System

Abstract

A system is provided.SOLUTION: The system includes means for a user to input and transmit a question or a problem through a terminal, means for a server to analyze the question or the problem received by the server by using a natural language processing technology and to extract a related keyword, means for the server to search a knowledge database based on the extracted keyword and to specify another user having appropriate specialized knowledge, means for the server to notify the user of the question or the problem and to urge a response, and means for the server to provide the response received from the user to the user of the transmission source.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the business world, communication friction resulting from differences in knowledge levels between employees and their superiors reduces work efficiency and causes employee dissatisfaction. These problems are a major obstacle to corporate growth and evolution, and traditional mailing lists and chat tools have not adequately resolved them. The objective of this invention is to provide a system that solves these issues and supports rapid and effective information sharing and problem solving within a company. [Means for solving the problem]

[0005] The present invention is a system that includes a means for users to input and send questions or issues via terminals, a means for a server to analyze the received questions or issues using natural language processing technology and extract related keywords, a means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise, a means for the server to notify the identified users of the questions or issues and prompt them to answer, and a means for the server to provide the answers received from the users to the original user. This reduces communication friction that arises from differences in knowledge levels between employees and their superiors, and improves the problem-solving ability of the entire organization.

[0006] "User" refers to a person who uses the system to input questions or issues and seek reference information for solving them.

[0007] A "terminal" is a device that allows a user to input and send questions or issues, and includes computers, smartphones, tablets, etc.

[0008] "Server" refers to a central device that receives questions or issues submitted by users and takes appropriate action.

[0009] "Natural language processing technology" refers to the technology that analyzes and understands human language and converts it into a form that can be used by a computer.

[0010] "Keywords" are short words or phrases that summarize the content of a question or issue and are used for search and analysis.

[0011] A "knowledge database" refers to a database in which previously accumulated information and specialized knowledge are stored in a structured manner.

[0012] "Other users with specialized knowledge" refers to users who have extensive knowledge and experience in a particular field.

[0013] "Notification" refers to the act or process of informing identified users that a question or issue exists.

[0014] "Answer" refers to content that indicates a solution or reference information provided by a specified user to a question or problem.

[0015] "Feedback" refers to the action of a user sending an evaluation or impression of the answer they received. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports rapid and effective information sharing and problem solving within a company. This system begins when a user inputs and sends a question or issue via a terminal, and the server analyzes the content using natural language processing technology and identifies other users with appropriate expertise.

[0038] Explanation of program processing

[0039] 1. User questions and issues posted

[0040] A user uses a terminal to enter their question or issue and submit it to the system. For example, a user might enter, "Please tell me how to create materials for a new marketing strategy."

[0041] 2. Collection and transmission of posts

[0042] The terminal transmits the user's input to the server.

[0043] 3. Receiving and analyzing questions and issues

[0044] The server uses natural language processing technology to analyze the questions and issues received from users and extract related keywords, such as "marketing strategy" and "document creation."

[0045] 4. Knowledge database reference

[0046] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions, answers, and specialized knowledge.

[0047] 5. Identifying users with the right expertise

[0048] The server compares the knowledge database with employee profile data to identify users with the appropriate expertise. For example, Employee A is knowledgeable about marketing, while Employee B is skilled in creating documents.

[0049] 6. Notification to Identified Users

[0050] The server then notifies the identified user of their question or issue and asks for a response. This process can be done using methods such as push notifications or emails.

[0051] 7. User-generated answers

[0052] The identified users use the devices to input and send answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0053] 8. Receiving and notifying responses

[0054] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[0055] 9. Providing Feedback

[0056] The user inputs feedback on the answers provided through the terminal and sends it to the server, which stores the feedback in a database and notifies the relevant users and administrators.

[0057] Specific processing examples

[0058] For example, if a user sends a question from a terminal such as "I want to know new methods for sales strategy," the server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C. Employee C receives this notification and enters an answer from his / her terminal, which is provided to the user. The user enters feedback on this answer, which the server receives and stores in the database.

[0059] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0060] The processing flow will be explained below.

[0061] Program processing flow

[0062] Step 1:

[0063] The user can input their questions or issues through the device and submit them. For example, they could input, "Please tell me how to create materials for a new marketing strategy."

[0064] Step 2:

[0065] The device sends the user's input to the server. The data sent includes meta-information such as the user ID, question, and the date and time of submission.

[0066] Step 3:

[0067] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0068] Step 4:

[0069] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions and answers, as well as specialized knowledge.

[0070] Step 5:

[0071] The server compares the knowledge database with employee profile data (expertise, past response history) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[0072] Step 6:

[0073] The server notifies the identified user of their questions or issues and requests answers. This notification is sent via push notifications, emails, and other means.

[0074] Step 7:

[0075] The identified users use the devices to input answers to questions and issues. Employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide templates that will help you create the materials."

[0076] Step 8:

[0077] The terminal transmits the input response data to the server. The transmitted data includes the response content, respondent ID, and response date and time.

[0078] Step 9:

[0079] The server then provides the responses received from the employees to the original sender. To do this, the server uses push notifications, emails, etc.

[0080] Step 10:

[0081] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[0082] Step 11:

[0083] The user inputs feedback for the provided answer through the terminal and transmits it to the server. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[0084] Step 12:

[0085] The terminal sends feedback data to the server, which includes the feedback content, the user ID, and the transmission date and time.

[0086] Step 13:

[0087] The server stores the received feedback in a database and notifies relevant employees and managers using push notifications, emails, etc.

[0088] In this way, the system of the present invention responds quickly and efficiently to questions and issues, and reduces communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] The goal is to provide a system that supports quick and effective information sharing and problem solving within a company. In particular, it is required to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors, and enable efficient responses.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes means for users to input and transmit questions or issues via an information terminal, means for analyzing the received questions or issues using natural language processing technology and extracting related terms, means for searching a knowledge database based on the extracted terms and identifying other users with appropriate expertise, means for notifying the identified users of the questions or issues and prompting them to respond, means for the identified users to input and transmit answers via their information terminals, and means for providing the transmitted answers to the original users. This makes it possible to respond to questions or issues quickly and efficiently and reduce communication friction caused by differences in knowledge levels between employees and their superiors.

[0094] "Information terminal" refers to an electronic device that a user uses to input, send, and receive data over a communications network. Examples include personal computers, smartphones, and tablets.

[0095] "Natural language processing technology" refers to a set of algorithms and techniques used by a server to analyze text data and understand words and phrases. This includes techniques such as SpaCy and BERT.

[0096] "Phrases" refer to important words and phrases extracted from the text entered by the user using natural language processing technology.

[0097] A "knowledge database" is a collection of data used by the server to gather information based on analysis, including past questions and answers and specialized knowledge. Examples include databases such as PostgreSQL and ElasticSearch (registered trademark).

[0098] "Expertise" refers to detailed knowledge and skills in a particular field or area that the server uses to provide the best possible answers to questions or challenges.

[0099] "Notification" refers to a message or alert sent by the server to an identified user to inform them of a question or issue and prompt them to respond, including email, push notification, messaging app, etc.

[0100] "Feedback" refers to the process by which the original user sends their rating and opinion on the provided answer to the server. This information is stored in a database for later analysis.

[0101] This invention is a system that supports quick and effective information sharing and problem solving within a company. The purpose of this system is to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors. Specific embodiments are shown below.

[0102] Users use an information terminal (e.g., PC or smartphone) to input their questions or issues and send them to the system. This input is saved in text format, and the information terminal sends the text data to the server. HTTPS is used as the communication protocol, so the data is encrypted before being sent.

[0103] The server analyzes the text data received from the user using natural language processing technology (e.g., SpaCy, BERT) and extracts related words. For example, if a user types, "Please tell me how to create a document for a new marketing strategy," the words "marketing strategy" and "document creation" are extracted.

[0104] The server searches a knowledge database (e.g., PostgreSQL or Elasticsearch) based on the extracted phrases to gather relevant information. This database stores past questions and answers, as well as specialized knowledge.

[0105] Next, the server identifies users with the appropriate expertise by comparing the results of the knowledge database search with the personal data of registered employees. For example, employee A who is knowledgeable about marketing and employee B who is skilled in creating documents can be identified.

[0106] The server notifies the identified user of the user's questions or issues through a notification system (e.g., email, push notification, messaging app). When the identified user enters and sends an answer through an information terminal, this answer is also received by the server and provided to the original user.

[0107] The original user inputs feedback on the provided answer through the information terminal and sends it to the server, which stores this feedback in a database and notifies the relevant users and administrators.

[0108] Specific examples

[0109] For example, if a user inputs a question such as "I would like to know new methods for sales strategies," the server receives the question, extracts the phrases "sales strategies" and "new methods," and searches the knowledge database. Based on the search results, it identifies employee C, who is knowledgeable about "sales strategies," and sends a notification to employee C. Employee C receives the notification and enters an answer on his information terminal, which is then provided to the original user. The user enters feedback on this answer, which the server receives and stores in the database.

[0110] Prompt Sentence Examples

[0111] "How do I create materials for a new marketing strategy?"

[0112] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] A user uses an information terminal to input and submit a question or problem. The input text data is in the format of "Please tell me how to create materials for a new marketing strategy." The terminal sends this text data to a server. The input data is in the form of text data, and the output is the text data sent to the server.

[0116] Step 2:

[0117] The server receives text data sent by the user. The server analyzes the received text data using natural language processing technology. Specifically, the text data is tokenized and important words and phrases are extracted. For example, the words "marketing strategy" and "document creation" are extracted. The input is the text data from the user, and the output is the extracted words and phrases.

[0118] Step 3:

[0119] The server queries a knowledge database based on the extracted phrases to collect related information. The knowledge database stores past questions and answers, and the query results include this related information. For example, a query such as "How to create materials for marketing strategies" returns related documents and answers. The input is the extracted phrases, and the output is related information.

[0120] Step 4:

[0121] Based on the information collected by the server, users with the appropriate expertise are identified. The server compares the knowledge database with the personal data of employees to find the most suitable answerer. For example, employee A who is knowledgeable about "marketing" and employee B who is skilled in "document creation" are identified. The input is the collected information, and the output is the identified user.

[0122] Step 5:

[0123] The server sends a notification to the identified user. The notification is sent via email, push notification, or messaging app. The notification contains the user's question or problem. For example, a notification may be sent in response to a question such as, "How do I create materials for a new marketing strategy?" The input is the identified user, and the output is the notification.

[0124] Step 6:

[0125] The identified user inputs and sends a response via the information terminal. For example, employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide a template that will be useful for creating materials." The terminal sends this response to the server. The input is the response from the user, and the output is the response sent to the server.

[0126] Step 7:

[0127] The server provides the answer received from the identified user to the original user. The answer is notified to the terminal and provided in a format that can be viewed by the original user. For example, an answer such as "Please refer to past marketing strategy materials" is displayed. The input is the received answer, and the output is the answer provided to the original user.

[0128] Step 8:

[0129] The original user inputs feedback for the provided answer and sends it through the terminal. The server receives this feedback and stores it in a database. The input is the feedback, and the output is the feedback stored in the database.

[0130] (Application example 1)

[0131] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] In modern companies, differences in knowledge levels between employees and superiors and communication friction can occur, delaying information sharing and problem-solving. Furthermore, at factories and other worksites, there is a lack of ways to quickly respond to technical issues and questions faced by workers, which can lead to reduced production efficiency and quality problems. There is a need to provide a means to resolve these issues and enable fast and effective information sharing within the company.

[0133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0134] In this invention, the server includes: a means for a user to input and transmit a question or problem via a terminal; a means for analyzing the received question or problem using natural language processing technology and extracting related keywords; a means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; a means for the server to notify the identified users of the question or problem and prompt them to respond; a means for the server to provide the user with the response received from the user; and a means for using a smart device to input the question or problem by voice from the site, convert it into text, and transmit it to the server. This enables quick problem solving and information sharing throughout the company, including site workers.

[0135] A "user" is a person or agent who utilizes the system to input and submit questions or issues.

[0136] A "terminal" is a device used by a user to input and send questions or issues, and includes smartphones, smart glasses, head-mounted displays, robots, etc.

[0137] "Questions and Issues" are problems users are facing or questions that need to be resolved.

[0138] A "server" is a central system that receives questions and issues, analyzes them, searches for relevant information, identifies users with specialized knowledge, notifies them, and provides answers.

[0139] "Natural language processing technology" is a computational technology that analyzes questions and issues received by the server and extracts related keywords.

[0140] "Related keywords" are important words or phrases necessary for solving a problem that are extracted from the question or issue entered by the user.

[0141] A "knowledge database" is a collection of searchable information that stores past questions, answers, and specialized knowledge.

[0142] "Other users" are people or agents with appropriate expertise for a question or issue.

[0143] "Notification" is the process by which the server notifies identified users of questions or issues.

[0144] The "means for prompting an answer" is a method by which the server requests an answer to resolve a question or problem from the identified user.

[0145] A "smart device" is a device that has functions such as voice input and text input and is used to send questions and issues from the field.

[0146] The "site" is the location where the user actually works, and includes a factory, a production line, an office, and the like.

[0147] "Voice input" refers to the act of a user verbally expressing a question or problem using a microphone.

[0148] "Convert to text" is the process of converting voice-input information into character string information.

[0149] "Send" is the act of moving information such as a question, assignment, answer, or notice from one point to another.

[0150] The present invention is a system that supports rapid and effective information sharing and problem solving within a company, and is configured to be usable particularly in factories and on-site. This system begins when a user inputs and transmits a question or issue by voice via a terminal. The server then analyzes the content using natural language processing technology, identifies other users with appropriate expertise, and notifies them.

[0151] Program Overview

[0152] When a user uses a smart device (e.g., smart glasses) to voice-input a question or issue from the field, it is converted into text and sent to a server. The server uses natural language processing technology to analyze the received question or issue and extract relevant keywords. These keywords are used to search a knowledge database to identify other users with appropriate expertise. Identified users are notified and can request an answer. Once an answer is provided, the server provides it to the original user. It also receives feedback from users and stores it in a database.

[0153] Hardware and software used

[0154] Smart devices: Devices such as smart glasses, smartphones, and head-mounted displays that have voice input and communication capabilities.

[0155] Server: Responsible for data analysis, natural language processing, database search, and notification functions.

[0156] The software used includes Python's speech_recognition library, requests library, Google® Cloud NLP API, and Firebase Cloud Messaging.

[0157] Natural language explanation of the process

[0158] 1. User speaks:

[0159] Using smart glasses or a smartphone, users speak their questions or tasks, which are then picked up by the device via a microphone.

[0160] 2. Speech to text conversion:

[0161] The smart device converts the speech into text using the speech_recognition library, and the converted text is sent directly to the server.

[0162] 3. Natural Language Processing on the Server:

[0163] The server analyzes the received text using the Google Cloud NLP API and extracts relevant keywords. For example, the keyword "machine settings" can be extracted from the question "Please tell me how to set up the machine."

[0164] 4. Database Search and User Identification:

[0165] The server searches the knowledge database based on the extracted keywords. After retrieving data containing relevant information, it identifies other users (workers) with the appropriate expertise.

[0166] 5. Notice to Identified Users:

[0167] Use Firebase Cloud Messaging to send notifications to identified users about their questions or issues.

[0168] 6. Answer submission and feedback:

[0169] The identified user enters a solution to the problem, which is sent to the server, which provides the solution to the original user and also receives feedback and stores it in a database.

[0170] Examples of concrete examples and prompts

[0171] Examples:

[0172] A factory worker asks the smart glasses how to set up a new machine by voice: "Please tell me how to set up a new machine." The voice is converted into text and sent to the server. The server extracts the keyword "machine setting" and searches a database of past information. A technician with relevant knowledge is identified and a notification is sent. The technician provides an appropriate answer, which is sent back to the worker. The worker configures the machine based on the answer and sends feedback.

[0173] Example prompt sentence:

[0174] "A user speaks a question into a pair of smart glasses, such as 'How do I configure my new machine?' Design a system that sends this question to a server, identifies users with relevant expertise, and provides an answer in real time."

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] Audio Input:

[0178] Using smart glasses or a smartphone, users can voice-input questions or issues that arise on-site. For example, they might say, "Please tell me how to set up a new machine." This voice data is then captured by the smart device.

[0179] Input: Audio data

[0180] Output: Captured audio data

[0181] How it works: The user speaks their question or problem into the microphone on their smart device.

[0182] Step 2:

[0183] Speech to text conversion:

[0184] The device uses the speech_recognition library to convert the captured voice data into text data, for example, "How do I set up my new machine?"

[0185] Input: Captured audio data

[0186] Output: Text data

[0187] How it works: Your smart device processes the voice data using a cloud service or built-in speech recognition function and converts it into text.

[0188] Step 3:

[0189] Sending text data:

[0190] The device sends the converted text data to the server using a network connection. For example, the text "How do I set up my new machine?" is sent to the server.

[0191] Input: Text data

[0192] Output: Text data sent to the server

[0193] How it works: A smart device sends text data to a server via a network.

[0194] Step 4:

[0195] Natural Language Processing Analysis:

[0196] The server analyzes the received text data using the Google Cloud NLP API and extracts relevant keywords. For example, "machine settings" is extracted from the text.

[0197] Input: Text data

[0198] Output: Extracted keywords

[0199] How it works: The server passes text data to the API, which performs natural language processing to extract keywords.

[0200] Step 5:

[0201] Knowledge Database Search:

[0202] The server searches a knowledge database based on the extracted keywords, thereby identifying users and information with related expertise.

[0203] Input: Extracted keywords

[0204] Output: Related expertise and user information

[0205] How it works: The server sends keywords as queries to the knowledge database to search for relevant data.

[0206] Step 6:

[0207] Expertise Identification and Notification:

[0208] The server uses the search results to identify users with the appropriate expertise and sends notifications using Firebase Cloud Messaging, including questions and issues.

[0209] Input: relevant expertise and user information

[0210] Output: Send notification

[0211] What happens: The server sends a push notification to the specified user.

[0212] Step 7:

[0213] User answer input:

[0214] The identified user is notified and uses the device to enter a response, such as "Please refer to the documentation on how to set up the machine."

[0215] Input: Notification content

[0216] Output: Response data

[0217] How it works: A user with expert knowledge types an answer into a terminal and sends it to the server.

[0218] Step 8:

[0219] Providing answers:

[0220] The server provides the received response to the original user, allowing the original user to quickly obtain information to resolve the problem.

[0221] Input: Answer data

[0222] Output: Provide the answer to the original user

[0223] Operation: The server sends the response data to the original user's device.

