System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting reports, feedback, and problem resolution proposals submitted by employees; means for filtering unwanted information from the collected information; means for storing and tagging the filtered information in a database; means for retraining a generative AI model using the stored information; means for transmitting the user's input to a server and requesting an answer in response to the question; means for searching for relevant information in the database and generating an optimal solution; and means for transmitting the generated answer to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Many employees in a company face various challenges in their daily work and spend time and effort trying to find solutions. Furthermore, the Elder system currently in place within the company only transfers individual experience and knowledge to a narrow range, preventing efficient work execution and knowledge sharing. As a result, employee work efficiency declines and profitability is hindered. There is a need to resolve these issues and provide an environment where employees can solve problems quickly and effectively. [Means for solving the problem]

[0005] This invention provides a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters unnecessary information from this data, and selects only highly relevant information. The collected and cleansed data is stored in a database and appropriately tagged to improve information searchability. Furthermore, the stored data is used to retrain a generative AI model, providing highly accurate solutions based on the latest data.

[0006] The system provides an interface that allows users to input issues or questions in natural language, and sends the input questions to a server requesting an answer. The server then searches for relevant information in a database, generates optimal solutions based on past success stories and expert advice, and provides them to the user. This system allows employees to quickly solve problems they face in their daily work, which is expected to improve work efficiency and increase profits.

[0007] An "employee" is an individual worker employed to perform work within a company.

[0008] A "report" is a document created by an employee to report the progress and results of work to their superiors or colleagues.

[0009] "Feedback" refers to receiving evaluations and opinions from others about the status and results of work.

[0010] A "problem-solving proposal" is a proposal that shows specific solutions or improvement ideas for the problems or issues being faced.

[0011] "Collection" refers to the act of gathering necessary data or information.

[0012] "Data" is information that represents facts or observations in numerical or written form.

[0013] "Filtering" is the process of separating important information from unimportant information and removing unnecessary information.

[0014] A "database" is a collection of information that systematically organizes a large amount of information so that it can be searched and used efficiently.

[0015] "Tagging" refers to attaching an identifiable label to data or information.

[0016] A "generative AI model" is an algorithm that uses artificial intelligence techniques to learn patterns from data and generate new information.

[0017] "Retraining" is the process of adding new data to an existing model to learn from it and improve its accuracy.

[0018] "Natural language" refers to the language that humans use on a daily basis, and is a concept that contrasts with formal language.

[0019] An "interface" is a point of contact or means by which a user interacts with a system.

[0020] A "server" is a computer that provides data and services to other computers on a network.

[0021] "Searching" is the process of locating information in a database based on specific criteria.

[0022] A "solution" is a specific means or method taken to solve a problem or issue.

[0023] "Success stories" are specific examples of projects or initiatives that have been implemented in the past and have been successful.

[0024] An "expert" is someone who has a high level of knowledge and skill in a particular field and is knowledgeable about that field.

[0025] "Optimal" refers to something that is most suitable for a particular condition or purpose. [Brief explanation of the drawings]

[0026] [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

[0027] 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.

[0028] First, the terms used in the following description will be explained.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] [First embodiment]

[0035] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0036] 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.

[0037] 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).

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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."

[0047] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Below, we will explain the program processing of this system in natural language and provide detailed examples.

[0048] Server-side implementation

[0049] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0050] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, leaving only specific problem-solving methods and success stories.

[0051] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI with a new dataset every six months.

[0052] Terminal side embodiment

[0053] Users interact with the system through a terminal, which provides a chat box-style interface where users can enter issues or questions in natural language. For example, a user might enter a question like, "How can I develop a new marketing strategy?"

[0054] The terminal sends the user's input directly to the server, requesting an answer to the question. This data transmission is done in real time.

[0055] Server Response Generation Embodiments

[0056] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" from the database.

[0057] Based on the search results, the server uses generative AI to generate the optimal solution. During this generation process, it generates an answer that includes specific implementation steps and points to note, based on past success stories and expert advice. The generated answer is then sent back to the user via their device. For example, it might be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[0058] User usage pattern

[0059] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server and displays it in real time. The user checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0060] In this way, the system of the present invention provides support for quickly and effectively resolving the challenges employees face every day, improving business efficiency and increasing profits.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Data collection

[0064] The server automatically collects reports, feedback, and problem-solving proposals from each employee on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0065] Step 2:

[0066] Data Cleansing

[0067] The server performs a cleansing process to remove noise and irrelevant information from the collected data, so that only specific problem-solving methods and success stories are retained.

[0068] Step 3:

[0069] Database storage and tagging

[0070] The server stores the cleansed data in a database and tags it, adding appropriate tags such as "project management" or "marketing strategy" to make searches more efficient.

[0071] Step 4:

[0072] Retraining the Model

[0073] The server periodically retrains the generative AI model using the stored data, for example, every six months using a new dataset.

[0074] Step 5:

[0075] Accepting user input

[0076] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[0077] Step 6:

[0078] Sending User Input

[0079] The device sends the user's input directly to the server and requests an answer to the question, a process that occurs in real time.

[0080] Step 7:

[0081] Database search

[0082] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" in the database.

[0083] Step 8:

[0084] Response Generation

[0085] Based on the search results, the server uses generative AI to generate the optimal solution, including specific implementation steps and points to note based on past success stories and expert advice.

[0086] Step 9:

[0087] Sending a response to the user

[0088] The server then sends the generated answer to the device, for example, in the form of "Please see the specific example below for how to create a marketing strategy..."

[0089] Step 10:

[0090] Checking and using responses

[0091] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0092] This process flow allows users to receive assistance in quickly and effectively resolving their issues.

[0093] Example 1

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

[0095] In today's corporate environment, employees submit huge volumes of reports, feedback, and problem-solving proposals. Therefore, there is a need to quickly extract useful data from this information and analyze and utilize it appropriately. However, traditional methods require manual data filtering and analysis, which takes a great deal of time and effort. To solve this problem, an efficient and automated data processing system is needed.

[0096] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0097] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering and cleansing unnecessary information from the collected data, means for storing the filtered and cleansed data in a database and tagging it appropriately, means for periodically retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for sending the user's input to the server and requesting answers corresponding to the questions, means for searching for related information in the database and generating optimal solutions based on the extracted information, and means for sending the generated answers to the user. This makes it possible to efficiently and automatically extract useful data from a vast amount of information and quickly provide support for problem solving.

[0098] "Means for collecting reports, feedback, and problem-solving proposals submitted by employees" refers to software and hardware means for automatically collecting various reports, feedback, and problem-solving proposal documents submitted by employees from internal systems.

[0099] "Means for filtering and cleansing unnecessary information from collected data" means algorithmic and software means for automatically detecting and removing noise and irrelevant information in collected data.

[0100] "Means for storing the filtered and cleansed data in a database and tagging it appropriately" refers to hardware and software means for storing the cleansed data in a database and tagging it with appropriate tags, such as "project management" and "marketing strategy," to further improve search efficiency.

[0101] "Means for periodically retraining a generative AI model using stored data" refers to providing software and computing resources for adjusting and optimizing the parameters of a generative AI model and retraining it using updated data stored in a database at regular intervals.

[0102] "Means for providing an interface that allows users to input tasks or questions in natural language" refers to software means for providing an interface that allows users to input tasks or questions in natural language, for example, a chat box-style UI.

[0103] "Means for sending user input to a server and requesting an answer corresponding to the question" refers to communication means and control software for sending natural language data entered by a user to a server in real time and requesting that the server generate an appropriate answer.

[0104] "Means for searching for relevant information in a database and generating optimal solutions based on the extracted information" refers to algorithms and software means by which a server searches for relevant information in a database and generates optimal solutions using a generative AI model based on the search results.

[0105] The "means for transmitting the generated answer to the user" refers to the communication means and software means for transmitting the answer generated by the server to the user's terminal in real time.

[0106] MODE FOR CARRYING OUT THE INVENTION

[0107] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information.

[0108] Server-side implementation

[0109] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, the server has the function of automatically extracting project reports at the end of each month. The hardware used includes the company's database server and network interface cards. The software used includes data collection scripts, cleansing algorithms, and tagging algorithms.

[0110] The collected data undergoes a cleansing process on the server for filtering. During this process, noise data and irrelevant information are automatically removed, leaving only specific problem-solving methods and success stories. The cleansed data is stored in a database and is assigned appropriate tags, such as "project management" or "marketing strategy." Tagging makes future searches more efficient. The stored data is used to retrain the generative AI model at regular intervals. For example, the server retrains the generative AI using a new dataset every six months.

[0111] Terminal side embodiment

[0112] Users interact with the system through terminals. The terminals provide a chat box-style interface where users can input issues or questions in natural language. For example, a user can input the question, "How do I develop a new marketing strategy?" The terminals transmit this input in real time to the server and request an answer to the question. The terminals include interface software and a network communication module.

[0113] Server Response Generation Embodiments

[0114] The server analyzes the user's input and searches for related information in the database. For example, it searches the database for data related to "marketing strategy." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, it refers to past success stories and expert advice to generate an answer that includes specific implementation steps and points to note. The generated answer is then sent back to the user via the device. For example, the answer may be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[0115] User usage pattern

[0116] The user enters a question in the chat box and clicks the send button. The terminal then receives a response from the server and displays it in real time. The user then checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal." In this way, the system of the present invention helps employees quickly and effectively solve the challenges they face every day, improving business efficiency and increasing revenue.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Program processing steps

[0119] Step 1: Data collection

[0120] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule.

[0121] Input: Reports, feedback, and problem-solving proposals stored in our internal systems.

[0122] What it does: The server runs the data collection script at the end of each month to get the latest reports and feedback.

[0123] Output: A list of the raw data collected.

[0124] Step 2: Data cleansing

[0125] The server cleanses the collected data and filters out unnecessary information.

[0126] Input: A list of the collected raw data.

[0127] What it does: The server runs a cleansing algorithm to remove noise data and irrelevant information.

[0128] Output: filtered clean data.

[0129] Step 3: Tag and store your data

[0130] The server stores the cleansed data in a database and tags it appropriately.

[0131] Input: Clean, cleansed data.

[0132] What it does: The server uses a tagging algorithm to assign tags like "project management" or "marketing strategy" and store them in a database.

[0133] Output: A database containing the tagged data.

[0134] Step 4: Periodically retrain the generative AI model

[0135] The server periodically retrains the generative AI model using the data stored in the database.

[0136] Input: The most recent dataset stored in the database.

[0137] How it works: Every six months, the server uses collected data to run a retraining algorithm for the generative AI model, improving the model's accuracy.

[0138] Output: A generative AI model that has been retrained and has improved performance.

[0139] Step 5: Accepting User Input

[0140] Users enter their assignments and questions into the chat box on their terminal.

[0141] Input: Issues or questions typed in natural language.

[0142] What happens: A user types "How can we develop a new marketing strategy?" into the chat box and clicks the send button.

[0143] Output: User input is sent from the terminal to the server.

[0144] Step 6: Sending User Input to the Server

[0145] The terminal sends the user's input as is to the server and requests a response.

[0146] Input: The assignment or question entered by the user.

[0147] Specific operation: The terminal sends input data to the server via the network.

[0148] Output: The user's input data received by the server.

[0149] Step 7: Parsing the Question

[0150] The server analyzes the user's input.

[0151] Input: Received user input data.

[0152] What it does: The server uses natural language processing (NLP) algorithms to parse the question and extract key keywords and intent.

[0153] Output: Extracted keywords and user intent.

[0154] Step 8: Search the database

[0155] The server searches for relevant information in a database based on the analysis results.

[0156] Input: Parsed keywords and user intent.

[0157] What happens: The server runs a database search algorithm to find relevant reports and success stories.

[0158] Output: A list of relevant information.

[0159] Step 9: Generate a solution

[0160] The server uses a generative AI model to generate the optimal solution.

[0161] Input: A list of search results and related information.

[0162] Specific operation: The server applies the generative AI model and generates an optimal solution based on the search results, including specific implementation steps and points to note.

[0163] Output: The generated solution.

[0164] Step 10: Submit your solution

[0165] The server transmits the generated solution to the terminal.

[0166] Input: The generated solution.

[0167] Specific operation: The server sends the solution to the terminal via the network.

[0168] Output: The solution displayed on the terminal.

[0169] Step 11: Check for a solution

[0170] The user checks the solution displayed on the terminal.

[0171] Input: The solution displayed in the terminal.

[0172] Specific Action: The user reviews the displayed solution and uses it as a reference for next steps.

[0173] Output: The solution confirmed by the user.

[0174] (Application example 1)

[0175] 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."

[0176] The reports, feedback, and problem-solving proposals submitted by factory workers are diverse and require time and effort. Effectively collecting and analyzing this information and quickly extracting relevant information is difficult. Furthermore, an efficient method is needed to enable real-time problem solving within factories.

[0177] 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.

[0178] In this invention, the server includes: means for collecting reports, feedback, and problem-solving proposals submitted by employees; means for filtering unnecessary information from the collected data; means for storing the filtered data in a database and tagging it; means for retraining the generative AI model using the stored data; means for providing an interface for users to input issues and questions in natural language; means for transmitting the user's input to the server and requesting answers corresponding to the questions; means for searching related information in the database and generating optimal solutions; means for providing problem-solving proposals based on the collected information, past success stories, and expert advice; and means for transmitting the generated answers to the user. This automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and enables efficient problem solving.

[0179] A "report" is a document that employees submit, detailing their daily work, progress, and issues.

[0180] "Feedback" refers to an employee expressing their opinions or thoughts about work or projects, or a document that contains the content of those opinions or thoughts.

[0181] A "problem-solving proposal" is a proposal that lists business problems and issues and provides specific solutions to them.

[0182] "Filtering" is the process of removing unnecessary information from collected data and selecting only highly relevant information.

[0183] "Tagging" is the process of assigning specific categories or keywords to data to make it easier to search and classify.

[0184] A "generative AI model" is an artificial intelligence model that uses machine learning based on large amounts of data to generate new information and solutions.

[0185] An "interface" refers to an operation screen or input device that allows a user to interact with a system.

[0186] A "database" is an electronic storage device for systematically organizing and storing data.

[0187] "Searching" is the act of finding specific information from data in a database.

[0188] A "solution" is a feasible response or means to a specific problem or issue.

[0189] A "success story" is a specific example of a past task or project that achieved a desired result.

[0190] "Expert advice" is advice or guidance from a professional with extensive knowledge and experience in a particular field.

[0191] The present invention is a system that efficiently collects reports, feedback, and problem-solving proposals from workers in a factory and provides advice in real time based on the collected information. Specific embodiments for realizing this system are described in detail below.

[0192] System Overview

[0193] The system of the present invention mainly consists of three main components: a server, a terminal (including a robot), and a user.

[0194] server

[0195] The server is responsible for the following:

[0196] 1. Data Collection and Storage

[0197] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker, and periodically transmits the collected data to the server.

[0198] 2. Data Cleansing and Filtering

[0199] Use the "DataCleanser" module to remove noise data and unnecessary information and extract only the most relevant information.

[0200] 3. Tagging and saving

[0201] The "DatabaseManager" module is used to assign appropriate tags to the cleansed data and store it in the database, such as "equipment maintenance" or "production line improvement."

[0202] 4. Retraining generative AI models

[0203] The stored data is used to periodically retrain the generative AI model, allowing it to generate up-to-date solutions based on new data.

[0204] Terminal (robot)

[0205] 1. Providing a user interface

[0206] The terminal provides an interface where users can input issues and questions in natural language. For example, a robot equipped with a tablet approaches a worker and accepts their reports and questions.

[0207] 2. Data Transmission

[0208] Collected data and user inputs are sent to a server in real time.

[0209] User

[0210] 1. Enter and submit your question

[0211] Users input issues or questions in natural language through the terminal interface and send them to the server. For example, they can input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[0212] 2. Receiving and Confirming Responses

[0213] The response from the server is provided to the user through the terminal, where the user can review and implement the displayed solution.

[0214] Processing flow

[0215] The server analyzes the user's input and searches for relevant information in the database. For example, it searches the database for data related to "equipment maintenance." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, an answer is generated that includes specific steps and points to note based on past success stories and expert advice. The generated answer is then sent to the user via their device.

[0216] Examples and prompts

[0217] As a concrete example, if a factory worker wants to know "machine maintenance procedures on line 2," he or she can input the question "Please tell me about the machine maintenance procedures on line 2" into the robot. In response to this question, the server will provide a solution including specific procedures based on past maintenance procedures and success stories.

[0218] Examples of prompt statements

[0219] Please tell me about the machine maintenance procedures for Line 2. Today's report indicates that an abnormality has been observed on Line 2.

[0220] In this way, the system of the present invention automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and can support efficient problem solving in real time.

[0221] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0222] Step 1:

[0223] Data collection

[0224] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker from the company's internal system. For example, a robot can collect reports at the end of each shift and send them to the server.

[0225] Input: Reports, feedback, and problem-solving proposals submitted by workers

[0226] Output: The collected raw dataset

[0227] Step 2:

[0228] Data Cleansing and Filtering

[0229] The server cleanses the collected data using the DataCleanser module, removing noise and unnecessary information, shaping the data and correcting outliers, and extracting only the most relevant data.

[0230] Input: Collected raw dataset

[0231] Output: A cleansed dataset

[0232] Step 3:

[0233] Tagging and database storage

[0234] The server uses the DatabaseManager module to tag the cleansed data appropriately, for example, with tags like "equipment maintenance" or "production line improvement," and then stores the tagged data in a database.

[0235] Input: Cleansed dataset

[0236] Output: A tagged dataset and data stored in a database

[0237] Step 4:

[0238] Retraining generative AI models

[0239] The server periodically retrains the "generative AI model" using the stored data, updating the machine learning algorithm so that it can generate up-to-date solutions based on new data.

