system

Abstract

We provide the system. [Solution] Means for collecting data from company-wide databases, file storage, mail servers, and project management tools, A means of cleaning and standardizing the format of the collected data, A method for tokenizing text data using natural language processing techniques and removing meaningless data, A means for sending pre-processed data to an interactive artificial intelligence interface and receiving analysis results, A means of analyzing the results, extracting useful information, and classifying it by category, A system that includes means of providing analysis results to humans.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional business management system, data collection across the entire company and its analysis rely on manual work, which has problems of requiring a great deal of labor and time. In addition, manual analysis involves a risk of human error, making it difficult to overlook important incident factors or take timely and appropriate actions. Furthermore, due to the existence of different data formats and unnecessary information, it has been difficult to perform consistent data analysis. There is a need for a consistent system that solves such problems, efficiently collects and preprocesses company-wide data, and provides analysis results in real time.

Means for Solving the Problems

[0005] To solve the above problems, the following means are provided. The system of the present invention includes means for collecting data from company-wide databases, file storage, mail servers, and project management tools. Furthermore, it includes means for cleaning and standardizing the format of the collected data. It includes means for tokenizing text data using natural language processing technology and removing meaningless data, and means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving the analysis results. Furthermore, the system includes means for analyzing the analysis results, extracting useful information, classifying it by category, and providing this information to humans. This means makes it possible to process and analyze company-wide data quickly and accurately, enabling early detection of critical incident factors and appropriate responses.

[0006] "Data collection means" refers to the technologies and equipment used to extract and collect necessary data from all company-wide databases, file storage, mail servers, and project management tools.

[0007] "Data cleaning methods" refer to the processes and techniques for shaping, normalizing, and standardizing the format of collected data.

[0008] "Natural language processing technology" is a technique that analyzes text data and performs tasks such as tokenization and stop word removal.

[0009] An "interactive artificial intelligence interface" is an interface technology that uses artificial intelligence to analyze input data and return the results.

[0010] "Analysis result extraction means" refers to a technology and apparatus that analyzes analysis results returned by artificial intelligence and extracts useful information.

[0011] "Information provision means" refers to technologies and devices that classify extracted useful information into categories and provide it to users.

[0012] A "stop word" is a word that is frequently removed during analysis and has no meaning in relation to the analysis result (e.g., and, the, etc.).

[0013] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a standard format for representing and structuring data in text format. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

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

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention provides a consistent system for efficiently collecting, preprocessing, and providing real-time analysis results for company-wide data. This system includes the following key modules:

[0036] 1. Data Acquisition Module

[0037] 2. Data Preprocessing Module

[0038] 3. ChatGPT (registered trademark) interface

[0039] 4. Analysis Module

[0040] 5. Output Module

[0041] The specific implementation of each module is as follows:

[0042] Data Acquisition Module

[0043] server

[0044] The server connects to multiple databases, file storage, mail servers, and project management tools throughout the company, and collects data periodically. For example, the server runs a scheduled job every day at 11 PM to extract data such as project progress, bug reports, and email communications via APIs.

[0045] Specific example

[0046] The server retrieves progress reports for all projects from the company's overall business database.

[0047] Data preprocessing module

[0048] server

[0049] The server preprocesses the collected data. This preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[0050] Specific example

[0051] The server analyzes all email data, removes signatures and advertisements, and converts it into clean text.

[0052] ChatGPT interface

[0053] terminal

[0054] The device sends pre-processed data to the ChatGPT API. The API receives the data and performs analysis. The device then saves the analysis results locally. These results include identified issues, proposed solutions, and key incident factors.

[0055] Specific example

[0056] The terminal sends the cleaned project data to ChatGPT and retrieves a list of predicted risk factors.

[0057] Analysis Module

[0058] server

[0059] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders.

[0060] Specific example

[0061] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays.

[0062] Output module

[0063] User

[0064] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[0065] Specific example

[0066] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[0067] Examples

[0068] In a certain software development project, the following processes are performed:

[0069] Data collection

[0070] The server collects task progress data from the project management tool and stores it temporarily.

[0071] Data preprocessing

[0072] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[0073] ChatGPT interface

[0074] The device sends clean data to the ChatGPT API and receives the analysis results.

[0075] analysis

[0076] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[0077] Output

[0078] Users receive reports, recognize significant risks, and take necessary actions.

[0079] In this way, the system collects and analyzes company-wide data in real time and provides users with important information, enabling efficient business management and early detection of problems.

[0080] The following describes the processing flow.

[0081] Step 1:

[0082] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[0083] Step 2:

[0084] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[0085] Step 3:

[0086] The server preprocesses the text data using natural language processing techniques. At this stage, tokenization is performed to remove unnecessary data (such as HTML tags and special characters). High-frequency, meaningless stop words are also removed.

[0087] Step 4:

[0088] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[0089] Step 5:

[0090] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[0091] Step 6:

[0092] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[0093] Step 7:

[0094] The server re-analyzes the saved analysis results and extracts particularly important information. For example, it prioritizes identifying frequently occurring issues and major incident risks.

[0095] Step 8:

[0096] The server organizes the extracted information by category and compiles it into a report. The report clearly outlines the solutions and incident causes.

[0097] Step 9:

[0098] Users receive reports and notifications generated by the server. Users review the report content and provide feedback to the system as needed to improve the accuracy of the data.

[0099] Step 10:

[0100] Users take appropriate action based on the report. For example, if a significant risk is reported, the project manager will immediately add resources to the response team.

[0101] (Example 1)

[0102] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0103] There is a need to efficiently collect information from across the entire company, preprocess and analyze it, and provide useful information to users in real time. Traditional systems require a lot of effort and time from data collection and preprocessing to analysis and output, resulting in a lack of immediacy and accuracy. Furthermore, the varying formats of the collected data make unified processing difficult.

[0104] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0105] In this invention, the server includes means for collecting data from the company-wide information management system, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the preprocessed data to an interactive artificial intelligence interface that works in conjunction with a generating AI model and receiving the analysis results, means for analyzing the analysis results, extracting important information, organizing it by category, and means for providing the analysis results to the user. This enables efficient collection and preprocessing of company-wide data and the provision of useful information in real time.

[0106] An "information management system" is a system that manages and stores data from various sources within an organization, such as databases, file storage, mail servers, and project management tools.

[0107] "Means of data collection" refers to the processes and technologies used to automatically collect data from information management systems.

[0108] "Cleaning" is a procedure to improve the quality of collected data by removing noise and unnecessary information.

[0109] "Methods for standardizing formats" refer to methods for standardizing data with different formats and structures and converting it into a consistent format.

[0110] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0111] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[0112] "Means of removing meaningless data" refers to techniques for removing unnecessary information and noise during the data processing process.

[0113] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate content.

[0114] An "interactive artificial intelligence interface" is an artificial intelligence tool that provides and analyzes information through dialogue with the user.

[0115] "Analysis results" refer to the final output data obtained using generative AI models and other analysis techniques.

[0116] "Methods for organizing by category" refer to techniques for classifying analysis results into specific categories and systematically organizing information.

[0117] "Means of providing to users" refers to methods and systems for providing analysis results in a format that users can use.

[0118] This invention provides a system for efficiently collecting and preprocessing data from a company-wide information management system and providing users with real-time analysis results using a generated AI model. This system includes the following key hardware and software components:

[0119] Data collection

[0120] server

[0121] The server collects data from multiple information management systems (e.g., databases, file storage, mail servers, project management tools).

[0122] For example, the server executes a scheduled job at 11 PM and retrieves project progress data via an API.

[0123] Data preprocessing

[0124] server

[0125] The server cleans and standardizes the format of the collected data.

[0126] Data cleaning involves removing unnecessary information (such as duplicate rows and blank rows).

[0127] We use natural language processing techniques to tokenize text data and remove stop words.

[0128] Analysis using the ChatGPT interface

[0129] terminal

[0130] The device sends pre-processed, clean data to a generative AI model like ChatGPT and receives the analysis results.

[0131] The device sends an API request and saves the analysis results to local storage.

[0132] Summary of analysis results

[0133] server

[0134] The server re-analyzes the results received from ChatGPT, extracts important information, and organizes it by category.

[0135] This information will be reported in a format useful to specific departments or project leaders.

[0136] Output to the user

[0137] User

[0138] Users receive reports and notifications sent from the server.

[0139] Users review the report, identify key risks and issues, and take action as needed.

[0140] User feedback is incorporated into the system, improving data accuracy.

[0141] Examples

[0142] In a certain software development project, the following processes are performed:

[0143] Data collection

[0144] The server collects task progress data from the project management tool and stores it temporarily.

[0145] Data preprocessing

[0146] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[0147] ChatGPT interface

[0148] The device sends clean data to the ChatGPT API and receives the analysis results.

[0149] analysis

[0150] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[0151] Output

[0152] Users receive reports, recognize significant risks, and take necessary actions.

[0153] Example of a prompt

[0154] The following is an example of a prompt message that a terminal sends to the ChatGPT interface:

[0155] Send project data in the following format:

[0156] task:

[0157] 1. In Progress - Implementation of Login Function - John Doe

[0158] 2. Completion - Database Structure Setup - Jane Smith

[0159] bug:

[0160] 101. High - System crash during form submission - Alice

[0161] communication:

[0162] 201. Sprint Planning Q1 - Next Sprint Tasks and Priorities

[0163] Based on this data, identify the risk factors and generate proposed solutions.

[0164] This invention enables efficient collection and preprocessing of company-wide data, as well as the provision of real-time analysis results, thereby facilitating business management and early detection of problems.

[0165] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0166] Step 1: Data Collection

[0167] server

[0168] Processing Overview: The server periodically collects data from the company's entire information management system.

[0169] Input: Data from databases, file storage, mail servers, and project management tools.

[0170] Data processing: Send an API request and retrieve the necessary data.

[0171] Output: Acquired raw data (e.g., project progress data, bug reports, email communications)

[0172] Specific operation: At 11 PM, the server executes a query like "SELECT FROM project_status WHERE date = CURRENT_DATE" to retrieve data from the database and save it in JSON format.

[0173] Step 2: Data preprocessing

[0174] server

[0175] Processing summary: The server cleans and standardizes the format of the collected data.

[0176] Input: Raw data collected in Step 1

[0177] Data processing: Data cleaning, removal of unnecessary rows and duplicate data, formatting standardization, tokenization of text data, removal of stop words.

[0178] Output: Pre-processed clean data

[0179] Specific operation: The server removes stop words such as "the" and "is" from the text data and tokenizes the text into its smallest units. For example, it removes email signatures and advertisements.

[0180] Step 3: Sending data to the generative AI model

[0181] terminal

[0182] Processing Overview: The terminal sends pre-processed data to the generating AI model (ChatGPT) and receives the analysis results.

[0183] Input: Clean data preprocessed in Step 2

[0184] Data processing: Data is sent via API requests and analyzed using a generative AI model.

[0185] Output: Analysis results from the generative AI model

[0186] Specific operation: The terminal sends an API request using "POST / v1 / engines / davinci-codex / completions" and retrieves the analysis results with the prompt "Please identify risk factors".

[0187] Step 4: Organizing the analysis results

[0188] server

[0189] Processing Overview: The server re-analyzes the analysis results received from the generated AI model, extracts important information, and organizes it by category.

[0190] Input: Analysis results obtained in Step 3

[0191] Data processing: Parse the analysis results and organize them by category (e.g., risk factors, solutions, critical incidents).

[0192] Output: Analysis results organized by category

[0193] Specific operation: The server parses the data in JSON format, classifies it into categories such as "critical bug" and "delivery delay risk," and generates a report.

[0194] Step 5: Output to the user

[0195] User

[0196] Processing summary: The user receives reports and notifications sent from the server.

[0197] Input: Analysis results compiled in Step 4

[0198] Data processing: Users review the information and take action as needed.

[0199] Output: Actions and feedback based on the results

[0200] Specific actions: Users receive risk notifications via email or dashboards, confirm a notification stating "Project X's progress is at significant risk," and take appropriate action.

[0201] Through the above processing steps, the system can efficiently collect, preprocess, and analyze company-wide data, and provide critical information in real time.

[0202] (Application Example 1)

[0203] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0204] Logistics centers require efficient operations, and it is crucial to monitor inventory, shipping status, and staff work progress in real time to respond quickly. However, centrally managing this data, analyzing it in real time to extract useful information, and responding quickly to incidents is difficult. Furthermore, properly pre-processing large amounts of data and removing irrelevant data requires considerable effort. Therefore, a consistent system is needed to efficiently collect and analyze data and optimize logistics center operations.

[0205] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0206] This invention includes a server that includes means for collecting data from company-wide databases, file storage, mail servers, and project management tools; means for cleaning and standardizing the format of the collected data; means for tokenizing text data using natural language processing technology and removing meaningless data; means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving analysis results; means for analyzing the analysis results, extracting useful information, and classifying it into categories; means for providing the analysis results to humans; means for collecting data in real time from various sensors and management systems within the logistics center; means for analyzing the collected data in real time, identifying bottlenecks and risk factors, and proposing solutions; and means for notifying important incidents in real time. This optimizes operations within the logistics center and enables efficient data management and rapid problem solving.

[0207] A "database" is a system that systematically stores information and data, making it possible to search and manipulate it.

[0208] "File storage" refers to a storage device or service for storing, accessing, and managing files of various formats.

[0209] A "mail server" is a server that manages the sending and receiving of emails, and is a device that has functions such as email distribution and storage.

[0210] A "project management tool" is software used for planning, executing, and monitoring projects, and provides functions such as task management and progress tracking.

[0211] "Cleaning" is the process of removing unnecessary elements and inaccurate information from data, and is a process to maintain data integrity.

[0212] "Format standardization" is the process of aligning the format and structure of multiple datasets into a consistent format, thereby improving data compatibility.

[0213] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for processing and analyzing text data.

[0214] "Tokenization" is the process of dividing text into units of words or phrases, and it is one of the basic preprocessing steps in natural language processing.

[0215] "Meaningless data" refers to data that is not necessary for the analysis or does not affect the results, and is usually removed before the analysis.

[0216] A "conversational artificial intelligence interface" is a system that interacts with users in a conversational format using artificial intelligence, and provides services such as answering questions and providing analysis results.

[0217] "Analysis results" refer to conclusions and information obtained based on data analysis, provided in a way that is beneficial to the user.

[0218] "Various sensors" are devices that detect the state of the environment or objects and acquire the data, such as devices that measure temperature, humidity, and location.

[0219] A "management system" is software or hardware used to efficiently manage resources and processes within a logistics center or organization.

[0220] "Real-time" refers to a temporal concept that means acquiring information as soon as an event occurs and processing and analyzing it immediately.

[0221] A "bottleneck" refers to an obstacle within a process or system that reduces productivity and efficiency.

[0222] A "risk factor" is an element or condition that could potentially cause problems in a business or process.

[0223] A "solution" is a specific method or means proposed to address a particular problem.

[0224] An "incident" refers to an unexpected event that occurs during normal business processes, and is a problem or obstacle that requires action.

[0225] "Notification" refers to a means of informing a user of a specific event or information, and is carried out in the form of alarms, messages, etc.

[0226] This invention is a system for real-time monitoring and efficient operation in a logistics center. The system is configured as follows:

[0227] System Configuration

[0228] 1. Data Acquisition Module

[0229] Hardware: Various sensors, management systems within the logistics center.

[0230] Processing: The server collects data in real time from various sensors and management systems installed within the logistics center. This includes inventory status, shipping status, and work progress.

[0231] 2. Data Preprocessing Module

[0232] Software: Python, natural language processing technology.

[0233] Processing: The server cleans and standardizes the collected data. It removes meaningless elements from the data and tokenizes the necessary information.

[0234] 3. ChatGPT Interface

[0235] Software: ChatGPT API.

[0236] Processing: Pre-processed data is sent to the ChatGPT API, and the analysis results are received. The server retrieves the analysis results and saves them locally.

[0237] 4. Analysis Module

[0238] Software: Python.

[0239] Processing: The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. It identifies risk factors and bottlenecks and generates solutions.

[0240] 5. Output Module

[0241] Hardware and software: User's smartphone, tablet, and notification applications.

[0242] Processing: Users can receive analysis results in real time. They will be notified immediately if a critical incident occurs.

[0243] Specific example

[0244] For example, if a new shipping bottleneck occurs at a logistics center, the server collects data from various sensors, cleans and preprocesses it in real time. The cleaned data is sent to the ChatGPT API, where analysis results are obtained. From these analysis results, the server identifies the bottleneck and generates a solution. This allows users (e.g., logistics center managers) to receive immediate notification and take appropriate action.

[0245] Example of a prompt

[0246] For example, you can obtain analysis results by sending a prompt message like the following to ChatGPT.

[0247] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[0248] This system efficiently collects data within the logistics center, preprocesses it, and provides the analysis results to the user in real time, thereby enabling efficient operations and rapid problem solving.

[0249] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0250] Step 1:

[0251] The server collects data in real time from various sensors and management systems within the logistics center. Specifically, the server obtains data such as inventory status, shipping status, and work progress via API. This input data consists of raw sensor data and system log data. The collected raw data is temporarily stored.

[0252] Step 2:

[0253] The server cleans and standardizes the collected data. Specifically, it removes unnecessary data and formats the necessary data. For example, it removes noise and errors from text data and standardizes the units of numerical data. The input to this process is the collected raw data, and the output is the cleaned data.