[0224] Step 9:

[0225] Collecting feedback:

[0226] The user inputs feedback on the answer from the terminal and sends it to the server, which stores this feedback in a database.

[0227] Input: User feedback

[0228] Output: Saved feedback data

[0229] How it works: The server receives the feedback and stores it in a database.

[0230] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0231] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also improves the quality of the services provided by combining it with an emotion engine that recognizes the user's emotions.

[0232] Explanation of program processing

[0233] 1. User questions and issues posted

[0234] The user uses the terminal to input their question or problem and submit it. For example, they might input, "Please tell me how to create materials for a new marketing strategy."

[0235] 2. Post content collection and emotion recognition

[0236] The device processes the user's input using an emotion engine to recognize the user's emotions. The emotion data includes emotion categories such as joy, sadness, and anger.

[0237] The device sends the question or issue along with the recognized emotion data to the server.

[0238] 3. Receiving and analyzing questions and issues

[0239] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0240] 4. Emotional Data Analysis

[0241] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[0242] 5. Knowledge Database Reference

[0243] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[0244] 6. Identifying users with the right expertise

[0245] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[0246] 7. Notification to Identified Users

[0247] The server notifies the identified user of their questions or issues along with their emotional data and asks for a response. This notification is sent via push notifications, emails, or other means.

[0248] 8. User-generated answers

[0249] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0250] 9. Receipt and Notification of Responses

[0251] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[0252] 10. Providing Feedback

[0253] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[0254] The device sends the feedback data and the recognized emotions to the server.

[0255] 11. Feedback Storage and Notification

[0256] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[0257] Specific processing examples

[0258] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[0259] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0260] The processing flow will be explained below.

[0261] Program processing flow

[0262] Step 1:

[0263] The user can input their question or problem through the terminal and submit it. For example, they can input, "Please tell me how to create materials for a new marketing strategy."

[0264] Step 2:

[0265] The device processes the input questions and issues using an emotion engine to recognize the user's emotions. Emotion data includes categories of emotions such as joy, sadness, anger, and anxiety.

[0266] Step 3:

[0267] The device sends the recognized emotion data and the question or problem to the server. The sent data includes the user ID, input content, emotion data, and the date and time of sending.

[0268] Step 4:

[0269] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0270] Step 5:

[0271] The server searches the knowledge database based on the extracted keywords and emotion data to collect related information, and selects high-priority information based on the emotion data.

[0272] Step 6:

[0273] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify users with appropriate expertise. For example, employee A who is knowledgeable about marketing strategies and employee B who is skilled in creating materials can be identified.

[0274] Step 7:

[0275] The server notifies the identified user of their questions or issues along with their emotional data and asks for their answers. These notifications are sent via push notifications, emails, etc.

[0276] Step 8:

[0277] The identified users use the devices to input answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0278] Step 9:

[0279] The terminal sends the entered answer data to the server. The sent data includes the answer content, respondent ID, and answer date and time.

[0280] Step 10:

[0281] The server then provides the responses received from employees to the original sender. To do this, the server uses push notifications, emails, etc.

[0282] Step 11:

[0283] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[0284] Step 12:

[0285] The user inputs feedback on the provided answer through the terminal, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[0286] Step 13:

[0287] The device sends the feedback data and the recognized emotion to the server. The sent data includes the feedback content, emotion data, user ID, and the date and time of sending.

[0288] Step 14:

[0289] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, etc.

[0290] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises from differences in knowledge levels between employees and their superiors.

[0291] Example 2

[0292] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0293] When sharing information or solving problems within a company, friction in communication arises due to differences in the knowledge levels of employees and their superiors. This friction prevents fast and effective information sharing, resulting in a decline in work efficiency. To address this issue, the present invention aims to realize more personalized responses and reduce friction in communication by recognizing users' emotions and providing information that takes these emotions into consideration.

[0294] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0295] In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the input content with an emotion engine and recognize the user's emotion; means for the terminal to transmit the recognized emotion data and the question or problem to the server; means for the server to analyze the received question or problem using natural language processing technology and extract related keywords; means for the server to analyze the received emotion data and set priorities for the search results; means for the server to search a knowledge database based on the extracted keywords and collect related information; means for the server to identify other users with appropriate expertise based on information in the knowledge database and user profile data; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the response received from the user to the user who sent the response. This reduces communication friction caused by differences in knowledge levels between employees and their superiors, enabling quick and effective information sharing.

[0296] A "terminal" is a device that allows a user to input questions or issues and send the content, and includes personal computers, smartphones, etc.

[0297] An "emotion engine" is software that processes user input and recognizes the emotions it conveys, and has the ability to classify emotions such as joy, anger, and sadness.

[0298] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and is expressed as text data.

[0299] The "server" is a central system that processes questions and issues received from users, searches a database and provides appropriate information.

[0300] "Natural language processing technology" is a technology that analyzes text data sent by users and extracts relevant keywords and important information.

[0301] "Keywords" are words or phrases that indicate important topics of a question or issue, extracted using natural language processing techniques.

[0302] A "knowledge database" is a data storage system that stores past questions, answers, and specialized knowledge, and is used by the server for searches.

[0303] "Profile data" refers to a dataset that includes information such as each employee's expertise, past response history, and emotional response experience.

[0304] "Identified User" refers to a user who has been determined to have the appropriate expertise for a question or issue based on the knowledge database and profile data.

[0305] "Feedback data" refers to data that indicates evaluations and opinions of answers provided by users, and is reanalyzed by the emotion engine.

[0306] MODE FOR CARRYING OUT THE INVENTION

[0307] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also aims to improve the quality of services provided through emotion recognition.

[0308] System Configuration

[0309] The system consists of the following main components:

[0310] Terminal: A device through which a user inputs questions or issues. Specific examples include personal computers and smartphones.

[0311] Emotion engine: Software that analyzes text data to recognize a user's emotions. A specific example is IBM Watson (registered trademark) Tone Analyzer.

[0312] Server: The central system that processes data received from users and provides appropriate information. Google Cloud Natural Language API is used as the natural language processing technology.

[0313] Knowledge database: A data storage system that stores past questions, answers, and specialized knowledge.

[0314] Profile database: A data set containing information such as each employee's expertise, past response history, and emotional response experience.

[0315] Program processing flow

[0316] The system processes as follows:

[0317] 1. User questions and issues posted

[0318] A user uses a device to type in and submit a question or issue, for example, "How do I create a document for a new marketing strategy?"

[0319] 2. Post content collection and emotion recognition

[0320] The device processes the user's input using an emotion engine and recognizes the user's emotions. The emotion data includes emotion classifications such as joy, sadness, and anger. The device then sends the recognized emotion data along with the question or issue to the server.

[0321] 3. Receiving and analyzing questions and issues

[0322] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0323] 4. Emotional Data Analysis

[0324] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[0325] 5. Knowledge Database Reference

[0326] The server searches a knowledge database based on the extracted keywords and emotion data. This database contains past questions and answers, as well as specialized knowledge.

[0327] 6. Identifying users with the right expertise

[0328] The server identifies other users with appropriate expertise based on the knowledge database and profile database. For example, employee A who is knowledgeable about marketing strategies and employee B who is knowledgeable about document creation are identified.

[0329] 7. Notification to Identified Users

[0330] The server notifies the identified user of their question or problem along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[0331] 8. User-generated answers

[0332] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0333] 9. Receipt and Notification of Responses

[0334] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[0335] 10. Providing Feedback

[0336] The user enters feedback on the provided answer, which is then analyzed by the emotion engine. For example, the user enters feedback such as "This was very helpful. Thank you very much." The device then sends the feedback data and the recognized emotion to the server.

[0337] 11. Feedback Storage and Notification

[0338] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers.

[0339] Specific examples

[0340] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[0341] Example prompts for generative AI models

[0342] Example prompt:

[0343] Please explain the program processing for the following system in natural language. Please write so that the subject is either the server, the terminal, or the user. Please use plain sentence endings.

[0344] system:

[0345] A system to reduce communication friction caused by differences in knowledge levels between employees and their superiors. By combining it with an emotion engine, the quality of the services provided is improved.

[0346] Specific processing steps:

[0347] 1. User questions and issues posted

[0348] 2. Post content collection and emotion recognition

[0349] 3. Receiving and analyzing questions and issues

[0350] 4. Emotional Data Analysis

[0351] 5. Knowledge Database Reference

[0352] 6. Identifying users with the right expertise

[0353] 7. Notification to Identified Users

[0354] 8. User-generated answers

[0355] 9. Receipt and Notification of Responses

[0356] 10. Providing Feedback

[0357] 11. Feedback Storage and Notification

[0358] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, it provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0360] Step 1:

[0361] The user uses the terminal to input a question or issue and transmits the content. For example, the user might input "Please tell me how to create materials for a new marketing strategy." This question or issue becomes input data and is transmitted to the terminal. The output is the input text information.

[0362] Step 2:

[0363] The device processes the input content using an emotion engine to recognize the user's emotion. The input is text data entered by the user, and this data is analyzed using an emotion engine (e.g., IBM Watson Tone Analyzer). As a result of the analysis, the user's emotion data (e.g., "anxiety," "confusion," etc.) is obtained. The output is the recognized emotion data.

[0364] Step 3:

[0365] The device sends the recognized emotion data and the text data of the question or problem to the server. The input is the emotion data obtained in step 2 and the text data of the user's question or problem. The output is the dataset sent to the server.

[0366] Step 4:

[0367] The server analyzes the questions and issues it receives using natural language processing technology (for example, Google Cloud Natural Language API) and extracts related keywords. The input is the dataset sent in step 3, and the natural language processing engine analyzes the text data to extract keywords such as "marketing strategy" and "document creation." The output is the extracted keywords.

[0368] Step 5:

[0369] The server analyzes the received emotion data and sets priorities for search results and inquiries. The input is the emotion data and keywords obtained in steps 2 and 4. By analyzing the emotion data, adjustments are made to prioritize a quick response, for example, if the user is feeling "anger." The output is prioritized keywords and inquiries.

[0370] Step 6:

[0371] The server searches the knowledge database based on the prioritized keywords and the query. The database contains past questions, answers, and specialized knowledge. The input is the prioritized keywords and the query set in step 5. The server searches for relevant information in the knowledge database and collects the results. The output is the search result information.

[0372] Step 7:

[0373] The server identifies other users with appropriate expertise based on the information in the knowledge database and the user's profile data. The input is the information retrieved in step 6 and the expertise information from the profile data database. The server compares these data and identifies users who are knowledgeable about marketing strategies or document creation, for example. The output is the identified appropriate users.

[0374] Step 8:

[0375] The server notifies the identified user of the question or issue along with emotion data and asks for a response. This notification is done using means such as push notification or email. The input is the user identified in step 7 and the question / issue data from step 3. The output is a notification to the identified user.

[0376] Step 9:

[0377] The identified user uses the terminal to input answers to questions or issues. For example, the user can respond, "Please refer to past marketing strategy materials," and the server can reply, "We will provide you with a template that will help you create the materials." The input is the answer data entered by the identified user. The output is the answer data sent to the server.

[0378] Step 10:

[0379] The server receives the identified user's answer and provides it to the user who posted the question. The input is the answer data obtained in step 9. The server sends this data to the user's terminal and provides information for solving the problem. The output is information provided to the user who posted the question.

[0380] Step 11:

[0381] The user inputs feedback for the provided answer, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much." The input is the feedback text data entered by the user. The output is the feedback data with emotion data analyzed by the emotion engine.

[0382] Step 12:

[0383] The terminal sends the feedback data to the server, which then stores it in the database. The input is the feedback data analyzed in step 11. The server stores it in the database and notifies the relevant employees and managers. The output is the stored feedback data and the notification.

[0384] (Application example 2)

[0385] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0386] In conventional factories, there was a lack of means to quickly respond to questions or concerns that operators had while working. This made it difficult to solve problems efficiently, causing stress and reduced productivity for operators. Furthermore, personalized responses that took into account the emotions felt by operators were not provided, which sometimes led to friction in communication.

[0387] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the user's input content using an emotion engine, recognize the user's emotion, and transmit the input content together with emotion data to the server; means for the server to analyze the question or problem received by the server using natural language processing technology and extract related keywords; means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the user with the response received from the user. This makes it possible to respond to questions or problems quickly and efficiently and provide personalized responses that take emotion data into consideration, thereby reducing communication friction and reducing operator stress.

[0388] A "user" is an entity that uses the system to input and send questions or issues.

[0389] The "terminal" is a device where users can input and send questions and issues, and which also recognizes emotions using an emotion engine.

[0390] The "emotion engine" is a technology that analyzes the user's input and voice and recognizes and classifies the user's emotions.

[0391] The "server" is a device that uses natural language processing technology to analyze received questions and issues, searches a knowledge database based on extracted keywords, identifies other users with appropriate expertise, and promotes notifications and responses.

[0392] "Natural language processing technology" is a technology that analyzes text data entered by a user and extracts related keywords.

[0393] "Keywords" are important words or phrases extracted from users' questions or issues.

[0394] A "knowledge database" is a collection of past questions and answers, as well as specialized knowledge.

[0395] "Expertise" is specific knowledge and skills that provide solutions to specific problems or challenges.

[0396] "Feedback" refers to ratings and comments that users make on answers provided.

[0397] "Emotion data" is data that indicates the emotional state of the user as recognized by the emotion engine.

[0398] "Profile Data" is information about an individual, such as an employee's expertise or past response history.

[0399] "Matching" is the process of matching a specific user with the most appropriate question.

[0400] This invention is a system that responds quickly and effectively to specific questions and issues by linking a terminal, an emotion engine, natural language processing technology, a knowledge database, and a server. A specific description will be given of an embodiment of this invention.

[0401] System Program

[0402] 1. Hardware and Software

[0403] Device: The device a user uses to input and submit a question or issue, such as smart glasses or a head-mounted display (e.g., Microsoft® HoloLens®).

[0404] Emotion engine: Technology that analyzes user voice input and text data to recognize emotions. As an example, we will use Affectiva's emotion recognition engine.

[0405] Natural language processing technology: Technology that analyzes user input data and extracts relevant keywords. We will use SpaCy as an example.

[0406] Server: A device that processes the received questions, issues, and sentiment data, searches a knowledge database, and identifies other users with appropriate expertise. For example, AWS (registered trademark) EC2 is used.

[0407] Knowledge database: A collection of past questions and answers, as well as accumulated expert knowledge. For example, we use Elasticsearch.

[0408] 2. Program processing flow

[0409] 1. User submission of questions and issues:

[0410] The user uses the terminal to input their questions or issues and send them. For example, they might input, "I don't know how to set up the manufacturing machine. Please help me."

[0411] 2. Post content collection and emotion recognition:

[0412] The device processes the user's input using an emotion engine to recognize the user's emotions, and sends the user's questions and issues along with emotional data (e.g., anxiety, irritation, etc.) to the server.

[0413] 3. Receiving and analyzing questions and issues:

[0414] The server analyzes the received questions and issues using natural language processing technology and extracts related keywords (e.g., "manufacturing machinery," "setting methods," etc.).

[0415] 4. Sentiment Data Analysis:

[0416] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses "anxiety," it prioritizes a quick response.

[0417] 5. Knowledge Base Reference:

[0418] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[0419] 6. Identifying users with the right expertise:

[0420] The server matches the profile data against a knowledge database to identify other users with relevant expertise, for example, users who are "familiar with setting up manufacturing machines."

[0421] 7. Notice to Identified Users:

[0422] The server notifies the identified user of their questions or issues along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[0423] 8. User responses:

[0424] The identified user uses the terminal to input answers to questions or issues, such as providing "detailed instructions on how to set up a manufacturing machine."

[0425] 9. Receiving and notifying responses:

[0426] The server receives the response and provides it to the original user, allowing the user to quickly obtain information to resolve the problem.

[0427] 10. Providing Feedback:

[0428] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[0429] 11. Feedback Storage and Notification:

[0430] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[0431] Prompt Sentence Examples

[0432] "I don't know how to set up the manufacturing machine. Please help me."

[0433] "Please make sure this part is installed correctly. I'm a little worried."

[0434] In this way, the system responds to user questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, reducing operator stress and improving productivity.

[0435] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0436] Step 1:

[0437] The user sends questions or issues to the device via voice or text input. The input data is the specific content of the question or issue, such as "I don't know how to set up a manufacturing machine. Please help me." The input data is saved as text.

[0438] Step 2:

[0439] The device passes the user's voice input or text to an emotion engine to recognize the user's emotion. The emotion engine (e.g., Affectiva) analyzes the voice or text data and generates emotion data (e.g., anxiety, irritation, etc.). This identifies the user's emotion and adds that information.

[0440] Step 3:

[0441] The device sends the recognized emotion data along with the text data of the question or task to the server. The sent data includes the content of the question or task and the user's emotional state at that time.

[0442] Step 4:

[0443] The questions and issues received by the server are analyzed using natural language processing technology. The natural language processing technology used (e.g., SpaCy) analyzes the text data and extracts related keywords. For example, keywords such as "manufacturing machine" and "setting method" are extracted.

[0444] Step 5:

[0445] The server searches a knowledge database based on the extracted keywords and the recognized emotion data. The database technology used (e.g., Elasticsearch) searches for related information and collects the most appropriate solutions and information. This allows related past questions and answers to be retrieved.

[0446] Step 6:

[0447] The server compares the information in the knowledge database with the profile database to identify users with appropriate expertise. The profile database contains each user's expertise and past response history, so for example, a user who is "expert in setting up manufacturing machines" can be identified.

[0448] Step 7:

[0449] The server notifies the identified user of the question or issue. The notification is sent via push notification or email along with emotion data, prompting the identified user to respond. This notification is expected to result in a prompt response.

[0450] Step 8:

[0451] Identified users input answers to questions and issues through terminals. The input data is specific solutions or reference materials, such as "detailed instructions on how to set up manufacturing machines."

[0452] Step 9:

[0453] The server receives the answer and provides it to the user. The server then sends the answer back to the original user, who then confirms the answer through their device. This allows the user to quickly obtain information to solve the problem.

[0454] Step 10:

[0455] The user inputs feedback on the answer provided through the terminal. The feedback data is analyzed by the emotion engine to obtain the user's emotional state and evaluation. For example, feedback such as "This was very helpful. Thank you very much" may be input.

[0456] Step 11:

[0457] The server stores the feedback and sentiment data in a database and notifies relevant employees and managers, providing insights to improve the quality of responses across the system.