[0240] Input: A dataset stored in a database

[0241] Output: Retrained generative AI model

[0242] Step 5:

[0243] Enter and submit a user question

[0244] Users input issues or questions in natural language through the terminal (robot) interface. This input data is sent to the server in real time. For example, a user might input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[0245] Input: Questions and issues entered in natural language

[0246] Output: The input data sent to the server

[0247] Step 6:

[0248] Search for related information in a database

[0249] The server receives the input data sent by the user and searches for related information in the database. It uses the "DatabaseManager" module to start searching for information based on related tags.

[0250] Input: User questions or challenges submitted

[0251] Output: Related information search results data

[0252] Step 7:

[0253] Solution Generation

[0254] The server uses a generative AI model based on the search results to generate an optimal solution, including specific steps and points to note, by referring to past success stories and expert advice.

[0255] Input: Search results for relevant information, and a retrained generative AI model

[0256] Output: Generated solution

[0257] Step 8:

[0258] Submitting and viewing answers

[0259] The server sends the generated solution to the user. The terminal (robot) displays the received solution to the user in real time. The user can check the solution and take the next step.

[0260] Input: Generated solution

[0261] Output: Solution displayed on the terminal

[0262] This allows for efficient collection of work reports within the factory, information cleansing and filtering, automatic generation of optimal solutions, and real-time problem resolution, all of which improves work efficiency and speeds up problem resolution.

[0263] 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.

[0264] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Additionally, the system incorporates an emotion engine that recognizes the user's emotions, enabling it to provide optimal answers based on the user's emotions. Below, the program processing of this system is explained in natural language and in detail with specific examples.

[0265] Server-side implementation

[0266] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0267] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, and retaining only specific problem-solving methods and success stories.

[0268] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI using a new dataset every six months to reflect the latest information.

[0269] Terminal side embodiment

[0270] Users interact with the system through a terminal. The terminal provides a chat box-style interface where users can input issues and questions in natural language. For example, a user might input a question such as, "How can I create a new marketing strategy?" The terminal is also equipped with an emotion engine that recognizes emotions from the user's input. For example, if a user inputs, "I'm stressed out about my latest project," the emotion engine will detect stress or anxiety.

[0271] The device sends the user's input and emotional data to the server and requests the best answer for the question, a process that occurs in real time.

[0272] Server Response Generation Embodiments

[0273] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[0274] Based on the search results, the server uses generative AI to generate the optimal solution. This process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. For example, if the user is feeling stressed, the server will also include advice on relaxation methods and stress management.

[0275] The generated answer is then sent back to the user via the device. For example, it might say, "Please see the specific example below for how to create a marketing strategy..." and also include advice such as, "We recommend taking short breaks to manage stress as you go along."

[0276] User usage pattern

[0277] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server, which is displayed in real time. The user then checks the provided solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds by presenting "Three steps for a successful client proposal," while also including advice tailored to the user's feelings.

[0278] In this way, the system of the present invention helps to solve problems quickly and effectively while taking into consideration the user's feelings, thereby improving business efficiency and increasing profits.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] Data collection

[0282] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of extracting project reports at the end of each month.

[0283] Step 2:

[0284] Data Cleansing

[0285] The server performs a cleansing process to remove noise and irrelevant information from the collected data. Specifically, it filters out personal opinions and casual conversations, leaving only specific problem-solving methods and success stories.

[0286] Step 3:

[0287] Database storage and tagging

[0288] The server stores the cleansed data in a database and appropriately tags it, for example, with tags like "project management" or "marketing strategy," making it easier to search.

[0289] Step 4:

[0290] Retraining the Model

[0291] The server retrains the generative AI model using new data, allowing it to provide highly accurate solutions based on the most recent data, for example, every six months.

[0292] Step 5:

[0293] Accepting user input

[0294] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[0295] Step 6:

[0296] emotion recognition

[0297] The device's built-in emotion engine recognizes emotions from user input. For example, if a user inputs "I'm feeling stressed about a recent project," the emotion engine will detect stress and anxiety.

[0298] Step 7:

[0299] Sending user input and emotion data

[0300] The device sends the user's input and emotional data to the server and requests an answer based on the question, a process that occurs in real time.

[0301] Step 8:

[0302] Database search

[0303] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[0304] Step 9:

[0305] Response Generation

[0306] The server generates optimal solutions based on the search results. It provides solutions that take into consideration the user's feelings, rather than just standard answers. For example, it suggests specific implementation steps and points to note for "marketing strategies" based on past success stories and expert advice.

[0307] Step 10:

[0308] Sending a response to the user

[0309] The server sends the generated answer to the terminal, for example, "Below are some specific examples of how to create a marketing strategy and relaxation methods for stress management."

[0310] Step 11:

[0311] Checking and using responses

[0312] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0313] Through this series of processing flows, the present invention supports the user in quickly and effectively resolving problems while taking into consideration the user's feelings.

[0314] Example 2

[0315] 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."

[0316] Conventional information collection and management systems struggled to efficiently collect reports, feedback, and problem-solving proposals submitted by employees and filter out unnecessary information. Furthermore, there were no systems that provided optimal answers that took user sentiment into account. This made information management cumbersome, making it difficult to provide appropriate support to users and preventing improvements in work efficiency. Furthermore, data management for appropriately retraining generative AI models was also cumbersome.

[0317] 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.

[0318] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for recognizing emotions from the user's input, means for searching for related information in the database and generating an optimal solution, and means for transmitting the generated answer to the user. This not only enables efficient filtering and appropriate management of information from employees, but also enables prompt provision of optimal answers that take user emotions into consideration, thereby improving business efficiency and the quality of user support.

[0319] A "report" is a document in which an employee describes work results, progress, problems, suggestions, etc.

[0320] "Feedback" is a document that includes evaluations, opinions, and areas for improvement regarding work.

[0321] A "problem-solving proposal" is a document that describes an appropriate solution or improvement plan for a specific problem or issue.

[0322] "Collection means" refers to the methods and functions for regularly collecting reports, feedback, and problem-solving proposals submitted by employees.

[0323] "Filtering means" refers to methods or functions for removing unnecessary information from collected data and selecting only highly relevant information.

[0324] The "storage means" refers to a method or function for storing the filtered data in a database and managing it so that it can be searched efficiently later.

[0325] "Tagging means" refers to methods or functions that assign keywords such as "project management" or "marketing strategy" to stored data to make it easier to search and identify.

[0326] "Retraining means" refers to the methods or functions that use stored data to periodically update a generative AI model to reflect new information.

[0327] "Means for providing an interface" refers to the method or function of providing an interactive screen or mechanism that allows users to input tasks or questions in natural language.

[0328] "Means for sending and requesting" refers to the methods and functions for sending user input to the server and requesting the appropriate response.

[0329] "Means for recognizing emotions" refers to a method or function for analyzing emotions from user input and identifying specific emotions.

[0330] "Search and generation tools" are methods and functions for locating relevant information in a database and generating optimal solutions or answers.

[0331] "Transmission means" refers to the method or function for sending and presenting the generated answer to the user.

[0332] This invention is a system that efficiently collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and provides optimal answers that take into account the user's feelings. The system is composed of three entities: a server, a terminal, and a user.

[0333] Server processing

[0334] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The specific implementation uses Python scripts to retrieve information using SQL queries. Cron jobs are used as the task scheduler.

[0335] Next, the collected data undergoes a cleansing process. At this stage, Apache Spark and Pandas are used to remove noisy data and irrelevant information, leaving only the most relevant information. Regular expressions are used to extract the necessary keywords and phrases. The filtered data is then stored in a database using Elasticsearch. Here, tags such as "project management" and "marketing strategy" are added. NLP (natural language processing) technology is used as the tagging algorithm.

[0336] Furthermore, the server periodically (e.g., every six months) retrains the generative AI model using the stored data, using TensorFlow or PyTorch to train the model and updating it with new datasets.

[0337] Processing by the terminal

[0338] The terminal provides a chatbox-style interface where users can input issues or questions in natural language. The interface is built using HTML and JavaScript, and sends user input to a server in real time. It uses NLP models such as BERT and RoBERTa as an emotion engine to analyze emotions from the user's text.

[0339] For example, if a user types "How can we develop a new marketing strategy?", the device sends this input and parsed sentiment data to the server via an HTTP request. The data is packaged in JSON format and deserialized after it is received by the server.

[0340] Server response generation

[0341] The server analyzes the user's input and emotional data and uses Elasticsearch to search for related information in a database. For example, it searches for data related to "marketing strategies" and analyzes the data while taking the user's emotional state into account. Based on the analysis results, it uses a generative AI model (e.g., GPT-3) to generate a natural language response.

[0342] The generated answers are designed to provide the best possible solution for the user, including specific steps and precautions, and if the user is feeling stressed, advice on relaxation and stress management is also included.

[0343] For example, a prompt might look like this:

[0344] 1. Example of user input:

[0345] "I'm feeling stressed about a recent project. What should I do?"

[0346] 2. The corresponding prompt:

[0347] "An employee wrote, 'I'm stressed out over a recent project.' Please provide specific stress management strategies. Also, include ways to reduce project management stress."

[0348] Terminal display of responses

[0349] Finally, the device displays the answers received from the server to the user in real time, such as "Please see the specific example below for how to create a marketing strategy..." and also provides advice such as "We recommend taking short breaks to manage stress as you go along."

[0350] This allows the user to check the provided solutions and use them as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server will present "three steps for a successful client proposal" and also include advice based on the user's feelings.

[0351] In this way, the system of the present invention solves problems quickly and effectively while taking into account the user's feelings, thereby improving business efficiency and increasing profits.

[0352] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0353] Step 1:

[0354] Data collection

[0355] The server collects employee reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The input is the reports, feedback, and problem-solving proposals submitted by employees, and the output is the collected data. The specific collection process involves executing SQL queries using a Python script to obtain the information. A Cron job is used for scheduling.

[0356] Step 2:

[0357] Data Cleansing

[0358] The server cleanses the collected data, removing noise and irrelevant information. This process uses Apache Spark and Pandas to analyze the data and filter out noise and unnecessary information. This scrutinizes the input data and produces filtered data as output. Specifically, it uses regular expressions to extract necessary keywords and phrases.

[0359] Step 3:

[0360] Data storage and tagging

[0361] The server stores the cleansed data in a database and assigns appropriate tags. The input is the cleansed data, and the output is tagged database entries. Specifically, Elasticsearch is used to assign tags such as "project management" and "marketing strategy" to the data. NLP technology is used as the tagging algorithm.

[0362] Step 4:

[0363] Retraining generative AI models

[0364] The server retrains the generative AI model using the stored data every specific period (e.g., every six months). The input is the stored dataset, and the output is the retrained generative AI model. Specifically, TensorFlow or PyTorch is used to retrain the AI ​​model using batch processing on the dataset.

[0365] Step 5:

[0366] Accepting user input

[0367] The terminal provides a chat box-style interface where users can input tasks and questions in natural language. The input is the natural language question or task from the user, and the output is the data that will be sent to the server. Specifically, a front end created with HTML and JavaScript provides the user interface and sends the input to the server in real time.

[0368] Step 6:

[0369] emotion recognition

[0370] The device recognizes emotions from the user's input. The input is the user's text data, and the output is analyzed emotion data. Specifically, it uses NLP models such as BERT and RoBERTa to analyze emotions from the input text.

[0371] Step 7:

[0372] Input and sending emotional data

[0373] The device sends the user's input and emotion data to the server. The input is the user's text data and emotion data, and the output is the data sent to the server. Specifically, the data is sent to the server using an HTTP request and packaged in JSON format.

[0374] Step 8:

[0375] Data analysis and response generation

[0376] The server analyzes the user's input and emotion data and searches for relevant information in the database. The input is the user's question and emotion data, and the output is the generated answer. Specifically, it uses Elasticsearch to search for relevant data and uses a generative AI model (e.g., GPT) to generate the optimal solution.

[0377] Step 9:

[0378] Submitting and viewing generated answers

[0379] The server sends the generated answer to the terminal, which displays it to the user. The input is the answer data from the server, and the output is the display data that the user can visually confirm. The specific operation is to send an HTTP response and display the answer on the front end.

[0380] Specific examples

[0381] In response to a user question such as, "I'm feeling stressed about a recent project. What should I do?", the server receives the input, "I'm feeling stressed about a recent project," and analyzes the emotion as stress. It searches for appropriate stress management methods from a related database and generates "specific stress management methods" using a generative AI model. For example, it presents guidelines such as "Three steps for a successful client proposal," while also including advice such as, "We recommend taking a short break for relaxation and stress management."

[0382] In this way, the system helps users solve problems quickly and effectively while taking their emotions into consideration, improving business efficiency and increasing profits.

[0383] (Application example 2)

[0384] 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."

[0385] Conventional data collection systems lack the ability to filter unnecessary information from collected reports, feedback, and problem-solving proposals, making it difficult to efficiently extract relevant information. Furthermore, there is no system that can recognize user emotions and generate appropriate responses based on them, which hinders the user experience.

[0386] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface through which a user inputs issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for searching related information in the database and generating an optimal solution, means for transmitting the generated answer to the user, and means for recognizing the user's emotions and generating an optimal response based on the emotions. This allows for providing an optimal solution that takes emotions into consideration, improving the user experience and business efficiency.

[0387] An "employee" is a staff member employed by a company or organization to perform work.

[0388] A "collection means" is a process or device for collecting specified data.

[0389] A "filtering means" is a process or device used to remove unwanted information from collected data.

[0390] A "database" is a system for efficiently storing, searching, and managing data.

[0391] A "tagging means" is a process or device that assigns a specific tag or label to stored data.

[0392] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information or answers from given data.

[0393] An "interface" is the input and output means by which a user interacts with a system.

[0394] A "server" is a computer system that processes data and provides services over a network.

[0395] A "means for recognizing emotions" is a process or device for analyzing and recognizing emotions from user input.

[0396] A "means for generating a response" is a process or device for generating optimal answers or advice based on input data and emotional information.

[0397] "Delivery staff" are workers who deliver food and other products to customers.

[0398] "Stress" is a state of mental or physical tension or strain.

[0399] A "prompt" is the original text or question that is input into a generative AI model.

[0400] This invention provides a system that automatically collects data such as reports, feedback, and problem-solving proposals submitted by employees and extracts highly relevant information.Furthermore, we provide an example of an application for delivery staff equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on them.

[0401] Server-side implementation

[0402] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. For example, it has a function that automatically collects reports from all staff after the end of each day's work. The collected data is then cleansed on the server for filtering purposes. Noisy data and irrelevant information are removed, and only specific problem-solving methods and success stories are retained. The cleansed data is stored in a database and tagged. This tagging improves search efficiency. The stored data is also used to retrain the generative AI model at regular intervals, so that the latest information is reflected.

[0403] Terminal side embodiment

[0404] Users interact with the system through a smartphone application. The app provides a chat box-style interface where users can input issues or questions in natural language. For example, a user might input a question such as, "I'm feeling stressed while delivering. Please help me." The app is equipped with an emotion engine that recognizes the user's emotions from the input. For example, if a user inputs, "I'm feeling very tired from recent deliveries," the emotion engine will detect stress or fatigue.

[0405] Server Response Generation Embodiments

[0406] The server analyzes the user's input and emotional data and searches for related information in a database. For example, it considers data related to "stress management for delivery" and the user's emotional state. Based on the search results, the server uses a generative AI model to generate the optimal solution. This generation process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. The generated answer is sent to the user via their device. For example, it provides specific examples such as "Try the following three steps to manage stress..." and also includes advice such as "We also recommend taking deep breaths and short breaks."

[0407] Hardware and Software

[0408] This system uses an advanced data processing system as the server and a relational database management system (RDBMS) as the database. Python and OpenAI AI technologies are used for the emotion recognition and generation AI model. Specifically, TextBlob is used for emotion analysis, and the OpenAI API is used for AI answer generation. The user interface is a smartphone application, and React Native is used as the front-end technology for its construction.

[0409] Prompt Sentence Examples

[0410] User Request: "What do you do when you're tired?"

[0411] Prompt the generative AI model: "How do you manage stress when you're tired?"

[0412] In this way, the system of the present invention increases the usefulness of collected data and provides optimal solutions based on user sentiment, thereby improving operational efficiency and improving the user experience.

[0413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0414] Step 1:

[0415] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. The input is the reports and feedback from the delivery staff, which the server collects. The output is a set of collected data, which is passed to the next step.

[0416] Step 2:

[0417] The server filters unnecessary information from the collected data. The inputs are reports and feedback, and the output is relevant data after removing noise data. Specifically, a data cleansing algorithm is applied to remove noise and irrelevant information.

[0418] Step 3:

[0419] The server stores the filtered data in a database and tags it. The input is the filtered data, and the output is tagged database records. Specifically, tags such as "delivery problem" and "customer satisfaction" are automatically assigned to each piece of data.

[0420] Step 4:

[0421] The server periodically retrains the generative AI model using the stored data. The input is the past data stored in the database, and the output is a generative AI model that reflects the latest data. Specifically, the AI ​​training algorithm updates the model using a new data set.

[0422] Step 5:

[0423] The user inputs a problem or question in natural language through the device. The input is a question from the user in natural language, and the output is the content of the question. Specifically, the user inputs a question into the chat box on their smartphone.

[0424] Step 6:

[0425] The terminal sends the user's input to the server and requests an answer according to the question. The input is the user's question data, and the output is the request data sent to the server. Specifically, the chat box interface sends the user's input to the server in real time.

[0426] Step 7:

[0427] The server analyzes the user's input and emotion data and searches for related information in a database. The input is the user's question data and the emotion analysis results, and the output is a collection of related information. Specifically, the text analysis algorithm generates emotion data, and the database query extracts related information.

[0428] Step 8:

[0429] The server uses a generative AI model to generate an optimal solution based on the search results. The input is a collection of related information and emotional data, and the output is the generated solution. Specifically, the generative AI model combines past success stories and expert advice to generate an answer.

[0430] Step 9:

[0431] The server sends the generated answer to the terminal, which then displays the answer to the user. The input is the generated solution, and the output is the answer displayed on the user's smartphone. Specifically, the server sends the generated answer to the terminal, which then displays it to the user.

[0432] Through the above steps, the system of the present invention can efficiently process reports and feedback from delivery staff and provide optimal solutions based on their emotions.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] [Second embodiment]

[0437] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0438] 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.

