, and means for adjusting the generated answer based on the user's emotional state. This makes it possible to generate an answer with an appropriate tone that is attuned to the user's emotions, and for the content of the answer to be conveyed to the user more effectively.

[0695] A "user" refers to a person who uses the system to input questions and receive answers.

[0696] "Means for receiving input" refers to a function that provides an interface for users to input questions as text.

[0697] A "server" refers to a computer system that receives questions submitted by users, analyzes them, and generates answers.

[0698] "Means of transmission" refers to the communication function that sends the questions entered by the user to the server.

[0699] An "emotion analysis engine" refers to software that analyzes user input and emotional data to recognize the user's emotional state.

[0700] "Generative artificial intelligence" refers to artificial intelligence that analyzes the content of a user's question and generates an appropriate answer based on that analysis.

[0701] "Means of adjustment" refers to a function that modifies the tone and content of the generated response according to the user's emotional state.

[0702] "Methods for formatting into an easy-to-read format" refers to a function that converts the generated and adjusted answers into a format that is easy for users to understand (such as HTML or Markdown).

[0703] "Means of display" refers to functions that visually display formatted answers to the user.

[0704] This invention provides a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[0705] System Overview

[0706] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion analysis engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[0707] System components

[0708] User's terminal

[0709] The terminal provides an interface for the user to enter questions. Specifically, it includes the following features:

[0710] Input interface:

[0711] Provide a text field and a submit button for the user to enter a question. For example, the user could enter, "Please tell me what to do if the KPI is not met."

[0712] Sending function:

[0713] The entered questions are converted into a specific format (e.g., JSON) and sent to the server. This function is implemented using AJAX or the fetch API.

[0714] Server side

[0715] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. Furthermore, it has a sentiment analysis engine that analyzes the user's emotions and adjusts the answers accordingly. Specifically, the following processes are performed:

[0716] Question received:

[0717] The server receives an HTTP POST request and extracts the question content from the request body. Node.js or Python frameworks are used for this process.

[0718] Emotional analysis using an emotion analysis engine:

[0719] A natural language processing engine (such as spaCy or NLTK) is used to analyze user input and other emotional data (e.g., text, facial expressions, etc.) to recognize the user's emotional state.

[0720] Natural language processing and response generation:

[0721] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (such as GPT-4) generates an appropriate answer. For example, in response to the question, "What are the countermeasures to take if the KPIs are not achieved?", the answer generated would be, "If the KPIs are not achieved, it is important to first identify the cause and then take appropriate countermeasures."

[0722] Adjusting the answer:

[0723] The sentiment analysis engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is irritated, the tone will be changed to be more polite and encouraging.

[0724] Format and submit your response:

[0725] The adjusted response is formatted into an easy-to-read format (e.g., HTML or Markdown), converted to JSON format, and sent back to the device.

[0726] User's device (display of answers)

[0727] The terminal has the function of visually displaying the response received from the server to the user.

[0728] Received a response:

[0729] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[0730] Show answers:

[0731] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[0732] Specific example

[0733] For example, a user, frustrated, might type, "What should I be careful about if I don't meet my KPIs?" and press the submit button. The terminal sends the question to the server. The server receives the question and uses an emotion analysis engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. The server might generate an answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." The server then adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, allowing the user to review and deepen their understanding.

[0734] This system will not only provide factual answers but also respond in a way that is sensitive to the user's emotions, which is expected to improve operational efficiency and customer satisfaction.

[0735] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0736] Step 1:

[0737] The user enters a question into the terminal's input interface and presses the submit button. The input interface includes a text field and a submit button. The data entered is the user's question text, such as, "Please tell me what to do if the KPI is not achieved."

[0738] Input: User's question text (e.g., "What are the countermeasures to take if the KPI is not met?")

[0739] Output: None

[0740] Step 2:

[0741] The terminal converts the entered question text into a specific format (e.g., JSON format) and sends it to the server. JavaScript's AJAX or fetch API is used for this conversion.

[0742] Input: User's question text

[0743] Data processing: Convert the question text to JSON format (e.g., {"question": "Please tell me what measures to take if the KPI is not achieved"})

[0744] Output: Question data in JSON format

[0745] Step 3:

[0746] The server receives the question as an HTTP POST request. Node.js or Python frameworks are used to extract the question content from the request body.

[0747] Input: Question data in JSON format (Example: {"question": "Please tell us what measures to take if the KPI is not achieved"})

[0748] Data processing: Extracting question text from JSON data

[0749] Output: Question text

[0750] Step 4:

[0751] The server uses an emotion analysis engine (e.g., spaCy or NLTK) to analyze the user's emotional state from the question text. The emotional state identifies conditions such as frustration, joy, and anxiety.

[0752] Input: Question text

[0753] Data processing: Analyzing emotional states using natural language processing algorithms.

[0754] Output: Emotional state (e.g., irritation)

[0755] Step 5:

[0756] The server analyzes the question text using a natural language processing engine (e.g., spaCy) and generates an answer using generative artificial intelligence (e.g., GPT-4).

[0757] Input: Question text

[0758] Data processing: Generate answers using natural language processing and generative artificial intelligence.

[0759] Output: Generated response text (Example: "If KPIs are not met, it is important to identify the cause and take corrective action.")

[0760] Step 6:

[0761] The server adjusts the tone and content of the generated response text based on the user's emotional state recognized by the sentiment analysis engine. For example, if the user is irritated, the response tone will be changed to something more encouraging.

[0762] Input: Generated response text and user's emotional state

[0763] Data processing: Adjust the tone of the response text (e.g., "Don't worry. Even if you don't meet the KPI, you can find the cause and make improvements to succeed next time.")

[0764] Output: Adjusted response text

[0765] Step 7:

[0766] The server formats the adjusted response text into a readable format (e.g., HTML or Markdown), converts it to JSON format, and sends it back to the terminal.

[0767] Input: Adjusted response text

[0768] Data processing: Format the response text into HTML or Markdown format, then convert it to JSON format (e.g., {"response": " Don't worry. Even if you don't meet your KPIs, you can find the cause and make improvements, and you'll succeed next time. "})

[0769] Output: Adjusted response data in JSON format

[0770] Step 8:

[0771] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the answer.

[0772] Input: Adjusted response data in JSON format

[0773] Data processing: Parse the JSON data and extract the response text.

[0774] Output: Adjusted response text

[0775] Step 9:

[0776] The device uses JavaScript to dynamically generate HTML based on the extracted response text and displays it interactively to the user. Specifically, the generated response is displayed at the bottom of the question form.

[0777] Input: Adjusted response text

[0778] Data processing: Dynamically generate HTML and display the answers.

[0779] Output: Displayed answer text

[0780] (Application Example 2)

[0781] 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."

[0782] Conventional question-answering systems failed to consider the user's emotional state when providing answers to their questions. As a result, users often experienced dissatisfaction and anxiety. Furthermore, these systems were insufficient as a means of reducing stress in the work environment, and there was a particular need for a rapid and emotionally empathetic response, especially in workplaces such as factories.

[0783] 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. In this invention, the server includes means including an emotion engine for analyzing the user's emotional state, means for generating an answer to the question using generative artificial intelligence, and means for adjusting the generated answer according to the user's emotional state. This makes it possible to provide an answer that matches the user's emotional state.

[0784] "User emotional state" refers to the psychological state or emotions a user exhibits when entering questions or receiving answers.

[0785] An "emotion engine" refers to a system that analyzes user input and other emotional data to recognize their emotional state.

[0786] "Generative artificial intelligence" refers to artificial intelligence models that generate answers to input questions.

[0787] A "natural language processing engine" refers to the technologies and algorithms used to analyze input natural language text and make its meaning easier to understand.

[0788] "Means of adjustment" refers to functions that modify the tone and content of generated responses based on the user's emotional state.

[0789] A "server" refers to a device or system that receives questions submitted by users, analyzes and generates answers, and performs sentiment analysis using an emotion engine.

[0790] "Means of display" refers to devices or interfaces that visually provide users with the responses returned from the server.

[0791] This invention is a system that allows users to input questions related to business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion engine equipped with emotion analysis capabilities, it becomes possible to adjust the tone and content according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and means for displaying those answers.

[0792] System Overview

[0793] This system includes means for receiving user questions as input, means for sending said questions to a server, means for generating answers to said questions using generative artificial intelligence (e.g., GPT-4), an emotion engine for analyzing the user's emotional state, means for adjusting the generated answers according to the user's emotional state, and means for returning and displaying the adjusted answers to the user.

[0794] Hardware and software to use

[0795] 1. Hardware

[0796] Robots installed inside the factory

[0797] Cloud server (for hosting Flask applications)

[0798] 2. Software

[0799] Flask (a Python web framework for receiving and providing responses to questions)

[0800] TextBlob (emotional analysis)

[0801] OpenAI API (natural language processing and response generation, specifically GPT-4)

[0802] Data flow and calculations

[0803] 1. The user inputs a question to the robot in the factory. For example, "What is causing the production line to be behind schedule?"

[0804] 2. The robot sends this question to the server using Flask. The server receives the HTTP request and extracts the question content from the request body.

[0805] 3. The server uses TextBlob to analyze the question and calculate the emotional polarity. This analysis classifies the user's emotional state as positive, negative, or neutral.

[0806] 4. The server uses the OpenAI API to generate an initial answer to the question.

[0807] 5. Next, adjust the tone of your response based on their emotional state. For example, if they are feeling negative emotions, add comforting words such as, "Don't worry."

[0808] 6. The adjusted response is sent back to the robot and displayed to the user.

[0809] Specific example

[0810] A worker in a factory asks a robot, "What is causing the production line to be delayed?" This question is sent to a server, which uses an emotion engine to recognize that the questioner's emotions are negative. The server generates an initial response, "The production line delay may be due to machine maintenance," and the emotion engine adjusts it by adding, "Don't worry." Ultimately, the response "Don't worry. The production line delay may be due to machine maintenance" is sent back to the user.

[0811] Example of a prompt

[0812] Please answer the following question: "What is causing the production line to be delayed?"