[0458] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0459] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0460] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0461] [Second embodiment]

[0462] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0463] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0464] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0465] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0466] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0467] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0468] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0469] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0470] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0471] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0472] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0473] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0474] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports rapid and effective information sharing and problem solving within a company. This system begins when a user inputs and sends a question or issue via a terminal, and the server analyzes the content using natural language processing technology and identifies other users with appropriate expertise.

[0475] Explanation of program processing

[0476] 1. User questions and issues posted

[0477] A user uses a terminal to enter their question or issue and submit it to the system. For example, a user might enter, "Please tell me how to create materials for a new marketing strategy."

[0478] 2. Collection and transmission of posts

[0479] The terminal transmits the user's input to the server.

[0480] 3. Receiving and analyzing questions and issues

[0481] The server uses natural language processing technology to analyze the questions and issues received from users and extract related keywords, such as "marketing strategy" and "document creation."

[0482] 4. Knowledge database reference

[0483] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions, answers, and specialized knowledge.

[0484] 5. Identifying users with the right expertise

[0485] The server compares the knowledge database with employee profile data to identify users with the appropriate expertise. For example, Employee A is knowledgeable about marketing, while Employee B is skilled in creating documents.

[0486] 6. Notification to Identified Users

[0487] The server then notifies the identified user of their question or issue and asks for a response. This process can be done using methods such as push notifications or emails.

[0488] 7. User-generated answers

[0489] The identified users use the devices to input and send answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0490] 8. Receiving and notifying responses

[0491] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[0492] 9. Providing Feedback

[0493] The user inputs feedback on the answers provided through the terminal and sends it to the server, which stores the feedback in a database and notifies the relevant users and administrators.

[0494] Specific processing examples

[0495] For example, if a user sends a question from a terminal such as "I want to know new methods for sales strategy," the server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C. Employee C receives this notification and enters an answer from his / her terminal, which is provided to the user. The user enters feedback on this answer, which the server receives and stores in the database.

[0496] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0497] The processing flow will be explained below.

[0498] Program processing flow

[0499] Step 1:

[0500] The user can input their questions or issues through the device and submit them. For example, they could input, "Please tell me how to create materials for a new marketing strategy."

[0501] Step 2:

[0502] The device sends the user's input to the server. The data sent includes meta-information such as the user ID, question, and the date and time of submission.

[0503] Step 3:

[0504] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0505] Step 4:

[0506] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions and answers, as well as specialized knowledge.

[0507] Step 5:

[0508] The server compares the knowledge database with employee profile data (expertise, past response history) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[0509] Step 6:

[0510] The server notifies the identified user of their questions or issues and requests answers. This notification is sent via push notifications, emails, and other means.

[0511] Step 7:

[0512] The identified users use the devices to input answers to questions and issues. Employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide templates that will help you create the materials."

[0513] Step 8:

[0514] The terminal transmits the input response data to the server. The transmitted data includes the response content, respondent ID, and response date and time.

[0515] Step 9:

[0516] The server then provides the responses received from the employees to the original sender. To do this, the server uses push notifications, emails, etc.

[0517] Step 10:

[0518] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[0519] Step 11:

[0520] The user inputs feedback for the provided answer through the terminal and transmits it to the server. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[0521] Step 12:

[0522] The terminal sends feedback data to the server, which includes the feedback content, the user ID, and the transmission date and time.

[0523] Step 13:

[0524] The server stores the received feedback in a database and notifies relevant employees and managers using push notifications, emails, etc.

[0525] In this way, the system of the present invention responds quickly and efficiently to questions and issues, and reduces communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0526] Example 1

[0527] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0528] The goal is to provide a system that supports quick and effective information sharing and problem solving within a company. In particular, it is required to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors, and enable efficient responses.

[0529] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0530] In this invention, the server includes means for users to input and transmit questions or issues via an information terminal, means for analyzing the received questions or issues using natural language processing technology and extracting related terms, means for searching a knowledge database based on the extracted terms and identifying other users with appropriate expertise, means for notifying the identified users of the questions or issues and prompting them to respond, means for the identified users to input and transmit answers via their information terminals, and means for providing the transmitted answers to the original users. This makes it possible to respond to questions or issues quickly and efficiently and reduce communication friction caused by differences in knowledge levels between employees and their superiors.

[0531] "Information terminal" refers to an electronic device that a user uses to input, send, and receive data over a communications network. Examples include personal computers, smartphones, and tablets.

[0532] "Natural language processing technology" refers to a set of algorithms and techniques used by a server to analyze text data and understand words and phrases. This includes techniques such as SpaCy and BERT.

[0533] "Phrases" refer to important words and phrases extracted from the text entered by the user using natural language processing technology.

[0534] A "knowledge database" is a collection of data used by a server to gather information based on analysis, including past questions and answers and specialized knowledge. Examples include databases such as PostgreSQL and Elasticsearch.

[0535] "Expertise" refers to detailed knowledge and skills in a particular field or area that the server uses to provide the best possible answers to questions or challenges.

[0536] "Notification" refers to a message or alert sent by the server to an identified user to inform them of a question or issue and prompt them to respond, including email, push notification, messaging app, etc.

[0537] "Feedback" refers to the process by which the original user sends their rating and opinion on the provided answer to the server. This information is stored in a database for later analysis.

[0538] This invention is a system that supports quick and effective information sharing and problem solving within a company. The purpose of this system is to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors. Specific embodiments are shown below.

[0539] Users use an information terminal (e.g., PC or smartphone) to input their questions or issues and send them to the system. This input is saved in text format, and the information terminal sends the text data to the server. HTTPS is used as the communication protocol, so the data is encrypted before being sent.

[0540] The server analyzes the text data received from the user using natural language processing technology (e.g., SpaCy, BERT) and extracts related words. For example, if a user types, "Please tell me how to create a document for a new marketing strategy," the words "marketing strategy" and "document creation" are extracted.

[0541] The server searches a knowledge database (e.g., PostgreSQL or Elasticsearch) based on the extracted phrases to gather relevant information. This database stores past questions and answers, as well as specialized knowledge.

[0542] Next, the server identifies users with the appropriate expertise by comparing the results of the knowledge database search with the personal data of registered employees. For example, employee A who is knowledgeable about marketing and employee B who is skilled in creating documents can be identified.

[0543] The server notifies the identified user of the user's questions or issues through a notification system (e.g., email, push notification, messaging app). When the identified user enters and sends an answer through an information terminal, this answer is also received by the server and provided to the original user.

[0544] The original user inputs feedback on the provided answer through the information terminal and sends it to the server, which stores this feedback in a database and notifies the relevant users and administrators.

[0545] Specific examples

[0546] For example, if a user inputs a question such as "I would like to know new methods for sales strategies," the server receives the question, extracts the phrases "sales strategies" and "new methods," and searches the knowledge database. Based on the search results, it identifies employee C, who is knowledgeable about "sales strategies," and sends a notification to employee C. Employee C receives the notification and enters an answer on his information terminal, which is then provided to the original user. The user enters feedback on this answer, which the server receives and stores in the database.

[0547] Prompt Sentence Examples

[0548] "How do I create materials for a new marketing strategy?"

[0549] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0550] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0551] Step 1:

[0552] A user uses an information terminal to input and submit a question or problem. The input text data is in the format of "Please tell me how to create materials for a new marketing strategy." The terminal sends this text data to a server. The input data is in the form of text data, and the output is the text data sent to the server.

[0553] Step 2:

[0554] The server receives text data sent by the user. The server analyzes the received text data using natural language processing technology. Specifically, the text data is tokenized and important words and phrases are extracted. For example, the words "marketing strategy" and "document creation" are extracted. The input is the text data from the user, and the output is the extracted words and phrases.

[0555] Step 3:

[0556] The server queries a knowledge database based on the extracted phrases to collect related information. The knowledge database stores past questions and answers, and the query results include this related information. For example, a query such as "How to create materials for marketing strategies" returns related documents and answers. The input is the extracted phrases, and the output is related information.

[0557] Step 4:

[0558] Based on the information collected by the server, users with the appropriate expertise are identified. The server compares the knowledge database with the personal data of employees to find the most suitable answerer. For example, employee A who is knowledgeable about "marketing" and employee B who is skilled in "document creation" are identified. The input is the collected information, and the output is the identified user.

[0559] Step 5:

[0560] The server sends a notification to the identified user. The notification is sent via email, push notification, or messaging app. The notification contains the user's question or problem. For example, a notification may be sent in response to a question such as, "How do I create materials for a new marketing strategy?" The input is the identified user, and the output is the notification.

[0561] Step 6:

[0562] The identified user inputs and sends a response via the information terminal. For example, employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide a template that will be useful for creating materials." The terminal sends this response to the server. The input is the response from the user, and the output is the response sent to the server.

[0563] Step 7:

[0564] The server provides the answer received from the identified user to the original user. The answer is notified to the terminal and provided in a format that can be viewed by the original user. For example, an answer such as "Please refer to past marketing strategy materials" is displayed. The input is the received answer, and the output is the answer provided to the original user.

[0565] Step 8:

[0566] The original user inputs feedback for the provided answer and sends it through the terminal. The server receives this feedback and stores it in a database. The input is the feedback, and the output is the feedback stored in the database.

[0567] (Application example 1)

[0568] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0569] In modern companies, differences in knowledge levels between employees and superiors and communication friction can occur, delaying information sharing and problem-solving. Furthermore, at factories and other worksites, there is a lack of ways to quickly respond to technical issues and questions faced by workers, which can lead to reduced production efficiency and quality problems. There is a need to provide a means to resolve these issues and enable fast and effective information sharing within the company.

[0570] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0571] In this invention, the server includes: a means for a user to input and transmit a question or problem via a terminal; a means for analyzing the received question or problem using natural language processing technology and extracting related keywords; a means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; a means for the server to notify the identified users of the question or problem and prompt them to respond; a means for the server to provide the user with the response received from the user; and a means for using a smart device to input the question or problem by voice from the site, convert it into text, and transmit it to the server. This enables quick problem solving and information sharing throughout the company, including site workers.

[0572] A "user" is a person or agent who utilizes the system to input and submit questions or issues.

[0573] A "terminal" is a device used by a user to input and send questions or issues, and includes smartphones, smart glasses, head-mounted displays, robots, etc.

[0574] "Questions and Issues" are problems users are facing or questions that need to be resolved.

[0575] A "server" is a central system that receives questions and issues, analyzes them, searches for relevant information, identifies users with specialized knowledge, notifies them, and provides answers.

[0576] "Natural language processing technology" is a computational technology that analyzes questions and issues received by the server and extracts related keywords.

[0577] "Related keywords" are important words or phrases necessary for solving a problem that are extracted from the question or issue entered by the user.

[0578] A "knowledge database" is a collection of searchable information that stores past questions, answers, and specialized knowledge.

[0579] "Other users" are people or agents with appropriate expertise for a question or issue.

[0580] "Notification" is the process by which the server notifies identified users of questions or issues.

[0581] The "means for prompting an answer" is a method by which the server requests an answer to resolve a question or problem from the identified user.

[0582] A "smart device" is a device that has functions such as voice input and text input and is used to send questions and issues from the field.

[0583] The "site" is the location where the user actually works, and includes a factory, a production line, an office, and the like.

[0584] "Voice input" refers to the act of a user verbally expressing a question or problem using a microphone.

[0585] "Convert to text" is the process of converting voice-input information into character string information.

[0586] "Send" is the act of moving information such as a question, assignment, answer, or notice from one point to another.

[0587] The present invention is a system that supports rapid and effective information sharing and problem solving within a company, and is configured to be usable particularly in factories and on-site. This system begins when a user inputs and transmits a question or issue by voice via a terminal. The server then analyzes the content using natural language processing technology, identifies other users with appropriate expertise, and notifies them.

[0588] Program Overview

[0589] When a user uses a smart device (e.g., smart glasses) to voice-input a question or issue from the field, it is converted into text and sent to a server. The server uses natural language processing technology to analyze the received question or issue and extract relevant keywords. These keywords are used to search a knowledge database to identify other users with appropriate expertise. Identified users are notified and can request an answer. Once an answer is provided, the server provides it to the original user. It also receives feedback from users and stores it in a database.

[0590] Hardware and software used

[0591] Smart devices: Devices such as smart glasses, smartphones, and head-mounted displays that have voice input and communication capabilities.

[0592] Server: Responsible for data analysis, natural language processing, database search, and notification functions.

[0593] Software used includes Python's speech_recognition library, requests library, Google Cloud NLP API, and Firebase Cloud Messaging.

[0594] Natural language explanation of the process

[0595] 1. User speaks:

[0596] Using smart glasses or a smartphone, users speak their questions or tasks, which are then picked up by the device via a microphone.

[0597] 2. Speech to text conversion:

[0598] The smart device converts the speech into text using the speech_recognition library, and the converted text is sent directly to the server.

[0599] 3. Natural Language Processing on the Server:

[0600] The server analyzes the received text using the Google Cloud NLP API and extracts relevant keywords. For example, the keyword "machine settings" can be extracted from the question "Please tell me how to set up the machine."

[0601] 4. Database Search and User Identification:

[0602] The server searches the knowledge database based on the extracted keywords. After retrieving data containing relevant information, it identifies other users (workers) with the appropriate expertise.

[0603] 5. Notice to Identified Users:

[0604] Use Firebase Cloud Messaging to send notifications to identified users about their questions or issues.

[0605] 6. Answer submission and feedback:

[0606] The identified user enters a solution to the problem, which is sent to the server, which provides the solution to the original user and also receives feedback and stores it in a database.

[0607] Examples of concrete examples and prompts

[0608] Examples:

[0609] A factory worker asks the smart glasses how to set up a new machine by voice: "Please tell me how to set up a new machine." The voice is converted into text and sent to the server. The server extracts the keyword "machine setting" and searches a database of past information. A technician with relevant knowledge is identified and a notification is sent. The technician provides an appropriate answer, which is sent back to the worker. The worker configures the machine based on the answer and sends feedback.

[0610] Example prompt sentence:

[0611] "A user speaks a question into a pair of smart glasses, such as 'How do I configure my new machine?' Design a system that sends this question to a server, identifies users with relevant expertise, and provides an answer in real time."

[0612] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0613] Step 1:

[0614] Audio Input:

[0615] Using smart glasses or a smartphone, users can voice-input questions or issues that arise on-site. For example, they might say, "Please tell me how to set up a new machine." This voice data is then captured by the smart device.

[0616] Input: Audio data

[0617] Output: Captured audio data

[0618] How it works: The user speaks their question or problem into the microphone on their smart device.

[0619] Step 2:

[0620] Speech to text conversion:

[0621] The device uses the speech_recognition library to convert the captured voice data into text data, for example, "How do I set up my new machine?"

[0622] Input: Captured audio data

[0623] Output: Text data

[0624] How it works: Your smart device processes the voice data using a cloud service or built-in speech recognition function and converts it into text.

[0625] Step 3:

[0626] Sending text data:

[0627] The device sends the converted text data to the server using a network connection. For example, the text "How do I set up my new machine?" is sent to the server.

[0628] Input: Text data

[0629] Output: Text data sent to the server

[0630] How it works: A smart device sends text data to a server via a network.

[0631] Step 4:

[0632] Natural Language Processing Analysis:

[0633] The server analyzes the received text data using the Google Cloud NLP API and extracts relevant keywords. For example, "machine settings" is extracted from the text.

[0634] Input: Text data

[0635] Output: Extracted keywords

[0636] How it works: The server passes text data to the API, which performs natural language processing to extract keywords.

[0637] Step 5:

[0638] Knowledge Database Search:

[0639] The server searches a knowledge database based on the extracted keywords, thereby identifying users and information with related expertise.

[0640] Input: Extracted keywords

[0641] Output: Related expertise and user information

[0642] How it works: The server sends keywords as queries to the knowledge database to search for relevant data.

[0643] Step 6:

[0644] Expertise Identification and Notification:

[0645] The server uses the search results to identify users with the appropriate expertise and sends notifications using Firebase Cloud Messaging, including questions and issues.

[0646] Input: relevant expertise and user information

[0647] Output: Send notification

[0648] What happens: The server sends a push notification to the specified user.

[0649] Step 7:

[0650] User answer input:

[0651] The identified user is notified and uses the device to enter a response, such as "Please refer to the documentation on how to set up the machine."

[0652] Input: Notification content

[0653] Output: Response data

[0654] How it works: A user with expert knowledge types an answer into a terminal and sends it to the server.

[0655] Step 8:

[0656] Providing answers:

[0657] The server provides the received response to the original user, allowing the original user to quickly obtain information to resolve the problem.

[0658] Input: Answer data

[0659] Output: Provide the answer to the original user

[0660] Operation: The server sends the response data to the original user's device.

[0661] Step 9:

[0662] Collecting feedback:

[0663] The user inputs feedback on the answer from the terminal and sends it to the server, which stores this feedback in a database.

[0664] Input: User feedback

[0665] Output: Saved feedback data

[0666] How it works: The server receives the feedback and stores it in a database.

[0667] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0668] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also improves the quality of the services provided by combining it with an emotion engine that recognizes the user's emotions.

[0669] Explanation of program processing

[0670] 1. User questions and issues posted

[0671] The user uses the terminal to input their question or problem and submit it. For example, they might input, "Please tell me how to create materials for a new marketing strategy."

[0672] 2. Post content collection and emotion recognition

[0673] The device processes the user's input using an emotion engine to recognize the user's emotions. The emotion data includes emotion categories such as joy, sadness, and anger.

[0674] The device sends the question or issue along with the recognized emotion data to the server.

[0675] 3. Receiving and analyzing questions and issues

[0676] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0677] 4. Emotional Data Analysis

[0678] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[0679] 5. Knowledge Database Reference

[0680] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[0681] 6. Identifying users with the right expertise

[0682] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[0683] 7. Notification to Identified Users

[0684] The server notifies the identified user of their questions or issues along with their emotional data and asks for a response. This notification is sent via push notifications, emails, or other means.

[0685] 8. User-generated answers

[0686] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0687] 9. Receipt and Notification of Responses

[0688] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[0689] 10. Providing Feedback

[0690] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[0691] The device sends the feedback data and the recognized emotions to the server.

[0692] 11. Feedback Storage and Notification

[0693] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[0694] Specific processing examples

[0695] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[0696] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0697] The processing flow will be explained below.

[0698] Program processing flow

[0699] Step 1:

[0700] The user can input their question or problem through the terminal and submit it. For example, they can input, "Please tell me how to create materials for a new marketing strategy."