[0439] 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).

[0440] 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.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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."

[0449] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Below, we will explain the program processing of this system in natural language and provide detailed examples.

[0450] Server-side implementation

[0451] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0452] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, leaving only specific problem-solving methods and success stories.

[0453] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI with a new dataset every six months.

[0454] Terminal side embodiment

[0455] Users interact with the system through a terminal, which provides a chat box-style interface where users can enter issues or questions in natural language. For example, a user might enter a question like, "How can I develop a new marketing strategy?"

[0456] The terminal sends the user's input directly to the server, requesting an answer to the question. This data transmission is done in real time.

[0457] Server Response Generation Embodiments

[0458] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" from the database.

[0459] Based on the search results, the server uses generative AI to generate the optimal solution. During this generation process, it generates an answer that includes specific implementation steps and points to note, based on past success stories and expert advice. The generated answer is then sent back to the user via their device. For example, it might be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[0460] User usage pattern

[0461] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server and displays it in real time. The user checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0462] In this way, the system of the present invention provides support for quickly and effectively resolving the challenges employees face every day, improving business efficiency and increasing profits.

[0463] The processing flow will be explained below.

[0464] Step 1:

[0465] Data collection

[0466] The server automatically collects reports, feedback, and problem-solving proposals from each employee on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0467] Step 2:

[0468] Data Cleansing

[0469] The server performs a cleansing process to remove noise and irrelevant information from the collected data, so that only specific problem-solving methods and success stories are retained.

[0470] Step 3:

[0471] Database storage and tagging

[0472] The server stores the cleansed data in a database and tags it, adding appropriate tags such as "project management" or "marketing strategy" to make searches more efficient.

[0473] Step 4:

[0474] Retraining the Model

[0475] The server periodically retrains the generative AI model using the stored data, for example, every six months using a new dataset.

[0476] Step 5:

[0477] Accepting user input

[0478] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[0479] Step 6:

[0480] Sending User Input

[0481] The device sends the user's input directly to the server and requests an answer to the question, a process that occurs in real time.

[0482] Step 7:

[0483] Database search

[0484] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" in the database.

[0485] Step 8:

[0486] Response Generation

[0487] Based on the search results, the server uses generative AI to generate the optimal solution, including specific implementation steps and points to note based on past success stories and expert advice.

[0488] Step 9:

[0489] Sending a response to the user

[0490] The server then sends the generated answer to the device, for example, in the form of "Please see the specific example below for how to create a marketing strategy..."

[0491] Step 10:

[0492] Checking and using responses

[0493] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0494] This process flow allows users to receive assistance in quickly and effectively resolving their issues.

[0495] Example 1

[0496] 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."

[0497] In today's corporate environment, employees submit huge volumes of reports, feedback, and problem-solving proposals. Therefore, there is a need to quickly extract useful data from this information and analyze and utilize it appropriately. However, traditional methods require manual data filtering and analysis, which takes a great deal of time and effort. To solve this problem, an efficient and automated data processing system is needed.

[0498] 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.

[0499] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering and cleansing unnecessary information from the collected data, means for storing the filtered and cleansed data in a database and tagging it appropriately, means for periodically retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for sending the user's input to the server and requesting answers corresponding to the questions, means for searching for related information in the database and generating optimal solutions based on the extracted information, and means for sending the generated answers to the user. This makes it possible to efficiently and automatically extract useful data from a vast amount of information and quickly provide support for problem solving.

[0500] "Means for collecting reports, feedback, and problem-solving proposals submitted by employees" refers to software and hardware means for automatically collecting various reports, feedback, and problem-solving proposal documents submitted by employees from internal systems.

[0501] "Means for filtering and cleansing unnecessary information from collected data" means algorithmic and software means for automatically detecting and removing noise and irrelevant information in collected data.

[0502] "Means for storing the filtered and cleansed data in a database and tagging it appropriately" refers to hardware and software means for storing the cleansed data in a database and tagging it with appropriate tags, such as "project management" and "marketing strategy," to further improve search efficiency.

[0503] "Means for periodically retraining a generative AI model using stored data" refers to providing software and computing resources for adjusting and optimizing the parameters of a generative AI model and retraining it using updated data stored in a database at regular intervals.

[0504] "Means for providing an interface that allows users to input tasks or questions in natural language" refers to software means for providing an interface that allows users to input tasks or questions in natural language, for example, a chat box-style UI.

[0505] "Means for sending user input to a server and requesting an answer corresponding to the question" refers to communication means and control software for sending natural language data entered by a user to a server in real time and requesting that the server generate an appropriate answer.

[0506] "Means for searching for relevant information in a database and generating optimal solutions based on the extracted information" refers to algorithms and software means by which a server searches for relevant information in a database and generates optimal solutions using a generative AI model based on the search results.

[0507] The "means for transmitting the generated answer to the user" refers to the communication means and software means for transmitting the answer generated by the server to the user's terminal in real time.

[0508] MODE FOR CARRYING OUT THE INVENTION

[0509] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information.

[0510] Server-side implementation

[0511] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, the server has the function of automatically extracting project reports at the end of each month. The hardware used includes the company's database server and network interface cards. The software used includes data collection scripts, cleansing algorithms, and tagging algorithms.

[0512] The collected data undergoes a cleansing process on the server for filtering. During this process, noise data and irrelevant information are automatically removed, leaving only specific problem-solving methods and success stories. The cleansed data is stored in a database and is assigned appropriate tags, such as "project management" or "marketing strategy." Tagging makes future searches more efficient. The stored data is used to retrain the generative AI model at regular intervals. For example, the server retrains the generative AI using a new dataset every six months.

[0513] Terminal side embodiment

[0514] Users interact with the system through terminals. The terminals provide a chat box-style interface where users can input issues or questions in natural language. For example, a user can input the question, "How do I develop a new marketing strategy?" The terminals transmit this input in real time to the server and request an answer to the question. The terminals include interface software and a network communication module.

[0515] Server Response Generation Embodiments

[0516] The server analyzes the user's input and searches for related information in the database. For example, it searches the database for data related to "marketing strategy." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, it refers to past success stories and expert advice to generate an answer that includes specific implementation steps and points to note. The generated answer is then sent back to the user via the device. For example, the answer may be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[0517] User usage pattern

[0518] The user enters a question in the chat box and clicks the send button. The terminal then receives a response from the server and displays it in real time. The user then checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal." In this way, the system of the present invention helps employees quickly and effectively solve the challenges they face every day, improving business efficiency and increasing revenue.

[0519] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0520] Program processing steps

[0521] Step 1: Data collection

[0522] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule.

[0523] Input: Reports, feedback, and problem-solving proposals stored in our internal systems.

[0524] What it does: The server runs the data collection script at the end of each month to get the latest reports and feedback.

[0525] Output: A list of the raw data collected.

[0526] Step 2: Data cleansing

[0527] The server cleanses the collected data and filters out unnecessary information.

[0528] Input: A list of the collected raw data.

[0529] What it does: The server runs a cleansing algorithm to remove noise data and irrelevant information.

[0530] Output: filtered clean data.

[0531] Step 3: Tag and store your data

[0532] The server stores the cleansed data in a database and tags it appropriately.

[0533] Input: Clean, cleansed data.

[0534] What it does: The server uses a tagging algorithm to assign tags like "project management" or "marketing strategy" and store them in a database.

[0535] Output: A database containing the tagged data.

[0536] Step 4: Periodically retrain the generative AI model

[0537] The server periodically retrains the generative AI model using the data stored in the database.

[0538] Input: The most recent dataset stored in the database.

[0539] How it works: Every six months, the server uses collected data to run a retraining algorithm for the generative AI model, improving the model's accuracy.

[0540] Output: A generative AI model that has been retrained and has improved performance.

[0541] Step 5: Accepting User Input

[0542] Users enter their assignments and questions into the chat box on their terminal.

[0543] Input: Issues or questions typed in natural language.

[0544] What happens: A user types "How can we develop a new marketing strategy?" into the chat box and clicks the send button.

[0545] Output: User input is sent from the terminal to the server.

[0546] Step 6: Sending User Input to the Server

[0547] The terminal sends the user's input as is to the server and requests a response.

[0548] Input: The assignment or question entered by the user.

[0549] Specific operation: The terminal sends input data to the server via the network.

[0550] Output: The user's input data received by the server.

[0551] Step 7: Parsing the Question

[0552] The server analyzes the user's input.

[0553] Input: Received user input data.

[0554] What it does: The server uses natural language processing (NLP) algorithms to parse the question and extract key keywords and intent.

[0555] Output: Extracted keywords and user intent.

[0556] Step 8: Search the database

[0557] The server searches for relevant information in a database based on the analysis results.

[0558] Input: Parsed keywords and user intent.

[0559] What happens: The server runs a database search algorithm to find relevant reports and success stories.

[0560] Output: A list of relevant information.

[0561] Step 9: Generate a solution

[0562] The server uses a generative AI model to generate the optimal solution.

[0563] Input: A list of search results and related information.

[0564] Specific operation: The server applies the generative AI model and generates an optimal solution based on the search results, including specific implementation steps and points to note.

[0565] Output: The generated solution.

[0566] Step 10: Submit your solution

[0567] The server transmits the generated solution to the terminal.

[0568] Input: The generated solution.

[0569] Specific operation: The server sends the solution to the terminal via the network.

[0570] Output: The solution displayed on the terminal.

[0571] Step 11: Check for a solution

[0572] The user checks the solution displayed on the terminal.

[0573] Input: The solution displayed in the terminal.

[0574] Specific Action: The user reviews the displayed solution and uses it as a reference for next steps.

[0575] Output: The solution confirmed by the user.

[0576] (Application example 1)

[0577] 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."

[0578] The reports, feedback, and problem-solving proposals submitted by factory workers are diverse and require time and effort. Effectively collecting and analyzing this information and quickly extracting relevant information is difficult. Furthermore, an efficient method is needed to enable real-time problem solving within factories.

[0579] 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.

[0580] In this invention, the server includes: means for collecting reports, feedback, and problem-solving proposals submitted by employees; means for filtering unnecessary information from the collected data; means for storing the filtered data in a database and tagging it; means for retraining the generative AI model using the stored data; means for providing an interface for users to input issues and questions in natural language; means for transmitting the user's input to the server and requesting answers corresponding to the questions; means for searching related information in the database and generating optimal solutions; means for providing problem-solving proposals based on the collected information, past success stories, and expert advice; and means for transmitting the generated answers to the user. This automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and enables efficient problem solving.

[0581] A "report" is a document that employees submit, detailing their daily work, progress, and issues.

[0582] "Feedback" refers to an employee expressing their opinions or thoughts about work or projects, or a document that contains the content of those opinions or thoughts.

[0583] A "problem-solving proposal" is a proposal that lists business problems and issues and provides specific solutions to them.

[0584] "Filtering" is the process of removing unnecessary information from collected data and selecting only highly relevant information.

[0585] "Tagging" is the process of assigning specific categories or keywords to data to make it easier to search and classify.

[0586] A "generative AI model" is an artificial intelligence model that uses machine learning based on large amounts of data to generate new information and solutions.

[0587] An "interface" refers to an operation screen or input device that allows a user to interact with a system.

[0588] A "database" is an electronic storage device for systematically organizing and storing data.

[0589] "Searching" is the act of finding specific information from data in a database.

[0590] A "solution" is a feasible response or means to a specific problem or issue.

[0591] A "success story" is a specific example of a past task or project that achieved a desired result.

[0592] "Expert advice" is advice or guidance from a professional with extensive knowledge and experience in a particular field.

[0593] The present invention is a system that efficiently collects reports, feedback, and problem-solving proposals from workers in a factory and provides advice in real time based on the collected information. Specific embodiments for realizing this system are described in detail below.

[0594] System Overview

[0595] The system of the present invention mainly consists of three main components: a server, a terminal (including a robot), and a user.

[0596] server

[0597] The server is responsible for the following:

[0598] 1. Data Collection and Storage

[0599] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker, and periodically transmits the collected data to the server.

[0600] 2. Data Cleansing and Filtering

[0601] Use the "DataCleanser" module to remove noise data and unnecessary information and extract only the most relevant information.

[0602] 3. Tagging and saving

[0603] The "DatabaseManager" module is used to assign appropriate tags to the cleansed data and store it in the database, such as "equipment maintenance" or "production line improvement."

[0604] 4. Retraining generative AI models

[0605] The stored data is used to periodically retrain the generative AI model, allowing it to generate up-to-date solutions based on new data.

[0606] Terminal (robot)

[0607] 1. Providing a user interface

[0608] The terminal provides an interface where users can input issues and questions in natural language. For example, a robot equipped with a tablet approaches a worker and accepts their reports and questions.

[0609] 2. Data Transmission

[0610] Collected data and user inputs are sent to a server in real time.

[0611] User

[0612] 1. Enter and submit your question

[0613] Users input issues or questions in natural language through the terminal interface and send them to the server. For example, they can input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[0614] 2. Receiving and Confirming Responses

[0615] The response from the server is provided to the user through the terminal, where the user can review and implement the displayed solution.

[0616] Processing flow

[0617] The server analyzes the user's input and searches for relevant information in the database. For example, it searches the database for data related to "equipment maintenance." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, an answer is generated that includes specific steps and points to note based on past success stories and expert advice. The generated answer is then sent to the user via their device.

[0618] Examples and prompts

[0619] As a concrete example, if a factory worker wants to know "machine maintenance procedures on line 2," he or she can input the question "Please tell me about the machine maintenance procedures on line 2" into the robot. In response to this question, the server will provide a solution including specific procedures based on past maintenance procedures and success stories.

[0620] Examples of prompt statements

[0621] Please tell me about the machine maintenance procedures for Line 2. Today's report indicates that an abnormality has been observed on Line 2.

[0622] In this way, the system of the present invention automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and can support efficient problem solving in real time.

[0623] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0624] Step 1:

[0625] Data collection

[0626] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker from the company's internal system. For example, a robot can collect reports at the end of each shift and send them to the server.

[0627] Input: Reports, feedback, and problem-solving proposals submitted by workers

[0628] Output: The collected raw dataset

[0629] Step 2:

[0630] Data Cleansing and Filtering

[0631] The server cleanses the collected data using the DataCleanser module, removing noise and unnecessary information, shaping the data and correcting outliers, and extracting only the most relevant data.

[0632] Input: Collected raw dataset

[0633] Output: A cleansed dataset

[0634] Step 3:

[0635] Tagging and database storage

[0636] The server uses the DatabaseManager module to tag the cleansed data appropriately, for example, with tags like "equipment maintenance" or "production line improvement," and then stores the tagged data in a database.

[0637] Input: Cleansed dataset

[0638] Output: A tagged dataset and data stored in a database

[0639] Step 4:

[0640] Retraining generative AI models

[0641] The server periodically retrains the "generative AI model" using the stored data, updating the machine learning algorithm so that it can generate up-to-date solutions based on new data.

[0642] Input: A dataset stored in a database

[0643] Output: Retrained generative AI model

[0644] Step 5:

[0645] Enter and submit a user question

[0646] Users input issues or questions in natural language through the terminal (robot) interface. This input data is sent to the server in real time. For example, a user might input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[0647] Input: Questions and issues entered in natural language

[0648] Output: The input data sent to the server

[0649] Step 6:

[0650] Search for related information in a database

[0651] The server receives the input data sent by the user and searches for related information in the database. It uses the "DatabaseManager" module to start searching for information based on related tags.

[0652] Input: User questions or challenges submitted

[0653] Output: Related information search results data

[0654] Step 7:

[0655] Solution Generation

[0656] The server uses a generative AI model based on the search results to generate an optimal solution, including specific steps and points to note, by referring to past success stories and expert advice.

[0657] Input: Search results for relevant information, and a retrained generative AI model

[0658] Output: Generated solution

[0659] Step 8:

[0660] Submitting and viewing answers

[0661] The server sends the generated solution to the user. The terminal (robot) displays the received solution to the user in real time. The user can check the solution and take the next step.

[0662] Input: Generated solution

[0663] Output: Solution displayed on the terminal

[0664] This allows for efficient collection of work reports within the factory, information cleansing and filtering, automatic generation of optimal solutions, and real-time problem resolution, all of which improves work efficiency and speeds up problem resolution.

[0665] 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.

[0666] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Additionally, the system incorporates an emotion engine that recognizes the user's emotions, enabling it to provide optimal answers based on the user's emotions. Below, the program processing of this system is explained in natural language and in detail with specific examples.

[0667] Server-side implementation

[0668] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0669] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, and retaining only specific problem-solving methods and success stories.

[0670] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI using a new dataset every six months to reflect the latest information.

[0671] Terminal side embodiment

[0672] Users interact with the system through a terminal. The terminal provides a chat box-style interface where users can input issues and questions in natural language. For example, a user might input a question such as, "How can I create a new marketing strategy?" The terminal is also equipped with an emotion engine that recognizes emotions from the user's input. For example, if a user inputs, "I'm stressed out about my latest project," the emotion engine will detect stress or anxiety.

[0673] The device sends the user's input and emotional data to the server and requests the best answer for the question, a process that occurs in real time.

[0674] Server Response Generation Embodiments

[0675] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[0676] Based on the search results, the server uses generative AI to generate the optimal solution. This process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. For example, if the user is feeling stressed, the server will also include advice on relaxation methods and stress management.

[0677] The generated answer is then sent back to the user via the device. For example, it might say, "Please see the specific example below for how to create a marketing strategy..." and also include advice such as, "We recommend taking short breaks to manage stress as you go along."

[0678] User usage pattern

[0679] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server, which is displayed in real time. The user then checks the provided solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds by presenting "Three steps for a successful client proposal," while also including advice tailored to the user's feelings.

[0680] In this way, the system of the present invention helps to solve problems quickly and effectively while taking into consideration the user's feelings, thereby improving business efficiency and increasing profits.

[0681] The processing flow will be explained below.

[0682] Step 1:

[0683] Data collection

[0684] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of extracting project reports at the end of each month.