[0813] In this way, it becomes possible to provide responses that are tailored to the user's emotional state, contributing to improvements in the factory's working environment and increased operational efficiency.

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] A user inputs a question into a robot in the factory. For example, they might ask, "What is causing the production line to be behind schedule?" At this stage, the input is text data entered by the user, and the robot receives this text data.

[0817] Step 2:

[0818] The terminal (robot) converts the received question text into JSON format and sends it to the server via an HTTP request. This transmission operation is performed using JavaScript, with the input being the question text and the output being JSON formatted data.

[0819] Step 3:

[0820] The server receives an HTTP request and extracts the question content from the request body. At this stage, the input is in JSON format, from which the question text is extracted. For example, the Flask framework in Python can be used to process the request.

[0821] Step 4:

[0822] The server uses the TextBlob library to analyze the question text and calculate the emotional polarity. The input is the question text, and the output is the emotional state (positive, negative, or neutral). Through this analysis, the server recognizes the user's emotional state.

[0823] Step 5:

[0824] The server uses the OpenAI API to generate an initial answer to a question. The input is the question text, and the output is the generated answer text. Specifically, a generative AI model (e.g., GPT-4) is used to generate the answer.

[0825] Step 6:

[0826] The server uses an emotion engine to generate responses, adjusting their tone and content according to the user's emotional state. The input is the generated response and the emotional state, and the output is the adjusted response. For example, in the case of a negative emotion, comforting words such as "Don't worry" are added before the response.

[0827] Step 7:

[0828] The server converts the formatted response into JSON format and sends it back to the robot (terminal) via an HTTP response. The input is the formatted response text, and the output is data in JSON format.

[0829] Step 8:

[0830] The robot (terminal) receives JSON data sent back from the server, parses the data, and obtains the answer. The input is data in JSON format, and the output is the answer text.

[0831] Step 9:

[0832] The robot (terminal) displays the acquired answer text to the user. Specifically, it displays the generated answer at the bottom of the user's question form. The input is the answer text, and the output is the answer displayed on the user's screen.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] [Third Embodiment]

[0837] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0838] 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.

[0839] 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).

[0840] 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.

[0841] 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.

[0842] 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).

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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".

[0849] This invention is a system that allows users to input questions regarding business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. Specific embodiments of the system of this invention are described below.

[0850] System Overview

[0851] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[0852] System components

[0853] User's terminal

[0854] The device provides an interface (UI) for the user to input and submit questions. Examples include browser-based forms and dedicated applications.

[0855] Input interface:

[0856] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[0857] Sending function:

[0858] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[0859] Server side

[0860] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server performs the following processes:

[0861] Question received:

[0862] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[0863] Natural language processing and response generation:

[0864] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4). For example, it might generate an answer such as, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. In this situation..."

[0865] Format and submit your response:

[0866] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[0867] User's device (display of answers)

[0868] The terminal visually displays the response received from the server to the user.

[0869] Received a response:

[0870] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[0871] Show answers:

[0872] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed in the browser to make them easy for the user to understand.

[0873] Specific example

[0874] For example, suppose a user enters a question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. The question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, who then reviews and deepens their understanding of the answer.

[0875] This system allows users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time. This is expected to lead to increased operational efficiency and improved customer satisfaction.

[0876] The following describes the processing flow.

[0877] Step 1:

[0878] User

[0879] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[0880] Step 2:

[0881] terminal

[0882] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[0883] Step 3:

[0884] terminal

[0885] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[0886] Step 4:

[0887] server

[0888] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[0889] Step 5:

[0890] server

[0891] The extracted question content is passed to a natural language processing engine for analysis. Examples of natural language processing engines include spaCy and NLTK.

[0892] Step 6:

[0893] server

[0894] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[0895] Step 7:

[0896] server

[0897] The generated responses are formatted into a user-friendly format such as HTML or Markdown, and then converted into JSON format.

[0898] Step 8:

[0899] server

[0900] The formatted response is sent to the terminal as an HTTP response.

[0901] Step 9:

[0902] terminal

[0903] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[0904] Step 10:

[0905] terminal

[0906] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. For example, the generated answers are displayed at the bottom of a question form.

[0907] Step 11:

[0908] User

[0909] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[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] Providing prompt and appropriate answers to questions regarding business terminology and key performance indicators (KPIs) is crucial for improving operational efficiency and customer satisfaction. However, traditional systems often took too long to analyze questions and generate answers, sometimes failing to provide appropriate responses. Furthermore, the lack of means to provide users with formatted answers sometimes made it difficult for them to understand the information.

[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 receiving a specific question from a user, means for sending the question to the server, means for generating an answer to the question using generative artificial intelligence, means for returning the generated answer to the user, means for displaying the returned answer to the user, means for the user to input a question using a browser or dedicated application, means for sending the question to the server using JavaScript's AJAX function or fetch API, means for analyzing the question using a natural language processing engine, means for formatting the generated answer into HTML or Markdown format, means for returning the formatted answer to the terminal in JSON format, and means for parsing the received JSON data, dynamically generating HTML, and displaying it to the user. As a result, users can quickly and appropriately obtain answers regarding technical terms and KPIs, which is expected to improve work efficiency and customer satisfaction.

[0915] A "specific question" is a question that describes information that a user wants to know about business terminology or key performance indicators (KPIs).

[0916] "Means for receiving input" refers to an interface that allows users to input questions and send them to the system.

[0917] "Means of sending to the server" refers to the communication function used to send user-entered questions to the server. Specifically, this involves using JavaScript's AJAX functionality or the fetch API.

[0918] "Generative artificial intelligence" refers to artificial intelligence models that generate appropriate answers to input questions. GPT-4 is an example of this type of system.

[0919] "Means for generating answers" refers to a function that uses generative artificial intelligence to generate appropriate answers to questions.

[0920] "Means of return" refers to the communication function used to send the generated response back to the user's device.

[0921] "Means of display" refers to an interface for visually displaying the response sent back from the server to the user.

[0922] A "browser or dedicated application" is software that a user uses to input and submit a question.

[0923] "AJAX functionality, or fetch API," is a JavaScript communication method for sending queries to a server asynchronously.

[0924] A "natural language processing engine" is a software engine used to analyze input questions. Examples include spaCy and NLTK.

[0925] "Means for formatting into HTML or Markdown format" refers to a function for converting the generated response into a format that is easy for the user to read.

[0926] The "means of returning in JSON format" refer to a function that converts the formatted response into JSON format and sends it back to the user's device.

[0927] "Method for parsing JSON data and dynamically generating HTML" refers to a function that analyzes received JSON data, dynamically generates HTML, and displays it to the user.

[0928] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. The system consists of a terminal for users to input questions, a server that receives and analyzes the questions and generates answers, and a terminal for displaying the generated answers.

[0929] User's terminal

[0930] The terminal provides an interface for users to input and submit questions. Examples include browser-based forms and dedicated applications. Users enter questions in a browser's text area or a dedicated application's input field and submit them by pressing a submit button. The terminal converts the entered questions into a specific format and sends them to the server. JavaScript's AJAX functionality or the fetch API is used for this transmission.

[0931] Server side

[0932] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server uses Node.js or Python frameworks (e.g., Express.js or Flask) to receive HTTP POST requests and parse the request body. The server then uses a natural language processing engine (e.g., spaCy or NLTK) to analyze the question content and generates an appropriate answer using generative artificial intelligence (e.g., the GPT-4 model). The generated answer is formatted into HTML or Markdown for readability. This formatted answer is then sent back to the terminal in JSON format. During the formatting process, readability is considered to ensure the user can easily understand the information.

[0933] User's device (display of answers)

[0934] The terminal is responsible for visually displaying the responses received from the server to the user. The terminal receives the HTTP response sent from the server and parses the received JSON data using JavaScript. Based on the parsed data, it dynamically generates HTML and displays it interactively to the user. This display allows the user to easily check the generated responses and use them to their advantage in their work.

[0935] Specific example

[0936] For example, suppose a user enters the question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. This question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as, "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, allowing the user to review and deepen their understanding.

[0937] Example of a prompt

[0938] "Please explain what it means when sales increase compared to the same period last year."

[0939] "Please tell me about measures to take if the customer satisfaction index declines."

[0940] "Could you tell me what impact an increase in inventory turnover would have?"

[0941] This system will enable users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time, which is expected to improve operational efficiency and customer satisfaction.

[0942] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0943] The processing flow of this system's program is explained by dividing it into the following processing steps.

[0944] Step 1:

[0945] The user enters the question using their device's browser or a dedicated application. For example, they might enter "What are the precautions to take if the KPI is not met?" into the text area. The input in this step is the question entered by the user, and the output is the text of that question.

[0946] Step 2:

[0947] The terminal converts the entered question into a specific format and sends it to the server. Specifically, it uses JavaScript's AJAX functionality or the fetch API to send the input text to the server as an HTTP POST request. In this step, the input is the question text entered by the user, and the output is the HTTP POST request sent to the server.

[0948] Step 3:

[0949] The server receives an HTTP POST request and parses its request body. The server uses Node.js or Python frameworks (such as Express.js or Flask) to achieve this. Specifically, it retrieves the question content through `req.body`. The input for this step is an HTTP POST request sent from the terminal, and the output is the parsed question text.

[0950] Step 4:

[0951] The server uses a natural language processing engine to analyze the question content. For example, it uses spaCy or NLTK to tokenize the text and tag parts of speech. The input for this step is the parsed question text, and the output is the tokenized question data.

[0952] Step 5:

[0953] The server generates appropriate answers to questions using a generative artificial intelligence model. Specifically, it invokes OpenAI's GPT-4 model, takes the analyzed question as a prompt, and generates an answer. The input for this step is tokenized question data, and the output is the generated answer text.

[0954] Step 6:

[0955] The server formats the generated response into HTML or Markdown format. For example, it encloses the generated response text in HTML tags and converts it into a user-friendly format. The input for this step is the generated response text, and the output is the formatted response HTML or Markdown data.

[0956] Step 7:

[0957] The server returns the formatted response to the terminal in JSON format. Specifically, it uses the res.json() method for output. The input for this step is the formatted response data, and the output is the JSON response sent to the terminal.