[0254] Step 3:

[0255] The server tokenizes the cleaned data using natural language processing techniques. Specifically, it uses Python's natural language processing library to split the text data into words and phrases and remove unnecessary stop words. The input to this process is the cleaned text data, and the output is tokenized data.

[0256] Step 4:

[0257] The server sends pre-processed data to the ChatGPT API and receives the analysis results. Specifically, the server creates a specific prompt message for the generating AI model and sends it as an API request. The input to this process is tokenized data and the prompt message, and the output is the analysis results returned in JSON format.

[0258] Step 5:

[0259] The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. Specifically, the server identifies specific incidents, risk factors, and solutions from the analysis results and organizes each into the appropriate category. The input for this process is the analysis results from ChatGPT, and the output is organized information.

[0260] Step 6:

[0261] The server provides the user with the analysis results. Specifically, the server sends notifications to the user's smartphone or tablet, informing them of important incidents and solutions in real time. The input for this process is organized information, and the output is a notification issued to the user.

[0262] Prompt statements as concrete examples:

[0263] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[0264] This enables the efficient collection, processing, and analysis of data within the logistics center, allowing for the provision of useful information to users in real time.

[0265] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0266] This invention is a system that combines a user emotion recognition engine with a consistent system that efficiently collects and preprocesses company-wide data and provides analysis results in real time. By reflecting emotion information in the analysis results, it becomes possible to provide more appropriate responses and instructions. This system includes the following main modules:

[0267] 1. Data Acquisition Module

[0268] 2. Data Preprocessing Module

[0269] 3. ChatGPT Interface

[0270] 4. Analysis Module

[0271] 5. Output Module

[0272] 6. Emotional Engine

[0273] The specific implementation of each module is as follows:

[0274] Data Acquisition Module

[0275] server

[0276] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[0277] Specific example

[0278] The server retrieves the progress reports of all projects from the business databases of the entire company.

[0279] Data preprocessing module

[0280] Server

[0281] The server preprocesses the collected data. This preprocessing includes data cleaning, format unification, tokenization of text data, and removal of unnecessary data. Using natural language processing techniques, mainly stop word removal and text normalization are performed.

[0282] Specific example

[0283] >

[0284] The server analyzes all email data, removes the signature and advertisement parts, and converts it into clean text.

[0285] ChatGPT interface

[0286] Terminal

[0287] The terminal converts the preprocessed data into a format acceptable to the interactive artificial intelligence interface, such as JSON format. Also, the terminal sends this converted data to the ChatGPT API to obtain the analysis results.

[0288] Specific example

[0289] The terminal sends the cleaned project data to ChatGPT to obtain a list of predicted risk factors.

[0290] Analysis module

[0291] Server

[0292] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders. This module also receives input from the emotion engine to adjust the priority of the analysis results.

[0293] Specific example

[0294] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays. It also adjusts priorities based on the project manager's sentiment data.

[0295] Output module

[0296] User

[0297] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[0298] Specific example

[0299] >

[0300] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[0301] Emotional Engine

[0302] terminal

[0303] The device analyzes the user's emotions from their voice and text data and retrieves that emotional information. The emotion engine sends the emotional analysis results to a server, which is then used to refine the analysis results.

[0304] Specific example

[0305] When the terminal analyzes the speech data of the project manager and determines that the stress level is high, it sends that information to the server.

[0306] Example

[0307] In a certain software development project, the following processes are carried out.

[0308] Data collection

[0309] The server collects the task progress status from the project management tool and temporarily stores it.

[0310] Data preprocessing

[0311] The server cleans the collected data and unifies the format. For example, it deletes useless lines and duplicate data.

[0312] ChatGPT interface

[0313] The terminal sends the clean data to the ChatGPT API and receives the analysis results.

[0314] Analysis

[0315] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report. Furthermore, it adjusts the priority of the analysis results based on the input from the sentiment engine.

[0316] Output

[0317] The user receives the report, recognizes important risks, and takes necessary countermeasures.

[0318] Sentiment engine

[0319] The device analyzes the user's emotions, sends that information to the server, and uses it to adjust the analysis results.

[0320] In this way, the system collects and analyzes company-wide data in real time, and provides users with important information that also takes into account their emotions, thereby enabling efficient business management and early detection of problems.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[0324] Step 2:

[0325] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[0326] Step 3:

[0327] The server preprocesses the text data using natural language processing techniques. It tokenizes the data, removes HTML tags and special characters, and eliminates frequent, meaningless stop words.

[0328] Step 4:

[0329] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[0330] Step 5:

[0331] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[0332] Step 6:

[0333] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[0334] Step 7:

[0335] The server receives input from the emotion engine and analyzes the user's emotions. For example, it analyzes the user's voice and text data to extract emotions such as anger, stress, and satisfaction.

[0336] Step 8:

[0337] The server adjusts the priority of analysis results received from ChatGPT based on emotional information from the emotion engine. For example, if the stress level is high, risk factors will be given a higher priority.

[0338] Step 9:

[0339] The server classifies the final analysis results, organizes them into categories such as issues, solutions, and incident factors, and compiles them into a report format. The report is provided in a format useful for specific departments or project leaders.

[0340] Step 10:

[0341] Users receive reports and notifications generated by the server and review their contents. Based on the reports, users take appropriate action and provide feedback to the system as needed to improve the accuracy of the data.

[0342] (Specific example)

[0343] Step 1: The server collects data from the project management tool at 11 PM and stores it temporarily.

[0344] Step 2: The server removes duplicate data and standardizes the text format.

[0345] Step 3: The server uses natural language processing techniques to tokenize the text data and remove stop words.

[0346] Step 4: The terminal converts the pre-processed data into JSON format.

[0347] Step 5: The device sends data in JSON format to the ChatGPT API and retrieves the analysis results.

[0348] Step 6: The device saves the analysis results from ChatGPT to local storage.

[0349] Step 7: The server analyzes the user's emotional data using an emotion engine and evaluates the emotional level.

[0350] Step 8: The server analyzes the sentiment information and adjusts the priority of the analysis results.

[0351] Step 9: The server classifies the final analysis results and compiles them into a report.

[0352] Step 10: The user receives the report, reviews its contents, and takes necessary actions.

[0353] This processing flow allows the system to collect and analyze company-wide data in real time, and provide information that takes user sentiment into consideration, thereby enabling efficient business management and early problem detection.

[0354] (Example 2)

[0355] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0356] In today's business environment, vast amounts of information are generated from numerous data sources, and there is a need to efficiently and effectively collect, organize, and analyze this data. However, conventional systems require a great deal of time and effort for data collection, cleaning, and analysis, making rapid decision-making difficult. Furthermore, while considering user sentiment information would enable more appropriate responses, this aspect is also not adequately addressed.

[0357] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data from company-wide data storage, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving the analysis results, means for extracting and classifying useful information from the analysis results, means for providing information based on the analysis results to humans, and means for analyzing emotional information from the user's text data and voice data and using that emotional information to adjust the analysis results. This makes it possible to collect and analyze company-wide data in real time and to quickly provide countermeasures that also take into account the user's emotional information.

[0358] "Data storage" refers to a storage device used to permanently store information.

[0359] "Cleaning" is a process that removes noise and unnecessary parts from data to improve its reliability.

[0360] "Standardizing the format" means converting collected data into a consistent format.

[0361] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0362] "Tokenization" is the process of dividing text data into semantic units such as words and phrases.

[0363] "Meaningless data" refers to information or noise that is not useful in analysis.

[0364] A "conversational artificial intelligence interface" is an interface that utilizes AI technology to engage in natural conversations with users.

[0365] "Analysis results" refer to useful information obtained by analyzing data.

[0366] "Emotional information" refers to data that indicates the emotional state of a user or other target.

[0367] "Adjustment" refers to modifying or optimizing analysis results or processes according to specific objectives.

[0368] A "user" refers to an individual or department that uses this system to obtain information and make decisions.

[0369] This invention provides a system for efficiently collecting, preprocessing, and analyzing company-wide data. This system consists of a data collection module, a data preprocessing module, an interactive artificial intelligence interface, an analysis module, an output module, and an emotion engine.

[0370] Data Acquisition Module

[0371] server

[0372] The server connects to company-wide data storage, file storage, mail servers, and project management tools, and periodically collects data. For example, the server runs scheduled jobs every day at 11 p.m. to retrieve project progress reports from the database, download the latest documents from file storage, and collect unread emails from the mail server.

[0373] Specific example

[0374] The server sends queries to the company-wide business database and retrieves progress reports. It downloads the latest documents from file storage and collects all unread emails from the mail server.

[0375] Data preprocessing module

[0376] server

[0377] The server preprocesses the collected data. Preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[0378] Specific example

[0379] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[0380] Interactive artificial intelligence interface

[0381] terminal

[0382] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[0383] Specific example

[0384] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[0385] Analysis Module

[0386] server

[0387] The server analyzes the results received from ChatGPT and extracts particularly important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[0388] Specific example

[0389] The server analyzes the results from ChatGPT using text mining techniques to extract critical bug reports and risk factors. It then cross-references this with project managers' sentiment data and prioritizes the risk items.

[0390] Output module

[0391] User

[0392] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[0393] Specific example

[0394] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[0395] Emotional Engine

[0396] terminal

[0397] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[0398] Specific example

[0399] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[0400] Examples of prompts for generative AI models

[0401] "You are a project management AI assistant. Analyze the following project data and list the predicted risk factors and their solutions: {Project Data}. Also, consider {Sentiment Data} as user sentiment data."

[0402] In this way, the system collects and analyzes company-wide data in real time, and provides important information while also considering user sentiment, thereby enabling efficient business management and early problem detection.

[0403] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0404] Step 1: Data Collection

[0405] server

[0406] The server connects to the company's data storage, file storage, mail server, and project management tools, and periodically collects data. This process integrates data from each data source and stores it as a single dataset.

[0407] Inputs: Data storage, file storage, mail servers, project management tools

[0408] Data processing: Send queries to retrieve data and save it to storage.

[0409] Output: Collected raw data

[0410] Specific actions

[0411] The server retrieves project progress reports from the database, downloads the latest documents from file storage, and collects unread emails from the mail server.

[0412] Step 2: Data Preprocessing

[0413] server

[0414] The server preprocesses the collected data. This step involves cleaning the data, standardizing its format, tokenizing text data, and removing unnecessary data. Natural language processing techniques are used, particularly for stop word removal and text normalization.

[0415] Input: Collected raw data

[0416] Data processing: Data cleaning, formatting standardization, text tokenization, removal of unnecessary data.

[0417] Output: Preprocessed data

[0418] Specific actions

[0419] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[0420] Step 3: Data conversion and transmission

[0421] terminal

[0422] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[0423] Input: Preprocessed data

[0424] Data processing: Formatting data into JSON format.

[0425] Output: JSON data sent to ChatGPT

[0426] Specific actions

[0427] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[0428] Step 4: Analysis

[0429] server

[0430] The server analyzes the results received from ChatGPT and extracts important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[0431] Input: ChatGPT analysis results

[0432] Data processing: Extraction of key information, categorization of information, prioritization using sentiment data.

[0433] Output: Classified important information

[0434] Specific actions

[0435] The server analyzes the results from ChatGPT and extracts critical bug reports and risk factors. It then cross-references the project manager's sentiment data and prioritizes the risk items.

[0436] Step 5: Report generation and notification

[0437] User

[0438] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[0439] Input: Classified important information

[0440] Data processing: Report generation, notification distribution

[0441] Output: Reports to users, real-time notifications

[0442] Specific actions

[0443] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[0444] Step 6: Sentiment Analysis

[0445] terminal

[0446] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[0447] Input: User voice data and text data

[0448] Data processing: Sentiment analysis, generation of sentiment data

[0449] Output: Sending emotion data to the server

[0450] Specific actions

[0451] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[0452] (Application Example 2)

[0453] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0454] In modern industrial facilities, optimizing production efficiency and early problem detection are crucial. However, conventional systems suffer from the time-consuming nature of data collection and analysis, making real-time analysis, including emotional data, difficult. Furthermore, analysis results that consider workers' emotions are often not provided, leading to overlooking declines in production efficiency due to stress and fatigue. To address these challenges, there is a need for systems that enable real-time data analysis and the integration of emotional data.

[0455] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0456] In this invention, the server includes means for collecting data from sensors and equipment in industrial facilities, means for collecting worker voice data using a voice recognition device, means for transmitting pre-processed data to an interactive artificial intelligence interface and receiving analysis results on production efficiency, potential problems, and risk factors, means for analyzing emotions from voice data and adjusting the priority of analysis results based on emotion data, and means for integrating analysis results and emotion data and providing them to workers and managers in real time. This enables maximizing production efficiency and early detection of problems.

[0457] A "sensor" is a device that detects environmental information and the status of equipment within an industrial facility and outputs it as data.

[0458] A "voice recognition device" is a device that records the voice of a worker and converts that voice into text data.

[0459] "Data collection" refers to the act of obtaining necessary data from all company-wide databases, file storage, mail servers, and project management tools.

[0460] "Data cleaning" is the process of removing meaningless parts and noise from collected data and standardizing the data format.

[0461] "Natural language processing technology" is a technique for analyzing text data and extracting meaningful information from it.

[0462] "Tokenization" is the process of dividing text data into words or phrases.

[0463] A "conversational artificial intelligence interface" is an artificial intelligence system designed to enable natural dialogue with humans, and typically sends and receives data via an API.

[0464] "Analysis results" refer to the output of data analysis obtained through artificial intelligence systems or other analytical means.

[0465] "Emotion analysis" is the process of identifying emotions from audio or text data and evaluating those emotional states.

[0466] "Priority adjustment" is the process of re-evaluating the importance and urgency of the analysis results and changing the order and content of the information provided.

[0467] "Real-time delivery" refers to providing collected data and analysis results immediately without delay.

[0468] This invention is a system that collects and analyzes company-wide data in real time at industrial facilities and provides information with prioritized based on worker sentiment. The system includes the following main modules:

[0469] First, the server collects data from various sensors and equipment within the industrial facility. This includes data such as temperature, humidity, and machine operation logs. It also collects voice data from workers using voice recognition devices.

[0470] Next, the collected data is cleaned and standardized by the server. Audio data is converted to a transcript and noise is removed.

[0471] The pre-processed data is sent from the server to an interactive artificial intelligence interface, specifically the ChatGPT API. ChatGPT analyzes the data and provides analysis results regarding optimization of production efficiency, potential problems, and risk factors.

[0472] Furthermore, the server uses an emotion analysis engine to analyze the worker's emotions from their voice and text data. Based on this emotion data, the priority of the analysis results is adjusted. For example, if a worker's stress level is high, that information is given more weight when proposing countermeasures.

[0473] Analysis results and sentiment data are integrated by a server and provided to workers and managers in real time. This allows for immediate recognition of important information and risk factors, enabling prompt and appropriate countermeasures to be taken.

[0474] As a concrete example, the following prompt message can be provided to ChatGPT to analyze the efficiency and risk factors of the production line:

[0475] Please analyze the machine operation data from the production line within the factory and the voice data of the factory workers, and provide the following information:

[0476] 1. Advice on maximizing production line efficiency.

[0477] 2. Potential problems and risk factors.

[0478] 3. Appropriate measures based on the stress and fatigue levels of workers.

[0479] Implementing this system requires sensors within the factory, voice recognition devices, the ChatGPT API, and an emotion analysis engine. Combining these elements will enable maximizing factory production efficiency and early detection of problems.

[0480] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0481] Step 1:

[0482] The server collects data from various sensors and equipment in industrial facilities. Specifically, it acquires temperature data from temperature sensors, operating status data from motion sensors, and worker voice data using a voice recognition device. The input data consists of temperature, operating status, and voice data, which are temporarily stored within the system. The output is an aggregate of unprocessed raw data.

[0483] Step 2:

[0484] The server cleans and standardizes the collected data. First, audio data is converted to text transcripts to remove noise and unnecessary information. Next, meaningless data is removed from temperature and operating status data, and the data format is standardized to a consistent format. The input data is raw data, and the output is cleaned and well-formed data.

[0485] Step 3:

[0486] The server sends cleaned data to the ChatGPT API. The server converts this data to JSON format and sends a request to the API to receive analysis results regarding production efficiency and risk factors. The input data is cleaned, unified data, and the output is the analysis results from ChatGPT.

[0487] Step 4:

[0488] The server uses an emotion analysis engine to analyze the worker's emotions from their voice data. Specifically, it determines stress levels and fatigue levels from the tone and content of the voice, and sends the results to the server as numerical data. The input data is a voice transcript, and the output is the emotion analysis result.

[0489] Step 5:

[0490] The server integrates the analysis results received from ChatGPT with sentiment data obtained from the sentiment analysis engine. Based on the sentiment data, it adjusts the priority of the analysis results and re-evaluates the severity of the problem and the urgency of countermeasures. The input data consists of analysis results and sentiment data, and the output is the adjusted analysis results.

[0491] Step 6:

[0492] The server provides the adjusted analysis results to workers and administrators in real time. Specifically, it displays important notifications and alerts on smart glasses or terminal displays. The input data is the adjusted analysis results, and the output is real-time notifications and alerts.

[0493] Step 7:

[0494] The user receives information from the system and provides feedback as needed. This feedback is sent to the server and incorporated into subsequent analyses. The input data is user feedback, and the output is an improvement in the system's performance.

[0495] These steps enable the optimization of production efficiency within industrial facilities, early detection of problems, and appropriate responses based on the emotional state of workers.