[0685] Step 2:

[0686] Data Cleansing

[0687] The server performs a cleansing process to remove noise and irrelevant information from the collected data. Specifically, it filters out personal opinions and casual conversations, leaving only specific problem-solving methods and success stories.

[0688] Step 3:

[0689] Database storage and tagging

[0690] The server stores the cleansed data in a database and appropriately tags it, for example, with tags like "project management" or "marketing strategy," making it easier to search.

[0691] Step 4:

[0692] Retraining the Model

[0693] The server retrains the generative AI model using new data, allowing it to provide highly accurate solutions based on the most recent data, for example, every six months.

[0694] Step 5:

[0695] Accepting user input

[0696] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[0697] Step 6:

[0698] emotion recognition

[0699] The device's built-in emotion engine recognizes emotions from user input. For example, if a user inputs "I'm feeling stressed about a recent project," the emotion engine will detect stress and anxiety.

[0700] Step 7:

[0701] Sending user input and emotion data

[0702] The device sends the user's input and emotional data to the server and requests an answer based on the question, a process that occurs in real time.

[0703] Step 8:

[0704] Database search

[0705] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[0706] Step 9:

[0707] Response Generation

[0708] The server generates optimal solutions based on the search results. It provides solutions that take into consideration the user's feelings, rather than just standard answers. For example, it suggests specific implementation steps and points to note for "marketing strategies" based on past success stories and expert advice.

[0709] Step 10:

[0710] Sending a response to the user

[0711] The server sends the generated answer to the terminal, for example, "Below are some specific examples of how to create a marketing strategy and relaxation methods for stress management."

[0712] Step 11:

[0713] Checking and using responses

[0714] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0715] Through this series of processing flows, the present invention supports the user in quickly and effectively resolving problems while taking into consideration the user's feelings.

[0716] Example 2

[0717] 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."

[0718] Conventional information collection and management systems struggled to efficiently collect reports, feedback, and problem-solving proposals submitted by employees and filter out unnecessary information. Furthermore, there were no systems that provided optimal answers that took user sentiment into account. This made information management cumbersome, making it difficult to provide appropriate support to users and preventing improvements in work efficiency. Furthermore, data management for appropriately retraining generative AI models was also cumbersome.

[0719] 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.

[0720] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for recognizing emotions from the user's input, means for searching for related information in the database and generating an optimal solution, and means for transmitting the generated answer to the user. This not only enables efficient filtering and appropriate management of information from employees, but also enables prompt provision of optimal answers that take user emotions into consideration, thereby improving business efficiency and the quality of user support.

[0721] A "report" is a document in which an employee describes work results, progress, problems, suggestions, etc.

[0722] "Feedback" is a document that includes evaluations, opinions, and areas for improvement regarding work.

[0723] A "problem-solving proposal" is a document that describes an appropriate solution or improvement plan for a specific problem or issue.

[0724] "Collection means" refers to the methods and functions for regularly collecting reports, feedback, and problem-solving proposals submitted by employees.

[0725] "Filtering means" refers to methods or functions for removing unnecessary information from collected data and selecting only highly relevant information.

[0726] The "storage means" refers to a method or function for storing the filtered data in a database and managing it so that it can be searched efficiently later.

[0727] "Tagging means" refers to methods or functions that assign keywords such as "project management" or "marketing strategy" to stored data to make it easier to search and identify.

[0728] "Retraining means" refers to the methods or functions that use stored data to periodically update a generative AI model to reflect new information.

[0729] "Means for providing an interface" refers to the method or function of providing an interactive screen or mechanism that allows users to input tasks or questions in natural language.

[0730] "Means for sending and requesting" refers to the methods and functions for sending user input to the server and requesting the appropriate response.

[0731] "Means for recognizing emotions" refers to a method or function for analyzing emotions from user input and identifying specific emotions.

[0732] "Search and generation tools" are methods and functions for locating relevant information in a database and generating optimal solutions or answers.

[0733] "Transmission means" refers to the method or function for sending and presenting the generated answer to the user.

[0734] This invention is a system that efficiently collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and provides optimal answers that take into account the user's feelings. The system is composed of three entities: a server, a terminal, and a user.

[0735] Server processing

[0736] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The specific implementation uses Python scripts to retrieve information using SQL queries. Cron jobs are used as the task scheduler.

[0737] Next, the collected data undergoes a cleansing process. At this stage, Apache Spark and Pandas are used to remove noisy data and irrelevant information, leaving only the most relevant information. Regular expressions are used to extract the necessary keywords and phrases. The filtered data is then stored in a database using Elasticsearch. Here, tags such as "project management" and "marketing strategy" are added. NLP (natural language processing) technology is used as the tagging algorithm.

[0738] Furthermore, the server periodically (e.g., every six months) retrains the generative AI model using the stored data, using TensorFlow or PyTorch to train the model and updating it with new datasets.

[0739] Processing by the terminal

[0740] The terminal provides a chatbox-style interface where users can input issues or questions in natural language. The interface is built using HTML and JavaScript, and sends user input to a server in real time. It uses NLP models such as BERT and RoBERTa as an emotion engine to analyze emotions from the user's text.

[0741] For example, if a user types "How can we develop a new marketing strategy?", the device sends this input and parsed sentiment data to the server via an HTTP request. The data is packaged in JSON format and deserialized after it is received by the server.

[0742] Server response generation

[0743] The server analyzes the user's input and emotional data and uses Elasticsearch to search for related information in a database. For example, it searches for data related to "marketing strategies" and analyzes the data while taking the user's emotional state into account. Based on the analysis results, it uses a generative AI model (e.g., GPT-3) to generate a natural language response.

[0744] The generated answers are designed to provide the best possible solution for the user, including specific steps and precautions, and if the user is feeling stressed, advice on relaxation and stress management is also included.

[0745] For example, a prompt might look like this:

[0746] 1. Example of user input:

[0747] "I'm feeling stressed about a recent project. What should I do?"

[0748] 2. The corresponding prompt:

[0749] "An employee wrote, 'I'm stressed out over a recent project.' Please provide specific stress management strategies. Also, include ways to reduce project management stress."

[0750] Terminal display of responses

[0751] Finally, the device displays the answers received from the server to the user in real time, such as "Please see the specific example below for how to create a marketing strategy..." and also provides advice such as "We recommend taking short breaks to manage stress as you go along."

[0752] This allows the user to check the provided solutions and use them as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server will present "three steps for a successful client proposal" and also include advice based on the user's feelings.

[0753] In this way, the system of the present invention solves problems quickly and effectively while taking into account the user's feelings, thereby improving business efficiency and increasing profits.

[0754] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0755] Step 1:

[0756] Data collection

[0757] The server collects employee reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The input is the reports, feedback, and problem-solving proposals submitted by employees, and the output is the collected data. The specific collection process involves executing SQL queries using a Python script to obtain the information. A Cron job is used for scheduling.

[0758] Step 2:

[0759] Data Cleansing

[0760] The server cleanses the collected data, removing noise and irrelevant information. This process uses Apache Spark and Pandas to analyze the data and filter out noise and unnecessary information. This scrutinizes the input data and produces filtered data as output. Specifically, it uses regular expressions to extract necessary keywords and phrases.

[0761] Step 3:

[0762] Data storage and tagging

[0763] The server stores the cleansed data in a database and assigns appropriate tags. The input is the cleansed data, and the output is tagged database entries. Specifically, Elasticsearch is used to assign tags such as "project management" and "marketing strategy" to the data. NLP technology is used as the tagging algorithm.

[0764] Step 4:

[0765] Retraining generative AI models

[0766] The server retrains the generative AI model using the stored data every specific period (e.g., every six months). The input is the stored dataset, and the output is the retrained generative AI model. Specifically, TensorFlow or PyTorch is used to retrain the AI ​​model using batch processing on the dataset.

[0767] Step 5:

[0768] Accepting user input

[0769] The terminal provides a chat box-style interface where users can input tasks and questions in natural language. The input is the natural language question or task from the user, and the output is the data that will be sent to the server. Specifically, a front end created with HTML and JavaScript provides the user interface and sends the input to the server in real time.

[0770] Step 6:

[0771] emotion recognition

[0772] The device recognizes emotions from the user's input. The input is the user's text data, and the output is analyzed emotion data. Specifically, it uses NLP models such as BERT and RoBERTa to analyze emotions from the input text.

[0773] Step 7:

[0774] Input and sending emotional data

[0775] The device sends the user's input and emotion data to the server. The input is the user's text data and emotion data, and the output is the data sent to the server. Specifically, the data is sent to the server using an HTTP request and packaged in JSON format.

[0776] Step 8:

[0777] Data analysis and response generation

[0778] The server analyzes the user's input and emotion data and searches for relevant information in the database. The input is the user's question and emotion data, and the output is the generated answer. Specifically, it uses Elasticsearch to search for relevant data and uses a generative AI model (e.g., GPT) to generate the optimal solution.

[0779] Step 9:

[0780] Submitting and viewing generated answers

[0781] The server sends the generated answer to the terminal, which displays it to the user. The input is the answer data from the server, and the output is the display data that the user can visually confirm. The specific operation is to send an HTTP response and display the answer on the front end.

[0782] Specific examples

[0783] In response to a user question such as, "I'm feeling stressed about a recent project. What should I do?", the server receives the input, "I'm feeling stressed about a recent project," and analyzes the emotion as stress. It searches for appropriate stress management methods from a related database and generates "specific stress management methods" using a generative AI model. For example, it presents guidelines such as "Three steps for a successful client proposal," while also including advice such as, "We recommend taking a short break for relaxation and stress management."

[0784] In this way, the system helps users solve problems quickly and effectively while taking their emotions into consideration, improving business efficiency and increasing profits.

[0785] (Application example 2)

[0786] 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."

[0787] Conventional data collection systems lack the ability to filter unnecessary information from collected reports, feedback, and problem-solving proposals, making it difficult to efficiently extract relevant information. Furthermore, there is no system that can recognize user emotions and generate appropriate responses based on them, which hinders the user experience.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface through which a user inputs issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for searching related information in the database and generating an optimal solution, means for transmitting the generated answer to the user, and means for recognizing the user's emotions and generating an optimal response based on the emotions. This allows for providing an optimal solution that takes emotions into consideration, improving the user experience and business efficiency.

[0789] An "employee" is a staff member employed by a company or organization to perform work.

[0790] A "collection means" is a process or device for collecting specified data.

[0791] A "filtering means" is a process or device used to remove unwanted information from collected data.

[0792] A "database" is a system for efficiently storing, searching, and managing data.

[0793] A "tagging means" is a process or device that assigns a specific tag or label to stored data.

[0794] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information or answers from given data.

[0795] An "interface" is the input and output means by which a user interacts with a system.

[0796] A "server" is a computer system that processes data and provides services over a network.

[0797] A "means for recognizing emotions" is a process or device for analyzing and recognizing emotions from user input.

[0798] A "means for generating a response" is a process or device for generating optimal answers or advice based on input data and emotional information.

[0799] "Delivery staff" are workers who deliver food and other products to customers.

[0800] "Stress" is a state of mental or physical tension or strain.

[0801] A "prompt" is the original text or question that is input into a generative AI model.

[0802] This invention provides a system that automatically collects data such as reports, feedback, and problem-solving proposals submitted by employees and extracts highly relevant information.Furthermore, we provide an example of an application for delivery staff equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on them.

[0803] Server-side implementation

[0804] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. For example, it has a function that automatically collects reports from all staff after the end of each day's work. The collected data is then cleansed on the server for filtering purposes. Noisy data and irrelevant information are removed, and only specific problem-solving methods and success stories are retained. The cleansed data is stored in a database and tagged. This tagging improves search efficiency. The stored data is also used to retrain the generative AI model at regular intervals, so that the latest information is reflected.

[0805] Terminal side embodiment

[0806] Users interact with the system through a smartphone application. The app provides a chat box-style interface where users can input issues or questions in natural language. For example, a user might input a question such as, "I'm feeling stressed while delivering. Please help me." The app is equipped with an emotion engine that recognizes the user's emotions from the input. For example, if a user inputs, "I'm feeling very tired from recent deliveries," the emotion engine will detect stress or fatigue.

[0807] Server Response Generation Embodiments

[0808] The server analyzes the user's input and emotional data and searches for related information in a database. For example, it considers data related to "stress management for delivery" and the user's emotional state. Based on the search results, the server uses a generative AI model to generate the optimal solution. This generation process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. The generated answer is sent to the user via their device. For example, it provides specific examples such as "Try the following three steps to manage stress..." and also includes advice such as "We also recommend taking deep breaths and short breaks."

[0809] Hardware and Software

[0810] This system uses an advanced data processing system as the server and a relational database management system (RDBMS) as the database. Python and OpenAI AI technologies are used for the emotion recognition and generation AI model. Specifically, TextBlob is used for emotion analysis, and the OpenAI API is used for AI answer generation. The user interface is a smartphone application, and React Native is used as the front-end technology for its construction.

[0811] Prompt Sentence Examples

[0812] User Request: "What do you do when you're tired?"

[0813] Prompt the generative AI model: "How do you manage stress when you're tired?"

[0814] In this way, the system of the present invention increases the usefulness of collected data and provides optimal solutions based on user sentiment, thereby improving operational efficiency and improving the user experience.

[0815] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0816] Step 1:

[0817] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. The input is the reports and feedback from the delivery staff, which the server collects. The output is a set of collected data, which is passed to the next step.

[0818] Step 2:

[0819] The server filters unnecessary information from the collected data. The inputs are reports and feedback, and the output is relevant data after removing noise data. Specifically, a data cleansing algorithm is applied to remove noise and irrelevant information.

[0820] Step 3:

[0821] The server stores the filtered data in a database and tags it. The input is the filtered data, and the output is tagged database records. Specifically, tags such as "delivery problem" and "customer satisfaction" are automatically assigned to each piece of data.

[0822] Step 4:

[0823] The server periodically retrains the generative AI model using the stored data. The input is the past data stored in the database, and the output is a generative AI model that reflects the latest data. Specifically, the AI ​​training algorithm updates the model using a new data set.

[0824] Step 5:

[0825] The user inputs a problem or question in natural language through the device. The input is a question from the user in natural language, and the output is the content of the question. Specifically, the user inputs a question into the chat box on their smartphone.

[0826] Step 6:

[0827] The terminal sends the user's input to the server and requests an answer according to the question. The input is the user's question data, and the output is the request data sent to the server. Specifically, the chat box interface sends the user's input to the server in real time.

[0828] Step 7:

[0829] The server analyzes the user's input and emotion data and searches for related information in a database. The input is the user's question data and the emotion analysis results, and the output is a collection of related information. Specifically, the text analysis algorithm generates emotion data, and the database query extracts related information.

[0830] Step 8:

[0831] The server uses a generative AI model to generate an optimal solution based on the search results. The input is a collection of related information and emotional data, and the output is the generated solution. Specifically, the generative AI model combines past success stories and expert advice to generate an answer.

[0832] Step 9:

[0833] The server sends the generated answer to the terminal, which then displays the answer to the user. The input is the generated solution, and the output is the answer displayed on the user's smartphone. Specifically, the server sends the generated answer to the terminal, which then displays it to the user.

[0834] Through the above steps, the system of the present invention can efficiently process reports and feedback from delivery staff and provide optimal solutions based on their emotions.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] [Third embodiment]

[0839] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0840] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0841] 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).

[0842] 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.

[0843] 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.

[0844] 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).

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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."

[0851] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Below, we will explain the program processing of this system in natural language and provide detailed examples.

[0852] Server-side implementation

[0853] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0854] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, leaving only specific problem-solving methods and success stories.

[0855] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI with a new dataset every six months.

[0856] Terminal side embodiment

[0857] Users interact with the system through a terminal, which provides a chat box-style interface where users can enter issues or questions in natural language. For example, a user might enter a question like, "How can I develop a new marketing strategy?"

[0858] The terminal sends the user's input directly to the server, requesting an answer to the question. This data transmission is done in real time.

[0859] Server Response Generation Embodiments

[0860] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" from the database.

[0861] Based on the search results, the server uses generative AI to generate the optimal solution. During this generation process, it generates an answer that includes specific implementation steps and points to note, based on past success stories and expert advice. The generated answer is then sent back to the user via their device. For example, it might be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[0862] User usage pattern

[0863] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server and displays it in real time. The user checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0864] In this way, the system of the present invention provides support for quickly and effectively resolving the challenges employees face every day, improving business efficiency and increasing profits.

[0865] The processing flow will be explained below.

[0866] Step 1:

[0867] Data collection

[0868] The server automatically collects reports, feedback, and problem-solving proposals from each employee on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[0869] Step 2:

[0870] Data Cleansing

[0871] The server performs a cleansing process to remove noise and irrelevant information from the collected data, so that only specific problem-solving methods and success stories are retained.

[0872] Step 3:

[0873] Database storage and tagging

[0874] The server stores the cleansed data in a database and tags it, adding appropriate tags such as "project management" or "marketing strategy" to make searches more efficient.

[0875] Step 4:

[0876] Retraining the Model

[0877] The server periodically retrains the generative AI model using the stored data, for example, every six months using a new dataset.

[0878] Step 5:

[0879] Accepting user input

[0880] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[0881] Step 6:

[0882] Sending User Input

[0883] The device sends the user's input directly to the server and requests an answer to the question, a process that occurs in real time.

[0884] Step 7:

[0885] Database search

[0886] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" in the database.

[0887] Step 8:

[0888] Response Generation

[0889] Based on the search results, the server uses generative AI to generate the optimal solution, including specific implementation steps and points to note based on past success stories and expert advice.

[0890] Step 9:

[0891] Sending a response to the user

[0892] The server then sends the generated answer to the device, for example, in the form of "Please see the specific example below for how to create a marketing strategy..."

[0893] Step 10:

[0894] Checking and using responses

[0895] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[0896] This process flow allows users to receive assistance in quickly and effectively resolving their issues.

[0897] Example 1

[0898] 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."