[0958] Step 8:

[0959] The terminal receives the HTTP response from the server and parses the JSON data. Specifically, it uses JavaScript to receive the HTTP response and the response.json() method to parse the JSON data. The input for this step is the JSON response sent from the server, and the output is the parsed JSON data.

[0960] Step 9:

[0961] The device dynamically generates HTML based on the parsed data and displays it interactively to the user. Specifically, it uses JavaScript DOM manipulation to generate new HTML elements and display them in the browser. The input for this step is parsed JSON data, and the output is the response text displayed in the browser.

[0962] Based on these steps, users can quickly obtain appropriate answers to questions about business terminology and KPIs, which is expected to improve operational efficiency and customer satisfaction.

[0963] (Application Example 1)

[0964] 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."

[0965] In factory settings, there is a need to quickly acquire information on robot status and key performance indicators (KPIs) so that maintenance staff can take appropriate action in real time. Conventional systems are time-consuming to answer questions, making efficient maintenance difficult. Furthermore, there is a lack of systems that provide accurate and easily understandable answers regarding technical jargon and content.

[0966] 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.

[0967] In this invention, the server includes means for receiving specific questions from a user, means for transmitting the questions to the server, means for generating answers to the questions using generative artificial intelligence, means for returning the generated answers to the user, and means for inputting questions regarding the status of robots and key performance indicators in a factory environment to support on-site maintenance work. As a result, maintenance staff can quickly obtain appropriate answers on-site, enabling efficient maintenance work.

[0968] "Means for receiving specific questions from users" refers to means of providing an interface for receiving questions entered by users.

[0969] "Means for sending the question to the server" refers to means that provide protocols and functions for sending questions entered by the user to the server.

[0970] "Means for generating an answer to the question using generative artificial intelligence" refers to means for generating an appropriate answer to a user's question using generative artificial intelligence.

[0971] "Means for returning the generated response to the user" refers to means of providing communication means or protocols for returning the generated response to the user.

[0972] "Means for displaying the returned response to the user" refers to means for providing a screen or interface for the user to view the received response.

[0973] "A means of inputting questions about the status of robots and key performance indicators in a factory environment to support on-site maintenance work" refers to a means of inputting questions about the status of robots and key performance indicators in a factory setting and obtaining answers to those questions to support maintenance work.

[0974] Modes for carrying out the invention

[0975] This invention is a system that supports on-site maintenance work in a factory environment by inputting questions regarding the status of robots and key performance indicators (KPIs). The embodiments of this system will be described in detail below.

[0976] System Overview

[0977] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[0978] System components

[0979] User's terminal

[0980] The device provides an interface (UI) for the user to input and submit questions. For example, a dedicated application installed on a smartphone or tablet falls into this category.

[0981] Input interface:

[0982] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "What are some ways to improve the robot's utilization rate?"

[0983] Sending function:

[0984] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[0985] Server side

[0986] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The following describes the processes performed by the server.

[0987] Question received:

[0988] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[0989] Natural language processing and response generation:

[0990] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4). For example, it might generate an answer such as, "If the robot's operating rate is low, the possible causes are as follows..."

[0991] Format and submit your response:

[0992] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[0993] User's device (display of answers)

[0994] The user's device then visually displays the response received from the server to the user.

[0995] Received a response:

[0996] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[0997] Show answers:

[0998] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed on a smartphone screen to make them easy for the user to understand.

[0999] Specific example

[1000] For example, suppose a user enters a question, "What are some ways to improve the robot's utilization rate?" and presses the send button. The question is sent to the server via a dedicated application on the smartphone. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. The server generates an answer such as, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." This answer is formatted on the server and sent back to the user's smartphone. Finally, the received answer is displayed on the smartphone screen, and the user can review and deepen their understanding of the answer.

[1001] Example of a prompt:

[1002] User question: What are some ways to improve the low utilization rate of robots?

[1003] answer:

[1004] This system allows factory maintenance staff to immediately obtain appropriate solutions on-site and carry out maintenance more efficiently.

[1005] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1006] Step 1:

[1007] Users enter questions using a dedicated application on their smartphone or tablet. The questions are in a format such as, "What are some ways to improve the robot's utilization rate?" The entered questions are captured as text data.

[1008] Step 2:

[1009] The terminal sends the entered question to the server. Specifically, it sends an HTTP POST request to the server using AJAX functionality or the fetch API. This request contains the text data of the question.

[1010] Step 3:

[1011] The server receives an HTTP POST request and extracts the question content from the request body. This process can be performed using frameworks such as Node.js or Python. The input obtained is the text data of the question.

[1012] Step 4:

[1013] The server analyzes the question using a natural language processing engine (e.g., spaCy or NLTK). The purpose of the analysis is to understand the meaning of the question and extract keywords and entities contained within it. For example, entities such as "robot," "operating rate," and "improvement measures" may be extracted.

[1014] Step 5:

[1015] The server uses generative artificial intelligence (e.g., GPT-4) to generate an appropriate answer. It creates a prompt based on the extracted entities and the context of the question, and inputs it into the generative AI. An example of a generated prompt is: "User question: What can I do to improve the robot's utilization rate? Answer: ".

[1016] Step 6:

[1017] A generative artificial intelligence generates a response based on the prompt text. This response might be something like, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." The generated response is returned to the server as text data.

[1018] Step 7:

[1019] The server formats the generated response into a readable format. It uses HTML, Markdown, or other formats to make it easy for the user to understand. This formatted response is then converted to JSON format and sent to the device.

[1020] Step 8:

[1021] The terminal receives an HTTP response from the server. The received response is parsed as JSON data, and the content of the response is retrieved.

[1022] Step 9:

[1023] The system visually displays the answers obtained by the device to the user. JavaScript is used to dynamically generate HTML, which is then displayed on the smartphone or tablet screen. For example, formatted answers are displayed on the screen, making them easy for the user to understand. As a result, maintenance staff can quickly take appropriate action on-site.

[1024] The above steps enable the creation of a system that allows for the rapid acquisition of answers to questions regarding the status of robots and key performance indicators (KPIs) in a factory environment.

[1025] 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.

[1026] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by incorporating an emotion engine that recognizes the user's emotions, it becomes possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[1027] System Overview

[1028] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[1029] System components

[1030] User's terminal

[1031] The device provides an interface (UI) for the user to input questions. Specifically, it includes the following features:

[1032] Input interface:

[1033] Provide a text field and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[1034] Sending function:

[1035] The entered questions are converted into a specific format (e.g., JSON format) and sent to the server. Specifically, JavaScript's AJAX functionality or the fetch API is used.

[1036] Server side

[1037] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. Furthermore, it has a function where an emotion engine analyzes the user's emotions and adjusts the answers accordingly. Specifically, it performs the following processes:

[1038] Question received:

[1039] The server receives an HTTP POST request and extracts the question content from the request body. Examples of frameworks used include Node.js and Python.

[1040] Emotional analysis using an emotion engine:

[1041] The system analyzes user input and other emotional data (e.g., voice, facial expressions) to recognize the user's emotional state. For example, natural language processing engines (such as spaCy and NLTK) and machine learning algorithms are used.

[1042] Natural language processing and response generation:

[1043] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (e.g., GPT-4) is used to generate an appropriate answer. For example, it might say, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. This indicates better-than-expected results."

[1044] Adjusting the answer:

[1045] The emotion engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is feeling dissatisfied, the response will be changed to a more polite and encouraging tone.

[1046] Format and submit your response:

[1047] The adjusted response is formatted into an easy-to-read format (HTML or Markdown), converted to JSON format, and sent back to the device.

[1048] User's device (display of answers)

[1049] The terminal visually displays the response received from the server to the user.

[1050] Received a response:

[1051] The system receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[1052] Show answers:

[1053] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[1054] Specific example

[1055] For example, a user, feeling emotionally frustrated, might type "What should I be careful about if I don't meet my KPIs?" and press the send button. The terminal sends the question to the server. The server receives the question and uses an emotion engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. An answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." is generated. The server adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, and the user reviews it to deepen their understanding.

[1056] This system allows users to quickly receive appropriate responses that are tailored to their emotions, which is expected to improve work efficiency and customer satisfaction.

[1057] The following describes the processing flow.

[1058] Step 1:

[1059] User

[1060] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[1061] Step 2:

[1062] terminal

[1063] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[1064] Step 3:

[1065] terminal

[1066] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[1067] Step 4:

[1068] server

[1069] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[1070] Step 5:

[1071] server

[1072] The extracted question content is passed to the emotion engine for analysis. The emotion engine uses natural language processing technology and machine learning algorithms to analyze emotional data from the user's input.

[1073] Step 6:

[1074] server

[1075] The emotion data analyzed by the emotion engine is stored, and the question content is passed to a natural language processing engine for analysis. Examples of such engines include spaCy and NLTK.

[1076] Step 7:

[1077] server

[1078] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[1079] Step 8:

[1080] server

[1081] The generated responses are compared with sentiment data from the sentiment engine, and the tone and content of the responses are adjusted accordingly. For example, if the user is dissatisfied, the tone of the response is changed to be more kind and polite.

[1082] Step 9:

[1083] server

[1084] The adjusted responses are formatted into user-friendly formats such as HTML or Markdown, and then converted into JSON format.

[1085] Step 10:

[1086] server

[1087] The formatted response is sent to the terminal as an HTTP response.

[1088] Step 11:

[1089] terminal

[1090] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[1091] Step 12:

[1092] terminal

[1093] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. Specifically, the generated answers are displayed at the bottom of the question form.

[1094] Step 13:

[1095] User

[1096] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[1097] (Example 2)

[1098] 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."

[1099] Traditional systems generate uniform answers to user-inputted questions, failing to consider the user's emotional state, resulting in inappropriate tone in the responses. Furthermore, there is a lack of methods to present generated answers in a more user-friendly and easily understandable format. These system limitations hinder improvements in customer satisfaction and operational efficiency.

[1100] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state using an emotion analysis engine, means for generating an answer to the question using generative artificial intelligence, and means for adjusting the generated answer based on the user's emotional state. This makes it possible to generate an answer with an appropriate tone that is attuned to the user's emotions, and for the content of the answer to be conveyed to the user more effectively.