[0496] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0497] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0498] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0499] [Second Embodiment]

[0500] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0501] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0502] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0503] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0504] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0505] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0506] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0507] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0508] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0509] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0510] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0511] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0512] This invention provides a consistent system for efficiently collecting, preprocessing, and providing real-time analysis results for company-wide data. This system includes the following key modules:

[0513] 1. Data Acquisition Module

[0514] 2. Data Preprocessing Module

[0515] 3. ChatGPT Interface

[0516] 4. Analysis Module

[0517] 5. Output Module

[0518] The specific implementation of each module is as follows:

[0519] Data Acquisition Module

[0520] server

[0521] The server connects to multiple databases, file storage, mail servers, and project management tools throughout the company, and collects data periodically. For example, the server runs a scheduled job every day at 11 PM to extract data such as project progress, bug reports, and email communications via APIs.

[0522] Specific example

[0523] The server retrieves progress reports for all projects from the company's overall business database.

[0524] Data preprocessing module

[0525] server

[0526] The server preprocesses the collected data. This preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[0527] Specific example

[0528] The server analyzes all email data, removes signatures and advertisements, and converts it into clean text.

[0529] ChatGPT interface

[0530] terminal

[0531] The device sends pre-processed data to the ChatGPT API. The API receives the data and performs analysis. The device then saves the analysis results locally. These results include identified issues, proposed solutions, and key incident factors.

[0532] Specific example

[0533] The terminal sends the cleaned project data to ChatGPT and retrieves a list of predicted risk factors.

[0534] Analysis Module

[0535] server

[0536] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders.

[0537] Specific example

[0538] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays.

[0539] Output module

[0540] User

[0541] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[0542] Specific example

[0543] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[0544] Examples

[0545] In a certain software development project, the following processes are performed:

[0546] Data collection

[0547] The server collects task progress data from the project management tool and stores it temporarily.

[0548] Data preprocessing

[0549] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[0550] ChatGPT interface

[0551] The device sends clean data to the ChatGPT API and receives the analysis results.

[0552] analysis

[0553] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[0554] Output

[0555] Users receive reports, recognize significant risks, and take necessary actions.

[0556] In this way, the system collects and analyzes company-wide data in real time and provides users with important information, enabling efficient business management and early detection of problems.

[0557] The following describes the processing flow.

[0558] Step 1:

[0559] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[0560] Step 2:

[0561] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[0562] Step 3:

[0563] The server preprocesses the text data using natural language processing techniques. At this stage, tokenization is performed to remove unnecessary data (such as HTML tags and special characters). High-frequency, meaningless stop words are also removed.

[0564] Step 4:

[0565] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[0566] Step 5:

[0567] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[0568] Step 6:

[0569] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[0570] Step 7:

[0571] The server re-analyzes the saved analysis results and extracts particularly important information. For example, it prioritizes identifying frequently occurring issues and major incident risks.

[0572] Step 8:

[0573] The server organizes the extracted information by category and compiles it into a report. The report clearly outlines the solutions and incident causes.

[0574] Step 9:

[0575] Users receive reports and notifications generated by the server. Users review the report content and provide feedback to the system as needed to improve the accuracy of the data.

[0576] Step 10:

[0577] Users take appropriate action based on the report. For example, if a significant risk is reported, the project manager will immediately add resources to the response team.

[0578] (Example 1)

[0579] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0580] There is a need to efficiently collect information from across the entire company, preprocess and analyze it, and provide useful information to users in real time. Traditional systems require a lot of effort and time from data collection and preprocessing to analysis and output, resulting in a lack of immediacy and accuracy. Furthermore, the varying formats of the collected data make unified processing difficult.

[0581] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0582] In this invention, the server includes means for collecting data from the company-wide information management system, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the preprocessed data to an interactive artificial intelligence interface that works in conjunction with a generating AI model and receiving the analysis results, means for analyzing the analysis results, extracting important information, organizing it by category, and means for providing the analysis results to the user. This enables efficient collection and preprocessing of company-wide data and the provision of useful information in real time.

[0583] An "information management system" is a system that manages and stores data from various sources within an organization, such as databases, file storage, mail servers, and project management tools.

[0584] "Means of data collection" refers to the processes and technologies used to automatically collect data from information management systems.

[0585] "Cleaning" is a procedure to improve the quality of collected data by removing noise and unnecessary information.

[0586] "Methods for standardizing formats" refer to methods for standardizing data with different formats and structures and converting it into a consistent format.

[0587] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0588] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[0589] "Means of removing meaningless data" refers to techniques for removing unnecessary information and noise during the data processing process.

[0590] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate content.

[0591] An "interactive artificial intelligence interface" is an artificial intelligence tool that provides and analyzes information through dialogue with the user.

[0592] "Analysis results" refer to the final output data obtained using generative AI models and other analysis techniques.

[0593] "Methods for organizing by category" refer to techniques for classifying analysis results into specific categories and systematically organizing information.

[0594] "Means of providing to users" refers to methods and systems for providing analysis results in a format that users can use.

[0595] This invention provides a system for efficiently collecting and preprocessing data from a company-wide information management system and providing users with real-time analysis results using a generated AI model. This system includes the following key hardware and software components:

[0596] Data collection

[0597] server

[0598] The server collects data from multiple information management systems (e.g., databases, file storage, mail servers, project management tools).

[0599] For example, the server executes a scheduled job at 11 PM and retrieves project progress data via an API.

[0600] Data preprocessing

[0601] server

[0602] The server cleans and standardizes the format of the collected data.

[0603] Data cleaning involves removing unnecessary information (such as duplicate rows and blank rows).

[0604] We use natural language processing techniques to tokenize text data and remove stop words.

[0605] Analysis using the ChatGPT interface

[0606] terminal

[0607] The device sends pre-processed, clean data to a generative AI model like ChatGPT and receives the analysis results.

[0608] The device sends an API request and saves the analysis results to local storage.

[0609] Summary of analysis results

[0610] server

[0611] The server re-analyzes the results received from ChatGPT, extracts important information, and organizes it by category.

[0612] This information will be reported in a format useful to specific departments or project leaders.

[0613] Output to the user

[0614] User

[0615] Users receive reports and notifications sent from the server.

[0616] Users review the report, identify key risks and issues, and take action as needed.

[0617] User feedback is incorporated into the system, improving data accuracy.

[0618] Examples

[0619] In a certain software development project, the following processes are performed:

[0620] Data collection

[0621] The server collects task progress data from the project management tool and stores it temporarily.

[0622] Data preprocessing

[0623] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[0624] ChatGPT interface

[0625] The device sends clean data to the ChatGPT API and receives the analysis results.

[0626] analysis

[0627] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[0628] Output

[0629] Users receive reports, recognize significant risks, and take necessary actions.

[0630] Example of a prompt

[0631] The following is an example of a prompt message that a terminal sends to the ChatGPT interface:

[0632] Send project data in the following format:

[0633] task:

[0634] 1. In Progress - Implementation of Login Function - John Doe

[0635] 2. Completion - Database Structure Setup - Jane Smith

[0636] bug:

[0637] 101. High - System crash during form submission - Alice

[0638] communication:

[0639] 201. Sprint Planning Q1 - Next Sprint Tasks and Priorities

[0640] Based on this data, identify the risk factors and generate proposed solutions.

[0641] This invention enables efficient collection and preprocessing of company-wide data, as well as the provision of real-time analysis results, thereby facilitating business management and early detection of problems.

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1: Data Collection

[0644] server

[0645] Processing Overview: The server periodically collects data from the company's entire information management system.

[0646] Input: Data from databases, file storage, mail servers, and project management tools.

[0647] Data processing: Send an API request and retrieve the necessary data.

[0648] Output: Acquired raw data (e.g., project progress data, bug reports, email communications)

[0649] Specific operation: At 11 PM, the server executes a query like "SELECT FROM project_status WHERE date = CURRENT_DATE" to retrieve data from the database and save it in JSON format.

[0650] Step 2: Data preprocessing

[0651] server

[0652] Processing summary: The server cleans and standardizes the format of the collected data.

[0653] Input: Raw data collected in Step 1

[0654] Data processing: Data cleaning, removal of unnecessary rows and duplicate data, formatting standardization, tokenization of text data, removal of stop words.

[0655] Output: Pre-processed clean data

[0656] Specific operation: The server removes stop words such as "the" and "is" from the text data and tokenizes the text into its smallest units. For example, it removes email signatures and advertisements.

[0657] Step 3: Sending data to the generative AI model

[0658] terminal

[0659] Processing Overview: The terminal sends pre-processed data to the generating AI model (ChatGPT) and receives the analysis results.

[0660] Input: Clean data preprocessed in Step 2

[0661] Data processing: Data is sent via API requests and analyzed using a generative AI model.

[0662] Output: Analysis results from the generative AI model

[0663] Specific operation: The terminal sends an API request using "POST / v1 / engines / davinci-codex / completions" and retrieves the analysis results with the prompt "Please identify risk factors".

[0664] Step 4: Organizing the analysis results

[0665] server

[0666] Processing Overview: The server re-analyzes the analysis results received from the generated AI model, extracts important information, and organizes it by category.

[0667] Input: Analysis results obtained in Step 3

[0668] Data processing: Parse the analysis results and organize them by category (e.g., risk factors, solutions, critical incidents).

[0669] Output: Analysis results organized by category

[0670] Specific operation: The server parses the data in JSON format, classifies it into categories such as "critical bug" and "delivery delay risk," and generates a report.

[0671] Step 5: Output to the user

[0672] User

[0673] Processing summary: The user receives reports and notifications sent from the server.

[0674] Input: Analysis results compiled in Step 4

[0675] Data processing: Users review the information and take action as needed.

[0676] Output: Actions and feedback based on the results

[0677] Specific actions: Users receive risk notifications via email or dashboards, confirm a notification stating "Project X's progress is at significant risk," and take appropriate action.

[0678] Through the above processing steps, the system can efficiently collect, preprocess, and analyze company-wide data, and provide critical information in real time.

[0679] (Application Example 1)

[0680] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0681] Logistics centers require efficient operations, and it is crucial to monitor inventory, shipping status, and staff work progress in real time to respond quickly. However, centrally managing this data, analyzing it in real time to extract useful information, and responding quickly to incidents is difficult. Furthermore, properly pre-processing large amounts of data and removing irrelevant data requires considerable effort. Therefore, a consistent system is needed to efficiently collect and analyze data and optimize logistics center operations.

[0682] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0683] This invention includes a server that includes means for collecting data from company-wide databases, file storage, mail servers, and project management tools; means for cleaning and standardizing the format of the collected data; means for tokenizing text data using natural language processing technology and removing meaningless data; means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving analysis results; means for analyzing the analysis results, extracting useful information, and classifying it into categories; means for providing the analysis results to humans; means for collecting data in real time from various sensors and management systems within the logistics center; means for analyzing the collected data in real time, identifying bottlenecks and risk factors, and proposing solutions; and means for notifying important incidents in real time. This optimizes operations within the logistics center and enables efficient data management and rapid problem solving.

[0684] A "database" is a system that systematically stores information and data, making it possible to search and manipulate it.

[0685] "File storage" refers to a storage device or service for storing, accessing, and managing files of various formats.

[0686] A "mail server" is a server that manages the sending and receiving of emails, and is a device that has functions such as email distribution and storage.

[0687] A "project management tool" is software used for planning, executing, and monitoring projects, and provides functions such as task management and progress tracking.

[0688] "Cleaning" is the process of removing unnecessary elements and inaccurate information from data, and is a process to maintain data integrity.

[0689] "Format standardization" is the process of aligning the format and structure of multiple datasets into a consistent format, thereby improving data compatibility.

[0690] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for processing and analyzing text data.

[0691] "Tokenization" is the process of dividing text into units of words or phrases, and it is one of the basic preprocessing steps in natural language processing.

[0692] "Meaningless data" refers to data that is not necessary for the analysis or does not affect the results, and is usually removed before the analysis.

[0693] A "conversational artificial intelligence interface" is a system that interacts with users in a conversational format using artificial intelligence, and provides services such as answering questions and providing analysis results.

[0694] "Analysis results" refer to conclusions and information obtained based on data analysis, provided in a way that is beneficial to the user.

[0695] "Various sensors" are devices that detect the state of the environment or objects and acquire the data, such as devices that measure temperature, humidity, and location.

[0696] A "management system" is software or hardware used to efficiently manage resources and processes within a logistics center or organization.

[0697] "Real-time" refers to a temporal concept that means acquiring information as soon as an event occurs and processing and analyzing it immediately.

[0698] A "bottleneck" refers to an obstacle within a process or system that reduces productivity and efficiency.

[0699] A "risk factor" is an element or condition that could potentially cause problems in a business or process.

[0700] A "solution" is a specific method or means proposed to address a particular problem.

[0701] An "incident" refers to an unexpected event that occurs during normal business processes, and is a problem or obstacle that requires action.

[0702] "Notification" refers to a means of informing a user of a specific event or information, and is carried out in the form of alarms, messages, etc.

[0703] This invention is a system for real-time monitoring and efficient operation in a logistics center. The system is configured as follows:

[0704] System Configuration

[0705] 1. Data Acquisition Module

[0706] Hardware: Various sensors, management systems within the logistics center.

[0707] Processing: The server collects data in real time from various sensors and management systems installed within the logistics center. This includes inventory status, shipping status, and work progress.

[0708] 2. Data Preprocessing Module

[0709] Software: Python, natural language processing technology.

[0710] Processing: The server cleans and standardizes the collected data. It removes meaningless elements from the data and tokenizes the necessary information.

[0711] 3. ChatGPT Interface

[0712] Software: ChatGPT API.

[0713] Processing: Pre-processed data is sent to the ChatGPT API, and the analysis results are received. The server retrieves the analysis results and saves them locally.

[0714] 4. Analysis Module

[0715] Software: Python.

[0716] Processing: The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. It identifies risk factors and bottlenecks and generates solutions.

[0717] 5. Output Module

[0718] Hardware and software: User's smartphone, tablet, and notification applications.

[0719] Processing: Users can receive analysis results in real time. They will be notified immediately if a critical incident occurs.

[0720] Specific example

[0721] For example, if a new shipping bottleneck occurs at a logistics center, the server collects data from various sensors, cleans and preprocesses it in real time. The cleaned data is sent to the ChatGPT API, where analysis results are obtained. From these analysis results, the server identifies the bottleneck and generates a solution. This allows users (e.g., logistics center managers) to receive immediate notification and take appropriate action.

[0722] Example of a prompt

[0723] For example, you can obtain analysis results by sending a prompt message like the following to ChatGPT.

[0724] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[0725] This system efficiently collects data within the logistics center, preprocesses it, and provides the analysis results to the user in real time, thereby enabling efficient operations and rapid problem solving.

[0726] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0727] Step 1:

[0728] The server collects data in real time from various sensors and management systems within the logistics center. Specifically, the server obtains data such as inventory status, shipping status, and work progress via API. This input data consists of raw sensor data and system log data. The collected raw data is temporarily stored.

[0729] Step 2:

[0730] The server cleans and standardizes the collected data. Specifically, it removes unnecessary data and formats the necessary data. For example, it removes noise and errors from text data and standardizes the units of numerical data. The input to this process is the collected raw data, and the output is the cleaned data.

[0731] Step 3:

[0732] The server tokenizes the cleaned data using natural language processing techniques. Specifically, it uses Python's natural language processing library to split the text data into words and phrases and remove unnecessary stop words. The input to this process is the cleaned text data, and the output is tokenized data.

[0733] Step 4:

[0734] The server sends pre-processed data to the ChatGPT API and receives the analysis results. Specifically, the server creates a specific prompt message for the generating AI model and sends it as an API request. The input to this process is tokenized data and the prompt message, and the output is the analysis results returned in JSON format.

[0735] Step 5:

[0736] The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. Specifically, the server identifies specific incidents, risk factors, and solutions from the analysis results and organizes each into the appropriate category. The input for this process is the analysis results from ChatGPT, and the output is organized information.

[0737] Step 6:

[0738] The server provides the user with the analysis results. Specifically, the server sends notifications to the user's smartphone or tablet, informing them of important incidents and solutions in real time. The input for this process is organized information, and the output is a notification issued to the user.

[0739] Prompt statements as concrete examples:

[0740] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[0741] This enables the efficient collection, processing, and analysis of data within the logistics center, allowing for the provision of useful information to users in real time.

[0742] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0743] This invention is a system that combines a user emotion recognition engine with a consistent system that efficiently collects and preprocesses company-wide data and provides analysis results in real time. By reflecting emotion information in the analysis results, it becomes possible to provide more appropriate responses and instructions. This system includes the following main modules:

[0744] 1. Data Acquisition Module

[0745] 2. Data Preprocessing Module

[0746] 3. ChatGPT Interface

[0747] 4. Analysis Module

[0748] 5. Output Module

[0749] 6. Emotional Engine

[0750] The specific implementation of each module is as follows:

[0751] Data Acquisition Module

[0752] server

[0753] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[0754] Specific example

[0755] The server retrieves progress reports for all projects from the company's overall business database.

[0756] Data preprocessing module

[0757] server

[0758] The server preprocesses the collected data. This preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[0759] Specific example

[0760] >

[0761] The server analyzes all email data, removes signatures and advertisements, and converts it into clean text.

[0762] ChatGPT interface

[0763] terminal

[0764] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON. The terminal then sends this converted data to the ChatGPT API to obtain the analysis results.