[0701] Step 2:

[0702] The device processes the input questions and issues using an emotion engine to recognize the user's emotions. Emotion data includes categories of emotions such as joy, sadness, anger, and anxiety.

[0703] Step 3:

[0704] The device sends the recognized emotion data and the question or problem to the server. The sent data includes the user ID, input content, emotion data, and the date and time of sending.

[0705] Step 4:

[0706] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0707] Step 5:

[0708] The server searches the knowledge database based on the extracted keywords and emotion data to collect related information, and selects high-priority information based on the emotion data.

[0709] Step 6:

[0710] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify users with appropriate expertise. For example, employee A who is knowledgeable about marketing strategies and employee B who is skilled in creating materials can be identified.

[0711] Step 7:

[0712] The server notifies the identified user of their questions or issues along with their emotional data and asks for their answers. These notifications are sent via push notifications, emails, etc.

[0713] Step 8:

[0714] The identified users use the devices to input answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0715] Step 9:

[0716] The terminal sends the entered answer data to the server. The sent data includes the answer content, respondent ID, and answer date and time.

[0717] Step 10:

[0718] The server then provides the responses received from employees to the original sender. To do this, the server uses push notifications, emails, etc.

[0719] Step 11:

[0720] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[0721] Step 12:

[0722] The user inputs feedback on the provided answer through the terminal, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[0723] Step 13:

[0724] The device sends the feedback data and the recognized emotion to the server. The sent data includes the feedback content, emotion data, user ID, and the date and time of sending.

[0725] Step 14:

[0726] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, etc.

[0727] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises from differences in knowledge levels between employees and their superiors.

[0728] Example 2

[0729] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0730] When sharing information or solving problems within a company, friction in communication arises due to differences in the knowledge levels of employees and their superiors. This friction prevents fast and effective information sharing, resulting in a decline in work efficiency. To address this issue, the present invention aims to realize more personalized responses and reduce friction in communication by recognizing users' emotions and providing information that takes these emotions into consideration.

[0731] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0732] In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the input content with an emotion engine and recognize the user's emotion; means for the terminal to transmit the recognized emotion data and the question or problem to the server; means for the server to analyze the received question or problem using natural language processing technology and extract related keywords; means for the server to analyze the received emotion data and set priorities for the search results; means for the server to search a knowledge database based on the extracted keywords and collect related information; means for the server to identify other users with appropriate expertise based on information in the knowledge database and user profile data; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the response received from the user to the user who sent the response. This reduces communication friction caused by differences in knowledge levels between employees and their superiors, enabling quick and effective information sharing.

[0733] A "terminal" is a device that allows a user to input questions or issues and send the content, and includes personal computers, smartphones, etc.

[0734] An "emotion engine" is software that processes user input and recognizes the emotions it conveys, and has the ability to classify emotions such as joy, anger, and sadness.

[0735] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and is expressed as text data.

[0736] The "server" is a central system that processes questions and issues received from users, searches a database and provides appropriate information.

[0737] "Natural language processing technology" is a technology that analyzes text data sent by users and extracts relevant keywords and important information.

[0738] "Keywords" are words or phrases that indicate important topics of a question or issue, extracted using natural language processing techniques.

[0739] A "knowledge database" is a data storage system that stores past questions, answers, and specialized knowledge, and is used by the server for searches.

[0740] "Profile data" refers to a dataset that includes information such as each employee's expertise, past response history, and emotional response experience.

[0741] "Identified User" refers to a user who has been determined to have the appropriate expertise for a question or issue based on the knowledge database and profile data.

[0742] "Feedback data" refers to data that indicates evaluations and opinions of answers provided by users, and is reanalyzed by the emotion engine.

[0743] MODE FOR CARRYING OUT THE INVENTION

[0744] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also aims to improve the quality of services provided through emotion recognition.

[0745] System Configuration

[0746] The system consists of the following main components:

[0747] Terminal: A device through which a user inputs questions or issues. Specific examples include personal computers and smartphones.

[0748] Emotion engine: Software that analyzes text data to recognize user emotions. A specific example is IBM Watson Tone Analyzer.

[0749] Server: The central system that processes data received from users and provides appropriate information. Google Cloud Natural Language API is used as the natural language processing technology.

[0750] Knowledge database: A data storage system that stores past questions, answers, and specialized knowledge.

[0751] Profile database: A data set containing information such as each employee's expertise, past response history, and emotional response experience.

[0752] Program processing flow

[0753] The system processes as follows:

[0754] 1. User questions and issues posted

[0755] A user uses a device to type in and submit a question or issue, for example, "How do I create a document for a new marketing strategy?"

[0756] 2. Post content collection and emotion recognition

[0757] The device processes the user's input using an emotion engine and recognizes the user's emotions. The emotion data includes emotion classifications such as joy, sadness, and anger. The device then sends the recognized emotion data along with the question or issue to the server.

[0758] 3. Receiving and analyzing questions and issues

[0759] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0760] 4. Emotional Data Analysis

[0761] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[0762] 5. Knowledge Database Reference

[0763] The server searches a knowledge database based on the extracted keywords and emotion data. This database contains past questions and answers, as well as specialized knowledge.

[0764] 6. Identifying users with the right expertise

[0765] The server identifies other users with appropriate expertise based on the knowledge database and profile database. For example, employee A who is knowledgeable about marketing strategies and employee B who is knowledgeable about document creation are identified.

[0766] 7. Notification to Identified Users

[0767] The server notifies the identified user of their question or problem along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[0768] 8. User-generated answers

[0769] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0770] 9. Receipt and Notification of Responses

[0771] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[0772] 10. Providing Feedback

[0773] The user enters feedback on the provided answer, which is then analyzed by the emotion engine. For example, the user enters feedback such as "This was very helpful. Thank you very much." The device then sends the feedback data and the recognized emotion to the server.

[0774] 11. Feedback Storage and Notification

[0775] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers.

[0776] Specific examples

[0777] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[0778] Example prompts for generative AI models

[0779] Example prompt:

[0780] Please explain the program processing for the following system in natural language. Please write so that the subject is either the server, the terminal, or the user. Please use plain sentence endings.

[0781] system:

[0782] A system to reduce communication friction caused by differences in knowledge levels between employees and their superiors. By combining it with an emotion engine, the quality of the services provided is improved.

[0783] Specific processing steps:

[0784] 1. User questions and issues posted

[0785] 2. Post content collection and emotion recognition

[0786] 3. Receiving and analyzing questions and issues

[0787] 4. Emotional Data Analysis

[0788] 5. Knowledge Database Reference

[0789] 6. Identifying users with the right expertise

[0790] 7. Notification to Identified Users

[0791] 8. User-generated answers

[0792] 9. Receipt and Notification of Responses

[0793] 10. Providing Feedback

[0794] 11. Feedback Storage and Notification

[0795] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, it provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0796] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0797] Step 1:

[0798] The user uses the terminal to input a question or issue and transmits the content. For example, the user might input "Please tell me how to create materials for a new marketing strategy." This question or issue becomes input data and is transmitted to the terminal. The output is the input text information.

[0799] Step 2:

[0800] The device processes the input content using an emotion engine to recognize the user's emotion. The input is text data entered by the user, and this data is analyzed using an emotion engine (e.g., IBM Watson Tone Analyzer). As a result of the analysis, the user's emotion data (e.g., "anxiety," "confusion," etc.) is obtained. The output is the recognized emotion data.

[0801] Step 3:

[0802] The device sends the recognized emotion data and the text data of the question or problem to the server. The input is the emotion data obtained in step 2 and the text data of the user's question or problem. The output is the dataset sent to the server.

[0803] Step 4:

[0804] The server analyzes the questions and issues it receives using natural language processing technology (for example, Google Cloud Natural Language API) and extracts related keywords. The input is the dataset sent in step 3, and the natural language processing engine analyzes the text data to extract keywords such as "marketing strategy" and "document creation." The output is the extracted keywords.

[0805] Step 5:

[0806] The server analyzes the received emotion data and sets priorities for search results and inquiries. The input is the emotion data and keywords obtained in steps 2 and 4. By analyzing the emotion data, adjustments are made to prioritize a quick response, for example, if the user is feeling "anger." The output is prioritized keywords and inquiries.

[0807] Step 6:

[0808] The server searches the knowledge database based on the prioritized keywords and the query. The database contains past questions, answers, and specialized knowledge. The input is the prioritized keywords and the query set in step 5. The server searches for relevant information in the knowledge database and collects the results. The output is the search result information.

[0809] Step 7:

[0810] The server identifies other users with appropriate expertise based on the information in the knowledge database and the user's profile data. The input is the information retrieved in step 6 and the expertise information from the profile data database. The server compares these data and identifies users who are knowledgeable about marketing strategies or document creation, for example. The output is the identified appropriate users.

[0811] Step 8:

[0812] The server notifies the identified user of the question or issue along with emotion data and asks for a response. This notification is done using means such as push notification or email. The input is the user identified in step 7 and the question / issue data from step 3. The output is a notification to the identified user.

[0813] Step 9:

[0814] The identified user uses the terminal to input answers to questions or issues. For example, the user can respond, "Please refer to past marketing strategy materials," and the server can reply, "We will provide you with a template that will help you create the materials." The input is the answer data entered by the identified user. The output is the answer data sent to the server.

[0815] Step 10:

[0816] The server receives the identified user's answer and provides it to the user who posted the question. The input is the answer data obtained in step 9. The server sends this data to the user's terminal and provides information for solving the problem. The output is information provided to the user who posted the question.

[0817] Step 11:

[0818] The user inputs feedback for the provided answer, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much." The input is the feedback text data entered by the user. The output is the feedback data with emotion data analyzed by the emotion engine.

[0819] Step 12:

[0820] The terminal sends the feedback data to the server, which then stores it in the database. The input is the feedback data analyzed in step 11. The server stores it in the database and notifies the relevant employees and managers. The output is the stored feedback data and the notification.

[0821] (Application example 2)

[0822] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0823] In conventional factories, there was a lack of means to quickly respond to questions or concerns that operators had while working. This made it difficult to solve problems efficiently, causing stress and reduced productivity for operators. Furthermore, personalized responses that took into account the emotions felt by operators were not provided, which sometimes led to friction in communication.

[0824] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the user's input content using an emotion engine, recognize the user's emotion, and transmit the input content together with emotion data to the server; means for the server to analyze the question or problem received by the server using natural language processing technology and extract related keywords; means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the user with the response received from the user. This makes it possible to respond to questions or problems quickly and efficiently and provide personalized responses that take emotion data into consideration, thereby reducing communication friction and reducing operator stress.

[0825] A "user" is an entity that uses the system to input and send questions or issues.

[0826] The "terminal" is a device where users can input and send questions and issues, and which also recognizes emotions using an emotion engine.

[0827] The "emotion engine" is a technology that analyzes the user's input and voice and recognizes and classifies the user's emotions.

[0828] The "server" is a device that uses natural language processing technology to analyze received questions and issues, searches a knowledge database based on extracted keywords, identifies other users with appropriate expertise, and promotes notifications and responses.

[0829] "Natural language processing technology" is a technology that analyzes text data entered by a user and extracts related keywords.

[0830] "Keywords" are important words or phrases extracted from users' questions or issues.

[0831] A "knowledge database" is a collection of past questions and answers, as well as specialized knowledge.

[0832] "Expertise" is specific knowledge and skills that provide solutions to specific problems or challenges.

[0833] "Feedback" refers to ratings and comments that users make on answers provided.

[0834] "Emotion data" is data that indicates the emotional state of the user as recognized by the emotion engine.

[0835] "Profile Data" is information about an individual, such as an employee's expertise or past response history.

[0836] "Matching" is the process of matching a specific user with the most appropriate question.

[0837] This invention is a system that responds quickly and effectively to specific questions and issues by linking a terminal, an emotion engine, natural language processing technology, a knowledge database, and a server. A specific description will be given of an embodiment of this invention.

[0838] System Program

[0839] 1. Hardware and Software

[0840] Device: The device that a user uses to input and submit their question or issue, such as smart glasses or a head-mounted display (e.g., Microsoft HoloLens).

[0841] Emotion engine: Technology that analyzes user voice input and text data to recognize emotions. As an example, we will use Affectiva's emotion recognition engine.

[0842] Natural language processing technology: Technology that analyzes user input data and extracts relevant keywords. We will use SpaCy as an example.

[0843] Server: A device that processes the received questions, issues, and sentiment data, searches the knowledge database, and identifies other users with appropriate expertise. For example, we use AWS EC2.

[0844] Knowledge database: A collection of past questions and answers, as well as accumulated expert knowledge. For example, we use Elasticsearch.

[0845] 2. Program processing flow

[0846] 1. User submission of questions and issues:

[0847] The user uses the terminal to input their questions or issues and send them. For example, they might input, "I don't know how to set up the manufacturing machine. Please help me."

[0848] 2. Post content collection and emotion recognition:

[0849] The device processes the user's input using an emotion engine to recognize the user's emotions, and sends the user's questions and issues along with emotional data (e.g., anxiety, irritation, etc.) to the server.

[0850] 3. Receiving and analyzing questions and issues:

[0851] The server analyzes the received questions and issues using natural language processing technology and extracts related keywords (e.g., "manufacturing machinery," "setting methods," etc.).

[0852] 4. Sentiment Data Analysis:

[0853] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses "anxiety," it prioritizes a quick response.

[0854] 5. Knowledge Base Reference:

[0855] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[0856] 6. Identifying users with the right expertise:

[0857] The server matches the profile data against a knowledge database to identify other users with relevant expertise, for example, users who are "familiar with setting up manufacturing machines."

[0858] 7. Notice to Identified Users:

[0859] The server notifies the identified user of their questions or issues along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[0860] 8. User responses:

[0861] The identified user uses the terminal to input answers to questions or issues, such as providing "detailed instructions on how to set up a manufacturing machine."

[0862] 9. Receiving and notifying responses:

[0863] The server receives the response and provides it to the original user, allowing the user to quickly obtain information to resolve the problem.

[0864] 10. Providing Feedback:

[0865] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[0866] 11. Feedback Storage and Notification:

[0867] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[0868] Prompt Sentence Examples

[0869] "I don't know how to set up the manufacturing machine. Please help me."

[0870] "Please make sure this part is installed correctly. I'm a little worried."

[0871] In this way, the system responds to user questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, reducing operator stress and improving productivity.

[0872] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0873] Step 1:

[0874] The user sends questions or issues to the device via voice or text input. The input data is the specific content of the question or issue, such as "I don't know how to set up a manufacturing machine. Please help me." The input data is saved as text.

[0875] Step 2:

[0876] The device passes the user's voice input or text to an emotion engine to recognize the user's emotion. The emotion engine (e.g., Affectiva) analyzes the voice or text data and generates emotion data (e.g., anxiety, irritation, etc.). This identifies the user's emotion and adds that information.

[0877] Step 3:

[0878] The device sends the recognized emotion data along with the text data of the question or task to the server. The sent data includes the content of the question or task and the user's emotional state at that time.

[0879] Step 4:

[0880] The questions and issues received by the server are analyzed using natural language processing technology. The natural language processing technology used (e.g., SpaCy) analyzes the text data and extracts related keywords. For example, keywords such as "manufacturing machine" and "setting method" are extracted.

[0881] Step 5:

[0882] The server searches a knowledge database based on the extracted keywords and the recognized emotion data. The database technology used (e.g., Elasticsearch) searches for related information and collects the most appropriate solutions and information. This allows related past questions and answers to be retrieved.

[0883] Step 6:

[0884] The server compares the information in the knowledge database with the profile database to identify users with appropriate expertise. The profile database contains each user's expertise and past response history, so for example, a user who is "expert in setting up manufacturing machines" can be identified.

[0885] Step 7:

[0886] The server notifies the identified user of the question or issue. The notification is sent via push notification or email along with emotion data, prompting the identified user to respond. This notification is expected to result in a prompt response.

[0887] Step 8:

[0888] Identified users input answers to questions and issues through terminals. The input data is specific solutions or reference materials, such as "detailed instructions on how to set up manufacturing machines."

[0889] Step 9:

[0890] The server receives the answer and provides it to the user. The server then sends the answer back to the original user, who then confirms the answer through their device. This allows the user to quickly obtain information to solve the problem.

[0891] Step 10:

[0892] The user inputs feedback on the answer provided through the terminal. The feedback data is analyzed by the emotion engine to obtain the user's emotional state and evaluation. For example, feedback such as "This was very helpful. Thank you very much" may be input.

[0893] Step 11:

[0894] The server stores the feedback and sentiment data in a database and notifies relevant employees and managers, providing insights to improve the quality of responses across the system.

[0895] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0896] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0897] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0898] [Third embodiment]

[0899] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0900] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0901] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0902] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0903] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0904] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0905] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0906] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0907] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0908] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0909] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0910] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0911] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports rapid and effective information sharing and problem solving within a company. This system begins when a user inputs and sends a question or issue via a terminal, and the server analyzes the content using natural language processing technology and identifies other users with appropriate expertise.

[0912] Explanation of program processing

[0913] 1. User questions and issues posted

[0914] A user uses a terminal to enter their question or issue and submit it to the system. For example, a user might enter, "Please tell me how to create materials for a new marketing strategy."

[0915] 2. Collection and transmission of posts

[0916] The terminal transmits the user's input to the server.

[0917] 3. Receiving and analyzing questions and issues

[0918] The server uses natural language processing technology to analyze the questions and issues received from users and extract related keywords, such as "marketing strategy" and "document creation."

[0919] 4. Knowledge database reference

[0920] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions, answers, and specialized knowledge.

[0921] 5. Identifying users with the right expertise

[0922] The server compares the knowledge database with employee profile data to identify users with the appropriate expertise. For example, Employee A is knowledgeable about marketing, while Employee B is skilled in creating documents.

[0923] 6. Notification to Identified Users

[0924] The server then notifies the identified user of their question or issue and asks for a response. This process can be done using methods such as push notifications or emails.

[0925] 7. User-generated answers

[0926] The identified users use the devices to input and send answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[0927] 8. Receiving and notifying responses

[0928] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[0929] 9. Providing Feedback

[0930] The user inputs feedback on the answers provided through the terminal and sends it to the server, which stores the feedback in a database and notifies the relevant users and administrators.

[0931] Specific processing examples

[0932] For example, if a user sends a question from a terminal such as "I want to know new methods for sales strategy," the server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C. Employee C receives this notification and enters an answer from his / her terminal, which is provided to the user. The user enters feedback on this answer, which the server receives and stores in the database.

[0933] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0934] The processing flow will be explained below.