[1101] A "user" refers to a person who uses the system to input questions and receive answers.

[1102] "Means for receiving input" refers to a function that provides an interface for users to input questions as text.

[1103] A "server" refers to a computer system that receives questions submitted by users, analyzes them, and generates answers.

[1104] "Means of transmission" refers to the communication function that sends the questions entered by the user to the server.

[1105] An "emotion analysis engine" refers to software that analyzes user input and emotional data to recognize the user's emotional state.

[1106] "Generative artificial intelligence" refers to artificial intelligence that analyzes the content of a user's question and generates an appropriate answer based on that analysis.

[1107] "Means of adjustment" refers to a function that modifies the tone and content of the generated response according to the user's emotional state.

[1108] "Methods for formatting into an easy-to-read format" refers to a function that converts the generated and adjusted answers into a format that is easy for users to understand (such as HTML or Markdown).

[1109] "Means of display" refers to functions that visually display formatted answers to the user.

[1110] This invention provides a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[1111] System Overview

[1112] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion analysis engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[1113] System components

[1114] User's terminal

[1115] The terminal provides an interface for the user to enter questions. Specifically, it includes the following features:

[1116] Input interface:

[1117] Provide a text field and a submit button for the user to enter a question. For example, the user could enter, "Please tell me what to do if the KPI is not met."

[1118] Sending function:

[1119] The entered questions are converted into a specific format (e.g., JSON) and sent to the server. This function is implemented using AJAX or the fetch API.

[1120] Server side

[1121] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. Furthermore, it has a sentiment analysis engine that analyzes the user's emotions and adjusts the answers accordingly. Specifically, the following processes are performed:

[1122] Question received:

[1123] The server receives an HTTP POST request and extracts the question content from the request body. Node.js or Python frameworks are used for this process.

[1124] Emotional analysis using an emotion analysis engine:

[1125] A natural language processing engine (such as spaCy or NLTK) is used to analyze user input and other emotional data (e.g., text, facial expressions, etc.) to recognize the user's emotional state.

[1126] Natural language processing and response generation:

[1127] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (such as GPT-4) generates an appropriate answer. For example, in response to the question, "What are the countermeasures to take if the KPIs are not achieved?", the answer generated would be, "If the KPIs are not achieved, it is important to first identify the cause and then take appropriate countermeasures."

[1128] Adjusting the answer:

[1129] The sentiment analysis engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is irritated, the tone will be changed to be more polite and encouraging.

[1130] Format and submit your response:

[1131] The adjusted response is formatted into an easy-to-read format (e.g., HTML or Markdown), converted to JSON format, and sent back to the device.

[1132] User's device (display of answers)

[1133] The terminal has the function of visually displaying the response received from the server to the user.

[1134] Received a response:

[1135] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[1136] Show answers:

[1137] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[1138] Specific example

[1139] For example, a user, frustrated, might type, "What should I be careful about if I don't meet my KPIs?" and press the submit button. The terminal sends the question to the server. The server receives the question and uses an emotion analysis engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. The server might generate an answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." The server then adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, allowing the user to review and deepen their understanding.

[1140] This system will not only provide factual answers but also respond in a way that is sensitive to the user's emotions, which is expected to improve operational efficiency and customer satisfaction.

[1141] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1142] Step 1:

[1143] The user enters a question into the terminal's input interface and presses the submit button. The input interface includes a text field and a submit button. The data entered is the user's question text, such as, "Please tell me what to do if the KPI is not achieved."

[1144] Input: User's question text (e.g., "What are the countermeasures to take if the KPI is not met?")

[1145] Output: None

[1146] Step 2:

[1147] The terminal converts the entered question text into a specific format (e.g., JSON format) and sends it to the server. JavaScript's AJAX or fetch API is used for this conversion.

[1148] Input: User's question text

[1149] Data processing: Convert the question text to JSON format (e.g., {"question": "Please tell me what measures to take if the KPI is not achieved"})

[1150] Output: Question data in JSON format

[1151] Step 3:

[1152] The server receives the question as an HTTP POST request. Node.js or Python frameworks are used to extract the question content from the request body.

[1153] Input: Question data in JSON format (Example: {"question": "Please tell us what measures to take if the KPI is not achieved"})

[1154] Data processing: Extracting question text from JSON data

[1155] Output: Question text

[1156] Step 4:

[1157] The server uses an emotion analysis engine (e.g., spaCy or NLTK) to analyze the user's emotional state from the question text. The emotional state identifies conditions such as frustration, joy, and anxiety.

[1158] Input: Question text

[1159] Data processing: Analyzing emotional states using natural language processing algorithms.

[1160] Output: Emotional state (e.g., irritation)

[1161] Step 5:

[1162] The server analyzes the question text using a natural language processing engine (e.g., spaCy) and generates an answer using generative artificial intelligence (e.g., GPT-4).

[1163] Input: Question text

[1164] Data processing: Generate answers using natural language processing and generative artificial intelligence.

[1165] Output: Generated response text (Example: "If KPIs are not met, it is important to identify the cause and take corrective action.")

[1166] Step 6:

[1167] The server adjusts the tone and content of the generated response text based on the user's emotional state recognized by the sentiment analysis engine. For example, if the user is irritated, the response tone will be changed to something more encouraging.

[1168] Input: Generated response text and user's emotional state

[1169] Data processing: Adjust the tone of the response text (e.g., "Don't worry. Even if you don't meet the KPI, you can find the cause and make improvements to succeed next time.")

[1170] Output: Adjusted response text

[1171] Step 7:

[1172] The server formats the adjusted response text into a readable format (e.g., HTML or Markdown), converts it to JSON format, and sends it back to the terminal.

[1173] Input: Adjusted response text

[1174] Data processing: Format the response text into HTML or Markdown format, then convert it to JSON format (e.g., {"response": " Don't worry. Even if you don't meet your KPIs, you can find the cause and make improvements, and you'll succeed next time. "})

[1175] Output: Adjusted response data in JSON format

[1176] Step 8:

[1177] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the answer.

[1178] Input: Adjusted response data in JSON format

[1179] Data processing: Parse the JSON data and extract the response text.

[1180] Output: Adjusted response text

[1181] Step 9:

[1182] The device uses JavaScript to dynamically generate HTML based on the extracted response text and displays it interactively to the user. Specifically, the generated response is displayed at the bottom of the question form.

[1183] Input: Adjusted response text

[1184] Data processing: Dynamically generate HTML and display the answers.

[1185] Output: Displayed answer text

[1186] (Application Example 2)

[1187] 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."

[1188] Conventional question-answering systems failed to consider the user's emotional state when providing answers to their questions. As a result, users often experienced dissatisfaction and anxiety. Furthermore, these systems were insufficient as a means of reducing stress in the work environment, and there was a particular need for a rapid and emotionally empathetic response, especially in workplaces such as factories.

[1189] 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. In this invention, the server includes means including an emotion engine for analyzing the user's emotional state, means for generating an answer to the question using generative artificial intelligence, and means for adjusting the generated answer according to the user's emotional state. This makes it possible to provide an answer that matches the user's emotional state.

[1190] "User emotional state" refers to the psychological state or emotions a user exhibits when entering questions or receiving answers.

[1191] An "emotion engine" refers to a system that analyzes user input and other emotional data to recognize their emotional state.

[1192] "Generative artificial intelligence" refers to artificial intelligence models that generate answers to input questions.

[1193] A "natural language processing engine" refers to the technologies and algorithms used to analyze input natural language text and make its meaning easier to understand.

[1194] "Means of adjustment" refers to functions that modify the tone and content of generated responses based on the user's emotional state.

[1195] A "server" refers to a device or system that receives questions submitted by users, analyzes and generates answers, and performs sentiment analysis using an emotion engine.

[1196] "Means of display" refers to devices or interfaces that visually provide users with the responses returned from the server.

[1197] This invention is a system that allows users to input questions related to business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion engine equipped with emotion analysis capabilities, it becomes possible to adjust the tone and content according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and means for displaying those answers.

[1198] System Overview

[1199] This system includes means for receiving user questions as input, means for sending said questions to a server, means for generating answers to said questions using generative artificial intelligence (e.g., GPT-4), an emotion engine for analyzing the user's emotional state, means for adjusting the generated answers according to the user's emotional state, and means for returning and displaying the adjusted answers to the user.

[1200] Hardware and software to use

[1201] 1. Hardware

[1202] Robots installed inside the factory

[1203] Cloud server (for hosting Flask applications)

[1204] 2. Software

[1205] Flask (a Python web framework for receiving and providing responses to questions)

[1206] TextBlob (emotional analysis)

[1207] OpenAI API (natural language processing and response generation, specifically GPT-4)

[1208] Data flow and calculations

[1209] 1. The user inputs a question to the robot in the factory. For example, "What is causing the production line to be behind schedule?"

[1210] 2. The robot sends this question to the server using Flask. The server receives the HTTP request and extracts the question content from the request body.

[1211] 3. The server uses TextBlob to analyze the question and calculate the emotional polarity. This analysis classifies the user's emotional state as positive, negative, or neutral.

[1212] 4. The server uses the OpenAI API to generate an initial answer to the question.

[1213] 5. Next, adjust the tone of your response based on their emotional state. For example, if they are feeling negative emotions, add comforting words such as, "Don't worry."

[1214] 6. The adjusted response is sent back to the robot and displayed to the user.

[1215] Specific example

[1216] A worker in a factory asks a robot, "What is causing the production line to be delayed?" This question is sent to a server, which uses an emotion engine to recognize that the questioner's emotions are negative. The server generates an initial response, "The production line delay may be due to machine maintenance," and the emotion engine adjusts it by adding, "Don't worry." Ultimately, the response "Don't worry. The production line delay may be due to machine maintenance" is sent back to the user.

[1217] Example of a prompt

[1218] Please answer the following question: "What is causing the production line to be delayed?"

[1219] In this way, it becomes possible to provide responses that are tailored to the user's emotional state, contributing to improvements in the factory's working environment and increased operational efficiency.