[0765] Specific example

[0766] The terminal sends the cleaned project data to ChatGPT and retrieves a list of predicted risk factors.

[0767] Analysis Module

[0768] server

[0769] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders. This module also receives input from the emotion engine to adjust the priority of the analysis results.

[0770] Specific example

[0771] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays. It also adjusts priorities based on the project manager's sentiment data.

[0772] Output module

[0773] User

[0774] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[0775] Specific example

[0776] >

[0777] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[0778] Emotional Engine

[0779] terminal

[0780] The device analyzes the user's emotions from their voice and text data and retrieves that emotional information. The emotion engine sends the emotional analysis results to a server, which is then used to refine the analysis results.

[0781] Specific example

[0782] The terminal analyzes the project manager's communication data and, if it determines that the stress level is high, sends that information to the server.

[0783] Examples

[0784] In a certain software development project, the following processes are performed:

[0785] Data collection

[0786] The server collects task progress data from the project management tool and stores it temporarily.

[0787] Data preprocessing

[0788] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[0789] ChatGPT interface

[0790] The device sends clean data to the ChatGPT API and receives the analysis results.

[0791] analysis

[0792] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report. Furthermore, it adjusts the priority of the analysis results based on input from the sentiment engine.

[0793] Output

[0794] Users receive reports, recognize significant risks, and take necessary actions.

[0795] Emotional Engine

[0796] The device analyzes the user's emotions, sends that information to the server, and uses it to adjust the analysis results.

[0797] In this way, the system collects and analyzes company-wide data in real time, and provides users with important information that also takes into account their emotions, thereby enabling efficient business management and early detection of problems.

[0798] The following describes the processing flow.

[0799] Step 1:

[0800] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[0801] Step 2:

[0802] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[0803] Step 3:

[0804] The server preprocesses the text data using natural language processing techniques. It tokenizes the data, removes HTML tags and special characters, and eliminates frequent, meaningless stop words.

[0805] Step 4:

[0806] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[0807] Step 5:

[0808] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[0809] Step 6:

[0810] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[0811] Step 7:

[0812] The server receives input from the emotion engine and analyzes the user's emotions. For example, it analyzes the user's voice and text data to extract emotions such as anger, stress, and satisfaction.

[0813] Step 8:

[0814] The server adjusts the priority of analysis results received from ChatGPT based on emotional information from the emotion engine. For example, if the stress level is high, risk factors will be given a higher priority.

[0815] Step 9:

[0816] The server classifies the final analysis results, organizes them into categories such as issues, solutions, and incident factors, and compiles them into a report format. The report is provided in a format useful for specific departments or project leaders.

[0817] Step 10:

[0818] Users receive reports and notifications generated by the server and review their contents. Based on the reports, users take appropriate action and provide feedback to the system as needed to improve the accuracy of the data.

[0819] (Specific example)

[0820] Step 1: The server collects data from the project management tool at 11 PM and stores it temporarily.

[0821] Step 2: The server removes duplicate data and standardizes the text format.

[0822] Step 3: The server uses natural language processing techniques to tokenize the text data and remove stop words.

[0823] Step 4: The terminal converts the pre-processed data into JSON format.

[0824] Step 5: The device sends data in JSON format to the ChatGPT API and retrieves the analysis results.

[0825] Step 6: The device saves the analysis results from ChatGPT to local storage.

[0826] Step 7: The server analyzes the user's emotional data using an emotion engine and evaluates the emotional level.

[0827] Step 8: The server analyzes the sentiment information and adjusts the priority of the analysis results.

[0828] Step 9: The server classifies the final analysis results and compiles them into a report.

[0829] Step 10: The user receives the report, reviews its contents, and takes necessary actions.

[0830] This processing flow allows the system to collect and analyze company-wide data in real time, and provide information that takes user sentiment into consideration, thereby enabling efficient business management and early problem detection.

[0831] (Example 2)

[0832] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0833] In today's business environment, vast amounts of information are generated from numerous data sources, and there is a need to efficiently and effectively collect, organize, and analyze this data. However, conventional systems require a great deal of time and effort for data collection, cleaning, and analysis, making rapid decision-making difficult. Furthermore, while considering user sentiment information would enable more appropriate responses, this aspect is also not adequately addressed.

[0834] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data from company-wide data storage, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving the analysis results, means for extracting and classifying useful information from the analysis results, means for providing information based on the analysis results to humans, and means for analyzing emotional information from the user's text data and voice data and using that emotional information to adjust the analysis results. This makes it possible to collect and analyze company-wide data in real time and to quickly provide countermeasures that also take into account the user's emotional information.

[0835] "Data storage" refers to a storage device used to permanently store information.

[0836] "Cleaning" is a process that removes noise and unnecessary parts from data to improve its reliability.

[0837] "Standardizing the format" means converting collected data into a consistent format.

[0838] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[0839] "Tokenization" is the process of dividing text data into semantic units such as words and phrases.

[0840] "Meaningless data" refers to information or noise that is not useful in analysis.

[0841] A "conversational artificial intelligence interface" is an interface that utilizes AI technology to engage in natural conversations with users.

[0842] "Analysis results" refer to useful information obtained by analyzing data.

[0843] "Emotional information" refers to data that indicates the emotional state of a user or other target.

[0844] "Adjustment" refers to modifying or optimizing analysis results or processes according to specific objectives.

[0845] A "user" refers to an individual or department that uses this system to obtain information and make decisions.

[0846] This invention provides a system for efficiently collecting, preprocessing, and analyzing company-wide data. This system consists of a data collection module, a data preprocessing module, an interactive artificial intelligence interface, an analysis module, an output module, and an emotion engine.

[0847] Data Acquisition Module

[0848] server

[0849] The server connects to company-wide data storage, file storage, mail servers, and project management tools, and periodically collects data. For example, the server runs scheduled jobs every day at 11 p.m. to retrieve project progress reports from the database, download the latest documents from file storage, and collect unread emails from the mail server.

[0850] Specific example

[0851] The server sends queries to the company-wide business database and retrieves progress reports. It downloads the latest documents from file storage and collects all unread emails from the mail server.

[0852] Data preprocessing module

[0853] server

[0854] The server preprocesses the collected data. Preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[0855] Specific example

[0856] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[0857] Interactive artificial intelligence interface

[0858] terminal

[0859] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[0860] Specific example

[0861] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[0862] Analysis Module

[0863] server

[0864] The server analyzes the results received from ChatGPT and extracts particularly important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[0865] Specific example

[0866] The server analyzes the results from ChatGPT using text mining techniques to extract critical bug reports and risk factors. It then cross-references this with project managers' sentiment data and prioritizes the risk items.

[0867] Output module

[0868] User

[0869] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[0870] Specific example

[0871] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[0872] Emotional Engine

[0873] terminal

[0874] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[0875] Specific example

[0876] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[0877] Examples of prompts for generative AI models

[0878] "You are a project management AI assistant. Analyze the following project data and list the predicted risk factors and their solutions: {Project Data}. Also, consider {Sentiment Data} as user sentiment data."

[0879] In this way, the system collects and analyzes company-wide data in real time, and provides important information while also considering user sentiment, thereby enabling efficient business management and early problem detection.

[0880] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0881] Step 1: Data Collection

[0882] server

[0883] The server connects to the company's data storage, file storage, mail server, and project management tools, and periodically collects data. This process integrates data from each data source and stores it as a single dataset.

[0884] Inputs: Data storage, file storage, mail servers, project management tools

[0885] Data processing: Send queries to retrieve data and save it to storage.

[0886] Output: Collected raw data

[0887] Specific actions

[0888] The server retrieves project progress reports from the database, downloads the latest documents from file storage, and collects unread emails from the mail server.

[0889] Step 2: Data Preprocessing

[0890] server

[0891] The server preprocesses the collected data. This step involves cleaning the data, standardizing its format, tokenizing text data, and removing unnecessary data. Natural language processing techniques are used, particularly for stop word removal and text normalization.

[0892] Input: Collected raw data

[0893] Data processing: Data cleaning, formatting standardization, text tokenization, removal of unnecessary data.

[0894] Output: Preprocessed data

[0895] Specific actions

[0896] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[0897] Step 3: Data conversion and transmission

[0898] terminal

[0899] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[0900] Input: Preprocessed data

[0901] Data processing: Formatting data into JSON format.

[0902] Output: JSON data sent to ChatGPT

[0903] Specific actions

[0904] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[0905] Step 4: Analysis

[0906] server

[0907] The server analyzes the results received from ChatGPT and extracts important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[0908] Input: ChatGPT analysis results

[0909] Data processing: Extraction of key information, categorization of information, prioritization using sentiment data.

[0910] Output: Classified important information

[0911] Specific actions

[0912] The server analyzes the results from ChatGPT and extracts critical bug reports and risk factors. It then cross-references the project manager's sentiment data and prioritizes the risk items.

[0913] Step 5: Report generation and notification

[0914] User

[0915] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[0916] Input: Classified important information

[0917] Data processing: Report generation, notification distribution

[0918] Output: Reports to users, real-time notifications

[0919] Specific actions

[0920] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[0921] Step 6: Sentiment Analysis

[0922] terminal

[0923] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[0924] Input: User voice data and text data

[0925] Data processing: Sentiment analysis, generation of sentiment data

[0926] Output: Sending emotion data to the server

[0927] Specific actions

[0928] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[0929] (Application Example 2)

[0930] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0931] In modern industrial facilities, optimizing production efficiency and early problem detection are crucial. However, conventional systems suffer from the time-consuming nature of data collection and analysis, making real-time analysis, including emotional data, difficult. Furthermore, analysis results that consider workers' emotions are often not provided, leading to overlooking declines in production efficiency due to stress and fatigue. To address these challenges, there is a need for systems that enable real-time data analysis and the integration of emotional data.

[0932] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0933] In this invention, the server includes means for collecting data from sensors and equipment in industrial facilities, means for collecting worker voice data using a voice recognition device, means for transmitting pre-processed data to an interactive artificial intelligence interface and receiving analysis results on production efficiency, potential problems, and risk factors, means for analyzing emotions from voice data and adjusting the priority of analysis results based on emotion data, and means for integrating analysis results and emotion data and providing them to workers and managers in real time. This enables maximizing production efficiency and early detection of problems.

[0934] A "sensor" is a device that detects environmental information and the status of equipment within an industrial facility and outputs it as data.

[0935] A "voice recognition device" is a device that records the voice of a worker and converts that voice into text data.

[0936] "Data collection" refers to the act of obtaining necessary data from all company-wide databases, file storage, mail servers, and project management tools.

[0937] "Data cleaning" is the process of removing meaningless parts and noise from collected data and standardizing the data format.

[0938] "Natural language processing technology" is a technique for analyzing text data and extracting meaningful information from it.

[0939] "Tokenization" is the process of dividing text data into words or phrases.

[0940] A "conversational artificial intelligence interface" is an artificial intelligence system designed to enable natural dialogue with humans, and typically sends and receives data via an API.

[0941] "Analysis results" refer to the output of data analysis obtained through artificial intelligence systems or other analytical means.

[0942] "Emotion analysis" is the process of identifying emotions from audio or text data and evaluating those emotional states.

[0943] "Priority adjustment" is the process of re-evaluating the importance and urgency of the analysis results and changing the order and content of the information provided.

[0944] "Real-time delivery" refers to providing collected data and analysis results immediately without delay.

[0945] This invention is a system that collects and analyzes company-wide data in real time at industrial facilities and provides information with prioritized based on worker sentiment. The system includes the following main modules:

[0946] First, the server collects data from various sensors and equipment within the industrial facility. This includes data such as temperature, humidity, and machine operation logs. It also collects voice data from workers using voice recognition devices.

[0947] Next, the collected data is cleaned and standardized by the server. Audio data is converted to a transcript and noise is removed.

[0948] The pre-processed data is sent from the server to an interactive artificial intelligence interface, specifically the ChatGPT API. ChatGPT analyzes the data and provides analysis results regarding optimization of production efficiency, potential problems, and risk factors.

[0949] Furthermore, the server uses an emotion analysis engine to analyze the worker's emotions from their voice and text data. Based on this emotion data, the priority of the analysis results is adjusted. For example, if a worker's stress level is high, that information is given more weight when proposing countermeasures.

[0950] Analysis results and sentiment data are integrated by a server and provided to workers and managers in real time. This allows for immediate recognition of important information and risk factors, enabling prompt and appropriate countermeasures to be taken.

[0951] As a concrete example, the following prompt message can be provided to ChatGPT to analyze the efficiency and risk factors of the production line:

[0952] Please analyze the machine operation data from the production line within the factory and the voice data of the factory workers, and provide the following information:

[0953] 1. Advice on maximizing production line efficiency.

[0954] 2. Potential problems and risk factors.

[0955] 3. Appropriate measures based on the stress and fatigue levels of workers.

[0956] Implementing this system requires sensors within the factory, voice recognition devices, the ChatGPT API, and an emotion analysis engine. Combining these elements will enable maximizing factory production efficiency and early detection of problems.

[0957] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0958] Step 1:

[0959] The server collects data from various sensors and equipment in industrial facilities. Specifically, it acquires temperature data from temperature sensors, operating status data from motion sensors, and worker voice data using a voice recognition device. The input data consists of temperature, operating status, and voice data, which are temporarily stored within the system. The output is an aggregate of unprocessed raw data.

[0960] Step 2:

[0961] The server cleans and standardizes the collected data. First, audio data is converted to text transcripts to remove noise and unnecessary information. Next, meaningless data is removed from temperature and operating status data, and the data format is standardized to a consistent format. The input data is raw data, and the output is cleaned and well-formed data.

[0962] Step 3:

[0963] The server sends cleaned data to the ChatGPT API. The server converts this data to JSON format and sends a request to the API to receive analysis results regarding production efficiency and risk factors. The input data is cleaned, unified data, and the output is the analysis results from ChatGPT.

[0964] Step 4:

[0965] The server uses an emotion analysis engine to analyze the worker's emotions from their voice data. Specifically, it determines stress levels and fatigue levels from the tone and content of the voice, and sends the results to the server as numerical data. The input data is a voice transcript, and the output is the emotion analysis result.

[0966] Step 5:

[0967] The server integrates the analysis results received from ChatGPT with sentiment data obtained from the sentiment analysis engine. Based on the sentiment data, it adjusts the priority of the analysis results and re-evaluates the severity of the problem and the urgency of countermeasures. The input data consists of analysis results and sentiment data, and the output is the adjusted analysis results.

[0968] Step 6:

[0969] The server provides the adjusted analysis results to workers and administrators in real time. Specifically, it displays important notifications and alerts on smart glasses or terminal displays. The input data is the adjusted analysis results, and the output is real-time notifications and alerts.

[0970] Step 7:

[0971] The user receives information from the system and provides feedback as needed. This feedback is sent to the server and incorporated into subsequent analyses. The input data is user feedback, and the output is an improvement in the system's performance.

[0972] These steps enable the optimization of production efficiency within industrial facilities, early detection of problems, and appropriate responses based on the emotional state of workers.

[0973] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0974] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0975] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0976] [Third Embodiment]

[0977] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0978] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0979] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0980] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0981] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0982] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0983] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0984] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0985] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0986] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0987] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0988] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0989] This invention provides a consistent system for efficiently collecting, preprocessing, and providing real-time analysis results for company-wide data. This system includes the following key modules:

[0990] 1. Data Acquisition Module

[0991] 2. Data Preprocessing Module

[0992] 3. ChatGPT Interface

[0993] 4. Analysis Module

[0994] 5. Output Module

[0995] The specific implementation of each module is as follows:

[0996] Data Acquisition Module

[0997] server

[0998] The server connects to multiple databases, file storage, mail servers, and project management tools throughout the company, and collects data periodically. For example, the server runs a scheduled job every day at 11 PM to extract data such as project progress, bug reports, and email communications via APIs.

[0999] Specific example

[1000] The server retrieves progress reports for all projects from the company's overall business database.

[1001] Data preprocessing module

[1002] server

[1003] The server preprocesses the collected data. This preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[1004] Specific example

[1005] The server analyzes all email data, removes signatures and advertisements, and converts it into clean text.

[1006] ChatGPT interface

[1007] terminal

[1008] The device sends pre-processed data to the ChatGPT API. The API receives the data and performs analysis. The device then saves the analysis results locally. These results include identified issues, proposed solutions, and key incident factors.

[1009] Specific example

[1010] The terminal sends the cleaned project data to ChatGPT and retrieves a list of predicted risk factors.

[1011] Analysis Module

[1012] server

[1013] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders.

[1014] Specific example

[1015] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays.

[1016] Output module

[1017] User

[1018] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[1019] Specific example

[1020] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[1021] Examples

[1022] In a certain software development project, the following processes are performed:

[1023] Data collection

[1024] The server collects task progress data from the project management tool and stores it temporarily.

[1025] Data preprocessing

[1026] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[1027] ChatGPT interface

[1028] The device sends clean data to the ChatGPT API and receives the analysis results.

[1029] analysis

[1030] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[1031] Output

[1032] Users receive reports, recognize significant risks, and take necessary actions.

[1033] In this way, the system collects and analyzes company-wide data in real time and provides users with important information, enabling efficient business management and early detection of problems.

[1034] The following describes the processing flow.

[1035] Step 1:

[1036] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[1037] Step 2:

[1038] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[1039] Step 3:

[1040] The server preprocesses the text data using natural language processing techniques. At this stage, tokenization is performed to remove unnecessary data (such as HTML tags and special characters). High-frequency, meaningless stop words are also removed.