[0899] In today's corporate environment, employees submit huge volumes of reports, feedback, and problem-solving proposals. Therefore, there is a need to quickly extract useful data from this information and analyze and utilize it appropriately. However, traditional methods require manual data filtering and analysis, which takes a great deal of time and effort. To solve this problem, an efficient and automated data processing system is needed.

[0900] 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.

[0901] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering and cleansing unnecessary information from the collected data, means for storing the filtered and cleansed data in a database and tagging it appropriately, means for periodically retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for sending the user's input to the server and requesting answers corresponding to the questions, means for searching for related information in the database and generating optimal solutions based on the extracted information, and means for sending the generated answers to the user. This makes it possible to efficiently and automatically extract useful data from a vast amount of information and quickly provide support for problem solving.

[0902] "Means for collecting reports, feedback, and problem-solving proposals submitted by employees" refers to software and hardware means for automatically collecting various reports, feedback, and problem-solving proposal documents submitted by employees from internal systems.

[0903] "Means for filtering and cleansing unnecessary information from collected data" means algorithmic and software means for automatically detecting and removing noise and irrelevant information in collected data.

[0904] "Means for storing the filtered and cleansed data in a database and tagging it appropriately" refers to hardware and software means for storing the cleansed data in a database and tagging it with appropriate tags, such as "project management" and "marketing strategy," to further improve search efficiency.

[0905] "Means for periodically retraining a generative AI model using stored data" refers to providing software and computing resources for adjusting and optimizing the parameters of a generative AI model and retraining it using updated data stored in a database at regular intervals.

[0906] "Means for providing an interface that allows users to input tasks or questions in natural language" refers to software means for providing an interface that allows users to input tasks or questions in natural language, for example, a chat box-style UI.

[0907] "Means for sending user input to a server and requesting an answer corresponding to the question" refers to communication means and control software for sending natural language data entered by a user to a server in real time and requesting that the server generate an appropriate answer.

[0908] "Means for searching for relevant information in a database and generating optimal solutions based on the extracted information" refers to algorithms and software means by which a server searches for relevant information in a database and generates optimal solutions using a generative AI model based on the search results.

[0909] The "means for transmitting the generated answer to the user" refers to the communication means and software means for transmitting the answer generated by the server to the user's terminal in real time.

[0910] MODE FOR CARRYING OUT THE INVENTION

[0911] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information.

[0912] Server-side implementation

[0913] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, the server has the function of automatically extracting project reports at the end of each month. The hardware used includes the company's database server and network interface cards. The software used includes data collection scripts, cleansing algorithms, and tagging algorithms.

[0914] The collected data undergoes a cleansing process on the server for filtering. During this process, noise data and irrelevant information are automatically removed, leaving only specific problem-solving methods and success stories. The cleansed data is stored in a database and is assigned appropriate tags, such as "project management" or "marketing strategy." Tagging makes future searches more efficient. The stored data is used to retrain the generative AI model at regular intervals. For example, the server retrains the generative AI using a new dataset every six months.

[0915] Terminal side embodiment

[0916] Users interact with the system through terminals. The terminals provide a chat box-style interface where users can input issues or questions in natural language. For example, a user can input the question, "How do I develop a new marketing strategy?" The terminals transmit this input in real time to the server and request an answer to the question. The terminals include interface software and a network communication module.

[0917] Server Response Generation Embodiments

[0918] The server analyzes the user's input and searches for related information in the database. For example, it searches the database for data related to "marketing strategy." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, it refers to past success stories and expert advice to generate an answer that includes specific implementation steps and points to note. The generated answer is then sent back to the user via the device. For example, the answer may be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[0919] User usage pattern

[0920] The user enters a question in the chat box and clicks the send button. The terminal then receives a response from the server and displays it in real time. The user then checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal." In this way, the system of the present invention helps employees quickly and effectively solve the challenges they face every day, improving business efficiency and increasing revenue.

[0921] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0922] Program processing steps

[0923] Step 1: Data collection

[0924] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule.

[0925] Input: Reports, feedback, and problem-solving proposals stored in our internal systems.

[0926] What it does: The server runs the data collection script at the end of each month to get the latest reports and feedback.

[0927] Output: A list of the raw data collected.

[0928] Step 2: Data cleansing

[0929] The server cleanses the collected data and filters out unnecessary information.

[0930] Input: A list of the collected raw data.

[0931] What it does: The server runs a cleansing algorithm to remove noise data and irrelevant information.

[0932] Output: filtered clean data.

[0933] Step 3: Tag and store your data

[0934] The server stores the cleansed data in a database and tags it appropriately.

[0935] Input: Clean, cleansed data.

[0936] What it does: The server uses a tagging algorithm to assign tags like "project management" or "marketing strategy" and store them in a database.

[0937] Output: A database containing the tagged data.

[0938] Step 4: Periodically retrain the generative AI model

[0939] The server periodically retrains the generative AI model using the data stored in the database.

[0940] Input: The most recent dataset stored in the database.

[0941] How it works: Every six months, the server uses collected data to run a retraining algorithm for the generative AI model, improving the model's accuracy.

[0942] Output: A generative AI model that has been retrained and has improved performance.

[0943] Step 5: Accepting User Input

[0944] Users enter their assignments and questions into the chat box on their terminal.

[0945] Input: Issues or questions typed in natural language.

[0946] What happens: A user types "How can we develop a new marketing strategy?" into the chat box and clicks the send button.

[0947] Output: User input is sent from the terminal to the server.

[0948] Step 6: Sending User Input to the Server

[0949] The terminal sends the user's input as is to the server and requests a response.

[0950] Input: The assignment or question entered by the user.

[0951] Specific operation: The terminal sends input data to the server via the network.

[0952] Output: The user's input data received by the server.

[0953] Step 7: Parsing the Question

[0954] The server analyzes the user's input.

[0955] Input: Received user input data.

[0956] What it does: The server uses natural language processing (NLP) algorithms to parse the question and extract key keywords and intent.

[0957] Output: Extracted keywords and user intent.

[0958] Step 8: Search the database

[0959] The server searches for relevant information in a database based on the analysis results.

[0960] Input: Parsed keywords and user intent.

[0961] What happens: The server runs a database search algorithm to find relevant reports and success stories.

[0962] Output: A list of relevant information.

[0963] Step 9: Generate a solution

[0964] The server uses a generative AI model to generate the optimal solution.

[0965] Input: A list of search results and related information.

[0966] Specific operation: The server applies the generative AI model and generates an optimal solution based on the search results, including specific implementation steps and points to note.

[0967] Output: The generated solution.

[0968] Step 10: Submit your solution

[0969] The server transmits the generated solution to the terminal.

[0970] Input: The generated solution.

[0971] Specific operation: The server sends the solution to the terminal via the network.

[0972] Output: The solution displayed on the terminal.

[0973] Step 11: Check for a solution

[0974] The user checks the solution displayed on the terminal.

[0975] Input: The solution displayed in the terminal.

[0976] Specific Action: The user reviews the displayed solution and uses it as a reference for next steps.

[0977] Output: The solution confirmed by the user.

[0978] (Application example 1)

[0979] 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."

[0980] The reports, feedback, and problem-solving proposals submitted by factory workers are diverse and require time and effort. Effectively collecting and analyzing this information and quickly extracting relevant information is difficult. Furthermore, an efficient method is needed to enable real-time problem solving within factories.

[0981] 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.

[0982] In this invention, the server includes: means for collecting reports, feedback, and problem-solving proposals submitted by employees; means for filtering unnecessary information from the collected data; means for storing the filtered data in a database and tagging it; means for retraining the generative AI model using the stored data; means for providing an interface for users to input issues and questions in natural language; means for transmitting the user's input to the server and requesting answers corresponding to the questions; means for searching related information in the database and generating optimal solutions; means for providing problem-solving proposals based on the collected information, past success stories, and expert advice; and means for transmitting the generated answers to the user. This automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and enables efficient problem solving.

[0983] A "report" is a document that employees submit, detailing their daily work, progress, and issues.

[0984] "Feedback" refers to an employee expressing their opinions or thoughts about work or projects, or a document that contains the content of those opinions or thoughts.

[0985] A "problem-solving proposal" is a proposal that lists business problems and issues and provides specific solutions to them.

[0986] "Filtering" is the process of removing unnecessary information from collected data and selecting only highly relevant information.

[0987] "Tagging" is the process of assigning specific categories or keywords to data to make it easier to search and classify.

[0988] A "generative AI model" is an artificial intelligence model that uses machine learning based on large amounts of data to generate new information and solutions.

[0989] An "interface" refers to an operation screen or input device that allows a user to interact with a system.

[0990] A "database" is an electronic storage device for systematically organizing and storing data.

[0991] "Searching" is the act of finding specific information from data in a database.

[0992] A "solution" is a feasible response or means to a specific problem or issue.

[0993] A "success story" is a specific example of a past task or project that achieved a desired result.

[0994] "Expert advice" is advice or guidance from a professional with extensive knowledge and experience in a particular field.

[0995] The present invention is a system that efficiently collects reports, feedback, and problem-solving proposals from workers in a factory and provides advice in real time based on the collected information. Specific embodiments for realizing this system are described in detail below.

[0996] System Overview

[0997] The system of the present invention mainly consists of three main components: a server, a terminal (including a robot), and a user.

[0998] server

[0999] The server is responsible for the following:

[1000] 1. Data Collection and Storage

[1001] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker, and periodically transmits the collected data to the server.

[1002] 2. Data Cleansing and Filtering

[1003] Use the "DataCleanser" module to remove noise data and unnecessary information and extract only the most relevant information.

[1004] 3. Tagging and saving

[1005] The "DatabaseManager" module is used to assign appropriate tags to the cleansed data and store it in the database, such as "equipment maintenance" or "production line improvement."

[1006] 4. Retraining generative AI models

[1007] The stored data is used to periodically retrain the generative AI model, allowing it to generate up-to-date solutions based on new data.

[1008] Terminal (robot)

[1009] 1. Providing a user interface

[1010] The terminal provides an interface where users can input issues and questions in natural language. For example, a robot equipped with a tablet approaches a worker and accepts their reports and questions.

[1011] 2. Data Transmission

[1012] Collected data and user inputs are sent to a server in real time.

[1013] User

[1014] 1. Enter and submit your question

[1015] Users input issues or questions in natural language through the terminal interface and send them to the server. For example, they can input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[1016] 2. Receiving and Confirming Responses

[1017] The response from the server is provided to the user through the terminal, where the user can review and implement the displayed solution.

[1018] Processing flow

[1019] The server analyzes the user's input and searches for relevant information in the database. For example, it searches the database for data related to "equipment maintenance." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, an answer is generated that includes specific steps and points to note based on past success stories and expert advice. The generated answer is then sent to the user via their device.

[1020] Examples and prompts

[1021] As a concrete example, if a factory worker wants to know "machine maintenance procedures on line 2," he or she can input the question "Please tell me about the machine maintenance procedures on line 2" into the robot. In response to this question, the server will provide a solution including specific procedures based on past maintenance procedures and success stories.

[1022] Examples of prompt statements

[1023] Please tell me about the machine maintenance procedures for Line 2. Today's report indicates that an abnormality has been observed on Line 2.

[1024] In this way, the system of the present invention automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and can support efficient problem solving in real time.

[1025] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1026] Step 1:

[1027] Data collection

[1028] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker from the company's internal system. For example, a robot can collect reports at the end of each shift and send them to the server.

[1029] Input: Reports, feedback, and problem-solving proposals submitted by workers

[1030] Output: The collected raw dataset

[1031] Step 2:

[1032] Data Cleansing and Filtering

[1033] The server cleanses the collected data using the DataCleanser module, removing noise and unnecessary information, shaping the data and correcting outliers, and extracting only the most relevant data.

[1034] Input: Collected raw dataset

[1035] Output: A cleansed dataset

[1036] Step 3:

[1037] Tagging and database storage

[1038] The server uses the DatabaseManager module to tag the cleansed data appropriately, for example, with tags like "equipment maintenance" or "production line improvement," and then stores the tagged data in a database.

[1039] Input: Cleansed dataset

[1040] Output: A tagged dataset and data stored in a database

[1041] Step 4:

[1042] Retraining generative AI models

[1043] The server periodically retrains the "generative AI model" using the stored data, updating the machine learning algorithm so that it can generate up-to-date solutions based on new data.

[1044] Input: A dataset stored in a database

[1045] Output: Retrained generative AI model

[1046] Step 5:

[1047] Enter and submit a user question

[1048] Users input issues or questions in natural language through the terminal (robot) interface. This input data is sent to the server in real time. For example, a user might input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[1049] Input: Questions and issues entered in natural language

[1050] Output: The input data sent to the server

[1051] Step 6:

[1052] Search for related information in a database

[1053] The server receives the input data sent by the user and searches for related information in the database. It uses the "DatabaseManager" module to start searching for information based on related tags.

[1054] Input: User questions or challenges submitted

[1055] Output: Related information search results data

[1056] Step 7:

[1057] Solution Generation

[1058] The server uses a generative AI model based on the search results to generate an optimal solution, including specific steps and points to note, by referring to past success stories and expert advice.

[1059] Input: Search results for relevant information, and a retrained generative AI model

[1060] Output: Generated solution

[1061] Step 8:

[1062] Submitting and viewing answers

[1063] The server sends the generated solution to the user. The terminal (robot) displays the received solution to the user in real time. The user can check the solution and take the next step.

[1064] Input: Generated solution

[1065] Output: Solution displayed on the terminal

[1066] This allows for efficient collection of work reports within the factory, information cleansing and filtering, automatic generation of optimal solutions, and real-time problem resolution, all of which improves work efficiency and speeds up problem resolution.

[1067] 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.

[1068] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Additionally, the system incorporates an emotion engine that recognizes the user's emotions, enabling it to provide optimal answers based on the user's emotions. Below, the program processing of this system is explained in natural language and in detail with specific examples.

[1069] Server-side implementation

[1070] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[1071] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, and retaining only specific problem-solving methods and success stories.

[1072] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI using a new dataset every six months to reflect the latest information.

[1073] Terminal side embodiment

[1074] Users interact with the system through a terminal. The terminal provides a chat box-style interface where users can input issues and questions in natural language. For example, a user might input a question such as, "How can I create a new marketing strategy?" The terminal is also equipped with an emotion engine that recognizes emotions from the user's input. For example, if a user inputs, "I'm stressed out about my latest project," the emotion engine will detect stress or anxiety.

[1075] The device sends the user's input and emotional data to the server and requests the best answer for the question, a process that occurs in real time.

[1076] Server Response Generation Embodiments

[1077] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[1078] Based on the search results, the server uses generative AI to generate the optimal solution. This process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. For example, if the user is feeling stressed, the server will also include advice on relaxation methods and stress management.

[1079] The generated answer is then sent back to the user via the device. For example, it might say, "Please see the specific example below for how to create a marketing strategy..." and also include advice such as, "We recommend taking short breaks to manage stress as you go along."

[1080] User usage pattern

[1081] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server, which is displayed in real time. The user then checks the provided solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds by presenting "Three steps for a successful client proposal," while also including advice tailored to the user's feelings.

[1082] In this way, the system of the present invention helps to solve problems quickly and effectively while taking into consideration the user's feelings, thereby improving business efficiency and increasing profits.

[1083] The processing flow will be explained below.

[1084] Step 1:

[1085] Data collection

[1086] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of extracting project reports at the end of each month.

[1087] Step 2:

[1088] Data Cleansing

[1089] The server performs a cleansing process to remove noise and irrelevant information from the collected data. Specifically, it filters out personal opinions and casual conversations, leaving only specific problem-solving methods and success stories.

[1090] Step 3:

[1091] Database storage and tagging

[1092] The server stores the cleansed data in a database and appropriately tags it, for example, with tags like "project management" or "marketing strategy," making it easier to search.

[1093] Step 4:

[1094] Retraining the Model

[1095] The server retrains the generative AI model using new data, allowing it to provide highly accurate solutions based on the most recent data, for example, every six months.

[1096] Step 5:

[1097] Accepting user input

[1098] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[1099] Step 6:

[1100] emotion recognition

[1101] The device's built-in emotion engine recognizes emotions from user input. For example, if a user inputs "I'm feeling stressed about a recent project," the emotion engine will detect stress and anxiety.

[1102] Step 7:

[1103] Sending user input and emotion data

[1104] The device sends the user's input and emotional data to the server and requests an answer based on the question, a process that occurs in real time.

[1105] Step 8:

[1106] Database search

[1107] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[1108] Step 9:

[1109] Response Generation

[1110] The server generates optimal solutions based on the search results. It provides solutions that take into consideration the user's feelings, rather than just standard answers. For example, it suggests specific implementation steps and points to note for "marketing strategies" based on past success stories and expert advice.

[1111] Step 10:

[1112] Sending a response to the user

[1113] The server sends the generated answer to the terminal, for example, "Below are some specific examples of how to create a marketing strategy and relaxation methods for stress management."

[1114] Step 11:

[1115] Checking and using responses

[1116] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[1117] Through this series of processing flows, the present invention supports the user in quickly and effectively resolving problems while taking into consideration the user's feelings.

[1118] Example 2

[1119] 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."

[1120] Conventional information collection and management systems struggled to efficiently collect reports, feedback, and problem-solving proposals submitted by employees and filter out unnecessary information. Furthermore, there were no systems that provided optimal answers that took user sentiment into account. This made information management cumbersome, making it difficult to provide appropriate support to users and preventing improvements in work efficiency. Furthermore, data management for appropriately retraining generative AI models was also cumbersome.

[1121] 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.

[1122] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for recognizing emotions from the user's input, means for searching for related information in the database and generating an optimal solution, and means for transmitting the generated answer to the user. This not only enables efficient filtering and appropriate management of information from employees, but also enables prompt provision of optimal answers that take user emotions into consideration, thereby improving business efficiency and the quality of user support.

[1123] A "report" is a document in which an employee describes work results, progress, problems, suggestions, etc.

[1124] "Feedback" is a document that includes evaluations, opinions, and areas for improvement regarding work.

[1125] A "problem-solving proposal" is a document that describes an appropriate solution or improvement plan for a specific problem or issue.