[0935] Program processing flow

[0936] Step 1:

[0937] The user can input their questions or issues through the device and submit them. For example, they could input, "Please tell me how to create materials for a new marketing strategy."

[0938] Step 2:

[0939] The device sends the user's input to the server. The data sent includes meta-information such as the user ID, question, and the date and time of submission.

[0940] Step 3:

[0941] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[0942] Step 4:

[0943] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions and answers, as well as specialized knowledge.

[0944] Step 5:

[0945] The server compares the knowledge database with employee profile data (expertise, past response history) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[0946] Step 6:

[0947] The server notifies the identified user of their questions or issues and requests answers. This notification is sent via push notifications, emails, and other means.

[0948] Step 7:

[0949] The identified users use the devices to input answers to questions and issues. Employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide templates that will help you create the materials."

[0950] Step 8:

[0951] The terminal transmits the input response data to the server. The transmitted data includes the response content, respondent ID, and response date and time.

[0952] Step 9:

[0953] The server then provides the responses received from the employees to the original sender. To do this, the server uses push notifications, emails, etc.

[0954] Step 10:

[0955] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[0956] Step 11:

[0957] The user inputs feedback for the provided answer through the terminal and transmits it to the server. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[0958] Step 12:

[0959] The terminal sends feedback data to the server, which includes the feedback content, the user ID, and the transmission date and time.

[0960] Step 13:

[0961] The server stores the received feedback in a database and notifies relevant employees and managers using push notifications, emails, etc.

[0962] In this way, the system of the present invention responds quickly and efficiently to questions and issues, and reduces communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0963] Example 1

[0964] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0965] The goal is to provide a system that supports quick and effective information sharing and problem solving within a company. In particular, it is required to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors, and enable efficient responses.

[0966] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0967] In this invention, the server includes means for users to input and transmit questions or issues via an information terminal, means for analyzing the received questions or issues using natural language processing technology and extracting related terms, means for searching a knowledge database based on the extracted terms and identifying other users with appropriate expertise, means for notifying the identified users of the questions or issues and prompting them to respond, means for the identified users to input and transmit answers via their information terminals, and means for providing the transmitted answers to the original users. This makes it possible to respond to questions or issues quickly and efficiently and reduce communication friction caused by differences in knowledge levels between employees and their superiors.

[0968] "Information terminal" refers to an electronic device that a user uses to input, send, and receive data over a communications network. Examples include personal computers, smartphones, and tablets.

[0969] "Natural language processing technology" refers to a set of algorithms and techniques used by a server to analyze text data and understand words and phrases. This includes techniques such as SpaCy and BERT.

[0970] "Phrases" refer to important words and phrases extracted from the text entered by the user using natural language processing technology.

[0971] A "knowledge database" is a collection of data used by a server to gather information based on analysis, including past questions and answers and specialized knowledge. Examples include databases such as PostgreSQL and Elasticsearch.

[0972] "Expertise" refers to detailed knowledge and skills in a particular field or area that the server uses to provide the best possible answers to questions or challenges.

[0973] "Notification" refers to a message or alert sent by the server to an identified user to inform them of a question or issue and prompt them to respond, including email, push notification, messaging app, etc.

[0974] "Feedback" refers to the process by which the original user sends their rating and opinion on the provided answer to the server. This information is stored in a database for later analysis.

[0975] This invention is a system that supports quick and effective information sharing and problem solving within a company. The purpose of this system is to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors. Specific embodiments are shown below.

[0976] Users use an information terminal (e.g., PC or smartphone) to input their questions or issues and send them to the system. This input is saved in text format, and the information terminal sends the text data to the server. HTTPS is used as the communication protocol, so the data is encrypted before being sent.

[0977] The server analyzes the text data received from the user using natural language processing technology (e.g., SpaCy, BERT) and extracts related words. For example, if a user types, "Please tell me how to create a document for a new marketing strategy," the words "marketing strategy" and "document creation" are extracted.

[0978] The server searches a knowledge database (e.g., PostgreSQL or Elasticsearch) based on the extracted phrases to gather relevant information. This database stores past questions and answers, as well as specialized knowledge.

[0979] Next, the server identifies users with the appropriate expertise by comparing the results of the knowledge database search with the personal data of registered employees. For example, employee A who is knowledgeable about marketing and employee B who is skilled in creating documents can be identified.

[0980] The server notifies the identified user of the user's questions or issues through a notification system (e.g., email, push notification, messaging app). When the identified user enters and sends an answer through an information terminal, this answer is also received by the server and provided to the original user.

[0981] The original user inputs feedback on the provided answer through the information terminal and sends it to the server, which stores this feedback in a database and notifies the relevant users and administrators.

[0982] Specific examples

[0983] For example, if a user inputs a question such as "I would like to know new methods for sales strategies," the server receives the question, extracts the phrases "sales strategies" and "new methods," and searches the knowledge database. Based on the search results, it identifies employee C, who is knowledgeable about "sales strategies," and sends a notification to employee C. Employee C receives the notification and enters an answer on his information terminal, which is then provided to the original user. The user enters feedback on this answer, which the server receives and stores in the database.

[0984] Prompt Sentence Examples

[0985] "How do I create materials for a new marketing strategy?"

[0986] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[0987] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0988] Step 1:

[0989] A user uses an information terminal to input and submit a question or problem. The input text data is in the format of "Please tell me how to create materials for a new marketing strategy." The terminal sends this text data to a server. The input data is in the form of text data, and the output is the text data sent to the server.

[0990] Step 2:

[0991] The server receives text data sent by the user. The server analyzes the received text data using natural language processing technology. Specifically, the text data is tokenized and important words and phrases are extracted. For example, the words "marketing strategy" and "document creation" are extracted. The input is the text data from the user, and the output is the extracted words and phrases.

[0992] Step 3:

[0993] The server queries a knowledge database based on the extracted phrases to collect related information. The knowledge database stores past questions and answers, and the query results include this related information. For example, a query such as "How to create materials for marketing strategies" returns related documents and answers. The input is the extracted phrases, and the output is related information.

[0994] Step 4:

[0995] Based on the information collected by the server, users with the appropriate expertise are identified. The server compares the knowledge database with the personal data of employees to find the most suitable answerer. For example, employee A who is knowledgeable about "marketing" and employee B who is skilled in "document creation" are identified. The input is the collected information, and the output is the identified user.

[0996] Step 5:

[0997] The server sends a notification to the identified user. The notification is sent via email, push notification, or messaging app. The notification contains the user's question or problem. For example, a notification may be sent in response to a question such as, "How do I create materials for a new marketing strategy?" The input is the identified user, and the output is the notification.

[0998] Step 6:

[0999] The identified user inputs and sends a response via the information terminal. For example, employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide a template that will be useful for creating materials." The terminal sends this response to the server. The input is the response from the user, and the output is the response sent to the server.

[1000] Step 7:

[1001] The server provides the answer received from the identified user to the original user. The answer is notified to the terminal and provided in a format that can be viewed by the original user. For example, an answer such as "Please refer to past marketing strategy materials" is displayed. The input is the received answer, and the output is the answer provided to the original user.

[1002] Step 8:

[1003] The original user inputs feedback for the provided answer and sends it through the terminal. The server receives this feedback and stores it in a database. The input is the feedback, and the output is the feedback stored in the database.

[1004] (Application example 1)

[1005] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1006] In modern companies, differences in knowledge levels between employees and superiors and communication friction can occur, delaying information sharing and problem-solving. Furthermore, at factories and other worksites, there is a lack of ways to quickly respond to technical issues and questions faced by workers, which can lead to reduced production efficiency and quality problems. There is a need to provide a means to resolve these issues and enable fast and effective information sharing within the company.

[1007] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1008] In this invention, the server includes: a means for a user to input and transmit a question or problem via a terminal; a means for analyzing the received question or problem using natural language processing technology and extracting related keywords; a means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; a means for the server to notify the identified users of the question or problem and prompt them to respond; a means for the server to provide the user with the response received from the user; and a means for using a smart device to input the question or problem by voice from the site, convert it into text, and transmit it to the server. This enables quick problem solving and information sharing throughout the company, including site workers.

[1009] A "user" is a person or agent who utilizes the system to input and submit questions or issues.

[1010] A "terminal" is a device used by a user to input and send questions or issues, and includes smartphones, smart glasses, head-mounted displays, robots, etc.

[1011] "Questions and Issues" are problems users are facing or questions that need to be resolved.

[1012] A "server" is a central system that receives questions and issues, analyzes them, searches for relevant information, identifies users with specialized knowledge, notifies them, and provides answers.

[1013] "Natural language processing technology" is a computational technology that analyzes questions and issues received by the server and extracts related keywords.

[1014] "Related keywords" are important words or phrases necessary for solving a problem that are extracted from the question or issue entered by the user.

[1015] A "knowledge database" is a collection of searchable information that stores past questions, answers, and specialized knowledge.

[1016] "Other users" are people or agents with appropriate expertise for a question or issue.

[1017] "Notification" is the process by which the server notifies identified users of questions or issues.

[1018] The "means for prompting an answer" is a method by which the server requests an answer to resolve a question or problem from the identified user.

[1019] A "smart device" is a device that has functions such as voice input and text input and is used to send questions and issues from the field.

[1020] The "site" is the location where the user actually works, and includes a factory, a production line, an office, and the like.

[1021] "Voice input" refers to the act of a user verbally expressing a question or problem using a microphone.

[1022] "Convert to text" is the process of converting voice-input information into character string information.

[1023] "Send" is the act of moving information such as a question, assignment, answer, or notice from one point to another.

[1024] The present invention is a system that supports rapid and effective information sharing and problem solving within a company, and is configured to be usable particularly in factories and on-site. This system begins when a user inputs and transmits a question or issue by voice via a terminal. The server then analyzes the content using natural language processing technology, identifies other users with appropriate expertise, and notifies them.

[1025] Program Overview

[1026] When a user uses a smart device (e.g., smart glasses) to voice-input a question or issue from the field, it is converted into text and sent to a server. The server uses natural language processing technology to analyze the received question or issue and extract relevant keywords. These keywords are used to search a knowledge database to identify other users with appropriate expertise. Identified users are notified and can request an answer. Once an answer is provided, the server provides it to the original user. It also receives feedback from users and stores it in a database.

[1027] Hardware and software used

[1028] Smart devices: Devices such as smart glasses, smartphones, and head-mounted displays that have voice input and communication capabilities.

[1029] Server: Responsible for data analysis, natural language processing, database search, and notification functions.

[1030] Software used includes Python's speech_recognition library, requests library, Google Cloud NLP API, and Firebase Cloud Messaging.

[1031] Natural language explanation of the process

[1032] 1. User speaks:

[1033] Using smart glasses or a smartphone, users speak their questions or tasks, which are then picked up by the device via a microphone.

[1034] 2. Speech to text conversion:

[1035] The smart device converts the speech into text using the speech_recognition library, and the converted text is sent directly to the server.

[1036] 3. Natural Language Processing on the Server:

[1037] The server analyzes the received text using the Google Cloud NLP API and extracts relevant keywords. For example, the keyword "machine settings" can be extracted from the question "Please tell me how to set up the machine."

[1038] 4. Database Search and User Identification:

[1039] The server searches the knowledge database based on the extracted keywords. After retrieving data containing relevant information, it identifies other users (workers) with the appropriate expertise.

[1040] 5. Notice to Identified Users:

[1041] Use Firebase Cloud Messaging to send notifications to identified users about their questions or issues.

[1042] 6. Answer submission and feedback:

[1043] The identified user enters a solution to the problem, which is sent to the server, which provides the solution to the original user and also receives feedback and stores it in a database.

[1044] Examples of concrete examples and prompts

[1045] Examples:

[1046] A factory worker asks the smart glasses how to set up a new machine by voice: "Please tell me how to set up a new machine." The voice is converted into text and sent to the server. The server extracts the keyword "machine setting" and searches a database of past information. A technician with relevant knowledge is identified and a notification is sent. The technician provides an appropriate answer, which is sent back to the worker. The worker configures the machine based on the answer and sends feedback.

[1047] Example prompt sentence:

[1048] "A user speaks a question into a pair of smart glasses, such as 'How do I configure my new machine?' Design a system that sends this question to a server, identifies users with relevant expertise, and provides an answer in real time."

[1049] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1050] Step 1:

[1051] Audio Input:

[1052] Using smart glasses or a smartphone, users can voice-input questions or issues that arise on-site. For example, they might say, "Please tell me how to set up a new machine." This voice data is then captured by the smart device.

[1053] Input: Audio data

[1054] Output: Captured audio data

[1055] How it works: The user speaks their question or problem into the microphone on their smart device.

[1056] Step 2:

[1057] Speech to text conversion:

[1058] The device uses the speech_recognition library to convert the captured voice data into text data, for example, "How do I set up my new machine?"

[1059] Input: Captured audio data

[1060] Output: Text data

[1061] How it works: Your smart device processes the voice data using a cloud service or built-in speech recognition function and converts it into text.

[1062] Step 3:

[1063] Sending text data:

[1064] The device sends the converted text data to the server using a network connection. For example, the text "How do I set up my new machine?" is sent to the server.

[1065] Input: Text data

[1066] Output: Text data sent to the server

[1067] How it works: A smart device sends text data to a server via a network.

[1068] Step 4:

[1069] Natural Language Processing Analysis:

[1070] The server analyzes the received text data using the Google Cloud NLP API and extracts relevant keywords. For example, "machine settings" is extracted from the text.

[1071] Input: Text data

[1072] Output: Extracted keywords

[1073] How it works: The server passes text data to the API, which performs natural language processing to extract keywords.

[1074] Step 5:

[1075] Knowledge Database Search:

[1076] The server searches a knowledge database based on the extracted keywords, thereby identifying users and information with related expertise.

[1077] Input: Extracted keywords

[1078] Output: Related expertise and user information

[1079] How it works: The server sends keywords as queries to the knowledge database to search for relevant data.

[1080] Step 6:

[1081] Expertise Identification and Notification:

[1082] The server uses the search results to identify users with the appropriate expertise and sends notifications using Firebase Cloud Messaging, including questions and issues.

[1083] Input: relevant expertise and user information

[1084] Output: Send notification

[1085] What happens: The server sends a push notification to the specified user.

[1086] Step 7:

[1087] User answer input:

[1088] The identified user is notified and uses the device to enter a response, such as "Please refer to the documentation on how to set up the machine."

[1089] Input: Notification content

[1090] Output: Response data

[1091] How it works: A user with expert knowledge types an answer into a terminal and sends it to the server.

[1092] Step 8:

[1093] Providing answers:

[1094] The server provides the received response to the original user, allowing the original user to quickly obtain information to resolve the problem.

[1095] Input: Answer data

[1096] Output: Provide the answer to the original user

[1097] Operation: The server sends the response data to the original user's device.

[1098] Step 9:

[1099] Collecting feedback:

[1100] The user inputs feedback on the answer from the terminal and sends it to the server, which stores this feedback in a database.

[1101] Input: User feedback

[1102] Output: Saved feedback data

[1103] How it works: The server receives the feedback and stores it in a database.

[1104] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1105] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also improves the quality of the services provided by combining it with an emotion engine that recognizes the user's emotions.

[1106] Explanation of program processing

[1107] 1. User questions and issues posted

[1108] The user uses the terminal to input their question or problem and submit it. For example, they might input, "Please tell me how to create materials for a new marketing strategy."

[1109] 2. Post content collection and emotion recognition

[1110] The device processes the user's input using an emotion engine to recognize the user's emotions. The emotion data includes emotion categories such as joy, sadness, and anger.

[1111] The device sends the question or issue along with the recognized emotion data to the server.

[1112] 3. Receiving and analyzing questions and issues

[1113] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[1114] 4. Emotional Data Analysis

[1115] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[1116] 5. Knowledge Database Reference

[1117] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[1118] 6. Identifying users with the right expertise

[1119] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[1120] 7. Notification to Identified Users

[1121] The server notifies the identified user of their questions or issues along with their emotional data and asks for a response. This notification is sent via push notifications, emails, or other means.

[1122] 8. User-generated answers

[1123] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[1124] 9. Receipt and Notification of Responses

[1125] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[1126] 10. Providing Feedback

[1127] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[1128] The device sends the feedback data and the recognized emotions to the server.

[1129] 11. Feedback Storage and Notification

[1130] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[1131] Specific processing examples

[1132] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[1133] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[1134] The processing flow will be explained below.

[1135] Program processing flow

[1136] Step 1:

[1137] The user can input their question or problem through the terminal and submit it. For example, they can input, "Please tell me how to create materials for a new marketing strategy."

[1138] Step 2:

[1139] The device processes the input questions and issues using an emotion engine to recognize the user's emotions. Emotion data includes categories of emotions such as joy, sadness, anger, and anxiety.

[1140] Step 3:

[1141] The device sends the recognized emotion data and the question or problem to the server. The sent data includes the user ID, input content, emotion data, and the date and time of sending.

[1142] Step 4:

[1143] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[1144] Step 5:

[1145] The server searches the knowledge database based on the extracted keywords and emotion data to collect related information, and selects high-priority information based on the emotion data.

[1146] Step 6:

[1147] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify users with appropriate expertise. For example, employee A who is knowledgeable about marketing strategies and employee B who is skilled in creating materials can be identified.

[1148] Step 7:

[1149] The server notifies the identified user of their questions or issues along with their emotional data and asks for their answers. These notifications are sent via push notifications, emails, etc.

[1150] Step 8:

[1151] The identified users use the devices to input answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[1152] Step 9:

[1153] The terminal sends the entered answer data to the server. The sent data includes the answer content, respondent ID, and answer date and time.

[1154] Step 10:

[1155] The server then provides the responses received from employees to the original sender. To do this, the server uses push notifications, emails, etc.

[1156] Step 11:

[1157] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[1158] Step 12:

[1159] The user inputs feedback on the provided answer through the terminal, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[1160] Step 13:

[1161] The device sends the feedback data and the recognized emotion to the server. The sent data includes the feedback content, emotion data, user ID, and the date and time of sending.

[1162] Step 14:

[1163] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, etc.

[1164] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises from differences in knowledge levels between employees and their superiors.

[1165] Example 2

[1166] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1167] When sharing information or solving problems within a company, friction in communication arises due to differences in the knowledge levels of employees and their superiors. This friction prevents fast and effective information sharing, resulting in a decline in work efficiency. To address this issue, the present invention aims to realize more personalized responses and reduce friction in communication by recognizing users' emotions and providing information that takes these emotions into consideration.