[1220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1221] Step 1:

[1222] A user inputs a question into a robot in the factory. For example, they might ask, "What is causing the production line to be behind schedule?" At this stage, the input is text data entered by the user, and the robot receives this text data.

[1223] Step 2:

[1224] The terminal (robot) converts the received question text into JSON format and sends it to the server via an HTTP request. This transmission operation is performed using JavaScript, with the input being the question text and the output being JSON formatted data.

[1225] Step 3:

[1226] The server receives an HTTP request and extracts the question content from the request body. At this stage, the input is in JSON format, from which the question text is extracted. For example, the Flask framework in Python can be used to process the request.

[1227] Step 4:

[1228] The server uses the TextBlob library to analyze the question text and calculate the emotional polarity. The input is the question text, and the output is the emotional state (positive, negative, or neutral). Through this analysis, the server recognizes the user's emotional state.

[1229] Step 5:

[1230] The server uses the OpenAI API to generate an initial answer to a question. The input is the question text, and the output is the generated answer text. Specifically, a generative AI model (e.g., GPT-4) is used to generate the answer.

[1231] Step 6:

[1232] The server uses an emotion engine to generate responses, adjusting their tone and content according to the user's emotional state. The input is the generated response and the emotional state, and the output is the adjusted response. For example, in the case of a negative emotion, comforting words such as "Don't worry" are added before the response.

[1233] Step 7:

[1234] The server converts the formatted response into JSON format and sends it back to the robot (terminal) via an HTTP response. The input is the formatted response text, and the output is data in JSON format.

[1235] Step 8:

[1236] The robot (terminal) receives JSON data sent back from the server, parses the data, and obtains the answer. The input is data in JSON format, and the output is the answer text.

[1237] Step 9:

[1238] The robot (terminal) displays the acquired answer text to the user. Specifically, it displays the generated answer at the bottom of the user's question form. The input is the answer text, and the output is the answer displayed on the user's screen.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] [Fourth Embodiment]

[1243] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1244] 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.

[1245] 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).

[1246] 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.

[1247] 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.

[1248] 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).

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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".

[1256] This invention is a system that allows users to input questions regarding business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. Specific embodiments of the system of this invention are described below.

[1257] System Overview

[1258] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[1259] System components

[1260] User's terminal

[1261] The device provides an interface (UI) for the user to input and submit questions. Examples include browser-based forms and dedicated applications.

[1262] Input interface:

[1263] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[1264] Sending function:

[1265] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[1266] Server side

[1267] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server performs the following processes:

[1268] Question received:

[1269] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[1270] Natural language processing and response generation:

[1271] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4). For example, it might generate an answer such as, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. In this situation..."

[1272] Format and submit your response:

[1273] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[1274] User's device (display of answers)

[1275] The terminal visually displays the response received from the server to the user.

[1276] Received a response:

[1277] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[1278] Show answers:

[1279] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed in the browser to make them easy for the user to understand.

[1280] Specific example

[1281] For example, suppose a user enters a question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. The question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, who then reviews and deepens their understanding of the answer.

[1282] This system allows users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time. This is expected to lead to increased operational efficiency and improved customer satisfaction.

[1283] The following describes the processing flow.

[1284] Step 1:

[1285] User

[1286] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[1287] Step 2:

[1288] terminal

[1289] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[1290] Step 3:

[1291] terminal

[1292] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[1293] Step 4:

[1294] server

[1295] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[1296] Step 5:

[1297] server

[1298] The extracted question content is passed to a natural language processing engine for analysis. Examples of natural language processing engines include spaCy and NLTK.

[1299] Step 6:

[1300] server

[1301] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[1302] Step 7:

[1303] server

[1304] The generated responses are formatted into a user-friendly format such as HTML or Markdown, and then converted into JSON format.

[1305] Step 8:

[1306] server

[1307] The formatted response is sent to the terminal as an HTTP response.

[1308] Step 9:

[1309] terminal

[1310] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[1311] Step 10:

[1312] terminal

[1313] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. For example, the generated answers are displayed at the bottom of a question form.

[1314] Step 11:

[1315] User

[1316] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[1317] (Example 1)

[1318] 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".

[1319] Providing prompt and appropriate answers to questions regarding business terminology and key performance indicators (KPIs) is crucial for improving operational efficiency and customer satisfaction. However, traditional systems often took too long to analyze questions and generate answers, sometimes failing to provide appropriate responses. Furthermore, the lack of means to provide users with formatted answers sometimes made it difficult for them to understand the information.

[1320] 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.

[1321] In this invention, the server includes means for receiving a specific question from a user, means for sending the question to the server, means for generating an answer to the question using generative artificial intelligence, means for returning the generated answer to the user, means for displaying the returned answer to the user, means for the user to input a question using a browser or dedicated application, means for sending the question to the server using JavaScript's AJAX function or fetch API, means for analyzing the question using a natural language processing engine, means for formatting the generated answer into HTML or Markdown format, means for returning the formatted answer to the terminal in JSON format, and means for parsing the received JSON data, dynamically generating HTML, and displaying it to the user. As a result, users can quickly and appropriately obtain answers regarding technical terms and KPIs, which is expected to improve work efficiency and customer satisfaction.

[1322] A "specific question" is a question that describes information that a user wants to know about business terminology or key performance indicators (KPIs).

[1323] "Means for receiving input" refers to an interface that allows users to input questions and send them to the system.

[1324] "Means of sending to the server" refers to the communication function used to send user-entered questions to the server. Specifically, this involves using JavaScript's AJAX functionality or the fetch API.

[1325] "Generative artificial intelligence" refers to artificial intelligence models that generate appropriate answers to input questions. GPT-4 is an example of this type of system.

[1326] "Means for generating answers" refers to a function that uses generative artificial intelligence to generate appropriate answers to questions.

[1327] "Means of return" refers to the communication function used to send the generated response back to the user's device.

[1328] "Means of display" refers to an interface for visually displaying the response sent back from the server to the user.

[1329] A "browser or dedicated application" is software that a user uses to input and submit a question.

[1330] "AJAX functionality, or fetch API," is a JavaScript communication method for sending queries to a server asynchronously.

[1331] A "natural language processing engine" is a software engine used to analyze input questions. Examples include spaCy and NLTK.

[1332] "Means for formatting into HTML or Markdown format" refers to a function for converting the generated response into a format that is easy for the user to read.

[1333] The "means of returning in JSON format" refer to a function that converts the formatted response into JSON format and sends it back to the user's device.

[1334] "Method for parsing JSON data and dynamically generating HTML" refers to a function that analyzes received JSON data, dynamically generates HTML, and displays it to the user.

[1335] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. The system consists of a terminal for users to input questions, a server that receives and analyzes the questions and generates answers, and a terminal for displaying the generated answers.

[1336] User's terminal

[1337] The terminal provides an interface for users to input and submit questions. Examples include browser-based forms and dedicated applications. Users enter questions in a browser's text area or a dedicated application's input field and submit them by pressing a submit button. The terminal converts the entered questions into a specific format and sends them to the server. JavaScript's AJAX functionality or the fetch API is used for this transmission.

[1338] Server side

[1339] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The server uses Node.js or Python frameworks (e.g., Express.js or Flask) to receive HTTP POST requests and parse the request body. The server then uses a natural language processing engine (e.g., spaCy or NLTK) to analyze the question content and generates an appropriate answer using generative artificial intelligence (e.g., the GPT-4 model). The generated answer is formatted into HTML or Markdown for readability. This formatted answer is then sent back to the terminal in JSON format. During the formatting process, readability is considered to ensure the user can easily understand the information.

[1340] User's device (display of answers)

[1341] The terminal is responsible for visually displaying the responses received from the server to the user. The terminal receives the HTTP response sent from the server and parses the received JSON data using JavaScript. Based on the parsed data, it dynamically generates HTML and displays it interactively to the user. This display allows the user to easily check the generated responses and use them to their advantage in their work.

[1342] Specific example

[1343] For example, suppose a user enters the question, "What are some things to keep in mind if we fail to meet our KPIs?" and presses the send button. This question is sent from the device to the server. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. An answer such as, "If you fail to meet your KPIs, it is important to analyze the cause and consider improvement measures..." is generated, formatted on the server side, and sent back to the device. Finally, the device displays the received answer to the user, allowing the user to review and deepen their understanding.

[1344] Example of a prompt

[1345] "Please explain what it means when sales increase compared to the same period last year."

[1346] "Please tell me about measures to take if the customer satisfaction index declines."

[1347] "Could you tell me what impact an increase in inventory turnover would have?"

[1348] This system will enable users to obtain accurate and appropriate answers to questions about technical terms and KPIs in a short amount of time, which is expected to improve operational efficiency and customer satisfaction.

[1349] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1350] The processing flow of this system's program is explained by dividing it into the following processing steps.

[1351] Step 1:

[1352] The user enters the question using their device's browser or a dedicated application. For example, they might enter "What are the precautions to take if the KPI is not met?" into the text area. The input in this step is the question entered by the user, and the output is the text of that question.

[1353] Step 2:

[1354] The terminal converts the entered question into a specific format and sends it to the server. Specifically, it uses JavaScript's AJAX functionality or the fetch API to send the input text to the server as an HTTP POST request. In this step, the input is the question text entered by the user, and the output is the HTTP POST request sent to the server.

[1355] Step 3:

[1356] The server receives an HTTP POST request and parses its request body. The server uses Node.js or Python frameworks (such as Express.js or Flask) to achieve this. Specifically, it retrieves the question content through `req.body`. The input for this step is an HTTP POST request sent from the terminal, and the output is the parsed question text.

[1357] Step 4:

[1358] The server uses a natural language processing engine to analyze the question content. For example, it uses spaCy or NLTK to tokenize the text and tag parts of speech. The input for this step is the parsed question text, and the output is the tokenized question data.

[1359] Step 5:

[1360] The server generates appropriate answers to questions using a generative artificial intelligence model. Specifically, it invokes OpenAI's GPT-4 model, takes the analyzed question as a prompt, and generates an answer. The input for this step is tokenized question data, and the output is the generated answer text.

[1361] Step 6:

[1362] The server formats the generated response into HTML or Markdown format. For example, it encloses the generated response text in HTML tags and converts it into a user-friendly format. The input for this step is the generated response text, and the output is the formatted response HTML or Markdown data.