[1126] "Collection means" refers to the methods and functions for regularly collecting reports, feedback, and problem-solving proposals submitted by employees.

[1127] "Filtering means" refers to methods or functions for removing unnecessary information from collected data and selecting only highly relevant information.

[1128] The "storage means" refers to a method or function for storing the filtered data in a database and managing it so that it can be searched efficiently later.

[1129] "Tagging means" refers to methods or functions that assign keywords such as "project management" or "marketing strategy" to stored data to make it easier to search and identify.

[1130] "Retraining means" refers to the methods or functions that use stored data to periodically update a generative AI model to reflect new information.

[1131] "Means for providing an interface" refers to the method or function of providing an interactive screen or mechanism that allows users to input tasks or questions in natural language.

[1132] "Means for sending and requesting" refers to the methods and functions for sending user input to the server and requesting the appropriate response.

[1133] "Means for recognizing emotions" refers to a method or function for analyzing emotions from user input and identifying specific emotions.

[1134] "Search and generation tools" are methods and functions for locating relevant information in a database and generating optimal solutions or answers.

[1135] "Transmission means" refers to the method or function for sending and presenting the generated answer to the user.

[1136] This invention is a system that efficiently collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and provides optimal answers that take into account the user's feelings. The system is composed of three entities: a server, a terminal, and a user.

[1137] Server processing

[1138] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The specific implementation uses Python scripts to retrieve information using SQL queries. Cron jobs are used as the task scheduler.

[1139] Next, the collected data undergoes a cleansing process. At this stage, Apache Spark and Pandas are used to remove noisy data and irrelevant information, leaving only the most relevant information. Regular expressions are used to extract the necessary keywords and phrases. The filtered data is then stored in a database using Elasticsearch. Here, tags such as "project management" and "marketing strategy" are added. NLP (natural language processing) technology is used as the tagging algorithm.

[1140] Furthermore, the server periodically (e.g., every six months) retrains the generative AI model using the stored data, using TensorFlow or PyTorch to train the model and updating it with new datasets.

[1141] Processing by the terminal

[1142] The terminal provides a chatbox-style interface where users can input issues or questions in natural language. The interface is built using HTML and JavaScript, and sends user input to a server in real time. It uses NLP models such as BERT and RoBERTa as an emotion engine to analyze emotions from the user's text.

[1143] For example, if a user types "How can we develop a new marketing strategy?", the device sends this input and parsed sentiment data to the server via an HTTP request. The data is packaged in JSON format and deserialized after it is received by the server.

[1144] Server response generation

[1145] The server analyzes the user's input and emotional data and uses Elasticsearch to search for related information in a database. For example, it searches for data related to "marketing strategies" and analyzes the data while taking the user's emotional state into account. Based on the analysis results, it uses a generative AI model (e.g., GPT-3) to generate a natural language response.

[1146] The generated answers are designed to provide the best possible solution for the user, including specific steps and precautions, and if the user is feeling stressed, advice on relaxation and stress management is also included.

[1147] For example, a prompt might look like this:

[1148] 1. Example of user input:

[1149] "I'm feeling stressed about a recent project. What should I do?"

[1150] 2. The corresponding prompt:

[1151] "An employee wrote, 'I'm stressed out over a recent project.' Please provide specific stress management strategies. Also, include ways to reduce project management stress."

[1152] Terminal display of responses

[1153] Finally, the device displays the answers received from the server to the user in real time, such as "Please see the specific example below for how to create a marketing strategy..." and also provides advice such as "We recommend taking short breaks to manage stress as you go along."

[1154] This allows the user to check the provided solutions and use them as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server will present "three steps for a successful client proposal" and also include advice based on the user's feelings.

[1155] In this way, the system of the present invention solves problems quickly and effectively while taking into account the user's feelings, thereby improving business efficiency and increasing profits.

[1156] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1157] Step 1:

[1158] Data collection

[1159] The server collects employee reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The input is the reports, feedback, and problem-solving proposals submitted by employees, and the output is the collected data. The specific collection process involves executing SQL queries using a Python script to obtain the information. A Cron job is used for scheduling.

[1160] Step 2:

[1161] Data Cleansing

[1162] The server cleanses the collected data, removing noise and irrelevant information. This process uses Apache Spark and Pandas to analyze the data and filter out noise and unnecessary information. This scrutinizes the input data and produces filtered data as output. Specifically, it uses regular expressions to extract necessary keywords and phrases.

[1163] Step 3:

[1164] Data storage and tagging

[1165] The server stores the cleansed data in a database and assigns appropriate tags. The input is the cleansed data, and the output is tagged database entries. Specifically, Elasticsearch is used to assign tags such as "project management" and "marketing strategy" to the data. NLP technology is used as the tagging algorithm.

[1166] Step 4:

[1167] Retraining generative AI models

[1168] The server retrains the generative AI model using the stored data every specific period (e.g., every six months). The input is the stored dataset, and the output is the retrained generative AI model. Specifically, TensorFlow or PyTorch is used to retrain the AI ​​model using batch processing on the dataset.

[1169] Step 5:

[1170] Accepting user input

[1171] The terminal provides a chat box-style interface where users can input tasks and questions in natural language. The input is the natural language question or task from the user, and the output is the data that will be sent to the server. Specifically, a front end created with HTML and JavaScript provides the user interface and sends the input to the server in real time.

[1172] Step 6:

[1173] emotion recognition

[1174] The device recognizes emotions from the user's input. The input is the user's text data, and the output is analyzed emotion data. Specifically, it uses NLP models such as BERT and RoBERTa to analyze emotions from the input text.

[1175] Step 7:

[1176] Input and sending emotional data

[1177] The device sends the user's input and emotion data to the server. The input is the user's text data and emotion data, and the output is the data sent to the server. Specifically, the data is sent to the server using an HTTP request and packaged in JSON format.

[1178] Step 8:

[1179] Data analysis and response generation

[1180] The server analyzes the user's input and emotion data and searches for relevant information in the database. The input is the user's question and emotion data, and the output is the generated answer. Specifically, it uses Elasticsearch to search for relevant data and uses a generative AI model (e.g., GPT) to generate the optimal solution.

[1181] Step 9:

[1182] Submitting and viewing generated answers

[1183] The server sends the generated answer to the terminal, which displays it to the user. The input is the answer data from the server, and the output is the display data that the user can visually confirm. The specific operation is to send an HTTP response and display the answer on the front end.

[1184] Specific examples

[1185] In response to a user question such as, "I'm feeling stressed about a recent project. What should I do?", the server receives the input, "I'm feeling stressed about a recent project," and analyzes the emotion as stress. It searches for appropriate stress management methods from a related database and generates "specific stress management methods" using a generative AI model. For example, it presents guidelines such as "Three steps for a successful client proposal," while also including advice such as, "We recommend taking a short break for relaxation and stress management."

[1186] In this way, the system helps users solve problems quickly and effectively while taking their emotions into consideration, improving business efficiency and increasing profits.

[1187] (Application example 2)

[1188] 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."

[1189] Conventional data collection systems lack the ability to filter unnecessary information from collected reports, feedback, and problem-solving proposals, making it difficult to efficiently extract relevant information. Furthermore, there is no system that can recognize user emotions and generate appropriate responses based on them, which hinders the user experience.

[1190] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface through which a user inputs issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for searching related information in the database and generating an optimal solution, means for transmitting the generated answer to the user, and means for recognizing the user's emotions and generating an optimal response based on the emotions. This allows for providing an optimal solution that takes emotions into consideration, improving the user experience and business efficiency.

[1191] An "employee" is a staff member employed by a company or organization to perform work.

[1192] A "collection means" is a process or device for collecting specified data.

[1193] A "filtering means" is a process or device used to remove unwanted information from collected data.

[1194] A "database" is a system for efficiently storing, searching, and managing data.

[1195] A "tagging means" is a process or device that assigns a specific tag or label to stored data.

[1196] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information or answers from given data.

[1197] An "interface" is the input and output means by which a user interacts with a system.

[1198] A "server" is a computer system that processes data and provides services over a network.

[1199] A "means for recognizing emotions" is a process or device for analyzing and recognizing emotions from user input.

[1200] A "means for generating a response" is a process or device for generating optimal answers or advice based on input data and emotional information.

[1201] "Delivery staff" are workers who deliver food and other products to customers.

[1202] "Stress" is a state of mental or physical tension or strain.

[1203] A "prompt" is the original text or question that is input into a generative AI model.

[1204] This invention provides a system that automatically collects data such as reports, feedback, and problem-solving proposals submitted by employees and extracts highly relevant information.Furthermore, we provide an example of an application for delivery staff equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on them.

[1205] Server-side implementation

[1206] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. For example, it has a function that automatically collects reports from all staff after the end of each day's work. The collected data is then cleansed on the server for filtering purposes. Noisy data and irrelevant information are removed, and only specific problem-solving methods and success stories are retained. The cleansed data is stored in a database and tagged. This tagging improves search efficiency. The stored data is also used to retrain the generative AI model at regular intervals, so that the latest information is reflected.

[1207] Terminal side embodiment

[1208] Users interact with the system through a smartphone application. The app provides a chat box-style interface where users can input issues or questions in natural language. For example, a user might input a question such as, "I'm feeling stressed while delivering. Please help me." The app is equipped with an emotion engine that recognizes the user's emotions from the input. For example, if a user inputs, "I'm feeling very tired from recent deliveries," the emotion engine will detect stress or fatigue.

[1209] Server Response Generation Embodiments

[1210] The server analyzes the user's input and emotional data and searches for related information in a database. For example, it considers data related to "stress management for delivery" and the user's emotional state. Based on the search results, the server uses a generative AI model to generate the optimal solution. This generation process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. The generated answer is sent to the user via their device. For example, it provides specific examples such as "Try the following three steps to manage stress..." and also includes advice such as "We also recommend taking deep breaths and short breaks."

[1211] Hardware and Software

[1212] This system uses an advanced data processing system as the server and a relational database management system (RDBMS) as the database. Python and OpenAI AI technologies are used for the emotion recognition and generation AI model. Specifically, TextBlob is used for emotion analysis, and the OpenAI API is used for AI answer generation. The user interface is a smartphone application, and React Native is used as the front-end technology for its construction.

[1213] Prompt Sentence Examples

[1214] User Request: "What do you do when you're tired?"

[1215] Prompt the generative AI model: "How do you manage stress when you're tired?"

[1216] In this way, the system of the present invention increases the usefulness of collected data and provides optimal solutions based on user sentiment, thereby improving operational efficiency and improving the user experience.

[1217] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1218] Step 1:

[1219] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. The input is the reports and feedback from the delivery staff, which the server collects. The output is a set of collected data, which is passed to the next step.

[1220] Step 2:

[1221] The server filters unnecessary information from the collected data. The inputs are reports and feedback, and the output is relevant data after removing noise data. Specifically, a data cleansing algorithm is applied to remove noise and irrelevant information.

[1222] Step 3:

[1223] The server stores the filtered data in a database and tags it. The input is the filtered data, and the output is tagged database records. Specifically, tags such as "delivery problem" and "customer satisfaction" are automatically assigned to each piece of data.

[1224] Step 4:

[1225] The server periodically retrains the generative AI model using the stored data. The input is the past data stored in the database, and the output is a generative AI model that reflects the latest data. Specifically, the AI ​​training algorithm updates the model using a new data set.

[1226] Step 5:

[1227] The user inputs a problem or question in natural language through the device. The input is a question from the user in natural language, and the output is the content of the question. Specifically, the user inputs a question into the chat box on their smartphone.

[1228] Step 6:

[1229] The terminal sends the user's input to the server and requests an answer according to the question. The input is the user's question data, and the output is the request data sent to the server. Specifically, the chat box interface sends the user's input to the server in real time.

[1230] Step 7:

[1231] The server analyzes the user's input and emotion data and searches for related information in a database. The input is the user's question data and the emotion analysis results, and the output is a collection of related information. Specifically, the text analysis algorithm generates emotion data, and the database query extracts related information.

[1232] Step 8:

[1233] The server uses a generative AI model to generate an optimal solution based on the search results. The input is a collection of related information and emotional data, and the output is the generated solution. Specifically, the generative AI model combines past success stories and expert advice to generate an answer.

[1234] Step 9:

[1235] The server sends the generated answer to the terminal, which then displays the answer to the user. The input is the generated solution, and the output is the answer displayed on the user's smartphone. Specifically, the server sends the generated answer to the terminal, which then displays it to the user.

[1236] Through the above steps, the system of the present invention can efficiently process reports and feedback from delivery staff and provide optimal solutions based on their emotions.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] [Fourth embodiment]

[1241] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1242] 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.

[1243] 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).

[1244] 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.

[1245] 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.

[1246] 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).

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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."

[1254] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Below, we will explain the program processing of this system in natural language and provide detailed examples.

[1255] Server-side implementation

[1256] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[1257] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, leaving only specific problem-solving methods and success stories.

[1258] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI with a new dataset every six months.

[1259] Terminal side embodiment

[1260] Users interact with the system through a terminal, which provides a chat box-style interface where users can enter issues or questions in natural language. For example, a user might enter a question like, "How can I develop a new marketing strategy?"

[1261] The terminal sends the user's input directly to the server, requesting an answer to the question. This data transmission is done in real time.

[1262] Server Response Generation Embodiments

[1263] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" from the database.

[1264] Based on the search results, the server uses generative AI to generate the optimal solution. During this generation process, it generates an answer that includes specific implementation steps and points to note, based on past success stories and expert advice. The generated answer is then sent back to the user via their device. For example, it might be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[1265] User usage pattern

[1266] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server and displays it in real time. The user checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[1267] In this way, the system of the present invention provides support for quickly and effectively resolving the challenges employees face every day, improving business efficiency and increasing profits.

[1268] The processing flow will be explained below.

[1269] Step 1:

[1270] Data collection

[1271] The server automatically collects reports, feedback, and problem-solving proposals from each employee on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[1272] Step 2:

[1273] Data Cleansing

[1274] The server performs a cleansing process to remove noise and irrelevant information from the collected data, so that only specific problem-solving methods and success stories are retained.

[1275] Step 3:

[1276] Database storage and tagging

[1277] The server stores the cleansed data in a database and tags it, adding appropriate tags such as "project management" or "marketing strategy" to make searches more efficient.

[1278] Step 4:

[1279] Retraining the Model

[1280] The server periodically retrains the generative AI model using the stored data, for example, every six months using a new dataset.

[1281] Step 5:

[1282] Accepting user input

[1283] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[1284] Step 6:

[1285] Sending User Input

[1286] The device sends the user's input directly to the server and requests an answer to the question, a process that occurs in real time.

[1287] Step 7:

[1288] Database search

[1289] The server analyzes the user's input and searches for related information in a database, for example, searching for data related to "marketing strategies" in the database.

[1290] Step 8:

[1291] Response Generation

[1292] Based on the search results, the server uses generative AI to generate the optimal solution, including specific implementation steps and points to note based on past success stories and expert advice.

[1293] Step 9:

[1294] Sending a response to the user

[1295] The server then sends the generated answer to the device, for example, in the form of "Please see the specific example below for how to create a marketing strategy..."

[1296] Step 10:

[1297] Checking and using responses

[1298] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[1299] This process flow allows users to receive assistance in quickly and effectively resolving their issues.

[1300] Example 1

[1301] 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."

[1302] In today's corporate environment, employees submit huge volumes of reports, feedback, and problem-solving proposals. Therefore, there is a need to quickly extract useful data from this information and analyze and utilize it appropriately. However, traditional methods require manual data filtering and analysis, which takes a great deal of time and effort. To solve this problem, an efficient and automated data processing system is needed.

[1303] 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.

[1304] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering and cleansing unnecessary information from the collected data, means for storing the filtered and cleansed data in a database and tagging it appropriately, means for periodically retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for sending the user's input to the server and requesting answers corresponding to the questions, means for searching for related information in the database and generating optimal solutions based on the extracted information, and means for sending the generated answers to the user. This makes it possible to efficiently and automatically extract useful data from a vast amount of information and quickly provide support for problem solving.

[1305] "Means for collecting reports, feedback, and problem-solving proposals submitted by employees" refers to software and hardware means for automatically collecting various reports, feedback, and problem-solving proposal documents submitted by employees from internal systems.

[1306] "Means for filtering and cleansing unnecessary information from collected data" means algorithmic and software means for automatically detecting and removing noise and irrelevant information in collected data.

[1307] "Means for storing the filtered and cleansed data in a database and tagging it appropriately" refers to hardware and software means for storing the cleansed data in a database and tagging it with appropriate tags, such as "project management" and "marketing strategy," to further improve search efficiency.

[1308] "Means for periodically retraining a generative AI model using stored data" refers to providing software and computing resources for adjusting and optimizing the parameters of a generative AI model and retraining it using updated data stored in a database at regular intervals.

[1309] "Means for providing an interface that allows users to input tasks or questions in natural language" refers to software means for providing an interface that allows users to input tasks or questions in natural language, for example, a chat box-style UI.

[1310] "Means for sending user input to a server and requesting an answer corresponding to the question" refers to communication means and control software for sending natural language data entered by a user to a server in real time and requesting that the server generate an appropriate answer.

[1311] "Means for searching for relevant information in a database and generating optimal solutions based on the extracted information" refers to algorithms and software means by which a server searches for relevant information in a database and generates optimal solutions using a generative AI model based on the search results.

[1312] The "means for transmitting the generated answer to the user" refers to the communication means and software means for transmitting the answer generated by the server to the user's terminal in real time.

[1313] MODE FOR CARRYING OUT THE INVENTION

[1314] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information.

[1315] Server-side implementation

[1316] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, the server has the function of automatically extracting project reports at the end of each month. The hardware used includes the company's database server and network interface cards. The software used includes data collection scripts, cleansing algorithms, and tagging algorithms.

[1317] The collected data undergoes a cleansing process on the server for filtering. During this process, noise data and irrelevant information are automatically removed, leaving only specific problem-solving methods and success stories. The cleansed data is stored in a database and is assigned appropriate tags, such as "project management" or "marketing strategy." Tagging makes future searches more efficient. The stored data is used to retrain the generative AI model at regular intervals. For example, the server retrains the generative AI using a new dataset every six months.