[1168] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1169] In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the input content with an emotion engine and recognize the user's emotion; means for the terminal to transmit the recognized emotion data and the question or problem to the server; means for the server to analyze the received question or problem using natural language processing technology and extract related keywords; means for the server to analyze the received emotion data and set priorities for the search results; means for the server to search a knowledge database based on the extracted keywords and collect related information; means for the server to identify other users with appropriate expertise based on information in the knowledge database and user profile data; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the response received from the user to the user who sent the response. This reduces communication friction caused by differences in knowledge levels between employees and their superiors, enabling quick and effective information sharing.

[1170] A "terminal" is a device that allows a user to input questions or issues and send the content, and includes personal computers, smartphones, etc.

[1171] An "emotion engine" is software that processes user input and recognizes the emotions it conveys, and has the ability to classify emotions such as joy, anger, and sadness.

[1172] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and is expressed as text data.

[1173] The "server" is a central system that processes questions and issues received from users, searches a database and provides appropriate information.

[1174] "Natural language processing technology" is a technology that analyzes text data sent by users and extracts relevant keywords and important information.

[1175] "Keywords" are words or phrases that indicate important topics of a question or issue, extracted using natural language processing techniques.

[1176] A "knowledge database" is a data storage system that stores past questions, answers, and specialized knowledge, and is used by the server for searches.

[1177] "Profile data" refers to a dataset that includes information such as each employee's expertise, past response history, and emotional response experience.

[1178] "Identified User" refers to a user who has been determined to have the appropriate expertise for a question or issue based on the knowledge database and profile data.

[1179] "Feedback data" refers to data that indicates evaluations and opinions of answers provided by users, and is reanalyzed by the emotion engine.

[1180] MODE FOR CARRYING OUT THE INVENTION

[1181] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also aims to improve the quality of services provided through emotion recognition.

[1182] System Configuration

[1183] The system consists of the following main components:

[1184] Terminal: A device through which a user inputs questions or issues. Specific examples include personal computers and smartphones.

[1185] Emotion engine: Software that analyzes text data to recognize user emotions. A specific example is IBM Watson Tone Analyzer.

[1186] Server: The central system that processes data received from users and provides appropriate information. Google Cloud Natural Language API is used as the natural language processing technology.

[1187] Knowledge database: A data storage system that stores past questions, answers, and specialized knowledge.

[1188] Profile database: A data set containing information such as each employee's expertise, past response history, and emotional response experience.

[1189] Program processing flow

[1190] The system processes as follows:

[1191] 1. User questions and issues posted

[1192] A user uses a device to type in and submit a question or issue, for example, "How do I create a document for a new marketing strategy?"

[1193] 2. Post content collection and emotion recognition

[1194] The device processes the user's input using an emotion engine and recognizes the user's emotions. The emotion data includes emotion classifications such as joy, sadness, and anger. The device then sends the recognized emotion data along with the question or issue to the server.

[1195] 3. Receiving and analyzing questions and issues

[1196] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[1197] 4. Emotional Data Analysis

[1198] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[1199] 5. Knowledge Database Reference

[1200] The server searches a knowledge database based on the extracted keywords and emotion data. This database contains past questions and answers, as well as specialized knowledge.

[1201] 6. Identifying users with the right expertise

[1202] The server identifies other users with appropriate expertise based on the knowledge database and profile database. For example, employee A who is knowledgeable about marketing strategies and employee B who is knowledgeable about document creation are identified.

[1203] 7. Notification to Identified Users

[1204] The server notifies the identified user of their question or problem along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[1205] 8. User-generated answers

[1206] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[1207] 9. Receipt and Notification of Responses

[1208] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[1209] 10. Providing Feedback

[1210] The user enters feedback on the provided answer, which is then analyzed by the emotion engine. For example, the user enters feedback such as "This was very helpful. Thank you very much." The device then sends the feedback data and the recognized emotion to the server.

[1211] 11. Feedback Storage and Notification

[1212] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers.

[1213] Specific examples

[1214] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[1215] Example prompts for generative AI models

[1216] Example prompt:

[1217] Please explain the program processing for the following system in natural language. Please write so that the subject is either the server, the terminal, or the user. Please use plain sentence endings.

[1218] system:

[1219] A system to reduce communication friction caused by differences in knowledge levels between employees and their superiors. By combining it with an emotion engine, the quality of the services provided is improved.

[1220] Specific processing steps:

[1221] 1. User questions and issues posted

[1222] 2. Post content collection and emotion recognition

[1223] 3. Receiving and analyzing questions and issues

[1224] 4. Emotional Data Analysis

[1225] 5. Knowledge Database Reference

[1226] 6. Identifying users with the right expertise

[1227] 7. Notification to Identified Users

[1228] 8. User-generated answers

[1229] 9. Receipt and Notification of Responses

[1230] 10. Providing Feedback

[1231] 11. Feedback Storage and Notification

[1232] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, it provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[1233] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1234] Step 1:

[1235] The user uses the terminal to input a question or issue and transmits the content. For example, the user might input "Please tell me how to create materials for a new marketing strategy." This question or issue becomes input data and is transmitted to the terminal. The output is the input text information.

[1236] Step 2:

[1237] The device processes the input content using an emotion engine to recognize the user's emotion. The input is text data entered by the user, and this data is analyzed using an emotion engine (e.g., IBM Watson Tone Analyzer). As a result of the analysis, the user's emotion data (e.g., "anxiety," "confusion," etc.) is obtained. The output is the recognized emotion data.

[1238] Step 3:

[1239] The device sends the recognized emotion data and the text data of the question or problem to the server. The input is the emotion data obtained in step 2 and the text data of the user's question or problem. The output is the dataset sent to the server.

[1240] Step 4:

[1241] The server analyzes the questions and issues it receives using natural language processing technology (for example, Google Cloud Natural Language API) and extracts related keywords. The input is the dataset sent in step 3, and the natural language processing engine analyzes the text data to extract keywords such as "marketing strategy" and "document creation." The output is the extracted keywords.

[1242] Step 5:

[1243] The server analyzes the received emotion data and sets priorities for search results and inquiries. The input is the emotion data and keywords obtained in steps 2 and 4. By analyzing the emotion data, adjustments are made to prioritize a quick response, for example, if the user is feeling "anger." The output is prioritized keywords and inquiries.

[1244] Step 6:

[1245] The server searches the knowledge database based on the prioritized keywords and the query. The database contains past questions, answers, and specialized knowledge. The input is the prioritized keywords and the query set in step 5. The server searches for relevant information in the knowledge database and collects the results. The output is the search result information.

[1246] Step 7:

[1247] The server identifies other users with appropriate expertise based on the information in the knowledge database and the user's profile data. The input is the information retrieved in step 6 and the expertise information from the profile data database. The server compares these data and identifies users who are knowledgeable about marketing strategies or document creation, for example. The output is the identified appropriate users.

[1248] Step 8:

[1249] The server notifies the identified user of the question or issue along with emotion data and asks for a response. This notification is done using means such as push notification or email. The input is the user identified in step 7 and the question / issue data from step 3. The output is a notification to the identified user.

[1250] Step 9:

[1251] The identified user uses the terminal to input answers to questions or issues. For example, the user can respond, "Please refer to past marketing strategy materials," and the server can reply, "We will provide you with a template that will help you create the materials." The input is the answer data entered by the identified user. The output is the answer data sent to the server.

[1252] Step 10:

[1253] The server receives the identified user's answer and provides it to the user who posted the question. The input is the answer data obtained in step 9. The server sends this data to the user's terminal and provides information for solving the problem. The output is information provided to the user who posted the question.

[1254] Step 11:

[1255] The user inputs feedback for the provided answer, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much." The input is the feedback text data entered by the user. The output is the feedback data with emotion data analyzed by the emotion engine.

[1256] Step 12:

[1257] The terminal sends the feedback data to the server, which then stores it in the database. The input is the feedback data analyzed in step 11. The server stores it in the database and notifies the relevant employees and managers. The output is the stored feedback data and the notification.

[1258] (Application example 2)

[1259] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1260] In conventional factories, there was a lack of means to quickly respond to questions or concerns that operators had while working. This made it difficult to solve problems efficiently, causing stress and reduced productivity for operators. Furthermore, personalized responses that took into account the emotions felt by operators were not provided, which sometimes led to friction in communication.

[1261] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the user's input content using an emotion engine, recognize the user's emotion, and transmit the input content together with emotion data to the server; means for the server to analyze the question or problem received by the server using natural language processing technology and extract related keywords; means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the user with the response received from the user. This makes it possible to respond to questions or problems quickly and efficiently and provide personalized responses that take emotion data into consideration, thereby reducing communication friction and reducing operator stress.

[1262] A "user" is an entity that uses the system to input and send questions or issues.

[1263] The "terminal" is a device where users can input and send questions and issues, and which also recognizes emotions using an emotion engine.

[1264] The "emotion engine" is a technology that analyzes the user's input and voice and recognizes and classifies the user's emotions.

[1265] The "server" is a device that uses natural language processing technology to analyze received questions and issues, searches a knowledge database based on extracted keywords, identifies other users with appropriate expertise, and promotes notifications and responses.

[1266] "Natural language processing technology" is a technology that analyzes text data entered by a user and extracts related keywords.

[1267] "Keywords" are important words or phrases extracted from users' questions or issues.

[1268] A "knowledge database" is a collection of past questions and answers, as well as specialized knowledge.

[1269] "Expertise" is specific knowledge and skills that provide solutions to specific problems or challenges.

[1270] "Feedback" refers to ratings and comments that users make on answers provided.

[1271] "Emotion data" is data that indicates the emotional state of the user as recognized by the emotion engine.

[1272] "Profile Data" is information about an individual, such as an employee's expertise or past response history.

[1273] "Matching" is the process of matching a specific user with the most appropriate question.

[1274] This invention is a system that responds quickly and effectively to specific questions and issues by linking a terminal, an emotion engine, natural language processing technology, a knowledge database, and a server. A specific description will be given of an embodiment of this invention.

[1275] System Program

[1276] 1. Hardware and Software

[1277] Device: The device that a user uses to input and submit their question or issue, such as smart glasses or a head-mounted display (e.g., Microsoft HoloLens).

[1278] Emotion engine: Technology that analyzes user voice input and text data to recognize emotions. As an example, we will use Affectiva's emotion recognition engine.

[1279] Natural language processing technology: Technology that analyzes user input data and extracts relevant keywords. We will use SpaCy as an example.

[1280] Server: A device that processes the received questions, issues, and sentiment data, searches the knowledge database, and identifies other users with appropriate expertise. For example, we use AWS EC2.

[1281] Knowledge database: A collection of past questions and answers, as well as accumulated expert knowledge. For example, we use Elasticsearch.

[1282] 2. Program processing flow

[1283] 1. User submission of questions and issues:

[1284] The user uses the terminal to input their questions or issues and send them. For example, they might input, "I don't know how to set up the manufacturing machine. Please help me."

[1285] 2. Post content collection and emotion recognition:

[1286] The device processes the user's input using an emotion engine to recognize the user's emotions, and sends the user's questions and issues along with emotional data (e.g., anxiety, irritation, etc.) to the server.

[1287] 3. Receiving and analyzing questions and issues:

[1288] The server analyzes the received questions and issues using natural language processing technology and extracts related keywords (e.g., "manufacturing machinery," "setting methods," etc.).

[1289] 4. Sentiment Data Analysis:

[1290] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses "anxiety," it prioritizes a quick response.

[1291] 5. Knowledge Base Reference:

[1292] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[1293] 6. Identifying users with the right expertise:

[1294] The server matches the profile data against a knowledge database to identify other users with relevant expertise, for example, users who are "familiar with setting up manufacturing machines."

[1295] 7. Notice to Identified Users:

[1296] The server notifies the identified user of their questions or issues along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[1297] 8. User responses:

[1298] The identified user uses the terminal to input answers to questions or issues, such as providing "detailed instructions on how to set up a manufacturing machine."

[1299] 9. Receiving and notifying responses:

[1300] The server receives the response and provides it to the original user, allowing the user to quickly obtain information to resolve the problem.

[1301] 10. Providing Feedback:

[1302] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[1303] 11. Feedback Storage and Notification:

[1304] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[1305] Prompt Sentence Examples

[1306] "I don't know how to set up the manufacturing machine. Please help me."

[1307] "Please make sure this part is installed correctly. I'm a little worried."

[1308] In this way, the system responds to user questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, reducing operator stress and improving productivity.

[1309] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1310] Step 1:

[1311] The user sends questions or issues to the device via voice or text input. The input data is the specific content of the question or issue, such as "I don't know how to set up a manufacturing machine. Please help me." The input data is saved as text.

[1312] Step 2:

[1313] The device passes the user's voice input or text to an emotion engine to recognize the user's emotion. The emotion engine (e.g., Affectiva) analyzes the voice or text data and generates emotion data (e.g., anxiety, irritation, etc.). This identifies the user's emotion and adds that information.

[1314] Step 3:

[1315] The device sends the recognized emotion data along with the text data of the question or task to the server. The sent data includes the content of the question or task and the user's emotional state at that time.

[1316] Step 4:

[1317] The questions and issues received by the server are analyzed using natural language processing technology. The natural language processing technology used (e.g., SpaCy) analyzes the text data and extracts related keywords. For example, keywords such as "manufacturing machine" and "setting method" are extracted.

[1318] Step 5:

[1319] The server searches a knowledge database based on the extracted keywords and the recognized emotion data. The database technology used (e.g., Elasticsearch) searches for related information and collects the most appropriate solutions and information. This allows related past questions and answers to be retrieved.

[1320] Step 6:

[1321] The server compares the information in the knowledge database with the profile database to identify users with appropriate expertise. The profile database contains each user's expertise and past response history, so for example, a user who is "expert in setting up manufacturing machines" can be identified.

[1322] Step 7:

[1323] The server notifies the identified user of the question or issue. The notification is sent via push notification or email along with emotion data, prompting the identified user to respond. This notification is expected to result in a prompt response.

[1324] Step 8:

[1325] Identified users input answers to questions and issues through terminals. The input data is specific solutions or reference materials, such as "detailed instructions on how to set up manufacturing machines."

[1326] Step 9:

[1327] The server receives the answer and provides it to the user. The server then sends the answer back to the original user, who then confirms the answer through their device. This allows the user to quickly obtain information to solve the problem.

[1328] Step 10:

[1329] The user inputs feedback on the answer provided through the terminal. The feedback data is analyzed by the emotion engine to obtain the user's emotional state and evaluation. For example, feedback such as "This was very helpful. Thank you very much" may be input.

[1330] Step 11:

[1331] The server stores the feedback and sentiment data in a database and notifies relevant employees and managers, providing insights to improve the quality of responses across the system.

[1332] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1333] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1334] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1335] [Fourth embodiment]

[1336] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1337] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1338] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1339] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1340] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1341] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1342] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1343] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1344] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1345] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1346] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1347] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1348] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1349] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports rapid and effective information sharing and problem solving within a company. This system begins when a user inputs and sends a question or issue via a terminal, and the server analyzes the content using natural language processing technology and identifies other users with appropriate expertise.

[1350] Explanation of program processing

[1351] 1. User questions and issues posted

[1352] A user uses a terminal to enter their question or issue and submit it to the system. For example, a user might enter, "Please tell me how to create materials for a new marketing strategy."

[1353] 2. Collection and transmission of posts

[1354] The terminal transmits the user's input to the server.

[1355] 3. Receiving and analyzing questions and issues

[1356] The server uses natural language processing technology to analyze the questions and issues received from users and extract related keywords, such as "marketing strategy" and "document creation."

[1357] 4. Knowledge database reference

[1358] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions, answers, and specialized knowledge.

[1359] 5. Identifying users with the right expertise

[1360] The server compares the knowledge database with employee profile data to identify users with the appropriate expertise. For example, Employee A is knowledgeable about marketing, while Employee B is skilled in creating documents.

[1361] 6. Notification to Identified Users

[1362] The server then notifies the identified user of their question or issue and asks for a response. This process can be done using methods such as push notifications or emails.

[1363] 7. User-generated answers

[1364] The identified users use the devices to input and send answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[1365] 8. Receiving and notifying responses

[1366] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[1367] 9. Providing Feedback

[1368] The user inputs feedback on the answers provided through the terminal and sends it to the server, which stores the feedback in a database and notifies the relevant users and administrators.

[1369] Specific processing examples

[1370] For example, if a user sends a question from a terminal such as "I want to know new methods for sales strategy," the server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C. Employee C receives this notification and enters an answer from his / her terminal, which is provided to the user. The user enters feedback on this answer, which the server receives and stores in the database.

[1371] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[1372] The processing flow will be explained below.

[1373] Program processing flow

[1374] Step 1:

[1375] The user can input their questions or issues through the device and submit them. For example, they could input, "Please tell me how to create materials for a new marketing strategy."

[1376] Step 2:

[1377] The device sends the user's input to the server. The data sent includes meta-information such as the user ID, question, and the date and time of submission.

[1378] Step 3:

[1379] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[1380] Step 4:

[1381] The server searches a knowledge database based on the extracted keywords to gather relevant information. This database contains past questions and answers, as well as specialized knowledge.

[1382] Step 5:

[1383] The server compares the knowledge database with employee profile data (expertise, past response history) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[1384] Step 6:

[1385] The server notifies the identified user of their questions or issues and requests answers. This notification is sent via push notifications, emails, and other means.

[1386] Step 7:

[1387] The identified users use the devices to input answers to questions and issues. Employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide templates that will help you create the materials."

[1388] Step 8:

[1389] The terminal transmits the input response data to the server. The transmitted data includes the response content, respondent ID, and response date and time.

[1390] Step 9:

[1391] The server then provides the responses received from the employees to the original sender. To do this, the server uses push notifications, emails, etc.

[1392] Step 10:

[1393] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[1394] Step 11:

[1395] The user inputs feedback for the provided answer through the terminal and transmits it to the server. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[1396] Step 12:

[1397] The terminal sends feedback data to the server, which includes the feedback content, the user ID, and the transmission date and time.

[1398] Step 13:

[1399] The server stores the received feedback in a database and notifies relevant employees and managers using push notifications, emails, etc.

[1400] In this way, the system of the present invention responds quickly and efficiently to questions and issues, and reduces communication friction that arises due to differences in knowledge levels between employees and their superiors.

[1401] Example 1

[1402] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1403] The goal is to provide a system that supports quick and effective information sharing and problem solving within a company. In particular, it is required to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors, and enable efficient responses.