[1363] Step 7:

[1364] The server returns the formatted response to the terminal in JSON format. Specifically, it uses the res.json() method for output. The input for this step is the formatted response data, and the output is the JSON response sent to the terminal.

[1365] Step 8:

[1366] The terminal receives the HTTP response from the server and parses the JSON data. Specifically, it uses JavaScript to receive the HTTP response and the response.json() method to parse the JSON data. The input for this step is the JSON response sent from the server, and the output is the parsed JSON data.

[1367] Step 9:

[1368] The device dynamically generates HTML based on the parsed data and displays it interactively to the user. Specifically, it uses JavaScript DOM manipulation to generate new HTML elements and display them in the browser. The input for this step is parsed JSON data, and the output is the response text displayed in the browser.

[1369] Based on these steps, users can quickly obtain appropriate answers to questions about business terminology and KPIs, which is expected to improve operational efficiency and customer satisfaction.

[1370] (Application Example 1)

[1371] 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".

[1372] In factory settings, there is a need to quickly acquire information on robot status and key performance indicators (KPIs) so that maintenance staff can take appropriate action in real time. Conventional systems are time-consuming to answer questions, making efficient maintenance difficult. Furthermore, there is a lack of systems that provide accurate and easily understandable answers regarding technical jargon and content.

[1373] 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.

[1374] In this invention, the server includes means for receiving specific questions from a user, means for transmitting the questions to the server, means for generating answers to the questions using generative artificial intelligence, means for returning the generated answers to the user, and means for inputting questions regarding the status of robots and key performance indicators in a factory environment to support on-site maintenance work. As a result, maintenance staff can quickly obtain appropriate answers on-site, enabling efficient maintenance work.

[1375] "Means for receiving specific questions from users" refers to means of providing an interface for receiving questions entered by users.

[1376] "Means for sending the question to the server" refers to means that provide protocols and functions for sending questions entered by the user to the server.

[1377] "Means for generating an answer to the question using generative artificial intelligence" refers to means for generating an appropriate answer to a user's question using generative artificial intelligence.

[1378] "Means for returning the generated response to the user" refers to means of providing communication means or protocols for returning the generated response to the user.

[1379] "Means for displaying the returned response to the user" refers to means for providing a screen or interface for the user to view the received response.

[1380] "A means of inputting questions about the status of robots and key performance indicators in a factory environment to support on-site maintenance work" refers to a means of inputting questions about the status of robots and key performance indicators in a factory setting and obtaining answers to those questions to support maintenance work.

[1381] Modes for carrying out the invention

[1382] This invention is a system that supports on-site maintenance work in a factory environment by inputting questions regarding the status of robots and key performance indicators (KPIs). The embodiments of this system will be described in detail below.

[1383] System Overview

[1384] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a terminal for displaying the generated answer.

[1385] System components

[1386] User's terminal

[1387] The device provides an interface (UI) for the user to input and submit questions. For example, a dedicated application installed on a smartphone or tablet falls into this category.

[1388] Input interface:

[1389] Provide a text area and a submit button for the user to enter a question. For example, the user might type, "What are some ways to improve the robot's utilization rate?"

[1390] Sending function:

[1391] The entered questions are converted into a specific format and sent to the server. Specifically, JavaScript's AJAX functionality and the fetch API are used.

[1392] Server side

[1393] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. The following describes the processes performed by the server.

[1394] Question received:

[1395] The server receives an HTTP POST request and parses the request body. For example, this can be done using a Node.js or Python framework.

[1396] Natural language processing and response generation:

[1397] The question content is analyzed using a natural language processing engine (e.g., spaCy or NLTK), and an appropriate answer is generated using generative artificial intelligence (e.g., GPT-4). For example, it might generate an answer such as, "If the robot's operating rate is low, the possible causes are as follows..."

[1398] Format and submit your response:

[1399] The generated responses are formatted into an easy-to-read format and sent back to the terminal in JSON format. The server then converts the generated responses into HTML or Markdown format.

[1400] User's device (display of answers)

[1401] The user's device then visually displays the response received from the server to the user.

[1402] Received a response:

[1403] The system receives an HTTP response from the server and parses the JSON data. This allows it to retrieve the content of the response sent back to the user.

[1404] Show answers:

[1405] Based on the parsed data, JavaScript is used to dynamically generate HTML and display it interactively to the user. For example, formatted answers can be displayed on a smartphone screen to make them easy for the user to understand.

[1406] Specific example

[1407] For example, suppose a user enters a question, "What are some ways to improve the robot's utilization rate?" and presses the send button. The question is sent to the server via a dedicated application on the smartphone. The server receives the question and analyzes its meaning using a natural language processing engine. Next, it uses generative artificial intelligence to generate an appropriate answer. The server generates an answer such as, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." This answer is formatted on the server and sent back to the user's smartphone. Finally, the received answer is displayed on the smartphone screen, and the user can review and deepen their understanding of the answer.

[1408] Example of a prompt:

[1409] User question: What are some ways to improve the low utilization rate of robots?

[1410] answer:

[1411] This system allows factory maintenance staff to immediately obtain appropriate solutions on-site and carry out maintenance more efficiently.

[1412] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1413] Step 1:

[1414] Users enter questions using a dedicated application on their smartphone or tablet. The questions are in a format such as, "What are some ways to improve the robot's utilization rate?" The entered questions are captured as text data.

[1415] Step 2:

[1416] The terminal sends the entered question to the server. Specifically, it sends an HTTP POST request to the server using AJAX functionality or the fetch API. This request contains the text data of the question.

[1417] Step 3:

[1418] The server receives an HTTP POST request and extracts the question content from the request body. This process can be performed using frameworks such as Node.js or Python. The input obtained is the text data of the question.

[1419] Step 4:

[1420] The server analyzes the question using a natural language processing engine (e.g., spaCy or NLTK). The purpose of the analysis is to understand the meaning of the question and extract keywords and entities contained within it. For example, entities such as "robot," "operating rate," and "improvement measures" may be extracted.

[1421] Step 5:

[1422] The server uses generative artificial intelligence (e.g., GPT-4) to generate an appropriate answer. It creates a prompt based on the extracted entities and the context of the question, and inputs it into the generative AI. An example of a generated prompt is: "User question: What can I do to improve the robot's utilization rate? Answer: ".

[1423] Step 6:

[1424] A generative artificial intelligence generates a response based on the prompt text. This response might be something like, "If the robot's utilization rate is low, the possible causes are as follows: 1. Insufficient maintenance and inspection, 2. Operator error, 3. Inappropriate workflow. Possible solutions include strengthening regular inspections, training operators, and reviewing the workflow." The generated response is returned to the server as text data.

[1425] Step 7:

[1426] The server formats the generated response into a readable format. It uses HTML, Markdown, or other formats to make it easy for the user to understand. This formatted response is then converted to JSON format and sent to the device.

[1427] Step 8:

[1428] The terminal receives an HTTP response from the server. The received response is parsed as JSON data, and the content of the response is retrieved.

[1429] Step 9:

[1430] The system visually displays the answers obtained by the device to the user. JavaScript is used to dynamically generate HTML, which is then displayed on the smartphone or tablet screen. For example, formatted answers are displayed on the screen, making them easy for the user to understand. As a result, maintenance staff can quickly take appropriate action on-site.

[1431] The above steps enable the creation of a system that allows for the rapid acquisition of answers to questions regarding the status of robots and key performance indicators (KPIs) in a factory environment.

[1432] 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.

[1433] This invention is a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by incorporating an emotion engine that recognizes the user's emotions, it becomes possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[1434] System Overview

[1435] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[1436] System components

[1437] User's terminal

[1438] The device provides an interface (UI) for the user to input questions. Specifically, it includes the following features:

[1439] Input interface:

[1440] Provide a text field and a submit button for the user to enter a question. For example, the user might type, "Please explain what it means when the ●● rate exceeds 100%."

[1441] Sending function:

[1442] The entered questions are converted into a specific format (e.g., JSON format) and sent to the server. Specifically, JavaScript's AJAX functionality or the fetch API is used.

[1443] Server side

[1444] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. Furthermore, it has a function where an emotion engine analyzes the user's emotions and adjusts the answers accordingly. Specifically, it performs the following processes:

[1445] Question received:

[1446] The server receives an HTTP POST request and extracts the question content from the request body. Examples of frameworks used include Node.js and Python.

[1447] Emotional analysis using an emotion engine:

[1448] The system analyzes user input and other emotional data (e.g., voice, facial expressions) to recognize the user's emotional state. For example, natural language processing engines (such as spaCy and NLTK) and machine learning algorithms are used.

[1449] Natural language processing and response generation:

[1450] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (e.g., GPT-4) is used to generate an appropriate answer. For example, it might say, "If the ●● rate exceeds 100%, it means that the actual value is higher than the predicted or planned value. This indicates better-than-expected results."

[1451] Adjusting the answer:

[1452] The emotion engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is feeling dissatisfied, the response will be changed to a more polite and encouraging tone.

[1453] Format and submit your response:

[1454] The adjusted response is formatted into an easy-to-read format (HTML or Markdown), converted to JSON format, and sent back to the device.

[1455] User's device (display of answers)

[1456] The terminal visually displays the response received from the server to the user.

[1457] Received a response:

[1458] The system receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[1459] Show answers:

[1460] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[1461] Specific example

[1462] For example, a user, feeling emotionally frustrated, might type "What should I be careful about if I don't meet my KPIs?" and press the send button. The terminal sends the question to the server. The server receives the question and uses an emotion engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. An answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." is generated. The server adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, and the user reviews it to deepen their understanding.

[1463] This system allows users to quickly receive appropriate responses that are tailored to their emotions, which is expected to improve work efficiency and customer satisfaction.

[1464] The following describes the processing flow.

[1465] Step 1:

[1466] User

[1467] The user enters their question using their device. For example, they might enter "Please explain what it means when the ●● rate exceeds 100%" into the inquiry form.