[1041] Step 4:

[1042] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[1043] Step 5:

[1044] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[1045] Step 6:

[1046] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[1047] Step 7:

[1048] The server re-analyzes the saved analysis results and extracts particularly important information. For example, it prioritizes identifying frequently occurring issues and major incident risks.

[1049] Step 8:

[1050] The server organizes the extracted information by category and compiles it into a report. The report clearly outlines the solutions and incident causes.

[1051] Step 9:

[1052] Users receive reports and notifications generated by the server. Users review the report content and provide feedback to the system as needed to improve the accuracy of the data.

[1053] Step 10:

[1054] Users take appropriate action based on the report. For example, if a significant risk is reported, the project manager will immediately add resources to the response team.

[1055] (Example 1)

[1056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1057] There is a need to efficiently collect information from across the entire company, preprocess and analyze it, and provide useful information to users in real time. Traditional systems require a lot of effort and time from data collection and preprocessing to analysis and output, resulting in a lack of immediacy and accuracy. Furthermore, the varying formats of the collected data make unified processing difficult.

[1058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1059] In this invention, the server includes means for collecting data from the company-wide information management system, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the preprocessed data to an interactive artificial intelligence interface that works in conjunction with a generating AI model and receiving the analysis results, means for analyzing the analysis results, extracting important information, organizing it by category, and means for providing the analysis results to the user. This enables efficient collection and preprocessing of company-wide data and the provision of useful information in real time.

[1060] An "information management system" is a system that manages and stores data from various sources within an organization, such as databases, file storage, mail servers, and project management tools.

[1061] "Means of data collection" refers to the processes and technologies used to automatically collect data from information management systems.

[1062] "Cleaning" is a procedure to improve the quality of collected data by removing noise and unnecessary information.

[1063] "Methods for standardizing formats" refer to methods for standardizing data with different formats and structures and converting it into a consistent format.

[1064] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[1065] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[1066] "Means of removing meaningless data" refers to techniques for removing unnecessary information and noise during the data processing process.

[1067] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate content.

[1068] An "interactive artificial intelligence interface" is an artificial intelligence tool that provides and analyzes information through dialogue with the user.

[1069] "Analysis results" refer to the final output data obtained using generative AI models and other analysis techniques.

[1070] "Methods for organizing by category" refer to techniques for classifying analysis results into specific categories and systematically organizing information.

[1071] "Means of providing to users" refers to methods and systems for providing analysis results in a format that users can use.

[1072] This invention provides a system for efficiently collecting and preprocessing data from a company-wide information management system and providing users with real-time analysis results using a generated AI model. This system includes the following key hardware and software components:

[1073] Data collection

[1074] server

[1075] The server collects data from multiple information management systems (e.g., databases, file storage, mail servers, project management tools).

[1076] For example, the server executes a scheduled job at 11 PM and retrieves project progress data via an API.

[1077] Data preprocessing

[1078] server

[1079] The server cleans and standardizes the format of the collected data.

[1080] Data cleaning involves removing unnecessary information (such as duplicate rows and blank rows).

[1081] We use natural language processing techniques to tokenize text data and remove stop words.

[1082] Analysis using the ChatGPT interface

[1083] terminal

[1084] The device sends pre-processed, clean data to a generative AI model like ChatGPT and receives the analysis results.

[1085] The device sends an API request and saves the analysis results to local storage.

[1086] Summary of analysis results

[1087] server

[1088] The server re-analyzes the results received from ChatGPT, extracts important information, and organizes it by category.

[1089] This information will be reported in a format useful to specific departments or project leaders.

[1090] Output to the user

[1091] User

[1092] Users receive reports and notifications sent from the server.

[1093] Users review the report, identify key risks and issues, and take action as needed.

[1094] User feedback is incorporated into the system, improving data accuracy.

[1095] Examples

[1096] In a certain software development project, the following processes are performed:

[1097] Data collection

[1098] The server collects task progress data from the project management tool and stores it temporarily.

[1099] Data preprocessing

[1100] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[1101] ChatGPT interface

[1102] The device sends clean data to the ChatGPT API and receives the analysis results.

[1103] analysis

[1104] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[1105] Output

[1106] Users receive reports, recognize significant risks, and take necessary actions.

[1107] Example of a prompt

[1108] The following is an example of a prompt message that a terminal sends to the ChatGPT interface:

[1109] Send project data in the following format:

[1110] task:

[1111] 1. In Progress - Implementation of Login Function - John Doe

[1112] 2. Completion - Database Structure Setup - Jane Smith

[1113] bug:

[1114] 101. High - System crash during form submission - Alice

[1115] communication:

[1116] 201. Sprint Planning Q1 - Next Sprint Tasks and Priorities

[1117] Based on this data, identify the risk factors and generate proposed solutions.

[1118] This invention enables efficient collection and preprocessing of company-wide data, as well as the provision of real-time analysis results, thereby facilitating business management and early detection of problems.

[1119] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1120] Step 1: Data Collection

[1121] server

[1122] Processing Overview: The server periodically collects data from the company's entire information management system.

[1123] Input: Data from databases, file storage, mail servers, and project management tools.

[1124] Data processing: Send an API request and retrieve the necessary data.

[1125] Output: Acquired raw data (e.g., project progress data, bug reports, email communications)

[1126] Specific operation: At 11 PM, the server executes a query like "SELECT FROM project_status WHERE date = CURRENT_DATE" to retrieve data from the database and save it in JSON format.

[1127] Step 2: Data preprocessing

[1128] server

[1129] Processing summary: The server cleans and standardizes the format of the collected data.

[1130] Input: Raw data collected in Step 1

[1131] Data processing: Data cleaning, removal of unnecessary rows and duplicate data, formatting standardization, tokenization of text data, removal of stop words.

[1132] Output: Pre-processed clean data

[1133] Specific operation: The server removes stop words such as "the" and "is" from the text data and tokenizes the text into its smallest units. For example, it removes email signatures and advertisements.

[1134] Step 3: Sending data to the generative AI model

[1135] terminal

[1136] Processing Overview: The terminal sends pre-processed data to the generating AI model (ChatGPT) and receives the analysis results.

[1137] Input: Clean data preprocessed in Step 2

[1138] Data processing: Data is sent via API requests and analyzed using a generative AI model.

[1139] Output: Analysis results from the generative AI model

[1140] Specific operation: The terminal sends an API request using "POST / v1 / engines / davinci-codex / completions" and retrieves the analysis results with the prompt "Please identify risk factors".

[1141] Step 4: Organizing the analysis results

[1142] server

[1143] Processing Overview: The server re-analyzes the analysis results received from the generated AI model, extracts important information, and organizes it by category.

[1144] Input: Analysis results obtained in Step 3

[1145] Data processing: Parse the analysis results and organize them by category (e.g., risk factors, solutions, critical incidents).

[1146] Output: Analysis results organized by category

[1147] Specific operation: The server parses the data in JSON format, classifies it into categories such as "critical bug" and "delivery delay risk," and generates a report.

[1148] Step 5: Output to the user

[1149] User

[1150] Processing summary: The user receives reports and notifications sent from the server.

[1151] Input: Analysis results compiled in Step 4

[1152] Data processing: Users review the information and take action as needed.

[1153] Output: Actions and feedback based on the results

[1154] Specific actions: Users receive risk notifications via email or dashboards, confirm a notification stating "Project X's progress is at significant risk," and take appropriate action.

[1155] Through the above processing steps, the system can efficiently collect, preprocess, and analyze company-wide data, and provide critical information in real time.

[1156] (Application Example 1)

[1157] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1158] Logistics centers require efficient operations, and it is crucial to monitor inventory, shipping status, and staff work progress in real time to respond quickly. However, centrally managing this data, analyzing it in real time to extract useful information, and responding quickly to incidents is difficult. Furthermore, properly pre-processing large amounts of data and removing irrelevant data requires considerable effort. Therefore, a consistent system is needed to efficiently collect and analyze data and optimize logistics center operations.

[1159] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1160] This invention includes a server that includes means for collecting data from company-wide databases, file storage, mail servers, and project management tools; means for cleaning and standardizing the format of the collected data; means for tokenizing text data using natural language processing technology and removing meaningless data; means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving analysis results; means for analyzing the analysis results, extracting useful information, and classifying it into categories; means for providing the analysis results to humans; means for collecting data in real time from various sensors and management systems within the logistics center; means for analyzing the collected data in real time, identifying bottlenecks and risk factors, and proposing solutions; and means for notifying important incidents in real time. This optimizes operations within the logistics center and enables efficient data management and rapid problem solving.

[1161] A "database" is a system that systematically stores information and data, making it possible to search and manipulate it.

[1162] "File storage" refers to a storage device or service for storing, accessing, and managing files of various formats.

[1163] A "mail server" is a server that manages the sending and receiving of emails, and is a device that has functions such as email distribution and storage.

[1164] A "project management tool" is software used for planning, executing, and monitoring projects, and provides functions such as task management and progress tracking.

[1165] "Cleaning" is the process of removing unnecessary elements and inaccurate information from data, and is a process to maintain data integrity.

[1166] "Format standardization" is the process of aligning the format and structure of multiple datasets into a consistent format, thereby improving data compatibility.

[1167] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for processing and analyzing text data.

[1168] "Tokenization" is the process of dividing text into units of words or phrases, and it is one of the basic preprocessing steps in natural language processing.

[1169] "Meaningless data" refers to data that is not necessary for the analysis or does not affect the results, and is usually removed before the analysis.

[1170] A "conversational artificial intelligence interface" is a system that interacts with users in a conversational format using artificial intelligence, and provides services such as answering questions and providing analysis results.

[1171] "Analysis results" refer to conclusions and information obtained based on data analysis, provided in a way that is beneficial to the user.

[1172] "Various sensors" are devices that detect the state of the environment or objects and acquire the data, such as devices that measure temperature, humidity, and location.

[1173] A "management system" is software or hardware used to efficiently manage resources and processes within a logistics center or organization.

[1174] "Real-time" refers to a temporal concept that means acquiring information as soon as an event occurs and processing and analyzing it immediately.

[1175] A "bottleneck" refers to an obstacle within a process or system that reduces productivity and efficiency.

[1176] A "risk factor" is an element or condition that could potentially cause problems in a business or process.

[1177] A "solution" is a specific method or means proposed to address a particular problem.

[1178] An "incident" refers to an unexpected event that occurs during normal business processes, and is a problem or obstacle that requires action.

[1179] "Notification" refers to a means of informing a user of a specific event or information, and is carried out in the form of alarms, messages, etc.

[1180] This invention is a system for real-time monitoring and efficient operation in a logistics center. The system is configured as follows:

[1181] System Configuration

[1182] 1. Data Acquisition Module

[1183] Hardware: Various sensors, management systems within the logistics center.

[1184] Processing: The server collects data in real time from various sensors and management systems installed within the logistics center. This includes inventory status, shipping status, and work progress.

[1185] 2. Data Preprocessing Module

[1186] Software: Python, natural language processing technology.

[1187] Processing: The server cleans and standardizes the collected data. It removes meaningless elements from the data and tokenizes the necessary information.

[1188] 3. ChatGPT Interface

[1189] Software: ChatGPT API.

[1190] Processing: Pre-processed data is sent to the ChatGPT API, and the analysis results are received. The server retrieves the analysis results and saves them locally.

[1191] 4. Analysis Module

[1192] Software: Python.

[1193] Processing: The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. It identifies risk factors and bottlenecks and generates solutions.

[1194] 5. Output Module

[1195] Hardware and software: User's smartphone, tablet, and notification applications.

[1196] Processing: Users can receive analysis results in real time. They will be notified immediately if a critical incident occurs.

[1197] Specific example

[1198] For example, if a new shipping bottleneck occurs at a logistics center, the server collects data from various sensors, cleans and preprocesses it in real time. The cleaned data is sent to the ChatGPT API, where analysis results are obtained. From these analysis results, the server identifies the bottleneck and generates a solution. This allows users (e.g., logistics center managers) to receive immediate notification and take appropriate action.

[1199] Example of a prompt

[1200] For example, you can obtain analysis results by sending a prompt message like the following to ChatGPT.

[1201] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[1202] This system efficiently collects data within the logistics center, preprocesses it, and provides the analysis results to the user in real time, thereby enabling efficient operations and rapid problem solving.

[1203] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1204] Step 1:

[1205] The server collects data in real time from various sensors and management systems within the logistics center. Specifically, the server obtains data such as inventory status, shipping status, and work progress via API. This input data consists of raw sensor data and system log data. The collected raw data is temporarily stored.

[1206] Step 2:

[1207] The server cleans and standardizes the collected data. Specifically, it removes unnecessary data and formats the necessary data. For example, it removes noise and errors from text data and standardizes the units of numerical data. The input to this process is the collected raw data, and the output is the cleaned data.

[1208] Step 3:

[1209] The server tokenizes the cleaned data using natural language processing techniques. Specifically, it uses Python's natural language processing library to split the text data into words and phrases and remove unnecessary stop words. The input to this process is the cleaned text data, and the output is tokenized data.

[1210] Step 4:

[1211] The server sends pre-processed data to the ChatGPT API and receives the analysis results. Specifically, the server creates a specific prompt message for the generating AI model and sends it as an API request. The input to this process is tokenized data and the prompt message, and the output is the analysis results returned in JSON format.

[1212] Step 5:

[1213] The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. Specifically, the server identifies specific incidents, risk factors, and solutions from the analysis results and organizes each into the appropriate category. The input for this process is the analysis results from ChatGPT, and the output is organized information.

[1214] Step 6:

[1215] The server provides the user with the analysis results. Specifically, the server sends notifications to the user's smartphone or tablet, informing them of important incidents and solutions in real time. The input for this process is organized information, and the output is a notification issued to the user.

[1216] Prompt statements as concrete examples:

[1217] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[1218] This enables the efficient collection, processing, and analysis of data within the logistics center, allowing for the provision of useful information to users in real time.

[1219] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1220] This invention is a system that combines a user emotion recognition engine with a consistent system that efficiently collects and preprocesses company-wide data and provides analysis results in real time. By reflecting emotion information in the analysis results, it becomes possible to provide more appropriate responses and instructions. This system includes the following main modules:

[1221] 1. Data Acquisition Module

[1222] 2. Data Preprocessing Module

[1223] 3. ChatGPT Interface

[1224] 4. Analysis Module

[1225] 5. Output Module

[1226] 6. Emotional Engine

[1227] The specific implementation of each module is as follows:

[1228] Data Acquisition Module

[1229] server

[1230] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[1231] Specific example

[1232] The server retrieves progress reports for all projects from the company's overall business database.

[1233] Data preprocessing module

[1234] server

[1235] The server preprocesses the collected data. This preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[1236] Specific example

[1237] >

[1238] The server analyzes all email data, removes signatures and advertisements, and converts it into clean text.

[1239] ChatGPT interface

[1240] terminal

[1241] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON. The terminal then sends this converted data to the ChatGPT API to obtain the analysis results.

[1242] Specific example

[1243] The terminal sends the cleaned project data to ChatGPT and retrieves a list of predicted risk factors.

[1244] Analysis Module

[1245] server

[1246] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders. This module also receives input from the emotion engine to adjust the priority of the analysis results.

[1247] Specific example

[1248] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays. It also adjusts priorities based on the project manager's sentiment data.

[1249] Output module

[1250] User

[1251] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[1252] Specific example

[1253] >

[1254] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[1255] Emotional Engine

[1256] terminal

[1257] The device analyzes the user's emotions from their voice and text data and retrieves that emotional information. The emotion engine sends the emotional analysis results to a server, which is then used to refine the analysis results.

[1258] Specific example

[1259] The terminal analyzes the project manager's communication data and, if it determines that the stress level is high, sends that information to the server.

[1260] Examples

[1261] In a certain software development project, the following processes are performed:

[1262] Data collection

[1263] The server collects task progress data from the project management tool and stores it temporarily.

[1264] Data preprocessing

[1265] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[1266] ChatGPT interface

[1267] The device sends clean data to the ChatGPT API and receives the analysis results.

[1268] analysis

[1269] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report. Furthermore, it adjusts the priority of the analysis results based on input from the sentiment engine.

[1270] Output

[1271] Users receive reports, recognize significant risks, and take necessary actions.

[1272] Emotional Engine

[1273] The device analyzes the user's emotions, sends that information to the server, and uses it to adjust the analysis results.

[1274] In this way, the system collects and analyzes company-wide data in real time, and provides users with important information that also takes into account their emotions, thereby enabling efficient business management and early detection of problems.

[1275] The following describes the processing flow.

[1276] Step 1:

[1277] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[1278] Step 2:

[1279] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[1280] Step 3:

[1281] The server preprocesses the text data using natural language processing techniques. It tokenizes the data, removes HTML tags and special characters, and eliminates frequent, meaningless stop words.

[1282] Step 4:

[1283] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[1284] Step 5:

[1285] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[1286] Step 6:

[1287] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[1288] Step 7:

[1289] The server receives input from the emotion engine and analyzes the user's emotions. For example, it analyzes the user's voice and text data to extract emotions such as anger, stress, and satisfaction.

[1290] Step 8:

[1291] The server adjusts the priority of analysis results received from ChatGPT based on emotional information from the emotion engine. For example, if the stress level is high, risk factors will be given a higher priority.

[1292] Step 9:

[1293] The server classifies the final analysis results, organizes them into categories such as issues, solutions, and incident factors, and compiles them into a report format. The report is provided in a format useful for specific departments or project leaders.