[1404] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1405] In this invention, the server includes means for users to input and transmit questions or issues via an information terminal, means for analyzing the received questions or issues using natural language processing technology and extracting related terms, means for searching a knowledge database based on the extracted terms and identifying other users with appropriate expertise, means for notifying the identified users of the questions or issues and prompting them to respond, means for the identified users to input and transmit answers via their information terminals, and means for providing the transmitted answers to the original users. This makes it possible to respond to questions or issues quickly and efficiently and reduce communication friction caused by differences in knowledge levels between employees and their superiors.

[1406] "Information terminal" refers to an electronic device that a user uses to input, send, and receive data over a communications network. Examples include personal computers, smartphones, and tablets.

[1407] "Natural language processing technology" refers to a set of algorithms and techniques used by a server to analyze text data and understand words and phrases. This includes techniques such as SpaCy and BERT.

[1408] "Phrases" refer to important words and phrases extracted from the text entered by the user using natural language processing technology.

[1409] A "knowledge database" is a collection of data used by a server to gather information based on analysis, including past questions and answers and specialized knowledge. Examples include databases such as PostgreSQL and Elasticsearch.

[1410] "Expertise" refers to detailed knowledge and skills in a particular field or area that the server uses to provide the best possible answers to questions or challenges.

[1411] "Notification" refers to a message or alert sent by the server to an identified user to inform them of a question or issue and prompt them to respond, including email, push notification, messaging app, etc.

[1412] "Feedback" refers to the process by which the original user sends their rating and opinion on the provided answer to the server. This information is stored in a database for later analysis.

[1413] This invention is a system that supports quick and effective information sharing and problem solving within a company. The purpose of this system is to reduce communication friction that arises due to differences in knowledge levels between employees and their superiors. Specific embodiments are shown below.

[1414] Users use an information terminal (e.g., PC or smartphone) to input their questions or issues and send them to the system. This input is saved in text format, and the information terminal sends the text data to the server. HTTPS is used as the communication protocol, so the data is encrypted before being sent.

[1415] The server analyzes the text data received from the user using natural language processing technology (e.g., SpaCy, BERT) and extracts related words. For example, if a user types, "Please tell me how to create a document for a new marketing strategy," the words "marketing strategy" and "document creation" are extracted.

[1416] The server searches a knowledge database (e.g., PostgreSQL or Elasticsearch) based on the extracted phrases to gather relevant information. This database stores past questions and answers, as well as specialized knowledge.

[1417] Next, the server identifies users with the appropriate expertise by comparing the results of the knowledge database search with the personal data of registered employees. For example, employee A who is knowledgeable about marketing and employee B who is skilled in creating documents can be identified.

[1418] The server notifies the identified user of the user's questions or issues through a notification system (e.g., email, push notification, messaging app). When the identified user enters and sends an answer through an information terminal, this answer is also received by the server and provided to the original user.

[1419] The original user inputs feedback on the provided answer through the information terminal and sends it to the server, which stores this feedback in a database and notifies the relevant users and administrators.

[1420] Specific examples

[1421] For example, if a user inputs a question such as "I would like to know new methods for sales strategies," the server receives the question, extracts the phrases "sales strategies" and "new methods," and searches the knowledge database. Based on the search results, it identifies employee C, who is knowledgeable about "sales strategies," and sends a notification to employee C. Employee C receives the notification and enters an answer on his information terminal, which is then provided to the original user. The user enters feedback on this answer, which the server receives and stores in the database.

[1422] Prompt Sentence Examples

[1423] "How do I create materials for a new marketing strategy?"

[1424] In this way, the system of the present invention can quickly and efficiently respond to questions and issues, and reduce communication friction that arises due to differences in knowledge levels between employees and their superiors.

[1425] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1426] Step 1:

[1427] A user uses an information terminal to input and submit a question or problem. The input text data is in the format of "Please tell me how to create materials for a new marketing strategy." The terminal sends this text data to a server. The input data is in the form of text data, and the output is the text data sent to the server.

[1428] Step 2:

[1429] The server receives text data sent by the user. The server analyzes the received text data using natural language processing technology. Specifically, the text data is tokenized and important words and phrases are extracted. For example, the words "marketing strategy" and "document creation" are extracted. The input is the text data from the user, and the output is the extracted words and phrases.

[1430] Step 3:

[1431] The server queries a knowledge database based on the extracted phrases to collect related information. The knowledge database stores past questions and answers, and the query results include this related information. For example, a query such as "How to create materials for marketing strategies" returns related documents and answers. The input is the extracted phrases, and the output is related information.

[1432] Step 4:

[1433] Based on the information collected by the server, users with the appropriate expertise are identified. The server compares the knowledge database with the personal data of employees to find the most suitable answerer. For example, employee A who is knowledgeable about "marketing" and employee B who is skilled in "document creation" are identified. The input is the collected information, and the output is the identified user.

[1434] Step 5:

[1435] The server sends a notification to the identified user. The notification is sent via email, push notification, or messaging app. The notification contains the user's question or problem. For example, a notification may be sent in response to a question such as, "How do I create materials for a new marketing strategy?" The input is the identified user, and the output is the notification.

[1436] Step 6:

[1437] The identified user inputs and sends a response via the information terminal. For example, employee A responds, "Please refer to past marketing strategy materials," and employee B replies, "We will provide a template that will be useful for creating materials." The terminal sends this response to the server. The input is the response from the user, and the output is the response sent to the server.

[1438] Step 7:

[1439] The server provides the answer received from the identified user to the original user. The answer is notified to the terminal and provided in a format that can be viewed by the original user. For example, an answer such as "Please refer to past marketing strategy materials" is displayed. The input is the received answer, and the output is the answer provided to the original user.

[1440] Step 8:

[1441] The original user inputs feedback for the provided answer and sends it through the terminal. The server receives this feedback and stores it in a database. The input is the feedback, and the output is the feedback stored in the database.

[1442] (Application example 1)

[1443] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1444] In modern companies, differences in knowledge levels between employees and superiors and communication friction can occur, delaying information sharing and problem-solving. Furthermore, at factories and other worksites, there is a lack of ways to quickly respond to technical issues and questions faced by workers, which can lead to reduced production efficiency and quality problems. There is a need to provide a means to resolve these issues and enable fast and effective information sharing within the company.

[1445] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1446] In this invention, the server includes: a means for a user to input and transmit a question or problem via a terminal; a means for analyzing the received question or problem using natural language processing technology and extracting related keywords; a means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; a means for the server to notify the identified users of the question or problem and prompt them to respond; a means for the server to provide the user with the response received from the user; and a means for using a smart device to input the question or problem by voice from the site, convert it into text, and transmit it to the server. This enables quick problem solving and information sharing throughout the company, including site workers.

[1447] A "user" is a person or agent who utilizes the system to input and submit questions or issues.

[1448] A "terminal" is a device used by a user to input and send questions or issues, and includes smartphones, smart glasses, head-mounted displays, robots, etc.

[1449] "Questions and Issues" are problems users are facing or questions that need to be resolved.

[1450] A "server" is a central system that receives questions and issues, analyzes them, searches for relevant information, identifies users with specialized knowledge, notifies them, and provides answers.

[1451] "Natural language processing technology" is a computational technology that analyzes questions and issues received by the server and extracts related keywords.

[1452] "Related keywords" are important words or phrases necessary for solving a problem that are extracted from the question or issue entered by the user.

[1453] A "knowledge database" is a collection of searchable information that stores past questions, answers, and specialized knowledge.

[1454] "Other users" are people or agents with appropriate expertise for a question or issue.

[1455] "Notification" is the process by which the server notifies identified users of questions or issues.

[1456] The "means for prompting an answer" is a method by which the server requests an answer to resolve a question or problem from the identified user.

[1457] A "smart device" is a device that has functions such as voice input and text input and is used to send questions and issues from the field.

[1458] The "site" is the location where the user actually works, and includes a factory, a production line, an office, and the like.

[1459] "Voice input" refers to the act of a user verbally expressing a question or problem using a microphone.

[1460] "Convert to text" is the process of converting voice-input information into character string information.

[1461] "Send" is the act of moving information such as a question, assignment, answer, or notice from one point to another.

[1462] The present invention is a system that supports rapid and effective information sharing and problem solving within a company, and is configured to be usable particularly in factories and on-site. This system begins when a user inputs and transmits a question or issue by voice via a terminal. The server then analyzes the content using natural language processing technology, identifies other users with appropriate expertise, and notifies them.

[1463] Program Overview

[1464] When a user uses a smart device (e.g., smart glasses) to voice-input a question or issue from the field, it is converted into text and sent to a server. The server uses natural language processing technology to analyze the received question or issue and extract relevant keywords. These keywords are used to search a knowledge database to identify other users with appropriate expertise. Identified users are notified and can request an answer. Once an answer is provided, the server provides it to the original user. It also receives feedback from users and stores it in a database.

[1465] Hardware and software used

[1466] Smart devices: Devices such as smart glasses, smartphones, and head-mounted displays that have voice input and communication capabilities.

[1467] Server: Responsible for data analysis, natural language processing, database search, and notification functions.

[1468] Software used includes Python's speech_recognition library, requests library, Google Cloud NLP API, and Firebase Cloud Messaging.

[1469] Natural language explanation of the process

[1470] 1. User speaks:

[1471] Using smart glasses or a smartphone, users speak their questions or tasks, which are then picked up by the device via a microphone.

[1472] 2. Speech to text conversion:

[1473] The smart device converts the speech into text using the speech_recognition library, and the converted text is sent directly to the server.

[1474] 3. Natural Language Processing on the Server:

[1475] The server analyzes the received text using the Google Cloud NLP API and extracts relevant keywords. For example, the keyword "machine settings" can be extracted from the question "Please tell me how to set up the machine."

[1476] 4. Database Search and User Identification:

[1477] The server searches the knowledge database based on the extracted keywords. After retrieving data containing relevant information, it identifies other users (workers) with the appropriate expertise.

[1478] 5. Notice to Identified Users:

[1479] Use Firebase Cloud Messaging to send notifications to identified users about their questions or issues.

[1480] 6. Answer submission and feedback:

[1481] The identified user enters a solution to the problem, which is sent to the server, which provides the solution to the original user and also receives feedback and stores it in a database.

[1482] Examples of concrete examples and prompts

[1483] Examples:

[1484] A factory worker asks the smart glasses how to set up a new machine by voice: "Please tell me how to set up a new machine." The voice is converted into text and sent to the server. The server extracts the keyword "machine setting" and searches a database of past information. A technician with relevant knowledge is identified and a notification is sent. The technician provides an appropriate answer, which is sent back to the worker. The worker configures the machine based on the answer and sends feedback.

[1485] Example prompt sentence:

[1486] "A user speaks a question into a pair of smart glasses, such as 'How do I configure my new machine?' Design a system that sends this question to a server, identifies users with relevant expertise, and provides an answer in real time."

[1487] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1488] Step 1:

[1489] Audio Input:

[1490] Using smart glasses or a smartphone, users can voice-input questions or issues that arise on-site. For example, they might say, "Please tell me how to set up a new machine." This voice data is then captured by the smart device.

[1491] Input: Audio data

[1492] Output: Captured audio data

[1493] How it works: The user speaks their question or problem into the microphone on their smart device.

[1494] Step 2:

[1495] Speech to text conversion:

[1496] The device uses the speech_recognition library to convert the captured voice data into text data, for example, "How do I set up my new machine?"

[1497] Input: Captured audio data

[1498] Output: Text data

[1499] How it works: Your smart device processes the voice data using a cloud service or built-in speech recognition function and converts it into text.

[1500] Step 3:

[1501] Sending text data:

[1502] The device sends the converted text data to the server using a network connection. For example, the text "How do I set up my new machine?" is sent to the server.

[1503] Input: Text data

[1504] Output: Text data sent to the server

[1505] How it works: A smart device sends text data to a server via a network.

[1506] Step 4:

[1507] Natural Language Processing Analysis:

[1508] The server analyzes the received text data using the Google Cloud NLP API and extracts relevant keywords. For example, "machine settings" is extracted from the text.

[1509] Input: Text data

[1510] Output: Extracted keywords

[1511] How it works: The server passes text data to the API, which performs natural language processing to extract keywords.

[1512] Step 5:

[1513] Knowledge Database Search:

[1514] The server searches a knowledge database based on the extracted keywords, thereby identifying users and information with related expertise.

[1515] Input: Extracted keywords

[1516] Output: Related expertise and user information

[1517] How it works: The server sends keywords as queries to the knowledge database to search for relevant data.

[1518] Step 6:

[1519] Expertise Identification and Notification:

[1520] The server uses the search results to identify users with the appropriate expertise and sends notifications using Firebase Cloud Messaging, including questions and issues.

[1521] Input: relevant expertise and user information

[1522] Output: Send notification

[1523] What happens: The server sends a push notification to the specified user.

[1524] Step 7:

[1525] User answer input:

[1526] The identified user is notified and uses the device to enter a response, such as "Please refer to the documentation on how to set up the machine."

[1527] Input: Notification content

[1528] Output: Response data

[1529] How it works: A user with expert knowledge types an answer into a terminal and sends it to the server.

[1530] Step 8:

[1531] Providing answers:

[1532] The server provides the received response to the original user, allowing the original user to quickly obtain information to resolve the problem.

[1533] Input: Answer data

[1534] Output: Provide the answer to the original user

[1535] Operation: The server sends the response data to the original user's device.

[1536] Step 9:

[1537] Collecting feedback:

[1538] The user inputs feedback on the answer from the terminal and sends it to the server, which stores this feedback in a database.

[1539] Input: User feedback

[1540] Output: Saved feedback data

[1541] How it works: The server receives the feedback and stores it in a database.

[1542] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1543] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also improves the quality of the services provided by combining it with an emotion engine that recognizes the user's emotions.

[1544] Explanation of program processing

[1545] 1. User questions and issues posted

[1546] The user uses the terminal to input their question or problem and submit it. For example, they might input, "Please tell me how to create materials for a new marketing strategy."

[1547] 2. Post content collection and emotion recognition

[1548] The device processes the user's input using an emotion engine to recognize the user's emotions. The emotion data includes emotion categories such as joy, sadness, and anger.

[1549] The device sends the question or issue along with the recognized emotion data to the server.

[1550] 3. Receiving and analyzing questions and issues

[1551] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[1552] 4. Emotional Data Analysis

[1553] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[1554] 5. Knowledge Database Reference

[1555] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[1556] 6. Identifying users with the right expertise

[1557] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify other users with appropriate expertise. For example, employee A, who is knowledgeable about marketing strategies, and employee B, who is knowledgeable about document creation, are identified.

[1558] 7. Notification to Identified Users

[1559] The server notifies the identified user of their questions or issues along with their emotional data and asks for a response. This notification is sent via push notifications, emails, or other means.

[1560] 8. User-generated answers

[1561] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[1562] 9. Receipt and Notification of Responses

[1563] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[1564] 10. Providing Feedback

[1565] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[1566] The device sends the feedback data and the recognized emotions to the server.

[1567] 11. Feedback Storage and Notification

[1568] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[1569] Specific processing examples

[1570] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[1571] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[1572] The processing flow will be explained below.

[1573] Program processing flow

[1574] Step 1:

[1575] The user can input their question or problem through the terminal and submit it. For example, they can input, "Please tell me how to create materials for a new marketing strategy."

[1576] Step 2:

[1577] The device processes the input questions and issues using an emotion engine to recognize the user's emotions. Emotion data includes categories of emotions such as joy, sadness, anger, and anxiety.

[1578] Step 3:

[1579] The device sends the recognized emotion data and the question or problem to the server. The sent data includes the user ID, input content, emotion data, and the date and time of sending.

[1580] Step 4:

[1581] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[1582] Step 5:

[1583] The server searches the knowledge database based on the extracted keywords and emotion data to collect related information, and selects high-priority information based on the emotion data.

[1584] Step 6:

[1585] The server compares the knowledge database with employee profile data (expertise, past response history, emotional response experience) to identify users with appropriate expertise. For example, employee A who is knowledgeable about marketing strategies and employee B who is skilled in creating materials can be identified.

[1586] Step 7:

[1587] The server notifies the identified user of their questions or issues along with their emotional data and asks for their answers. These notifications are sent via push notifications, emails, etc.

[1588] Step 8:

[1589] The identified users use the devices to input answers to questions or issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[1590] Step 9:

[1591] The terminal sends the entered answer data to the server. The sent data includes the answer content, respondent ID, and answer date and time.

[1592] Step 10:

[1593] The server then provides the responses received from employees to the original sender. To do this, the server uses push notifications, emails, etc.

[1594] Step 11:

[1595] The user uses the device to review the answers provided. For example, the user reviews the information received from employees A and B and understands the steps to resolve the issue.

[1596] Step 12:

[1597] The user inputs feedback on the provided answer through the terminal, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much."

[1598] Step 13:

[1599] The device sends the feedback data and the recognized emotion to the server. The sent data includes the feedback content, emotion data, user ID, and the date and time of sending.

[1600] Step 14:

[1601] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, etc.

[1602] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, thereby reducing communication friction that arises from differences in knowledge levels between employees and their superiors.

[1603] Example 2

[1604] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1605] When sharing information or solving problems within a company, friction in communication arises due to differences in the knowledge levels of employees and their superiors. This friction prevents fast and effective information sharing, resulting in a decline in work efficiency. To address this issue, the present invention aims to realize more personalized responses and reduce friction in communication by recognizing users' emotions and providing information that takes these emotions into consideration.

[1606] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1607] In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the input content with an emotion engine and recognize the user's emotion; means for the terminal to transmit the recognized emotion data and the question or problem to the server; means for the server to analyze the received question or problem using natural language processing technology and extract related keywords; means for the server to analyze the received emotion data and set priorities for the search results; means for the server to search a knowledge database based on the extracted keywords and collect related information; means for the server to identify other users with appropriate expertise based on information in the knowledge database and user profile data; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the response received from the user to the user who sent the response. This reduces communication friction caused by differences in knowledge levels between employees and their superiors, enabling quick and effective information sharing.

[1608] A "terminal" is a device that allows a user to input questions or issues and send the content, and includes personal computers, smartphones, etc.

[1609] An "emotion engine" is software that processes user input and recognizes the emotions it conveys, and has the ability to classify emotions such as joy, anger, and sadness.

[1610] "Emotion data" refers to the user's emotional information recognized by the emotion engine, and is expressed as text data.

[1611] The "server" is a central system that processes questions and issues received from users, searches a database and provides appropriate information.