[1468] Step 2:

[1469] terminal

[1470] The system retrieves the question entered by the user, and if the submit button is pressed, it uses JavaScript or similar methods to convert the question data into JSON format.

[1471] Step 3:

[1472] terminal

[1473] The converted question data is sent to the server as an HTTP POST request. For example, this can be done using AJAX or the fetch API.

[1474] Step 4:

[1475] server

[1476] The server receives an HTTP POST request and extracts the question content from the request body. For example, this can be done using a Node.js or Python framework.

[1477] Step 5:

[1478] server

[1479] The extracted question content is passed to the emotion engine for analysis. The emotion engine uses natural language processing technology and machine learning algorithms to analyze emotional data from the user's input.

[1480] Step 6:

[1481] server

[1482] The emotion data analyzed by the emotion engine is stored, and the question content is passed to a natural language processing engine for analysis. Examples of such engines include spaCy and NLTK.

[1483] Step 7:

[1484] server

[1485] Based on data analyzed by a natural language processing engine, a generative artificial intelligence (e.g., GPT-4) is used to generate appropriate responses.

[1486] Step 8:

[1487] server

[1488] The generated responses are compared with sentiment data from the sentiment engine, and the tone and content of the responses are adjusted accordingly. For example, if the user is dissatisfied, the tone of the response is changed to be more kind and polite.

[1489] Step 9:

[1490] server

[1491] The adjusted responses are formatted into user-friendly formats such as HTML or Markdown, and then converted into JSON format.

[1492] Step 10:

[1493] server

[1494] The formatted response is sent to the terminal as an HTTP response.

[1495] Step 11:

[1496] terminal

[1497] It receives an HTTP response from the server and parses (analyzes) the response data in JSON format.

[1498] Step 12:

[1499] terminal

[1500] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and the user's answers are displayed interactively. Specifically, the generated answers are displayed at the bottom of the question form.

[1501] Step 13:

[1502] User

[1503] Users review the displayed answers to deepen their understanding of technical terms and KPIs. They also consider their next actions based on the answers they received.

[1504] (Example 2)

[1505] 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".

[1506] Traditional systems generate uniform answers to user-inputted questions, failing to consider the user's emotional state, resulting in inappropriate tone in the responses. Furthermore, there is a lack of methods to present generated answers in a more user-friendly and easily understandable format. These system limitations hinder improvements in customer satisfaction and operational efficiency.

[1507] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state using an emotion analysis engine, means for generating an answer to the question using generative artificial intelligence, and means for adjusting the generated answer based on the user's emotional state. This makes it possible to generate an answer with an appropriate tone that is attuned to the user's emotions, and for the content of the answer to be conveyed to the user more effectively.

[1508] A "user" refers to a person who uses the system to input questions and receive answers.

[1509] "Means for receiving input" refers to a function that provides an interface for users to input questions as text.

[1510] A "server" refers to a computer system that receives questions submitted by users, analyzes them, and generates answers.

[1511] "Means of transmission" refers to the communication function that sends the questions entered by the user to the server.

[1512] An "emotion analysis engine" refers to software that analyzes user input and emotional data to recognize the user's emotional state.

[1513] "Generative artificial intelligence" refers to artificial intelligence that analyzes the content of a user's question and generates an appropriate answer based on that analysis.

[1514] "Means of adjustment" refers to a function that modifies the tone and content of the generated response according to the user's emotional state.

[1515] "Methods for formatting into an easy-to-read format" refers to a function that converts the generated and adjusted answers into a format that is easy for users to understand (such as HTML or Markdown).

[1516] "Means of display" refers to functions that visually display formatted answers to the user.

[1517] This invention provides a system that allows users to input questions about business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion analysis engine that recognizes the user's emotions, it is possible to adjust the tone and content of the answers according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and a terminal that displays the generated answers.

[1518] System Overview

[1519] This system consists of a terminal where the user inputs a question, a server that receives and analyzes the question and generates an answer, and a means for displaying that answer to the user. It also incorporates an emotion analysis engine that recognizes the user's emotions and adjusts the content and tone of the answer based on that information.

[1520] System components

[1521] User's terminal

[1522] The terminal provides an interface for the user to enter questions. Specifically, it includes the following features:

[1523] Input interface:

[1524] Provide a text field and a submit button for the user to enter a question. For example, the user could enter, "Please tell me what to do if the KPI is not met."

[1525] Sending function:

[1526] The entered questions are converted into a specific format (e.g., JSON) and sent to the server. This function is implemented using AJAX or the fetch API.

[1527] Server side

[1528] The server is responsible for receiving questions submitted by users, analyzing them, and generating answers. Furthermore, it has a sentiment analysis engine that analyzes the user's emotions and adjusts the answers accordingly. Specifically, the following processes are performed:

[1529] Question received:

[1530] The server receives an HTTP POST request and extracts the question content from the request body. Node.js or Python frameworks are used for this process.

[1531] Emotional analysis using an emotion analysis engine:

[1532] A natural language processing engine (such as spaCy or NLTK) is used to analyze user input and other emotional data (e.g., text, facial expressions, etc.) to recognize the user's emotional state.

[1533] Natural language processing and response generation:

[1534] The question is passed to a natural language processing engine for analysis, and a generative artificial intelligence (such as GPT-4) generates an appropriate answer. For example, in response to the question, "What are the countermeasures to take if the KPIs are not achieved?", the answer generated would be, "If the KPIs are not achieved, it is important to first identify the cause and then take appropriate countermeasures."

[1535] Adjusting the answer:

[1536] The sentiment analysis engine adjusts the tone and content of the generated response based on the user's emotional state. For example, if the user is irritated, the tone will be changed to be more polite and encouraging.

[1537] Format and submit your response:

[1538] The adjusted response is formatted into an easy-to-read format (e.g., HTML or Markdown), converted to JSON format, and sent back to the device.

[1539] User's device (display of answers)

[1540] The terminal has the function of visually displaying the response received from the server to the user.

[1541] Received a response:

[1542] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the response content.

[1543] Show answers:

[1544] Based on the parsed data, HTML is dynamically generated using JavaScript and other tools, and displayed interactively to the user. Specifically, the generated answers are displayed at the bottom of the question form.

[1545] Specific example

[1546] For example, a user, frustrated, might type, "What should I be careful about if I don't meet my KPIs?" and press the submit button. The terminal sends the question to the server. The server receives the question and uses an emotion analysis engine to recognize the user's frustration. Next, it analyzes the question using a natural language processing engine, and a generative artificial intelligence generates an appropriate answer. The server might generate an answer like, "If you don't meet your KPIs, it's important to analyze the cause and think about ways to improve..." The server then adjusts the tone to reflect the frustration, changing it to something like, "Don't worry. Even if you don't meet your KPIs, you can find the cause and improve to succeed next time." Finally, the adjusted answer is sent back to the terminal, allowing the user to review and deepen their understanding.

[1547] This system will not only provide factual answers but also respond in a way that is sensitive to the user's emotions, which is expected to improve operational efficiency and customer satisfaction.

[1548] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1549] Step 1:

[1550] The user enters a question into the terminal's input interface and presses the submit button. The input interface includes a text field and a submit button. The data entered is the user's question text, such as, "Please tell me what to do if the KPI is not achieved."

[1551] Input: User's question text (e.g., "What are the countermeasures to take if the KPI is not met?")

[1552] Output: None

[1553] Step 2:

[1554] The terminal converts the entered question text into a specific format (e.g., JSON format) and sends it to the server. JavaScript's AJAX or fetch API is used for this conversion.

[1555] Input: User's question text

[1556] Data processing: Convert the question text to JSON format (e.g., {"question": "Please tell me what measures to take if the KPI is not achieved"})

[1557] Output: Question data in JSON format

[1558] Step 3:

[1559] The server receives the question as an HTTP POST request. Node.js or Python frameworks are used to extract the question content from the request body.

[1560] Input: Question data in JSON format (Example: {"question": "Please tell us what measures to take if the KPI is not achieved"})

[1561] Data processing: Extracting question text from JSON data

[1562] Output: Question text

[1563] Step 4:

[1564] The server uses an emotion analysis engine (e.g., spaCy or NLTK) to analyze the user's emotional state from the question text. The emotional state identifies conditions such as frustration, joy, and anxiety.

[1565] Input: Question text

[1566] Data processing: Analyzing emotional states using natural language processing algorithms.

[1567] Output: Emotional state (e.g., irritation)

[1568] Step 5:

[1569] The server analyzes the question text using a natural language processing engine (e.g., spaCy) and generates an answer using generative artificial intelligence (e.g., GPT-4).

[1570] Input: Question text

[1571] Data processing: Generate answers using natural language processing and generative artificial intelligence.

[1572] Output: Generated response text (Example: "If KPIs are not met, it is important to identify the cause and take corrective action.")

[1573] Step 6:

[1574] The server adjusts the tone and content of the generated response text based on the user's emotional state recognized by the sentiment analysis engine. For example, if the user is irritated, the response tone will be changed to something more encouraging.

[1575] Input: Generated response text and user's emotional state

[1576] Data processing: Adjust the tone of the response text (e.g., "Don't worry. Even if you don't meet the KPI, you can find the cause and make improvements to succeed next time.")

[1577] Output: Adjusted response text

[1578] Step 7:

[1579] The server formats the adjusted response text into a readable format (e.g., HTML or Markdown), converts it to JSON format, and sends it back to the terminal.

[1580] Input: Adjusted response text

[1581] Data processing: Format the response text into HTML or Markdown format, then convert it to JSON format (e.g., {"response": " Don't worry. Even if you don't meet your KPIs, you can find the cause and make improvements, and you'll succeed next time. "})

[1582] Output: Adjusted response data in JSON format

[1583] Step 8:

[1584] The terminal receives an HTTP response from the server, parses the JSON data, and retrieves the answer.

[1585] Input: Adjusted response data in JSON format

[1586] Data processing: Parse the JSON data and extract the response text.

[1587] Output: Adjusted response text

[1588] Step 9:

[1589] The device uses JavaScript to dynamically generate HTML based on the extracted response text and displays it interactively to the user. Specifically, the generated response is displayed at the bottom of the question form.

[1590] Input: Adjusted response text

[1591] Data processing: Dynamically generate HTML and display the answers.