[1294] Step 10:

[1295] Users receive reports and notifications generated by the server and review their contents. Based on the reports, users take appropriate action and provide feedback to the system as needed to improve the accuracy of the data.

[1296] (Specific example)

[1297] Step 1: The server collects data from the project management tool at 11 PM and stores it temporarily.

[1298] Step 2: The server removes duplicate data and standardizes the text format.

[1299] Step 3: The server uses natural language processing techniques to tokenize the text data and remove stop words.

[1300] Step 4: The terminal converts the pre-processed data into JSON format.

[1301] Step 5: The device sends data in JSON format to the ChatGPT API and retrieves the analysis results.

[1302] Step 6: The device saves the analysis results from ChatGPT to local storage.

[1303] Step 7: The server analyzes the user's emotional data using an emotion engine and evaluates the emotional level.

[1304] Step 8: The server analyzes the sentiment information and adjusts the priority of the analysis results.

[1305] Step 9: The server classifies the final analysis results and compiles them into a report.

[1306] Step 10: The user receives the report, reviews its contents, and takes necessary actions.

[1307] This processing flow allows the system to collect and analyze company-wide data in real time, and provide information that takes user sentiment into consideration, thereby enabling efficient business management and early problem detection.

[1308] (Example 2)

[1309] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1310] In today's business environment, vast amounts of information are generated from numerous data sources, and there is a need to efficiently and effectively collect, organize, and analyze this data. However, conventional systems require a great deal of time and effort for data collection, cleaning, and analysis, making rapid decision-making difficult. Furthermore, while considering user sentiment information would enable more appropriate responses, this aspect is also not adequately addressed.

[1311] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data from company-wide data storage, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving the analysis results, means for extracting and classifying useful information from the analysis results, means for providing information based on the analysis results to humans, and means for analyzing emotional information from the user's text data and voice data and using that emotional information to adjust the analysis results. This makes it possible to collect and analyze company-wide data in real time and to quickly provide countermeasures that also take into account the user's emotional information.

[1312] "Data storage" refers to a storage device used to permanently store information.

[1313] "Cleaning" is a process that removes noise and unnecessary parts from data to improve its reliability.

[1314] "Standardizing the format" means converting collected data into a consistent format.

[1315] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[1316] "Tokenization" is the process of dividing text data into semantic units such as words and phrases.

[1317] "Meaningless data" refers to information or noise that is not useful in analysis.

[1318] A "conversational artificial intelligence interface" is an interface that utilizes AI technology to engage in natural conversations with users.

[1319] "Analysis results" refer to useful information obtained by analyzing data.

[1320] "Emotional information" refers to data that indicates the emotional state of a user or other target.

[1321] "Adjustment" refers to modifying or optimizing analysis results or processes according to specific objectives.

[1322] A "user" refers to an individual or department that uses this system to obtain information and make decisions.

[1323] This invention provides a system for efficiently collecting, preprocessing, and analyzing company-wide data. This system consists of a data collection module, a data preprocessing module, an interactive artificial intelligence interface, an analysis module, an output module, and an emotion engine.

[1324] Data Acquisition Module

[1325] server

[1326] The server connects to company-wide data storage, file storage, mail servers, and project management tools, and periodically collects data. For example, the server runs scheduled jobs every day at 11 p.m. to retrieve project progress reports from the database, download the latest documents from file storage, and collect unread emails from the mail server.

[1327] Specific example

[1328] The server sends queries to the company-wide business database and retrieves progress reports. It downloads the latest documents from file storage and collects all unread emails from the mail server.

[1329] Data preprocessing module

[1330] server

[1331] The server preprocesses the collected data. Preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[1332] Specific example

[1333] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[1334] Interactive artificial intelligence interface

[1335] terminal

[1336] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[1337] Specific example

[1338] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[1339] Analysis Module

[1340] server

[1341] The server analyzes the results received from ChatGPT and extracts particularly important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[1342] Specific example

[1343] The server analyzes the results from ChatGPT using text mining techniques to extract critical bug reports and risk factors. It then cross-references this with project managers' sentiment data and prioritizes the risk items.

[1344] Output module

[1345] User

[1346] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[1347] Specific example

[1348] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[1349] Emotional Engine

[1350] terminal

[1351] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[1352] Specific example

[1353] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[1354] Examples of prompts for generative AI models

[1355] "You are a project management AI assistant. Analyze the following project data and list the predicted risk factors and their solutions: {Project Data}. Also, consider {Sentiment Data} as user sentiment data."

[1356] In this way, the system collects and analyzes company-wide data in real time, and provides important information while also considering user sentiment, thereby enabling efficient business management and early problem detection.

[1357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1358] Step 1: Data Collection

[1359] server

[1360] The server connects to the company's data storage, file storage, mail server, and project management tools, and periodically collects data. This process integrates data from each data source and stores it as a single dataset.

[1361] Inputs: Data storage, file storage, mail servers, project management tools

[1362] Data processing: Send queries to retrieve data and save it to storage.

[1363] Output: Collected raw data

[1364] Specific actions

[1365] The server retrieves project progress reports from the database, downloads the latest documents from file storage, and collects unread emails from the mail server.

[1366] Step 2: Data Preprocessing

[1367] server

[1368] The server preprocesses the collected data. This step involves cleaning the data, standardizing its format, tokenizing text data, and removing unnecessary data. Natural language processing techniques are used, particularly for stop word removal and text normalization.

[1369] Input: Collected raw data

[1370] Data processing: Data cleaning, formatting standardization, text tokenization, removal of unnecessary data.

[1371] Output: Preprocessed data

[1372] Specific actions

[1373] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[1374] Step 3: Data conversion and transmission

[1375] terminal

[1376] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[1377] Input: Preprocessed data

[1378] Data processing: Formatting data into JSON format.

[1379] Output: JSON data sent to ChatGPT

[1380] Specific actions

[1381] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[1382] Step 4: Analysis

[1383] server

[1384] The server analyzes the results received from ChatGPT and extracts important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[1385] Input: ChatGPT analysis results

[1386] Data processing: Extraction of key information, categorization of information, prioritization using sentiment data.

[1387] Output: Classified important information

[1388] Specific actions

[1389] The server analyzes the results from ChatGPT and extracts critical bug reports and risk factors. It then cross-references the project manager's sentiment data and prioritizes the risk items.

[1390] Step 5: Report generation and notification

[1391] User

[1392] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[1393] Input: Classified important information

[1394] Data processing: Report generation, notification distribution

[1395] Output: Reports to users, real-time notifications

[1396] Specific actions

[1397] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[1398] Step 6: Sentiment Analysis

[1399] terminal

[1400] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[1401] Input: User voice data and text data

[1402] Data processing: Sentiment analysis, generation of sentiment data

[1403] Output: Sending emotion data to the server

[1404] Specific actions

[1405] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[1406] (Application Example 2)

[1407] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1408] In modern industrial facilities, optimizing production efficiency and early problem detection are crucial. However, conventional systems suffer from the time-consuming nature of data collection and analysis, making real-time analysis, including emotional data, difficult. Furthermore, analysis results that consider workers' emotions are often not provided, leading to overlooking declines in production efficiency due to stress and fatigue. To address these challenges, there is a need for systems that enable real-time data analysis and the integration of emotional data.

[1409] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1410] In this invention, the server includes means for collecting data from sensors and equipment in industrial facilities, means for collecting worker voice data using a voice recognition device, means for transmitting pre-processed data to an interactive artificial intelligence interface and receiving analysis results on production efficiency, potential problems, and risk factors, means for analyzing emotions from voice data and adjusting the priority of analysis results based on emotion data, and means for integrating analysis results and emotion data and providing them to workers and managers in real time. This enables maximizing production efficiency and early detection of problems.

[1411] A "sensor" is a device that detects environmental information and the status of equipment within an industrial facility and outputs it as data.

[1412] A "voice recognition device" is a device that records the voice of a worker and converts that voice into text data.

[1413] "Data collection" refers to the act of obtaining necessary data from all company-wide databases, file storage, mail servers, and project management tools.

[1414] "Data cleaning" is the process of removing meaningless parts and noise from collected data and standardizing the data format.

[1415] "Natural language processing technology" is a technique for analyzing text data and extracting meaningful information from it.

[1416] "Tokenization" is the process of dividing text data into words or phrases.

[1417] A "conversational artificial intelligence interface" is an artificial intelligence system designed to enable natural dialogue with humans, and typically sends and receives data via an API.

[1418] "Analysis results" refer to the output of data analysis obtained through artificial intelligence systems or other analytical means.

[1419] "Emotion analysis" is the process of identifying emotions from audio or text data and evaluating those emotional states.

[1420] "Priority adjustment" is the process of re-evaluating the importance and urgency of the analysis results and changing the order and content of the information provided.

[1421] "Real-time delivery" refers to providing collected data and analysis results immediately without delay.

[1422] This invention is a system that collects and analyzes company-wide data in real time at industrial facilities and provides information with prioritized based on worker sentiment. The system includes the following main modules:

[1423] First, the server collects data from various sensors and equipment within the industrial facility. This includes data such as temperature, humidity, and machine operation logs. It also collects voice data from workers using voice recognition devices.

[1424] Next, the collected data is cleaned and standardized by the server. Audio data is converted to a transcript and noise is removed.

[1425] The pre-processed data is sent from the server to an interactive artificial intelligence interface, specifically the ChatGPT API. ChatGPT analyzes the data and provides analysis results regarding optimization of production efficiency, potential problems, and risk factors.

[1426] Furthermore, the server uses an emotion analysis engine to analyze the worker's emotions from their voice and text data. Based on this emotion data, the priority of the analysis results is adjusted. For example, if a worker's stress level is high, that information is given more weight when proposing countermeasures.

[1427] Analysis results and sentiment data are integrated by a server and provided to workers and managers in real time. This allows for immediate recognition of important information and risk factors, enabling prompt and appropriate countermeasures to be taken.

[1428] As a concrete example, the following prompt message can be provided to ChatGPT to analyze the efficiency and risk factors of the production line:

[1429] Please analyze the machine operation data from the production line within the factory and the voice data of the factory workers, and provide the following information:

[1430] 1. Advice on maximizing production line efficiency.

[1431] 2. Potential problems and risk factors.

[1432] 3. Appropriate measures based on the stress and fatigue levels of workers.

[1433] Implementing this system requires sensors within the factory, voice recognition devices, the ChatGPT API, and an emotion analysis engine. Combining these elements will enable maximizing factory production efficiency and early detection of problems.

[1434] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1435] Step 1:

[1436] The server collects data from various sensors and equipment in industrial facilities. Specifically, it acquires temperature data from temperature sensors, operating status data from motion sensors, and worker voice data using a voice recognition device. The input data consists of temperature, operating status, and voice data, which are temporarily stored within the system. The output is an aggregate of unprocessed raw data.

[1437] Step 2:

[1438] The server cleans and standardizes the collected data. First, audio data is converted to text transcripts to remove noise and unnecessary information. Next, meaningless data is removed from temperature and operating status data, and the data format is standardized to a consistent format. The input data is raw data, and the output is cleaned and well-formed data.

[1439] Step 3:

[1440] The server sends cleaned data to the ChatGPT API. The server converts this data to JSON format and sends a request to the API to receive analysis results regarding production efficiency and risk factors. The input data is cleaned, unified data, and the output is the analysis results from ChatGPT.

[1441] Step 4:

[1442] The server uses an emotion analysis engine to analyze the worker's emotions from their voice data. Specifically, it determines stress levels and fatigue levels from the tone and content of the voice, and sends the results to the server as numerical data. The input data is a voice transcript, and the output is the emotion analysis result.

[1443] Step 5:

[1444] The server integrates the analysis results received from ChatGPT with sentiment data obtained from the sentiment analysis engine. Based on the sentiment data, it adjusts the priority of the analysis results and re-evaluates the severity of the problem and the urgency of countermeasures. The input data consists of analysis results and sentiment data, and the output is the adjusted analysis results.

[1445] Step 6:

[1446] The server provides the adjusted analysis results to workers and administrators in real time. Specifically, it displays important notifications and alerts on smart glasses or terminal displays. The input data is the adjusted analysis results, and the output is real-time notifications and alerts.

[1447] Step 7:

[1448] The user receives information from the system and provides feedback as needed. This feedback is sent to the server and incorporated into subsequent analyses. The input data is user feedback, and the output is an improvement in the system's performance.

[1449] These steps enable the optimization of production efficiency within industrial facilities, early detection of problems, and appropriate responses based on the emotional state of workers.

[1450] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1451] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1452] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1453] [Fourth Embodiment]

[1454] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1455] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1456] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1457] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1458] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1459] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1460] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1461] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1462] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1463] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1464] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1465] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1466] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1467] This invention provides a consistent system for efficiently collecting, preprocessing, and providing real-time analysis results for company-wide data. This system includes the following key modules:

[1468] 1. Data Acquisition Module

[1469] 2. Data Preprocessing Module

[1470] 3. ChatGPT Interface

[1471] 4. Analysis Module

[1472] 5. Output Module

[1473] The specific implementation of each module is as follows:

[1474] Data Acquisition Module

[1475] server

[1476] The server connects to multiple databases, file storage, mail servers, and project management tools throughout the company, and collects data periodically. For example, the server runs a scheduled job every day at 11 PM to extract data such as project progress, bug reports, and email communications via APIs.

[1477] Specific example

[1478] The server retrieves progress reports for all projects from the company's overall business database.

[1479] Data preprocessing module

[1480] server

[1481] The server preprocesses the collected data. This preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[1482] Specific example

[1483] The server analyzes all email data, removes signatures and advertisements, and converts it into clean text.

[1484] ChatGPT interface

[1485] terminal

[1486] The device sends pre-processed data to the ChatGPT API. The API receives the data and performs analysis. The device then saves the analysis results locally. These results include identified issues, proposed solutions, and key incident factors.

[1487] Specific example

[1488] The terminal sends the cleaned project data to ChatGPT and retrieves a list of predicted risk factors.

[1489] Analysis Module

[1490] server

[1491] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders.

[1492] Specific example

[1493] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays.

[1494] Output module

[1495] User

[1496] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[1497] Specific example

[1498] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[1499] Examples

[1500] In a certain software development project, the following processes are performed:

[1501] Data collection

[1502] The server collects task progress data from the project management tool and stores it temporarily.

[1503] Data preprocessing

[1504] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[1505] ChatGPT interface

[1506] The device sends clean data to the ChatGPT API and receives the analysis results.

[1507] analysis

[1508] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[1509] Output

[1510] Users receive reports, recognize significant risks, and take necessary actions.

[1511] In this way, the system collects and analyzes company-wide data in real time and provides users with important information, enabling efficient business management and early detection of problems.

[1512] The following describes the processing flow.

[1513] Step 1:

[1514] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[1515] Step 2:

[1516] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[1517] Step 3:

[1518] The server preprocesses the text data using natural language processing techniques. At this stage, tokenization is performed to remove unnecessary data (such as HTML tags and special characters). High-frequency, meaningless stop words are also removed.

[1519] Step 4:

[1520] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[1521] Step 5:

[1522] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[1523] Step 6:

[1524] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[1525] Step 7:

[1526] The server re-analyzes the saved analysis results and extracts particularly important information. For example, it prioritizes identifying frequently occurring issues and major incident risks.

[1527] Step 8:

[1528] The server organizes the extracted information by category and compiles it into a report. The report clearly outlines the solutions and incident causes.

[1529] Step 9:

[1530] Users receive reports and notifications generated by the server. Users review the report content and provide feedback to the system as needed to improve the accuracy of the data.

[1531] Step 10:

[1532] Users take appropriate action based on the report. For example, if a significant risk is reported, the project manager will immediately add resources to the response team.

[1533] (Example 1)

[1534] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1535] There is a need to efficiently collect information from across the entire company, preprocess and analyze it, and provide useful information to users in real time. Traditional systems require a lot of effort and time from data collection and preprocessing to analysis and output, resulting in a lack of immediacy and accuracy. Furthermore, the varying formats of the collected data make unified processing difficult.

[1536] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1537] In this invention, the server includes means for collecting data from the company-wide information management system, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the preprocessed data to an interactive artificial intelligence interface that works in conjunction with a generating AI model and receiving the analysis results, means for analyzing the analysis results, extracting important information, organizing it by category, and means for providing the analysis results to the user. This enables efficient collection and preprocessing of company-wide data and the provision of useful information in real time.

[1538] An "information management system" is a system that manages and stores data from various sources within an organization, such as databases, file storage, mail servers, and project management tools.

[1539] "Means of data collection" refers to the processes and technologies used to automatically collect data from information management systems.

[1540] "Cleaning" is a procedure to improve the quality of collected data by removing noise and unnecessary information.

[1541] "Methods for standardizing formats" refer to methods for standardizing data with different formats and structures and converting it into a consistent format.

[1542] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[1543] "Tokenization" is the process of dividing text data into its smallest units, such as words or phrases.

[1544] "Means of removing meaningless data" refers to techniques for removing unnecessary information and noise during the data processing process.

[1545] A "generative AI model" is a model that uses artificial intelligence to analyze data and generate content.

[1546] An "interactive artificial intelligence interface" is an artificial intelligence tool that provides and analyzes information through dialogue with the user.

[1547] "Analysis results" refer to the final output data obtained using generative AI models and other analysis techniques.

[1548] "Methods for organizing by category" refer to techniques for classifying analysis results into specific categories and systematically organizing information.