[1318] Terminal side embodiment

[1319] Users interact with the system through terminals. The terminals provide a chat box-style interface where users can input issues or questions in natural language. For example, a user can input the question, "How do I develop a new marketing strategy?" The terminals transmit this input in real time to the server and request an answer to the question. The terminals include interface software and a network communication module.

[1320] Server Response Generation Embodiments

[1321] The server analyzes the user's input and searches for related information in the database. For example, it searches the database for data related to "marketing strategy." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, it refers to past success stories and expert advice to generate an answer that includes specific implementation steps and points to note. The generated answer is then sent back to the user via the device. For example, the answer may be presented in the form of, "Please see the specific example below for how to create a marketing strategy..."

[1322] User usage pattern

[1323] The user enters a question in the chat box and clicks the send button. The terminal then receives a response from the server and displays it in real time. The user then checks the displayed solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal." In this way, the system of the present invention helps employees quickly and effectively solve the challenges they face every day, improving business efficiency and increasing revenue.

[1324] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1325] Program processing steps

[1326] Step 1: Data collection

[1327] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule.

[1328] Input: Reports, feedback, and problem-solving proposals stored in our internal systems.

[1329] What it does: The server runs the data collection script at the end of each month to get the latest reports and feedback.

[1330] Output: A list of the raw data collected.

[1331] Step 2: Data cleansing

[1332] The server cleanses the collected data and filters out unnecessary information.

[1333] Input: A list of the collected raw data.

[1334] What it does: The server runs a cleansing algorithm to remove noise data and irrelevant information.

[1335] Output: filtered clean data.

[1336] Step 3: Tag and store your data

[1337] The server stores the cleansed data in a database and tags it appropriately.

[1338] Input: Clean, cleansed data.

[1339] What it does: The server uses a tagging algorithm to assign tags like "project management" or "marketing strategy" and store them in a database.

[1340] Output: A database containing the tagged data.

[1341] Step 4: Periodically retrain the generative AI model

[1342] The server periodically retrains the generative AI model using the data stored in the database.

[1343] Input: The most recent dataset stored in the database.

[1344] How it works: Every six months, the server uses collected data to run a retraining algorithm for the generative AI model, improving the model's accuracy.

[1345] Output: A generative AI model that has been retrained and has improved performance.

[1346] Step 5: Accepting User Input

[1347] Users enter their assignments and questions into the chat box on their terminal.

[1348] Input: Issues or questions typed in natural language.

[1349] What happens: A user types "How can we develop a new marketing strategy?" into the chat box and clicks the send button.

[1350] Output: User input is sent from the terminal to the server.

[1351] Step 6: Sending User Input to the Server

[1352] The terminal sends the user's input as is to the server and requests a response.

[1353] Input: The assignment or question entered by the user.

[1354] Specific operation: The terminal sends input data to the server via the network.

[1355] Output: The user's input data received by the server.

[1356] Step 7: Parsing the Question

[1357] The server analyzes the user's input.

[1358] Input: Received user input data.

[1359] What it does: The server uses natural language processing (NLP) algorithms to parse the question and extract key keywords and intent.

[1360] Output: Extracted keywords and user intent.

[1361] Step 8: Search the database

[1362] The server searches for relevant information in a database based on the analysis results.

[1363] Input: Parsed keywords and user intent.

[1364] What happens: The server runs a database search algorithm to find relevant reports and success stories.

[1365] Output: A list of relevant information.

[1366] Step 9: Generate a solution

[1367] The server uses a generative AI model to generate the optimal solution.

[1368] Input: A list of search results and related information.

[1369] Specific operation: The server applies the generative AI model and generates an optimal solution based on the search results, including specific implementation steps and points to note.

[1370] Output: The generated solution.

[1371] Step 10: Submit your solution

[1372] The server transmits the generated solution to the terminal.

[1373] Input: The generated solution.

[1374] Specific operation: The server sends the solution to the terminal via the network.

[1375] Output: The solution displayed on the terminal.

[1376] Step 11: Check for a solution

[1377] The user checks the solution displayed on the terminal.

[1378] Input: The solution displayed in the terminal.

[1379] Specific Action: The user reviews the displayed solution and uses it as a reference for next steps.

[1380] Output: The solution confirmed by the user.

[1381] (Application example 1)

[1382] 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."

[1383] The reports, feedback, and problem-solving proposals submitted by factory workers are diverse and require time and effort. Effectively collecting and analyzing this information and quickly extracting relevant information is difficult. Furthermore, an efficient method is needed to enable real-time problem solving within factories.

[1384] 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.

[1385] In this invention, the server includes: means for collecting reports, feedback, and problem-solving proposals submitted by employees; means for filtering unnecessary information from the collected data; means for storing the filtered data in a database and tagging it; means for retraining the generative AI model using the stored data; means for providing an interface for users to input issues and questions in natural language; means for transmitting the user's input to the server and requesting answers corresponding to the questions; means for searching related information in the database and generating optimal solutions; means for providing problem-solving proposals based on the collected information, past success stories, and expert advice; and means for transmitting the generated answers to the user. This automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and enables efficient problem solving.

[1386] A "report" is a document that employees submit, detailing their daily work, progress, and issues.

[1387] "Feedback" refers to an employee expressing their opinions or thoughts about work or projects, or a document that contains the content of those opinions or thoughts.

[1388] A "problem-solving proposal" is a proposal that lists business problems and issues and provides specific solutions to them.

[1389] "Filtering" is the process of removing unnecessary information from collected data and selecting only highly relevant information.

[1390] "Tagging" is the process of assigning specific categories or keywords to data to make it easier to search and classify.

[1391] A "generative AI model" is an artificial intelligence model that uses machine learning based on large amounts of data to generate new information and solutions.

[1392] An "interface" refers to an operation screen or input device that allows a user to interact with a system.

[1393] A "database" is an electronic storage device for systematically organizing and storing data.

[1394] "Searching" is the act of finding specific information from data in a database.

[1395] A "solution" is a feasible response or means to a specific problem or issue.

[1396] A "success story" is a specific example of a past task or project that achieved a desired result.

[1397] "Expert advice" is advice or guidance from a professional with extensive knowledge and experience in a particular field.

[1398] The present invention is a system that efficiently collects reports, feedback, and problem-solving proposals from workers in a factory and provides advice in real time based on the collected information. Specific embodiments for realizing this system are described in detail below.

[1399] System Overview

[1400] The system of the present invention mainly consists of three main components: a server, a terminal (including a robot), and a user.

[1401] server

[1402] The server is responsible for the following:

[1403] 1. Data Collection and Storage

[1404] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker, and periodically transmits the collected data to the server.

[1405] 2. Data Cleansing and Filtering

[1406] Use the "DataCleanser" module to remove noise data and unnecessary information and extract only the most relevant information.

[1407] 3. Tagging and saving

[1408] The "DatabaseManager" module is used to assign appropriate tags to the cleansed data and store it in the database, such as "equipment maintenance" or "production line improvement."

[1409] 4. Retraining generative AI models

[1410] The stored data is used to periodically retrain the generative AI model, allowing it to generate up-to-date solutions based on new data.

[1411] Terminal (robot)

[1412] 1. Providing a user interface

[1413] The terminal provides an interface where users can input issues and questions in natural language. For example, a robot equipped with a tablet approaches a worker and accepts their reports and questions.

[1414] 2. Data Transmission

[1415] Collected data and user inputs are sent to a server in real time.

[1416] User

[1417] 1. Enter and submit your question

[1418] Users input issues or questions in natural language through the terminal interface and send them to the server. For example, they can input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[1419] 2. Receiving and Confirming Responses

[1420] The response from the server is provided to the user through the terminal, where the user can review and implement the displayed solution.

[1421] Processing flow

[1422] The server analyzes the user's input and searches for relevant information in the database. For example, it searches the database for data related to "equipment maintenance." Based on the search results, the server uses a generative AI model to generate the optimal solution. During this generation process, an answer is generated that includes specific steps and points to note based on past success stories and expert advice. The generated answer is then sent to the user via their device.

[1423] Examples and prompts

[1424] As a concrete example, if a factory worker wants to know "machine maintenance procedures on line 2," he or she can input the question "Please tell me about the machine maintenance procedures on line 2" into the robot. In response to this question, the server will provide a solution including specific procedures based on past maintenance procedures and success stories.

[1425] Examples of prompt statements

[1426] Please tell me about the machine maintenance procedures for Line 2. Today's report indicates that an abnormality has been observed on Line 2.

[1427] In this way, the system of the present invention automates the collection of work reports and feedback within the factory, extracts only highly relevant information, and can support efficient problem solving in real time.

[1428] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1429] Step 1:

[1430] Data collection

[1431] The server automatically collects reports, feedback, and problem-solving proposals submitted by each worker from the company's internal system. For example, a robot can collect reports at the end of each shift and send them to the server.

[1432] Input: Reports, feedback, and problem-solving proposals submitted by workers

[1433] Output: The collected raw dataset

[1434] Step 2:

[1435] Data Cleansing and Filtering

[1436] The server cleanses the collected data using the DataCleanser module, removing noise and unnecessary information, shaping the data and correcting outliers, and extracting only the most relevant data.

[1437] Input: Collected raw dataset

[1438] Output: A cleansed dataset

[1439] Step 3:

[1440] Tagging and database storage

[1441] The server uses the DatabaseManager module to tag the cleansed data appropriately, for example, with tags like "equipment maintenance" or "production line improvement," and then stores the tagged data in a database.

[1442] Input: Cleansed dataset

[1443] Output: A tagged dataset and data stored in a database

[1444] Step 4:

[1445] Retraining generative AI models

[1446] The server periodically retrains the "generative AI model" using the stored data, updating the machine learning algorithm so that it can generate up-to-date solutions based on new data.

[1447] Input: A dataset stored in a database

[1448] Output: Retrained generative AI model

[1449] Step 5:

[1450] Enter and submit a user question

[1451] Users input issues or questions in natural language through the terminal (robot) interface. This input data is sent to the server in real time. For example, a user might input a question such as, "Please tell me about the machine maintenance procedures on Line 2."

[1452] Input: Questions and issues entered in natural language

[1453] Output: The input data sent to the server

[1454] Step 6:

[1455] Search for related information in a database

[1456] The server receives the input data sent by the user and searches for related information in the database. It uses the "DatabaseManager" module to start searching for information based on related tags.

[1457] Input: User questions or challenges submitted

[1458] Output: Related information search results data

[1459] Step 7:

[1460] Solution Generation

[1461] The server uses a generative AI model based on the search results to generate an optimal solution, including specific steps and points to note, by referring to past success stories and expert advice.

[1462] Input: Search results for relevant information, and a retrained generative AI model

[1463] Output: Generated solution

[1464] Step 8:

[1465] Submitting and viewing answers

[1466] The server sends the generated solution to the user. The terminal (robot) displays the received solution to the user in real time. The user can check the solution and take the next step.

[1467] Input: Generated solution

[1468] Output: Solution displayed on the terminal

[1469] This allows for efficient collection of work reports within the factory, information cleansing and filtering, automatic generation of optimal solutions, and real-time problem resolution, all of which improves work efficiency and speeds up problem resolution.

[1470] 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.

[1471] The present invention is a system that collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and selects only highly relevant information. Additionally, the system incorporates an emotion engine that recognizes the user's emotions, enabling it to provide optimal answers based on the user's emotions. Below, the program processing of this system is explained in natural language and in detail with specific examples.

[1472] Server-side implementation

[1473] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of automatically extracting project reports at the end of each month.

[1474] The collected data is then subjected to a cleansing process on the server to filter it out, automatically removing noise and irrelevant information, and retaining only specific problem-solving methods and success stories.

[1475] The cleansed data is stored in a database and tagged. This tagging improves search efficiency by adding appropriate tags such as "project management" and "marketing strategy." The stored data is used to retrain the generative AI model periodically. For example, the server retrains the generative AI using a new dataset every six months to reflect the latest information.

[1476] Terminal side embodiment

[1477] Users interact with the system through a terminal. The terminal provides a chat box-style interface where users can input issues and questions in natural language. For example, a user might input a question such as, "How can I create a new marketing strategy?" The terminal is also equipped with an emotion engine that recognizes emotions from the user's input. For example, if a user inputs, "I'm stressed out about my latest project," the emotion engine will detect stress or anxiety.

[1478] The device sends the user's input and emotional data to the server and requests the best answer for the question, a process that occurs in real time.

[1479] Server Response Generation Embodiments

[1480] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[1481] Based on the search results, the server uses generative AI to generate the optimal solution. This process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. For example, if the user is feeling stressed, the server will also include advice on relaxation methods and stress management.

[1482] The generated answer is then sent back to the user via the device. For example, it might say, "Please see the specific example below for how to create a marketing strategy..." and also include advice such as, "We recommend taking short breaks to manage stress as you go along."

[1483] User usage pattern

[1484] The user enters a question in the chat box and clicks the send button. The device then receives a response from the server, which is displayed in real time. The user then checks the provided solution and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds by presenting "Three steps for a successful client proposal," while also including advice tailored to the user's feelings.

[1485] In this way, the system of the present invention helps to solve problems quickly and effectively while taking into consideration the user's feelings, thereby improving business efficiency and increasing profits.

[1486] The processing flow will be explained below.

[1487] Step 1:

[1488] Data collection

[1489] The server automatically collects reports, feedback, and problem-solving proposals from each employee from the company's internal systems on a regular basis according to a pre-set schedule. For example, it has the function of extracting project reports at the end of each month.

[1490] Step 2:

[1491] Data Cleansing

[1492] The server performs a cleansing process to remove noise and irrelevant information from the collected data. Specifically, it filters out personal opinions and casual conversations, leaving only specific problem-solving methods and success stories.

[1493] Step 3:

[1494] Database storage and tagging

[1495] The server stores the cleansed data in a database and appropriately tags it, for example, with tags like "project management" or "marketing strategy," making it easier to search.

[1496] Step 4:

[1497] Retraining the Model

[1498] The server retrains the generative AI model using new data, allowing it to provide highly accurate solutions based on the most recent data, for example, every six months.

[1499] Step 5:

[1500] Accepting user input

[1501] The terminal provides a chat box-style interface where users can enter challenges or questions in natural language, for example, a user might type, "How can we develop a new marketing strategy?"

[1502] Step 6:

[1503] emotion recognition

[1504] The device's built-in emotion engine recognizes emotions from user input. For example, if a user inputs "I'm feeling stressed about a recent project," the emotion engine will detect stress and anxiety.

[1505] Step 7:

[1506] Sending user input and emotion data

[1507] The device sends the user's input and emotional data to the server and requests an answer based on the question, a process that occurs in real time.

[1508] Step 8:

[1509] Database search

[1510] The server analyzes the user's input and emotional data and searches for relevant information in a database, for example, data related to "marketing strategies" and taking into account the user's emotional state.

[1511] Step 9:

[1512] Response Generation

[1513] The server generates optimal solutions based on the search results. It provides solutions that take into consideration the user's feelings, rather than just standard answers. For example, it suggests specific implementation steps and points to note for "marketing strategies" based on past success stories and expert advice.

[1514] Step 10:

[1515] Sending a response to the user

[1516] The server sends the generated answer to the terminal, for example, "Below are some specific examples of how to create a marketing strategy and relaxation methods for stress management."

[1517] Step 11:

[1518] Checking and using responses

[1519] The user checks the solution provided by the device and uses it as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server responds with "Three steps for a successful client proposal."

[1520] Through this series of processing flows, the present invention supports the user in quickly and effectively resolving problems while taking into consideration the user's feelings.

[1521] Example 2

[1522] 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."

[1523] Conventional information collection and management systems struggled to efficiently collect reports, feedback, and problem-solving proposals submitted by employees and filter out unnecessary information. Furthermore, there were no systems that provided optimal answers that took user sentiment into account. This made information management cumbersome, making it difficult to provide appropriate support to users and preventing improvements in work efficiency. Furthermore, data management for appropriately retraining generative AI models was also cumbersome.

[1524] 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.

[1525] In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface for users to input issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for recognizing emotions from the user's input, means for searching for related information in the database and generating an optimal solution, and means for transmitting the generated answer to the user. This not only enables efficient filtering and appropriate management of information from employees, but also enables prompt provision of optimal answers that take user emotions into consideration, thereby improving business efficiency and the quality of user support.

[1526] A "report" is a document in which an employee describes work results, progress, problems, suggestions, etc.

[1527] "Feedback" is a document that includes evaluations, opinions, and areas for improvement regarding work.

[1528] A "problem-solving proposal" is a document that describes an appropriate solution or improvement plan for a specific problem or issue.

[1529] "Collection means" refers to the methods and functions for regularly collecting reports, feedback, and problem-solving proposals submitted by employees.

[1530] "Filtering means" refers to methods or functions for removing unnecessary information from collected data and selecting only highly relevant information.

[1531] The "storage means" refers to a method or function for storing the filtered data in a database and managing it so that it can be searched efficiently later.

[1532] "Tagging means" refers to methods or functions that assign keywords such as "project management" or "marketing strategy" to stored data to make it easier to search and identify.

[1533] "Retraining means" refers to the methods or functions that use stored data to periodically update a generative AI model to reflect new information.

[1534] "Means for providing an interface" refers to the method or function of providing an interactive screen or mechanism that allows users to input tasks or questions in natural language.

[1535] "Means for sending and requesting" refers to the methods and functions for sending user input to the server and requesting the appropriate response.

[1536] "Means for recognizing emotions" refers to a method or function for analyzing emotions from user input and identifying specific emotions.

[1537] "Search and generation tools" are methods and functions for locating relevant information in a database and generating optimal solutions or answers.

[1538] "Transmission means" refers to the method or function for sending and presenting the generated answer to the user.

[1539] This invention is a system that efficiently collects reports, feedback, and problem-solving proposals submitted by employees, filters out unnecessary information, and provides optimal answers that take into account the user's feelings. The system is composed of three entities: a server, a terminal, and a user.