[1592] Output: Displayed answer text

[1593] (Application Example 2)

[1594] 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".

[1595] Conventional question-answering systems failed to consider the user's emotional state when providing answers to their questions. As a result, users often experienced dissatisfaction and anxiety. Furthermore, these systems were insufficient as a means of reducing stress in the work environment, and there was a particular need for a rapid and emotionally empathetic response, especially in workplaces such as factories.

[1596] 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. In this invention, the server includes means including an emotion engine for analyzing the user's emotional state, means for generating an answer to the question using generative artificial intelligence, and means for adjusting the generated answer according to the user's emotional state. This makes it possible to provide an answer that matches the user's emotional state.

[1597] "User emotional state" refers to the psychological state or emotions a user exhibits when entering questions or receiving answers.

[1598] An "emotion engine" refers to a system that analyzes user input and other emotional data to recognize their emotional state.

[1599] "Generative artificial intelligence" refers to artificial intelligence models that generate answers to input questions.

[1600] A "natural language processing engine" refers to the technologies and algorithms used to analyze input natural language text and make its meaning easier to understand.

[1601] "Means of adjustment" refers to functions that modify the tone and content of generated responses based on the user's emotional state.

[1602] A "server" refers to a device or system that receives questions submitted by users, analyzes and generates answers, and performs sentiment analysis using an emotion engine.

[1603] "Means of display" refers to devices or interfaces that visually provide users with the responses returned from the server.

[1604] This invention is a system that allows users to input questions related to business terminology and key performance indicators (KPIs), and generates appropriate answers to those questions. In particular, by combining it with an emotion engine equipped with emotion analysis capabilities, it becomes possible to adjust the tone and content according to the user's emotional state. This system consists of a user terminal, a server that receives and analyzes questions and generates answers, and means for displaying those answers.

[1605] System Overview

[1606] This system includes means for receiving user questions as input, means for sending said questions to a server, means for generating answers to said questions using generative artificial intelligence (e.g., GPT-4), an emotion engine for analyzing the user's emotional state, means for adjusting the generated answers according to the user's emotional state, and means for returning and displaying the adjusted answers to the user.

[1607] Hardware and software to use

[1608] 1. Hardware

[1609] Robots installed inside the factory

[1610] Cloud server (for hosting Flask applications)

[1611] 2. Software

[1612] Flask (a Python web framework for receiving and providing responses to questions)

[1613] TextBlob (emotional analysis)

[1614] OpenAI API (natural language processing and response generation, specifically GPT-4)

[1615] Data flow and calculations

[1616] 1. The user inputs a question to the robot in the factory. For example, "What is causing the production line to be behind schedule?"

[1617] 2. The robot sends this question to the server using Flask. The server receives the HTTP request and extracts the question content from the request body.

[1618] 3. The server uses TextBlob to analyze the question and calculate the emotional polarity. This analysis classifies the user's emotional state as positive, negative, or neutral.

[1619] 4. The server uses the OpenAI API to generate an initial answer to the question.

[1620] 5. Next, adjust the tone of your response based on their emotional state. For example, if they are feeling negative emotions, add comforting words such as, "Don't worry."

[1621] 6. The adjusted response is sent back to the robot and displayed to the user.

[1622] Specific example

[1623] A worker in a factory asks a robot, "What is causing the production line to be delayed?" This question is sent to a server, which uses an emotion engine to recognize that the questioner's emotions are negative. The server generates an initial response, "The production line delay may be due to machine maintenance," and the emotion engine adjusts it by adding, "Don't worry." Ultimately, the response "Don't worry. The production line delay may be due to machine maintenance" is sent back to the user.

[1624] Example of a prompt

[1625] Please answer the following question: "What is causing the production line to be delayed?"

[1626] In this way, it becomes possible to provide responses that are tailored to the user's emotional state, contributing to improvements in the factory's working environment and increased operational efficiency.

[1627] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1628] Step 1:

[1629] A user inputs a question into a robot in the factory. For example, they might ask, "What is causing the production line to be behind schedule?" At this stage, the input is text data entered by the user, and the robot receives this text data.

[1630] Step 2:

[1631] The terminal (robot) converts the received question text into JSON format and sends it to the server via an HTTP request. This transmission operation is performed using JavaScript, with the input being the question text and the output being JSON formatted data.

[1632] Step 3:

[1633] The server receives an HTTP request and extracts the question content from the request body. At this stage, the input is in JSON format, from which the question text is extracted. For example, the Flask framework in Python can be used to process the request.

[1634] Step 4:

[1635] The server uses the TextBlob library to analyze the question text and calculate the emotional polarity. The input is the question text, and the output is the emotional state (positive, negative, or neutral). Through this analysis, the server recognizes the user's emotional state.

[1636] Step 5:

[1637] The server uses the OpenAI API to generate an initial answer to a question. The input is the question text, and the output is the generated answer text. Specifically, a generative AI model (e.g., GPT-4) is used to generate the answer.

[1638] Step 6:

[1639] The server uses an emotion engine to generate responses, adjusting their tone and content according to the user's emotional state. The input is the generated response and the emotional state, and the output is the adjusted response. For example, in the case of a negative emotion, comforting words such as "Don't worry" are added before the response.

[1640] Step 7:

[1641] The server converts the formatted response into JSON format and sends it back to the robot (terminal) via an HTTP response. The input is the formatted response text, and the output is data in JSON format.

[1642] Step 8:

[1643] The robot (terminal) receives JSON data sent back from the server, parses the data, and obtains the answer. The input is data in JSON format, and the output is the answer text.

[1644] Step 9:

[1645] The robot (terminal) displays the acquired answer text to the user. Specifically, it displays the generated answer at the bottom of the user's question form. The input is the answer text, and the output is the answer displayed on the user's screen.

[1646] 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.

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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.

[1652] 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.

[1653] 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.

[1654] 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."

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] 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.

[1662] 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.

[1663] 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.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] The following is further disclosed regarding the embodiments described above.

[1668] (Claim 1)

[1669] A means of receiving specific questions from users,

[1670] A means for sending the question to the server,

[1671] A means for generating an answer to the question using generative artificial intelligence,

[1672] A means for returning the generated response to the user,

[1673] A means for displaying the returned response to the user,

[1674] A system that includes this.

[1675] (Claim 2)

[1676] The system according to claim 1, which analyzes an input question using a natural language processing engine and generates an appropriate answer.

[1677] (Claim 3)

[1678] The system according to claim 1, which formats the generated response into a format that is easy for the user to read.

[1679] "Example 1"

[1680] (Claim 1)

[1681] A means of receiving specific questions from users,

[1682] A means for sending the question to the server,

[1683] A means for generating an answer to the question using generative artificial intelligence,

[1684] A means for returning the generated response to the user,

[1685] A means for displaying the returned response to the user,

[1686] A means by which the user enters questions using a browser or a dedicated application,

[1687] A means of sending a question to the server using JavaScript's AJAX functionality or the fetch API,

[1688] A means of analyzing a question using a natural language processing engine,

[1689] A means of formatting the generated response into HTML or Markdown format,

[1690] A means of returning the formatted response to the terminal in JSON format,

[1691] A method for parsing received JSON data, dynamically generating HTML, and displaying it to the user,

[1692] A system that includes this.

[1693] (Claim 2)

[1694] The system according to claim 1, which analyzes an input question using a natural language processing engine and generates an appropriate answer.

[1695] (Claim 3)

[1696] The system according to claim 1, which formats the generated response into a format that is easy for the user to read.

[1697] "Application Example 1"

[1698] (Claim 1)

[1699] A means of receiving specific questions from users,

[1700] A means for sending the question to the server,

[1701] A means for generating an answer to the question using generative artificial intelligence,

[1702] A means for returning the generated response to the user,

[1703] A means for displaying the returned response to the user,

[1704] A means of inputting questions about the status of robots and key performance indicators in a factory environment to support on-site maintenance work,

[1705] A system that includes this.

[1706] (Claim 2)

[1707] The system according to claim 1, which analyzes an input question using a natural language processing engine and generates an appropriate answer.

[1708] (Claim 3)

[1709] The system according to claim 1, which formats the generated response into a format that is easy for the user to read.

[1710] "Example 2 of combining an emotion engine"

[1711] (Claim 1)

[1712] A means of receiving specific questions from users,

[1713] A means for sending the question to the server,

[1714] A means of analyzing a user's emotional state using an emotion analysis engine,

[1715] A means for generating an answer to the question using generative artificial intelligence,

[1716] A means of adjusting the generated response based on the user's emotional state,

[1717] A means for formatting the adjusted response into a user-friendly format,

[1718] A means for displaying the returned response to the user,

[1719] A system that includes this.

[1720] (Claim 2)

[1721] The system according to claim 1, which analyzes an input question using a natural language processing engine and generates an appropriate answer.

[1722] (Claim 3)

[1723] The system according to claim 1, which formats the adjusted response into a format such as HTML or Markdown.

[1724] "Application example 2 when combining with an emotional engine"

[1725] (Claim 1)

[1726] A means of receiving specific questions from users,

[1727] A means for sending the question to the server,

[1728] A means for generating an answer to the question using generative artificial intelligence,

[1729] A means including an emotion engine for analyzing the user's emotional state,

[1730] A means for adjusting the generated response according to the user's emotional state,

[1731] A means for returning the adjusted response to the user,

[1732] A means for displaying the returned response to the user,

[1733] A system that includes this.

[1734] (Claim 2)

[1735] The system according to claim 1, which analyzes an input question using a natural language processing engine and generates an appropriate answer.

[1736] (Claim 3)

[1737] The system according to claim 1, which formats the generated response into a user-friendly format and adjusts it based on the user's emotional state. [Explanation of symbols]

[1738] 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 of receiving specific questions from users, A means for sending the question to the server, A means for generating an answer to the question using generative artificial intelligence, A means for returning the generated response to the user, A means for displaying the returned response to the user, A system that includes this.

2. The system according to claim 1, which analyzes an input question using a natural language processing engine and generates an appropriate answer.

3. The system according to claim 1, which formats the generated response into a format that is easy for the user to read.

Images