[1549] "Means of providing to users" refers to methods and systems for providing analysis results in a format that users can use.

[1550] This invention provides a system for efficiently collecting and preprocessing data from a company-wide information management system and providing users with real-time analysis results using a generated AI model. This system includes the following key hardware and software components:

[1551] Data collection

[1552] server

[1553] The server collects data from multiple information management systems (e.g., databases, file storage, mail servers, project management tools).

[1554] For example, the server executes a scheduled job at 11 PM and retrieves project progress data via an API.

[1555] Data preprocessing

[1556] server

[1557] The server cleans and standardizes the format of the collected data.

[1558] Data cleaning involves removing unnecessary information (such as duplicate rows and blank rows).

[1559] We use natural language processing techniques to tokenize text data and remove stop words.

[1560] Analysis using the ChatGPT interface

[1561] terminal

[1562] The device sends pre-processed, clean data to a generative AI model like ChatGPT and receives the analysis results.

[1563] The device sends an API request and saves the analysis results to local storage.

[1564] Summary of analysis results

[1565] server

[1566] The server re-analyzes the results received from ChatGPT, extracts important information, and organizes it by category.

[1567] This information will be reported in a format useful to specific departments or project leaders.

[1568] Output to the user

[1569] User

[1570] Users receive reports and notifications sent from the server.

[1571] Users review the report, identify key risks and issues, and take action as needed.

[1572] User feedback is incorporated into the system, improving data accuracy.

[1573] Examples

[1574] In a certain software development project, the following processes are performed:

[1575] Data collection

[1576] The server collects task progress data from the project management tool and stores it temporarily.

[1577] Data preprocessing

[1578] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[1579] ChatGPT interface

[1580] The device sends clean data to the ChatGPT API and receives the analysis results.

[1581] analysis

[1582] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report.

[1583] Output

[1584] Users receive reports, recognize significant risks, and take necessary actions.

[1585] Example of a prompt

[1586] The following is an example of a prompt message that a terminal sends to the ChatGPT interface:

[1587] Send project data in the following format:

[1588] task:

[1589] 1. In Progress - Implementation of Login Function - John Doe

[1590] 2. Completion - Database Structure Setup - Jane Smith

[1591] bug:

[1592] 101. High - System crash during form submission - Alice

[1593] communication:

[1594] 201. Sprint Planning Q1 - Next Sprint Tasks and Priorities

[1595] Based on this data, identify the risk factors and generate proposed solutions.

[1596] This invention enables efficient collection and preprocessing of company-wide data, as well as the provision of real-time analysis results, thereby facilitating business management and early detection of problems.

[1597] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1598] Step 1: Data Collection

[1599] server

[1600] Processing Overview: The server periodically collects data from the company's entire information management system.

[1601] Input: Data from databases, file storage, mail servers, and project management tools.

[1602] Data processing: Send an API request and retrieve the necessary data.

[1603] Output: Acquired raw data (e.g., project progress data, bug reports, email communications)

[1604] Specific operation: At 11 PM, the server executes a query like "SELECT FROM project_status WHERE date = CURRENT_DATE" to retrieve data from the database and save it in JSON format.

[1605] Step 2: Data preprocessing

[1606] server

[1607] Processing summary: The server cleans and standardizes the format of the collected data.

[1608] Input: Raw data collected in Step 1

[1609] Data processing: Data cleaning, removal of unnecessary rows and duplicate data, formatting standardization, tokenization of text data, removal of stop words.

[1610] Output: Pre-processed clean data

[1611] Specific operation: The server removes stop words such as "the" and "is" from the text data and tokenizes the text into its smallest units. For example, it removes email signatures and advertisements.

[1612] Step 3: Sending data to the generative AI model

[1613] terminal

[1614] Processing Overview: The terminal sends pre-processed data to the generating AI model (ChatGPT) and receives the analysis results.

[1615] Input: Clean data preprocessed in Step 2

[1616] Data processing: Data is sent via API requests and analyzed using a generative AI model.

[1617] Output: Analysis results from the generative AI model

[1618] Specific operation: The terminal sends an API request using "POST / v1 / engines / davinci-codex / completions" and retrieves the analysis results with the prompt "Please identify risk factors".

[1619] Step 4: Organizing the analysis results

[1620] server

[1621] Processing Overview: The server re-analyzes the analysis results received from the generated AI model, extracts important information, and organizes it by category.

[1622] Input: Analysis results obtained in Step 3

[1623] Data processing: Parse the analysis results and organize them by category (e.g., risk factors, solutions, critical incidents).

[1624] Output: Analysis results organized by category

[1625] Specific operation: The server parses the data in JSON format, classifies it into categories such as "critical bug" and "delivery delay risk," and generates a report.

[1626] Step 5: Output to the user

[1627] User

[1628] Processing summary: The user receives reports and notifications sent from the server.

[1629] Input: Analysis results compiled in Step 4

[1630] Data processing: Users review the information and take action as needed.

[1631] Output: Actions and feedback based on the results

[1632] Specific actions: Users receive risk notifications via email or dashboards, confirm a notification stating "Project X's progress is at significant risk," and take appropriate action.

[1633] Through the above processing steps, the system can efficiently collect, preprocess, and analyze company-wide data, and provide critical information in real time.

[1634] (Application Example 1)

[1635] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1636] Logistics centers require efficient operations, and it is crucial to monitor inventory, shipping status, and staff work progress in real time to respond quickly. However, centrally managing this data, analyzing it in real time to extract useful information, and responding quickly to incidents is difficult. Furthermore, properly pre-processing large amounts of data and removing irrelevant data requires considerable effort. Therefore, a consistent system is needed to efficiently collect and analyze data and optimize logistics center operations.

[1637] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1638] This invention includes a server that includes means for collecting data from company-wide databases, file storage, mail servers, and project management tools; means for cleaning and standardizing the format of the collected data; means for tokenizing text data using natural language processing technology and removing meaningless data; means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving analysis results; means for analyzing the analysis results, extracting useful information, and classifying it into categories; means for providing the analysis results to humans; means for collecting data in real time from various sensors and management systems within the logistics center; means for analyzing the collected data in real time, identifying bottlenecks and risk factors, and proposing solutions; and means for notifying important incidents in real time. This optimizes operations within the logistics center and enables efficient data management and rapid problem solving.

[1639] A "database" is a system that systematically stores information and data, making it possible to search and manipulate it.

[1640] "File storage" refers to a storage device or service for storing, accessing, and managing files of various formats.

[1641] A "mail server" is a server that manages the sending and receiving of emails, and is a device that has functions such as email distribution and storage.

[1642] A "project management tool" is software used for planning, executing, and monitoring projects, and provides functions such as task management and progress tracking.

[1643] "Cleaning" is the process of removing unnecessary elements and inaccurate information from data, and is a process to maintain data integrity.

[1644] "Format standardization" is the process of aligning the format and structure of multiple datasets into a consistent format, thereby improving data compatibility.

[1645] "Natural language processing technology" is a technology that uses computers to understand and analyze human language, and is used for processing and analyzing text data.

[1646] "Tokenization" is the process of dividing text into units of words or phrases, and it is one of the basic preprocessing steps in natural language processing.

[1647] "Meaningless data" refers to data that is not necessary for the analysis or does not affect the results, and is usually removed before the analysis.

[1648] A "conversational artificial intelligence interface" is a system that interacts with users in a conversational format using artificial intelligence, and provides services such as answering questions and providing analysis results.

[1649] "Analysis results" refer to conclusions and information obtained based on data analysis, provided in a way that is beneficial to the user.

[1650] "Various sensors" are devices that detect the state of the environment or objects and acquire the data, such as devices that measure temperature, humidity, and location.

[1651] A "management system" is software or hardware used to efficiently manage resources and processes within a logistics center or organization.

[1652] "Real-time" refers to a temporal concept that means acquiring information as soon as an event occurs and processing and analyzing it immediately.

[1653] A "bottleneck" refers to an obstacle within a process or system that reduces productivity and efficiency.

[1654] A "risk factor" is an element or condition that could potentially cause problems in a business or process.

[1655] A "solution" is a specific method or means proposed to address a particular problem.

[1656] An "incident" refers to an unexpected event that occurs during normal business processes, and is a problem or obstacle that requires action.

[1657] "Notification" refers to a means of informing a user of a specific event or information, and is carried out in the form of alarms, messages, etc.

[1658] This invention is a system for real-time monitoring and efficient operation in a logistics center. The system is configured as follows:

[1659] System Configuration

[1660] 1. Data Acquisition Module

[1661] Hardware: Various sensors, management systems within the logistics center.

[1662] Processing: The server collects data in real time from various sensors and management systems installed within the logistics center. This includes inventory status, shipping status, and work progress.

[1663] 2. Data Preprocessing Module

[1664] Software: Python, natural language processing technology.

[1665] Processing: The server cleans and standardizes the collected data. It removes meaningless elements from the data and tokenizes the necessary information.

[1666] 3. ChatGPT Interface

[1667] Software: ChatGPT API.

[1668] Processing: Pre-processed data is sent to the ChatGPT API, and the analysis results are received. The server retrieves the analysis results and saves them locally.

[1669] 4. Analysis Module

[1670] Software: Python.

[1671] Processing: The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. It identifies risk factors and bottlenecks and generates solutions.

[1672] 5. Output Module

[1673] Hardware and software: User's smartphone, tablet, and notification applications.

[1674] Processing: Users can receive analysis results in real time. They will be notified immediately if a critical incident occurs.

[1675] Specific example

[1676] For example, if a new shipping bottleneck occurs at a logistics center, the server collects data from various sensors, cleans and preprocesses it in real time. The cleaned data is sent to the ChatGPT API, where analysis results are obtained. From these analysis results, the server identifies the bottleneck and generates a solution. This allows users (e.g., logistics center managers) to receive immediate notification and take appropriate action.

[1677] Example of a prompt

[1678] For example, you can obtain analysis results by sending a prompt message like the following to ChatGPT.

[1679] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[1680] This system efficiently collects data within the logistics center, preprocesses it, and provides the analysis results to the user in real time, thereby enabling efficient operations and rapid problem solving.

[1681] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1682] Step 1:

[1683] The server collects data in real time from various sensors and management systems within the logistics center. Specifically, the server obtains data such as inventory status, shipping status, and work progress via API. This input data consists of raw sensor data and system log data. The collected raw data is temporarily stored.

[1684] Step 2:

[1685] The server cleans and standardizes the collected data. Specifically, it removes unnecessary data and formats the necessary data. For example, it removes noise and errors from text data and standardizes the units of numerical data. The input to this process is the collected raw data, and the output is the cleaned data.

[1686] Step 3:

[1687] The server tokenizes the cleaned data using natural language processing techniques. Specifically, it uses Python's natural language processing library to split the text data into words and phrases and remove unnecessary stop words. The input to this process is the cleaned text data, and the output is tokenized data.

[1688] Step 4:

[1689] The server sends pre-processed data to the ChatGPT API and receives the analysis results. Specifically, the server creates a specific prompt message for the generating AI model and sends it as an API request. The input to this process is tokenized data and the prompt message, and the output is the analysis results returned in JSON format.

[1690] Step 5:

[1691] The server analyzes the results received from ChatGPT, extracts useful information, and categorizes it. Specifically, the server identifies specific incidents, risk factors, and solutions from the analysis results and organizes each into the appropriate category. The input for this process is the analysis results from ChatGPT, and the output is organized information.

[1692] Step 6:

[1693] The server provides the user with the analysis results. Specifically, the server sends notifications to the user's smartphone or tablet, informing them of important incidents and solutions in real time. The input for this process is organized information, and the output is a notification issued to the user.

[1694] Prompt statements as concrete examples:

[1695] Analyze the following logistics center data and propose key risk factors and solutions. Data: { "Inventory Status": "Low", "Shipping Delays": "High", "Work Progress": "Slow"}

[1696] This enables the efficient collection, processing, and analysis of data within the logistics center, allowing for the provision of useful information to users in real time.

[1697] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1698] This invention is a system that combines a user emotion recognition engine with a consistent system that efficiently collects and preprocesses company-wide data and provides analysis results in real time. By reflecting emotion information in the analysis results, it becomes possible to provide more appropriate responses and instructions. This system includes the following main modules:

[1699] 1. Data Acquisition Module

[1700] 2. Data Preprocessing Module

[1701] 3. ChatGPT Interface

[1702] 4. Analysis Module

[1703] 5. Output Module

[1704] 6. Emotional Engine

[1705] The specific implementation of each module is as follows:

[1706] Data Acquisition Module

[1707] server

[1708] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[1709] Specific example

[1710] The server retrieves progress reports for all projects from the company's overall business database.

[1711] Data preprocessing module

[1712] server

[1713] The server preprocesses the collected data. This preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[1714] Specific example

[1715] >

[1716] The server analyzes all email data, removes signatures and advertisements, and converts it into clean text.

[1717] ChatGPT interface

[1718] terminal

[1719] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON. The terminal then sends this converted data to the ChatGPT API to obtain the analysis results.

[1720] Specific example

[1721] The terminal sends the cleaned project data to ChatGPT and retrieves a list of predicted risk factors.

[1722] Analysis Module

[1723] server

[1724] The server analyzes the results received from ChatGPT and extracts particularly important information. This extracted information is organized into categories such as issues, solutions, and incident factors. The analysis results are then reported in a format useful for specific departments or project leaders. This module also receives input from the emotion engine to adjust the priority of the analysis results.

[1725] Specific example

[1726] The server analyzes the results from ChatGPT and extracts risk factors related to critical bugs and project delays. It also adjusts priorities based on the project manager's sentiment data.

[1727] Output module

[1728] User

[1729] Users receive reports and notifications generated by the system. This allows project managers and department leaders to identify critical incident factors in real time and take timely action. Users who review the reports can provide feedback to the system as needed to improve the accuracy of the data.

[1730] Specific example

[1731] >

[1732] Users, such as project managers, receive risk notifications from the server and quickly implement necessary countermeasures.

[1733] Emotional Engine

[1734] terminal

[1735] The device analyzes the user's emotions from their voice and text data and retrieves that emotional information. The emotion engine sends the emotional analysis results to a server, which is then used to refine the analysis results.

[1736] Specific example

[1737] The terminal analyzes the project manager's communication data and, if it determines that the stress level is high, sends that information to the server.

[1738] Examples

[1739] In a certain software development project, the following processes are performed:

[1740] Data collection

[1741] The server collects task progress data from the project management tool and stores it temporarily.

[1742] Data preprocessing

[1743] The server cleans and standardizes the format of the collected data. For example, it removes unnecessary rows and duplicate data.

[1744] ChatGPT interface

[1745] The device sends clean data to the ChatGPT API and receives the analysis results.

[1746] analysis

[1747] The server analyzes the results from ChatGPT, extracts particularly important information, and generates a report. Furthermore, it adjusts the priority of the analysis results based on input from the sentiment engine.

[1748] Output

[1749] Users receive reports, recognize significant risks, and take necessary actions.

[1750] Emotional Engine

[1751] The device analyzes the user's emotions, sends that information to the server, and uses it to adjust the analysis results.

[1752] In this way, the system collects and analyzes company-wide data in real time, and provides users with important information that also takes into account their emotions, thereby enabling efficient business management and early detection of problems.

[1753] The following describes the processing flow.

[1754] Step 1:

[1755] The server connects to all company-wide databases, file storage, mail servers, and project management tools, and performs periodic data collection tasks. For example, a job scheduled to start at 11 PM every day collects data such as project progress, bug reports, and email communications.

[1756] Step 2:

[1757] The server cleans and standardizes the collected data. Specifically, it normalizes the data, removes duplicate entries, and standardizes the text encoding.

[1758] Step 3:

[1759] The server preprocesses the text data using natural language processing techniques. It tokenizes the data, removes HTML tags and special characters, and eliminates frequent, meaningless stop words.

[1760] Step 4:

[1761] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept, such as JSON.

[1762] Step 5:

[1763] The device sends the converted data to the ChatGPT API. The API receives the data, performs analysis, and generates analysis results including issues, solutions, and incident factors.

[1764] Step 6:

[1765] The device receives the analysis results returned from the ChatGPT API and saves them to local storage.

[1766] Step 7:

[1767] The server receives input from the emotion engine and analyzes the user's emotions. For example, it analyzes the user's voice and text data to extract emotions such as anger, stress, and satisfaction.

[1768] Step 8:

[1769] The server adjusts the priority of analysis results received from ChatGPT based on emotional information from the emotion engine. For example, if the stress level is high, risk factors will be given a higher priority.

[1770] Step 9:

[1771] The server classifies the final analysis results, organizes them into categories such as issues, solutions, and incident factors, and compiles them into a report format. The report is provided in a format useful for specific departments or project leaders.

[1772] Step 10:

[1773] Users receive reports and notifications generated by the server and review their contents. Based on the reports, users take appropriate action and provide feedback to the system as needed to improve the accuracy of the data.

[1774] (Specific example)

[1775] Step 1: The server collects data from the project management tool at 11 PM and stores it temporarily.

[1776] Step 2: The server removes duplicate data and standardizes the text format.

[1777] Step 3: The server uses natural language processing techniques to tokenize the text data and remove stop words.

[1778] Step 4: The terminal converts the pre-processed data into JSON format.

[1779] Step 5: The device sends data in JSON format to the ChatGPT API and retrieves the analysis results.

[1780] Step 6: The device saves the analysis results from ChatGPT to local storage.