[1540] Server processing

[1541] The server automatically collects each employee's reports, feedback, and problem-solving proposals from the company's internal systems on a regular basis according to a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The specific implementation uses Python scripts to retrieve information using SQL queries. Cron jobs are used as the task scheduler.

[1542] Next, the collected data undergoes a cleansing process. At this stage, Apache Spark and Pandas are used to remove noisy data and irrelevant information, leaving only the most relevant information. Regular expressions are used to extract the necessary keywords and phrases. The filtered data is then stored in a database using Elasticsearch. Here, tags such as "project management" and "marketing strategy" are added. NLP (natural language processing) technology is used as the tagging algorithm.

[1543] Furthermore, the server periodically (e.g., every six months) retrains the generative AI model using the stored data, using TensorFlow or PyTorch to train the model and updating it with new datasets.

[1544] Processing by the terminal

[1545] The terminal provides a chatbox-style interface where users can input issues or questions in natural language. The interface is built using HTML and JavaScript, and sends user input to a server in real time. It uses NLP models such as BERT and RoBERTa as an emotion engine to analyze emotions from the user's text.

[1546] For example, if a user types "How can we develop a new marketing strategy?", the device sends this input and parsed sentiment data to the server via an HTTP request. The data is packaged in JSON format and deserialized after it is received by the server.

[1547] Server response generation

[1548] The server analyzes the user's input and emotional data and uses Elasticsearch to search for related information in a database. For example, it searches for data related to "marketing strategies" and analyzes the data while taking the user's emotional state into account. Based on the analysis results, it uses a generative AI model (e.g., GPT-3) to generate a natural language response.

[1549] The generated answers are designed to provide the best possible solution for the user, including specific steps and precautions, and if the user is feeling stressed, advice on relaxation and stress management is also included.

[1550] For example, a prompt might look like this:

[1551] 1. Example of user input:

[1552] "I'm feeling stressed about a recent project. What should I do?"

[1553] 2. The corresponding prompt:

[1554] "An employee wrote, 'I'm stressed out over a recent project.' Please provide specific stress management strategies. Also, include ways to reduce project management stress."

[1555] Terminal display of responses

[1556] Finally, the device displays the answers received from the server to the user in real time, such as "Please see the specific example below for how to create a marketing strategy..." and also provides advice such as "We recommend taking short breaks to manage stress as you go along."

[1557] This allows the user to check the provided solutions and use them as a reference for the next step. For example, in response to the question, "I'm thinking about proposing a new digital marketing campaign. How should I proceed?", the server will present "three steps for a successful client proposal" and also include advice based on the user's feelings.

[1558] In this way, the system of the present invention solves problems quickly and effectively while taking into account the user's feelings, thereby improving business efficiency and increasing profits.

[1559] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1560] Step 1:

[1561] Data collection

[1562] The server collects employee reports, feedback, and problem-solving proposals from the company's internal systems based on a pre-set schedule. For example, project reports are automatically extracted at the end of each month. The input is the reports, feedback, and problem-solving proposals submitted by employees, and the output is the collected data. The specific collection process involves executing SQL queries using a Python script to obtain the information. A Cron job is used for scheduling.

[1563] Step 2:

[1564] Data Cleansing

[1565] The server cleanses the collected data, removing noise and irrelevant information. This process uses Apache Spark and Pandas to analyze the data and filter out noise and unnecessary information. This scrutinizes the input data and produces filtered data as output. Specifically, it uses regular expressions to extract necessary keywords and phrases.

[1566] Step 3:

[1567] Data storage and tagging

[1568] The server stores the cleansed data in a database and assigns appropriate tags. The input is the cleansed data, and the output is tagged database entries. Specifically, Elasticsearch is used to assign tags such as "project management" and "marketing strategy" to the data. NLP technology is used as the tagging algorithm.

[1569] Step 4:

[1570] Retraining generative AI models

[1571] The server retrains the generative AI model using the stored data every specific period (e.g., every six months). The input is the stored dataset, and the output is the retrained generative AI model. Specifically, TensorFlow or PyTorch is used to retrain the AI ​​model using batch processing on the dataset.

[1572] Step 5:

[1573] Accepting user input

[1574] The terminal provides a chat box-style interface where users can input tasks and questions in natural language. The input is the natural language question or task from the user, and the output is the data that will be sent to the server. Specifically, a front end created with HTML and JavaScript provides the user interface and sends the input to the server in real time.

[1575] Step 6:

[1576] emotion recognition

[1577] The device recognizes emotions from the user's input. The input is the user's text data, and the output is analyzed emotion data. Specifically, it uses NLP models such as BERT and RoBERTa to analyze emotions from the input text.

[1578] Step 7:

[1579] Input and sending emotional data

[1580] The device sends the user's input and emotion data to the server. The input is the user's text data and emotion data, and the output is the data sent to the server. Specifically, the data is sent to the server using an HTTP request and packaged in JSON format.

[1581] Step 8:

[1582] Data analysis and response generation

[1583] The server analyzes the user's input and emotion data and searches for relevant information in the database. The input is the user's question and emotion data, and the output is the generated answer. Specifically, it uses Elasticsearch to search for relevant data and uses a generative AI model (e.g., GPT) to generate the optimal solution.

[1584] Step 9:

[1585] Submitting and viewing generated answers

[1586] The server sends the generated answer to the terminal, which displays it to the user. The input is the answer data from the server, and the output is the display data that the user can visually confirm. The specific operation is to send an HTTP response and display the answer on the front end.

[1587] Specific examples

[1588] In response to a user question such as, "I'm feeling stressed about a recent project. What should I do?", the server receives the input, "I'm feeling stressed about a recent project," and analyzes the emotion as stress. It searches for appropriate stress management methods from a related database and generates "specific stress management methods" using a generative AI model. For example, it presents guidelines such as "Three steps for a successful client proposal," while also including advice such as, "We recommend taking a short break for relaxation and stress management."

[1589] In this way, the system helps users solve problems quickly and effectively while taking their emotions into consideration, improving business efficiency and increasing profits.

[1590] (Application example 2)

[1591] 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."

[1592] Conventional data collection systems lack the ability to filter unnecessary information from collected reports, feedback, and problem-solving proposals, making it difficult to efficiently extract relevant information. Furthermore, there is no system that can recognize user emotions and generate appropriate responses based on them, which hinders the user experience.

[1593] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting reports, feedback, and problem-solving proposals submitted by employees, means for filtering unnecessary information from the collected data, means for storing the filtered data in a database and tagging it, means for retraining the generative AI model using the stored data, means for providing an interface through which a user inputs issues and questions in natural language, means for transmitting the user's input to the server and requesting an answer corresponding to the question, means for searching related information in the database and generating an optimal solution, means for transmitting the generated answer to the user, and means for recognizing the user's emotions and generating an optimal response based on the emotions. This allows for providing an optimal solution that takes emotions into consideration, improving the user experience and business efficiency.

[1594] An "employee" is a staff member employed by a company or organization to perform work.

[1595] A "collection means" is a process or device for collecting specified data.

[1596] A "filtering means" is a process or device used to remove unwanted information from collected data.

[1597] A "database" is a system for efficiently storing, searching, and managing data.

[1598] A "tagging means" is a process or device that assigns a specific tag or label to stored data.

[1599] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information or answers from given data.

[1600] An "interface" is the input and output means by which a user interacts with a system.

[1601] A "server" is a computer system that processes data and provides services over a network.

[1602] A "means for recognizing emotions" is a process or device for analyzing and recognizing emotions from user input.

[1603] A "means for generating a response" is a process or device for generating optimal answers or advice based on input data and emotional information.

[1604] "Delivery staff" are workers who deliver food and other products to customers.

[1605] "Stress" is a state of mental or physical tension or strain.

[1606] A "prompt" is the original text or question that is input into a generative AI model.

[1607] This invention provides a system that automatically collects data such as reports, feedback, and problem-solving proposals submitted by employees and extracts highly relevant information.Furthermore, we provide an example of an application for delivery staff equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on them.

[1608] Server-side implementation

[1609] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. For example, it has a function that automatically collects reports from all staff after the end of each day's work. The collected data is then cleansed on the server for filtering purposes. Noisy data and irrelevant information are removed, and only specific problem-solving methods and success stories are retained. The cleansed data is stored in a database and tagged. This tagging improves search efficiency. The stored data is also used to retrain the generative AI model at regular intervals, so that the latest information is reflected.

[1610] Terminal side embodiment

[1611] Users interact with the system through a smartphone application. The app provides a chat box-style interface where users can input issues or questions in natural language. For example, a user might input a question such as, "I'm feeling stressed while delivering. Please help me." The app is equipped with an emotion engine that recognizes the user's emotions from the input. For example, if a user inputs, "I'm feeling very tired from recent deliveries," the emotion engine will detect stress or fatigue.

[1612] Server Response Generation Embodiments

[1613] The server analyzes the user's input and emotional data and searches for related information in a database. For example, it considers data related to "stress management for delivery" and the user's emotional state. Based on the search results, the server uses a generative AI model to generate the optimal solution. This generation process takes into account past success stories, expert advice, and the user's emotions to generate an answer that includes specific steps to take and important points to note. The generated answer is sent to the user via their device. For example, it provides specific examples such as "Try the following three steps to manage stress..." and also includes advice such as "We also recommend taking deep breaths and short breaks."

[1614] Hardware and Software

[1615] This system uses an advanced data processing system as the server and a relational database management system (RDBMS) as the database. Python and OpenAI AI technologies are used for the emotion recognition and generation AI model. Specifically, TextBlob is used for emotion analysis, and the OpenAI API is used for AI answer generation. The user interface is a smartphone application, and React Native is used as the front-end technology for its construction.

[1616] Prompt Sentence Examples

[1617] User Request: "What do you do when you're tired?"

[1618] Prompt the generative AI model: "How do you manage stress when you're tired?"

[1619] In this way, the system of the present invention increases the usefulness of collected data and provides optimal solutions based on user sentiment, thereby improving operational efficiency and improving the user experience.

[1620] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1621] Step 1:

[1622] The server periodically collects reports, feedback, and problem-solving proposals submitted by delivery staff. The input is the reports and feedback from the delivery staff, which the server collects. The output is a set of collected data, which is passed to the next step.

[1623] Step 2:

[1624] The server filters unnecessary information from the collected data. The inputs are reports and feedback, and the output is relevant data after removing noise data. Specifically, a data cleansing algorithm is applied to remove noise and irrelevant information.

[1625] Step 3:

[1626] The server stores the filtered data in a database and tags it. The input is the filtered data, and the output is tagged database records. Specifically, tags such as "delivery problem" and "customer satisfaction" are automatically assigned to each piece of data.

[1627] Step 4:

[1628] The server periodically retrains the generative AI model using the stored data. The input is the past data stored in the database, and the output is a generative AI model that reflects the latest data. Specifically, the AI ​​training algorithm updates the model using a new data set.

[1629] Step 5:

[1630] The user inputs a problem or question in natural language through the device. The input is a question from the user in natural language, and the output is the content of the question. Specifically, the user inputs a question into the chat box on their smartphone.

[1631] Step 6:

[1632] The terminal sends the user's input to the server and requests an answer according to the question. The input is the user's question data, and the output is the request data sent to the server. Specifically, the chat box interface sends the user's input to the server in real time.

[1633] Step 7:

[1634] The server analyzes the user's input and emotion data and searches for related information in a database. The input is the user's question data and the emotion analysis results, and the output is a collection of related information. Specifically, the text analysis algorithm generates emotion data, and the database query extracts related information.

[1635] Step 8:

[1636] The server uses a generative AI model to generate an optimal solution based on the search results. The input is a collection of related information and emotional data, and the output is the generated solution. Specifically, the generative AI model combines past success stories and expert advice to generate an answer.

[1637] Step 9:

[1638] The server sends the generated answer to the terminal, which then displays the answer to the user. The input is the generated solution, and the output is the answer displayed on the user's smartphone. Specifically, the server sends the generated answer to the terminal, which then displays it to the user.

[1639] Through the above steps, the system of the present invention can efficiently process reports and feedback from delivery staff and provide optimal solutions based on their emotions.

[1640] 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.

[1641] 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.

[1642] 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.

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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).

[1647] 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.

[1648] 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."

[1649] 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.

[1650] 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).

[1651] 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.

[1652] 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.

[1653] 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.

[1654] 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.

[1655] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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.

[1661] The following is further disclosed regarding the above embodiment.

[1662] (Claim 1)

[1663] A means of collecting employee reports, feedback, and problem-solving proposals;

[1664] a means for filtering unwanted information from the collected data;

[1665] a means for storing the filtered data in a database and tagging it;

[1666] a means for retraining the generative AI model using the stored data; and

[1667] means for providing an interface for users to input tasks or questions in natural language;

[1668] means for transmitting user input to a server to request an answer in response to the question;

[1669] a means of searching for relevant information in a database and generating optimal solutions;

[1670] The system includes means for transmitting the generated answer to the user.

[1671] (Claim 2)

[1672] 10. The system of claim 1, wherein the means for cleansing and tagging data includes the ability to automatically remove noisy data and extract only highly relevant information.

[1673] (Claim 3)

[1674] 2. The system of claim 1, wherein the means for generating a solution according to a user's problem or question includes a function for generating an optimal answer based on past success stories and expert advice.

[1675] "Example 1"

[1676] (Claim 1)

[1677] A means of collecting employee reports, feedback, and problem-solving proposals;

[1678] a means of filtering and cleansing unwanted information from the collected data;

[1679] A means of storing the filtered and cleansed data in a database and tagging it appropriately;

[1680] a means for periodically retraining the generative AI model using the stored data; and

[1681] means for providing an interface for users to input tasks or questions in natural language;

[1682] means for transmitting user input to a server to request an answer in response to the question;

[1683] A means of searching for relevant information in the database and generating optimal solutions based on the extracted information;

[1684] The system includes means for transmitting the generated answer to the user.

[1685] (Claim 2)

[1686] 10. The system of claim 1, wherein the means for cleansing and tagging data includes the ability to automatically remove noisy data and extract and tag only highly relevant information.

[1687] (Claim 3)

[1688] The system of claim 1, wherein the means for generating solutions to the user's problems or questions includes a function for generating optimal answers including specific implementation steps and points to note based on past success stories and expert advice.

[1689] "Application Example 1"

[1690] (Claim 1)

[1691] A means of collecting employee reports, feedback, and problem-solving proposals;

[1692] a means for filtering unwanted information from the collected data;

[1693] a means for storing the filtered data in a database and tagging it;

[1694] a means for retraining the generative AI model using the stored data; and

[1695] means for providing an interface for users to input tasks or questions in natural language;

[1696] means for transmitting user input to a server to request an answer in response to the question;

[1697] a means of searching for relevant information in a database and generating optimal solutions;

[1698] A means of providing problem-solving proposals based on collected information, past success stories, and expert advice;

[1699] The system includes means for transmitting the generated answer to the user.

[1700] (Claim 2)

[1701] 10. The system of claim 1, wherein the means for cleansing and tagging data includes the ability to automatically remove noisy data and extract only highly relevant information.

[1702] (Claim 3)

[1703] 2. The system of claim 1, wherein the means for generating a solution according to a user's problem or question includes a function for generating an optimal answer based on past success stories and expert advice.

[1704] "Example 2: Combining Emotion Engines"

[1705] (Claim 1)

[1706] A means of collecting employee reports, feedback, and problem-solving proposals;

[1707] a means for filtering unwanted information from the collected data;

[1708] a means for storing the filtered data in a database and tagging it;

[1709] a means for retraining the generative AI model using the stored data; and

[1710] means for providing an interface for users to input tasks or questions in natural language;

[1711] means for transmitting user input to a server to request an answer in response to the question;

[1712] means for recognizing emotions from user input;

[1713] a means of searching for relevant information in a database and generating optimal solutions;

[1714] The system includes means for transmitting the generated answer to the user.

[1715] (Claim 2)

[1716] 10. The system of claim 1, wherein the means for cleansing and tagging data includes the ability to automatically remove noisy data and extract only highly relevant information.

[1717] (Claim 3)

[1718] The system of claim 1, wherein the means for generating solutions to a user's problems or questions includes a function for generating optimal answers based on past success stories and expert advice, as well as a function for generating answers taking into account the user's emotional state.

[1719] "Application example 2 when combining emotion engines"

[1720] (Claim 1)

[1721] A means of collecting employee reports, feedback, and problem-solving proposals;

[1722] a means for filtering unwanted information from the collected data;

[1723] a means for storing the filtered data in a database and tagging it;

[1724] a means for retraining the generative AI model using the stored data; and

[1725] means for providing an interface for users to input tasks or questions in natural language;

[1726] means for transmitting user input to a server to request an answer in response to the question;

[1727] a means of searching for relevant information in a database and generating optimal solutions;

[1728] means for transmitting the generated answer to the user;

[1729] and means for recognizing a user's emotion and generating an optimal response based on the emotion.

[1730] (Claim 2)

[1731] 10. The system of claim 1, wherein the means for cleansing and tagging data includes the ability to automatically remove noisy data and extract only highly relevant information.

[1732] (Claim 3)

[1733] 2. The system of claim 1, wherein the means for generating a solution according to a user's problem or question includes a function for generating an optimal answer based on past success stories and expert advice. [Explanation of symbols]

[1734] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting employee reports, feedback, and problem-solving proposals; a means for filtering unwanted information from the collected data; a means for storing the filtered data in a database and tagging it; a means for retraining the generative AI model using the stored data; and means for providing an interface for users to input tasks or questions in natural language; means for transmitting user input to a server to request an answer in response to the question; a means of searching for relevant information in a database and generating optimal solutions; The system includes means for transmitting the generated answer to the user.

2. 10. The system of claim 1, wherein the means for cleansing and tagging data includes a function for automatically removing noisy data and extracting only highly relevant information.

3. The system of claim 1 , wherein the means for generating a solution according to a user's problem or question includes a function for generating an optimal answer based on past success stories and expert advice.

Images