[1612] "Natural language processing technology" is a technology that analyzes text data sent by users and extracts relevant keywords and important information.

[1613] "Keywords" are words or phrases that indicate important topics of a question or issue, extracted using natural language processing techniques.

[1614] A "knowledge database" is a data storage system that stores past questions, answers, and specialized knowledge, and is used by the server for searches.

[1615] "Profile data" refers to a dataset that includes information such as each employee's expertise, past response history, and emotional response experience.

[1616] "Identified User" refers to a user who has been determined to have the appropriate expertise for a question or issue based on the knowledge database and profile data.

[1617] "Feedback data" refers to data that indicates evaluations and opinions of answers provided by users, and is reanalyzed by the emotion engine.

[1618] MODE FOR CARRYING OUT THE INVENTION

[1619] This invention is a system that reduces communication friction caused by differences in knowledge levels between employees and their superiors, and supports quick and effective information sharing and problem solving within a company. It also aims to improve the quality of services provided through emotion recognition.

[1620] System Configuration

[1621] The system consists of the following main components:

[1622] Terminal: A device through which a user inputs questions or issues. Specific examples include personal computers and smartphones.

[1623] Emotion engine: Software that analyzes text data to recognize user emotions. A specific example is IBM Watson Tone Analyzer.

[1624] Server: The central system that processes data received from users and provides appropriate information. Google Cloud Natural Language API is used as the natural language processing technology.

[1625] Knowledge database: A data storage system that stores past questions, answers, and specialized knowledge.

[1626] Profile database: A data set containing information such as each employee's expertise, past response history, and emotional response experience.

[1627] Program processing flow

[1628] The system processes as follows:

[1629] 1. User questions and issues posted

[1630] A user uses a device to type in and submit a question or issue, for example, "How do I create a document for a new marketing strategy?"

[1631] 2. Post content collection and emotion recognition

[1632] The device processes the user's input using an emotion engine and recognizes the user's emotions. The emotion data includes emotion classifications such as joy, sadness, and anger. The device then sends the recognized emotion data along with the question or issue to the server.

[1633] 3. Receiving and analyzing questions and issues

[1634] The server uses natural language processing technology to analyze the questions and issues received and extracts related keywords, such as "marketing strategy" and "document creation."

[1635] 4. Emotional Data Analysis

[1636] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses anger, a quick response will be prioritized.

[1637] 5. Knowledge Database Reference

[1638] The server searches a knowledge database based on the extracted keywords and emotion data. This database contains past questions and answers, as well as specialized knowledge.

[1639] 6. Identifying users with the right expertise

[1640] The server identifies other users with appropriate expertise based on the knowledge database and profile database. For example, employee A who is knowledgeable about marketing strategies and employee B who is knowledgeable about document creation are identified.

[1641] 7. Notification to Identified Users

[1642] The server notifies the identified user of their question or problem along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[1643] 8. User-generated answers

[1644] The identified users use the devices to input answers to questions and issues. For example, employee A might respond, "Please refer to past marketing strategy materials," and employee B might reply, "We will provide templates that will help you create the materials."

[1645] 9. Receipt and Notification of Responses

[1646] The server receives the response and provides it to the user, allowing the user to quickly obtain information to resolve the problem.

[1647] 10. Providing Feedback

[1648] The user enters feedback on the provided answer, which is then analyzed by the emotion engine. For example, the user enters feedback such as "This was very helpful. Thank you very much." The device then sends the feedback data and the recognized emotion to the server.

[1649] 11. Feedback Storage and Notification

[1650] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers.

[1651] Specific examples

[1652] For example, if a user sends a question from a device such as "I would like to know about new methods for sales strategy," the device analyzes the question using its emotion engine and recognizes the user's emotion as "anxiety." The server receives the question, extracts keywords such as "sales strategy" and "new methods," and searches the knowledge database. Based on the search results, employee C, who is knowledgeable about sales strategy, is identified and a notification is sent to employee C along with the emotion data. Employee C receives this notification and replies from his device, "I will provide a concrete example of a new method." The user reviews the answer and sends feedback such as "That was very helpful. Thank you." This feedback is also analyzed by the emotion engine and sent to the server.

[1653] Example prompts for generative AI models

[1654] Example prompt:

[1655] Please explain the program processing for the following system in natural language. Please write so that the subject is either the server, the terminal, or the user. Please use plain sentence endings.

[1656] system:

[1657] A system to reduce communication friction caused by differences in knowledge levels between employees and their superiors. By combining it with an emotion engine, the quality of the services provided is improved.

[1658] Specific processing steps:

[1659] 1. User questions and issues posted

[1660] 2. Post content collection and emotion recognition

[1661] 3. Receiving and analyzing questions and issues

[1662] 4. Emotional Data Analysis

[1663] 5. Knowledge Database Reference

[1664] 6. Identifying users with the right expertise

[1665] 7. Notification to Identified Users

[1666] 8. User-generated answers

[1667] 9. Receipt and Notification of Responses

[1668] 10. Providing Feedback

[1669] 11. Feedback Storage and Notification

[1670] In this way, the system of the present invention responds to questions and issues quickly and efficiently, and by taking emotional data into account, it provides a more personalized response, thereby reducing communication friction that arises due to differences in knowledge levels between employees and their superiors.

[1671] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1672] Step 1:

[1673] The user uses the terminal to input a question or issue and transmits the content. For example, the user might input "Please tell me how to create materials for a new marketing strategy." This question or issue becomes input data and is transmitted to the terminal. The output is the input text information.

[1674] Step 2:

[1675] The device processes the input content using an emotion engine to recognize the user's emotion. The input is text data entered by the user, and this data is analyzed using an emotion engine (e.g., IBM Watson Tone Analyzer). As a result of the analysis, the user's emotion data (e.g., "anxiety," "confusion," etc.) is obtained. The output is the recognized emotion data.

[1676] Step 3:

[1677] The device sends the recognized emotion data and the text data of the question or problem to the server. The input is the emotion data obtained in step 2 and the text data of the user's question or problem. The output is the dataset sent to the server.

[1678] Step 4:

[1679] The server analyzes the questions and issues it receives using natural language processing technology (for example, Google Cloud Natural Language API) and extracts related keywords. The input is the dataset sent in step 3, and the natural language processing engine analyzes the text data to extract keywords such as "marketing strategy" and "document creation." The output is the extracted keywords.

[1680] Step 5:

[1681] The server analyzes the received emotion data and sets priorities for search results and inquiries. The input is the emotion data and keywords obtained in steps 2 and 4. By analyzing the emotion data, adjustments are made to prioritize a quick response, for example, if the user is feeling "anger." The output is prioritized keywords and inquiries.

[1682] Step 6:

[1683] The server searches the knowledge database based on the prioritized keywords and the query. The database contains past questions, answers, and specialized knowledge. The input is the prioritized keywords and the query set in step 5. The server searches for relevant information in the knowledge database and collects the results. The output is the search result information.

[1684] Step 7:

[1685] The server identifies other users with appropriate expertise based on the information in the knowledge database and the user's profile data. The input is the information retrieved in step 6 and the expertise information from the profile data database. The server compares these data and identifies users who are knowledgeable about marketing strategies or document creation, for example. The output is the identified appropriate users.

[1686] Step 8:

[1687] The server notifies the identified user of the question or issue along with emotion data and asks for a response. This notification is done using means such as push notification or email. The input is the user identified in step 7 and the question / issue data from step 3. The output is a notification to the identified user.

[1688] Step 9:

[1689] The identified user uses the terminal to input answers to questions or issues. For example, the user can respond, "Please refer to past marketing strategy materials," and the server can reply, "We will provide you with a template that will help you create the materials." The input is the answer data entered by the identified user. The output is the answer data sent to the server.

[1690] Step 10:

[1691] The server receives the identified user's answer and provides it to the user who posted the question. The input is the answer data obtained in step 9. The server sends this data to the user's terminal and provides information for solving the problem. The output is information provided to the user who posted the question.

[1692] Step 11:

[1693] The user inputs feedback for the provided answer, and the feedback is analyzed by the emotion engine. For example, the user inputs feedback such as "This was very helpful. Thank you very much." The input is the feedback text data entered by the user. The output is the feedback data with emotion data analyzed by the emotion engine.

[1694] Step 12:

[1695] The terminal sends the feedback data to the server, which then stores it in the database. The input is the feedback data analyzed in step 11. The server stores it in the database and notifies the relevant employees and managers. The output is the stored feedback data and the notification.

[1696] (Application example 2)

[1697] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1698] In conventional factories, there was a lack of means to quickly respond to questions or concerns that operators had while working. This made it difficult to solve problems efficiently, causing stress and reduced productivity for operators. Furthermore, personalized responses that took into account the emotions felt by operators were not provided, which sometimes led to friction in communication.

[1699] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for a user to input and transmit a question or problem through a terminal; means for the terminal to process the user's input content using an emotion engine, recognize the user's emotion, and transmit the input content together with emotion data to the server; means for the server to analyze the question or problem received by the server using natural language processing technology and extract related keywords; means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; means for the server to notify the identified users of the question or problem and prompt them to respond; and means for the server to provide the user with the response received from the user. This makes it possible to respond to questions or problems quickly and efficiently and provide personalized responses that take emotion data into consideration, thereby reducing communication friction and reducing operator stress.

[1700] A "user" is an entity that uses the system to input and send questions or issues.

[1701] The "terminal" is a device where users can input and send questions and issues, and which also recognizes emotions using an emotion engine.

[1702] The "emotion engine" is a technology that analyzes the user's input and voice and recognizes and classifies the user's emotions.

[1703] The "server" is a device that uses natural language processing technology to analyze received questions and issues, searches a knowledge database based on extracted keywords, identifies other users with appropriate expertise, and promotes notifications and responses.

[1704] "Natural language processing technology" is a technology that analyzes text data entered by a user and extracts related keywords.

[1705] "Keywords" are important words or phrases extracted from users' questions or issues.

[1706] A "knowledge database" is a collection of past questions and answers, as well as specialized knowledge.

[1707] "Expertise" is specific knowledge and skills that provide solutions to specific problems or challenges.

[1708] "Feedback" refers to ratings and comments that users make on answers provided.

[1709] "Emotion data" is data that indicates the emotional state of the user as recognized by the emotion engine.

[1710] "Profile Data" is information about an individual, such as an employee's expertise or past response history.

[1711] "Matching" is the process of matching a specific user with the most appropriate question.

[1712] This invention is a system that responds quickly and effectively to specific questions and issues by linking a terminal, an emotion engine, natural language processing technology, a knowledge database, and a server. A specific description will be given of an embodiment of this invention.

[1713] System Program

[1714] 1. Hardware and Software

[1715] Device: The device that a user uses to input and submit their question or issue, such as smart glasses or a head-mounted display (e.g., Microsoft HoloLens).

[1716] Emotion engine: Technology that analyzes user voice input and text data to recognize emotions. As an example, we will use Affectiva's emotion recognition engine.

[1717] Natural language processing technology: Technology that analyzes user input data and extracts relevant keywords. We will use SpaCy as an example.

[1718] Server: A device that processes the received questions, issues, and sentiment data, searches the knowledge database, and identifies other users with appropriate expertise. For example, we use AWS EC2.

[1719] Knowledge database: A collection of past questions and answers, as well as accumulated expert knowledge. For example, we use Elasticsearch.

[1720] 2. Program processing flow

[1721] 1. User submission of questions and issues:

[1722] The user uses the terminal to input their questions or issues and send them. For example, they might input, "I don't know how to set up the manufacturing machine. Please help me."

[1723] 2. Post content collection and emotion recognition:

[1724] The device processes the user's input using an emotion engine to recognize the user's emotions, and sends the user's questions and issues along with emotional data (e.g., anxiety, irritation, etc.) to the server.

[1725] 3. Receiving and analyzing questions and issues:

[1726] The server analyzes the received questions and issues using natural language processing technology and extracts related keywords (e.g., "manufacturing machinery," "setting methods," etc.).

[1727] 4. Sentiment Data Analysis:

[1728] The server analyzes the received emotion data and prioritizes search results based on that data. For example, if the user expresses "anxiety," it prioritizes a quick response.

[1729] 5. Knowledge Base Reference:

[1730] The server searches a knowledge database based on the extracted keywords and emotion data to collect relevant information. This database contains past questions and answers, as well as specialized knowledge.

[1731] 6. Identifying users with the right expertise:

[1732] The server matches the profile data against a knowledge database to identify other users with relevant expertise, for example, users who are "familiar with setting up manufacturing machines."

[1733] 7. Notice to Identified Users:

[1734] The server notifies the identified user of their questions or issues along with their emotional data and prompts them to respond. This notification is sent via push notifications, emails, etc.

[1735] 8. User responses:

[1736] The identified user uses the terminal to input answers to questions or issues, such as providing "detailed instructions on how to set up a manufacturing machine."

[1737] 9. Receiving and notifying responses:

[1738] The server receives the response and provides it to the original user, allowing the user to quickly obtain information to resolve the problem.

[1739] 10. Providing Feedback:

[1740] The user can input feedback for the answer provided through the terminal, and the feedback is analyzed by the emotion engine. For example, the user can input feedback such as "This was very helpful. Thank you very much."

[1741] 11. Feedback Storage and Notification:

[1742] The server stores the received feedback and sentiment data in a database and notifies relevant employees and managers using push notifications, emails, and other methods.

[1743] Prompt Sentence Examples

[1744] "I don't know how to set up the manufacturing machine. Please help me."

[1745] "Please make sure this part is installed correctly. I'm a little worried."

[1746] In this way, the system responds to user questions and issues quickly and efficiently, and by taking emotional data into account, provides a more personalized response, reducing operator stress and improving productivity.

[1747] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1748] Step 1:

[1749] The user sends questions or issues to the device via voice or text input. The input data is the specific content of the question or issue, such as "I don't know how to set up a manufacturing machine. Please help me." The input data is saved as text.

[1750] Step 2:

[1751] The device passes the user's voice input or text to an emotion engine to recognize the user's emotion. The emotion engine (e.g., Affectiva) analyzes the voice or text data and generates emotion data (e.g., anxiety, irritation, etc.). This identifies the user's emotion and adds that information.

[1752] Step 3:

[1753] The device sends the recognized emotion data along with the text data of the question or task to the server. The sent data includes the content of the question or task and the user's emotional state at that time.

[1754] Step 4:

[1755] The questions and issues received by the server are analyzed using natural language processing technology. The natural language processing technology used (e.g., SpaCy) analyzes the text data and extracts related keywords. For example, keywords such as "manufacturing machine" and "setting method" are extracted.

[1756] Step 5:

[1757] The server searches a knowledge database based on the extracted keywords and the recognized emotion data. The database technology used (e.g., Elasticsearch) searches for related information and collects the most appropriate solutions and information. This allows related past questions and answers to be retrieved.

[1758] Step 6:

[1759] The server compares the information in the knowledge database with the profile database to identify users with appropriate expertise. The profile database contains each user's expertise and past response history, so for example, a user who is "expert in setting up manufacturing machines" can be identified.

[1760] Step 7:

[1761] The server notifies the identified user of the question or issue. The notification is sent via push notification or email along with emotion data, prompting the identified user to respond. This notification is expected to result in a prompt response.

[1762] Step 8:

[1763] Identified users input answers to questions and issues through terminals. The input data is specific solutions or reference materials, such as "detailed instructions on how to set up manufacturing machines."

[1764] Step 9:

[1765] The server receives the answer and provides it to the user. The server then sends the answer back to the original user, who then confirms the answer through their device. This allows the user to quickly obtain information to solve the problem.

[1766] Step 10:

[1767] The user inputs feedback on the answer provided through the terminal. The feedback data is analyzed by the emotion engine to obtain the user's emotional state and evaluation. For example, feedback such as "This was very helpful. Thank you very much" may be input.

[1768] Step 11:

[1769] The server stores the feedback and sentiment data in a database and notifies relevant employees and managers, providing insights to improve the quality of responses across the system.

[1770] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1771] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1772] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1773] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1774] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1775] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1776] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1777] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1778] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1779] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1780] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1781] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1782] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1783] 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.

[1784] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1785] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1786] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1787] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1788] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1789] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1790] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1791] The following is further disclosed regarding the above embodiment.

[1792] (Claim 1)

[1793] A means for users to input and submit questions and issues through a terminal;

[1794] A means for analyzing questions and issues received by the server using natural language processing technology and extracting related keywords;

[1795] A means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise;

[1796] The server notifies the identified user of the question or issue and prompts for a response;

[1797] a means for the server to provide the response received from the user to the original user;

[1798] A system including:

[1799] (Claim 2)

[1800] 10. The system of claim 1, wherein the server receives feedback from the user and stores it in a database.

[1801] (Claim 3)

[1802] 10. The system of claim 1, wherein the system uses user profile data to match the most suitable questions to the identified user.

[1803] "Example 1"

[1804] (Claim 1)

[1805] A means for users to input and send questions and issues through an information terminal;

[1806] A means for analyzing questions and issues received by the server using natural language processing technology and extracting related words and phrases;

[1807] A means for the server to search a knowledge database based on the extracted words and phrases to identify other users with appropriate expertise;

[1808] The server notifies the identified user of the question or issue and prompts for a response;

[1809] A means for the identified user to input and transmit a response via an information terminal;

[1810] a means for the server to provide the submitted response to the original user;

[1811] A system including:

[1812] (Claim 2)

[1813] 10. The system of claim 1, wherein the server receives feedback from the user and stores it in a database.

[1814] (Claim 3)

[1815] 10. The system of claim 1, wherein the system uses personal data of the user to match the most suitable question to the identified user.

[1816] "Application Example 1"

[1817] New Claims

[1818] (Claim 1)

[1819] A means for users to input and submit questions and issues through a terminal;

[1820] A means for analyzing questions and issues received by the server using natural language processing technology and extracting related keywords;

[1821] A means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise;

[1822] The server notifies the identified user of the question or issue and prompts for a response;

[1823] a means for the server to provide the response received from the user to the original user;

[1824] A method to input questions and issu...

Claims

1. A means for users to input and submit questions and issues through a terminal; A means for analyzing questions and issues received by the server using natural language processing technology and extracting related keywords; A means for the server to search a knowledge database based on the extracted keywords and identify other users with appropriate expertise; The server notifies the identified user of the question or issue and prompts for a response; a means for the server to provide the response received from the user to the original user; A system including:

2. The system of claim 1, wherein the server receives feedback from the user and stores it in a database.

3. 10. The system of claim 1, wherein user profile data is used to match the most suitable question to the identified user.

Images