[1781] Step 7: The server analyzes the user's emotional data using an emotion engine and evaluates the emotional level.

[1782] Step 8: The server analyzes the sentiment information and adjusts the priority of the analysis results.

[1783] Step 9: The server classifies the final analysis results and compiles them into a report.

[1784] Step 10: The user receives the report, reviews its contents, and takes necessary actions.

[1785] This processing flow allows the system to collect and analyze company-wide data in real time, and provide information that takes user sentiment into consideration, thereby enabling efficient business management and early problem detection.

[1786] (Example 2)

[1787] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1788] In today's business environment, vast amounts of information are generated from numerous data sources, and there is a need to efficiently and effectively collect, organize, and analyze this data. However, conventional systems require a great deal of time and effort for data collection, cleaning, and analysis, making rapid decision-making difficult. Furthermore, while considering user sentiment information would enable more appropriate responses, this aspect is also not adequately addressed.

[1789] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data from company-wide data storage, means for cleaning and standardizing the format of the collected data, means for tokenizing text data using natural language processing technology and removing meaningless data, means for transmitting the pre-processed data to an interactive artificial intelligence interface and receiving the analysis results, means for extracting and classifying useful information from the analysis results, means for providing information based on the analysis results to humans, and means for analyzing emotional information from the user's text data and voice data and using that emotional information to adjust the analysis results. This makes it possible to collect and analyze company-wide data in real time and to quickly provide countermeasures that also take into account the user's emotional information.

[1790] "Data storage" refers to a storage device used to permanently store information.

[1791] "Cleaning" is a process that removes noise and unnecessary parts from data to improve its reliability.

[1792] "Standardizing the format" means converting collected data into a consistent format.

[1793] "Natural language processing technology" refers to the technology that enables computers to understand, interpret, and generate human language.

[1794] "Tokenization" is the process of dividing text data into semantic units such as words and phrases.

[1795] "Meaningless data" refers to information or noise that is not useful in analysis.

[1796] A "conversational artificial intelligence interface" is an interface that utilizes AI technology to engage in natural conversations with users.

[1797] "Analysis results" refer to useful information obtained by analyzing data.

[1798] "Emotional information" refers to data that indicates the emotional state of a user or other target.

[1799] "Adjustment" refers to modifying or optimizing analysis results or processes according to specific objectives.

[1800] A "user" refers to an individual or department that uses this system to obtain information and make decisions.

[1801] This invention provides a system for efficiently collecting, preprocessing, and analyzing company-wide data. This system consists of a data collection module, a data preprocessing module, an interactive artificial intelligence interface, an analysis module, an output module, and an emotion engine.

[1802] Data Acquisition Module

[1803] server

[1804] The server connects to company-wide data storage, file storage, mail servers, and project management tools, and periodically collects data. For example, the server runs scheduled jobs every day at 11 p.m. to retrieve project progress reports from the database, download the latest documents from file storage, and collect unread emails from the mail server.

[1805] Specific example

[1806] The server sends queries to the company-wide business database and retrieves progress reports. It downloads the latest documents from file storage and collects all unread emails from the mail server.

[1807] Data preprocessing module

[1808] server

[1809] The server preprocesses the collected data. Preprocessing includes data cleaning, formatting standardization, tokenization of text data, and removal of unnecessary data. Natural language processing techniques are used, primarily for stop word removal and text normalization.

[1810] Specific example

[1811] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[1812] Interactive artificial intelligence interface

[1813] terminal

[1814] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[1815] Specific example

[1816] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[1817] Analysis Module

[1818] server

[1819] The server analyzes the results received from ChatGPT and extracts particularly important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[1820] Specific example

[1821] The server analyzes the results from ChatGPT using text mining techniques to extract critical bug reports and risk factors. It then cross-references this with project managers' sentiment data and prioritizes the risk items.

[1822] Output module

[1823] User

[1824] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[1825] Specific example

[1826] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[1827] Emotional Engine

[1828] terminal

[1829] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[1830] Specific example

[1831] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[1832] Examples of prompts for generative AI models

[1833] "You are a project management AI assistant. Analyze the following project data and list the predicted risk factors and their solutions: {Project Data}. Also, consider {Sentiment Data} as user sentiment data."

[1834] In this way, the system collects and analyzes company-wide data in real time, and provides important information while also considering user sentiment, thereby enabling efficient business management and early problem detection.

[1835] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1836] Step 1: Data Collection

[1837] server

[1838] The server connects to the company's data storage, file storage, mail server, and project management tools, and periodically collects data. This process integrates data from each data source and stores it as a single dataset.

[1839] Inputs: Data storage, file storage, mail servers, project management tools

[1840] Data processing: Send queries to retrieve data and save it to storage.

[1841] Output: Collected raw data

[1842] Specific actions

[1843] The server retrieves project progress reports from the database, downloads the latest documents from file storage, and collects unread emails from the mail server.

[1844] Step 2: Data Preprocessing

[1845] server

[1846] The server preprocesses the collected data. This step involves cleaning the data, standardizing its format, tokenizing text data, and removing unnecessary data. Natural language processing techniques are used, particularly for stop word removal and text normalization.

[1847] Input: Collected raw data

[1848] Data processing: Data cleaning, formatting standardization, text tokenization, removal of unnecessary data.

[1849] Output: Preprocessed data

[1850] Specific actions

[1851] The server analyzes the received email data, detecting and removing email signatures and advertising information. Then, it uses regular expressions to convert the text data into a unified format.

[1852] Step 3: Data conversion and transmission

[1853] terminal

[1854] The terminal converts the pre-processed data into a format that the interactive artificial intelligence interface can accept (e.g., JSON). This data is sent to the ChatGPT API, and the terminal waits for the analysis results to be returned.

[1855] Input: Preprocessed data

[1856] Data processing: Formatting data into JSON format.

[1857] Output: JSON data sent to ChatGPT

[1858] Specific actions

[1859] The terminal formats the cleaned project data into JSON format and sends this data to the ChatGPT API. After obtaining the analysis results, it saves the results to a local database.

[1860] Step 4: Analysis

[1861] server

[1862] The server analyzes the results received from ChatGPT and extracts important information. The extracted information is organized into categories such as issues, solutions, and incident factors. User sentiment information provided by the sentiment engine is also included in the analysis, and the priority of the results is adjusted accordingly.

[1863] Input: ChatGPT analysis results

[1864] Data processing: Extraction of key information, categorization of information, prioritization using sentiment data.

[1865] Output: Classified important information

[1866] Specific actions

[1867] The server analyzes the results from ChatGPT and extracts critical bug reports and risk factors. It then cross-references the project manager's sentiment data and prioritizes the risk items.

[1868] Step 5: Report generation and notification

[1869] User

[1870] Users receive generated reports and notifications, allowing them to identify critical incident factors in real time. This enables project managers and department leaders to quickly pinpoint incident causes and take necessary actions. User feedback further improves the accuracy of the system's data.

[1871] Input: Classified important information

[1872] Data processing: Report generation, notification distribution

[1873] Output: Reports to users, real-time notifications

[1874] Specific actions

[1875] Users, especially project managers, receive risk notifications sent from the server and view them in real time on the dashboard. Based on this information, they quickly assemble a response team and implement necessary countermeasures.

[1876] Step 6: Sentiment Analysis

[1877] terminal

[1878] The device analyzes voice and text data obtained from the user to evaluate the user's emotions. The emotional data analyzed by the emotion engine is sent to a server and used to refine the analysis results.

[1879] Input: User voice data and text data

[1880] Data processing: Sentiment analysis, generation of sentiment data

[1881] Output: Sending emotion data to the server

[1882] Specific actions

[1883] The device analyzes audio data recorded during project meetings to assess the project manager's stress and anxiety levels. This information is sent to a server and included in the project risk assessment criteria.

[1884] (Application Example 2)

[1885] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1886] In modern industrial facilities, optimizing production efficiency and early problem detection are crucial. However, conventional systems suffer from the time-consuming nature of data collection and analysis, making real-time analysis, including emotional data, difficult. Furthermore, analysis results that consider workers' emotions are often not provided, leading to overlooking declines in production efficiency due to stress and fatigue. To address these challenges, there is a need for systems that enable real-time data analysis and the integration of emotional data.

[1887] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1888] In this invention, the server includes means for collecting data from sensors and equipment in industrial facilities, means for collecting worker voice data using a voice recognition device, means for transmitting pre-processed data to an interactive artificial intelligence interface and receiving analysis results on production efficiency, potential problems, and risk factors, means for analyzing emotions from voice data and adjusting the priority of analysis results based on emotion data, and means for integrating analysis results and emotion data and providing them to workers and managers in real time. This enables maximizing production efficiency and early detection of problems.

[1889] A "sensor" is a device that detects environmental information and the status of equipment within an industrial facility and outputs it as data.

[1890] A "voice recognition device" is a device that records the voice of a worker and converts that voice into text data.

[1891] "Data collection" refers to the act of obtaining necessary data from all company-wide databases, file storage, mail servers, and project management tools.

[1892] "Data cleaning" is the process of removing meaningless parts and noise from collected data and standardizing the data format.

[1893] "Natural language processing technology" is a technique for analyzing text data and extracting meaningful information from it.

[1894] "Tokenization" is the process of dividing text data into words or phrases.

[1895] A "conversational artificial intelligence interface" is an artificial intelligence system designed to enable natural dialogue with humans, and typically sends and receives data via an API.

[1896] "Analysis results" refer to the output of data analysis obtained through artificial intelligence systems or other analytical means.

[1897] "Emotion analysis" is the process of identifying emotions from audio or text data and evaluating those emotional states.

[1898] "Priority adjustment" is the process of re-evaluating the importance and urgency of the analysis results and changing the order and content of the information provided.

[1899] "Real-time delivery" refers to providing collected data and analysis results immediately without delay.

[1900] This invention is a system that collects and analyzes company-wide data in real time at industrial facilities and provides information with prioritized based on worker sentiment. The system includes the following main modules:

[1901] First, the server collects data from various sensors and equipment within the industrial facility. This includes data such as temperature, humidity, and machine operation logs. It also collects voice data from workers using voice recognition devices.

[1902] Next, the collected data is cleaned and standardized by the server. Audio data is converted to a transcript and noise is removed.

[1903] The pre-processed data is sent from the server to an interactive artificial intelligence interface, specifically the ChatGPT API. ChatGPT analyzes the data and provides analysis results regarding optimization of production efficiency, potential problems, and risk factors.

[1904] Furthermore, the server uses an emotion analysis engine to analyze the worker's emotions from their voice and text data. Based on this emotion data, the priority of the analysis results is adjusted. For example, if a worker's stress level is high, that information is given more weight when proposing countermeasures.

[1905] Analysis results and sentiment data are integrated by a server and provided to workers and managers in real time. This allows for immediate recognition of important information and risk factors, enabling prompt and appropriate countermeasures to be taken.

[1906] As a concrete example, the following prompt message can be provided to ChatGPT to analyze the efficiency and risk factors of the production line:

[1907] Please analyze the machine operation data from the production line within the factory and the voice data of the factory workers, and provide the following information:

[1908] 1. Advice on maximizing production line efficiency.

[1909] 2. Potential problems and risk factors.

[1910] 3. Appropriate measures based on the stress and fatigue levels of workers.

[1911] Implementing this system requires sensors within the factory, voice recognition devices, the ChatGPT API, and an emotion analysis engine. Combining these elements will enable maximizing factory production efficiency and early detection of problems.

[1912] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1913] Step 1:

[1914] The server collects data from various sensors and equipment in industrial facilities. Specifically, it acquires temperature data from temperature sensors, operating status data from motion sensors, and worker voice data using a voice recognition device. The input data consists of temperature, operating status, and voice data, which are temporarily stored within the system. The output is an aggregate of unprocessed raw data.

[1915] Step 2:

[1916] The server cleans and standardizes the collected data. First, audio data is converted to text transcripts to remove noise and unnecessary information. Next, meaningless data is removed from temperature and operating status data, and the data format is standardized to a consistent format. The input data is raw data, and the output is cleaned and well-formed data.

[1917] Step 3:

[1918] The server sends cleaned data to the ChatGPT API. The server converts this data to JSON format and sends a request to the API to receive analysis results regarding production efficiency and risk factors. The input data is cleaned, unified data, and the output is the analysis results from ChatGPT.

[1919] Step 4:

[1920] The server uses an emotion analysis engine to analyze the worker's emotions from their voice data. Specifically, it determines stress levels and fatigue levels from the tone and content of the voice, and sends the results to the server as numerical data. The input data is a voice transcript, and the output is the emotion analysis result.

[1921] Step 5:

[1922] The server integrates the analysis results received from ChatGPT with sentiment data obtained from the sentiment analysis engine. Based on the sentiment data, it adjusts the priority of the analysis results and re-evaluates the severity of the problem and the urgency of countermeasures. The input data consists of analysis results and sentiment data, and the output is the adjusted analysis results.

[1923] Step 6:

[1924] The server provides the adjusted analysis results to workers and administrators in real time. Specifically, it displays important notifications and alerts on smart glasses or terminal displays. The input data is the adjusted analysis results, and the output is real-time notifications and alerts.

[1925] Step 7:

[1926] The user receives information from the system and provides feedback as needed. This feedback is sent to the server and incorporated into subsequent analyses. The input data is user feedback, and the output is an improvement in the system's performance.

[1927] These steps enable the optimization of production efficiency within industrial facilities, early detection of problems, and appropriate responses based on the emotional state of workers.

[1928] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1929] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1930] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1931] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1932] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1933] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1934] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1935] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1936] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1937] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1938] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1939] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1940] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1941] 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.

[1942] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1943] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1944] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1945] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1946] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1947] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1948] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1949] The following is further disclosed regarding the embodiments described above.

[1950] (Claim 1)

[1951] Means for collecting data from company-wide databases, file storage, mail servers, and project management tools,

[1952] A means of cleaning and standardizing the format of the collected data,

[1953] A method for tokenizing text data using natural language processing techniques and removing meaningless data,

[1954] A means for sending pre-processed data to an interactive artificial intelligence interface and receiving analysis results,

[1955] A means of analyzing the results, extracting useful information, and classifying it by category,

[1956] A system that includes means of providing analysis results to humans.

[1957] (Claim 2)

[1958] The system according to claim 1, wherein the means for tokenizing text data using natural language processing techniques and removing meaningless data includes means for removing stop words.

[1959] (Claim 3)

[1960] The system according to claim 1, wherein the means for receiving analysis results from an interactive artificial intelligence interface is a means for receiving analysis results in JSON format.

[1961] "Example 1"

[1962] (Claim 1)

[1963] A means of collecting data from the company-wide information management system,

[1964] A means of cleaning and standardizing the format of the collected data,

[1965] A method for tokenizing text data using natural language processing techniques and removing meaningless data,

[1966] A means of sending pre-processed data to an interactive artificial intelligence interface that works in conjunction with a generating AI model, and receiving the analysis results,

[1967] A means of analyzing the results, extracting important information, and organizing it by category,

[1968] A system that includes means for providing analysis results to the user.

[1969] (Claim 2)

[1970] The system according to claim 1, wherein the means for tokenizing text data using natural language processing techniques and removing meaningless data includes means for removing stop words.

[1971] (Claim 3)

[1972] The system according to claim 1, wherein the means for receiving analysis results from an interactive artificial intelligence interface that works in conjunction with a generating AI model is a means for receiving analysis results in a standard data format.

[1973] "Application Example 1"

[1974] (Claim 1)

[1975] Means for collecting data from company-wide databases, file storage, mail servers, and project management tools,

[1976] A means of cleaning and standardizing the format of the collected data,

[1977] A method for tokenizing text data using natural language processing techniques and removing meaningless data,

[1978] A means for sending pre-processed data to an interactive artificial intelligence interface and receiving analysis results,

[1979] A means of analyzing the results, extracting useful information, and classifying it by category,

[1980] Means of providing analysis results to humans,

[1981] A means of collecting data in real time from various sensors and management systems within the logistics center,

[1982] A means to analyze collected data in real time, identify bottlenecks and risk factors, and propose solutions,

[1983] A system that includes means for notifying important incidents in real time.

[1984] (Claim 2)

[1985] The system according to claim 1, wherein the means for tokenizing text data using natural language processing techniques and removing meaningless data includes means for removing stop words.

[1986] (Claim 3)

[1987] The system according to claim 1, wherein the means for receiving analysis results from an interactive artificial intelligence interface is a means for receiving analysis results in JSON format.

[1988] "Example 2 of combining an emotion engine"

[1989] (Claim 1)

[1990] A means of collecting data from company-wide data storage,

[1991] A means of cleaning and standardizing the format of the collected data,

[1992] A method for tokenizing text data using natural language processing techniques and removing meaningless data,

[1993] A means for sending pre-processed data to an interactive artificial intelligence interface and receiving analysis results,

[1994] A means of extracting and classifying useful information from the analysis results,

[1995] Means of providing information to humans based on analysis results,

[1996] A system that includes means for analyzing emotional information from user text data and voice data, and using that emotional information to adjust the analysis results.

[1997] (Claim 2)

[1998] The system according to claim 1, wherein the means for tokenizing text data using natural language processing techniques and removing meaningless data includes means for removing stop words.

[1999] (Claim 3)

[2000] The system according to claim 1, wherein the means for receiving analysis results from an interactive artificial intelligence interface is a means for receiving analysis results in JSON format.

[2001] "Application example 2 when combining with an emotional engine"

[2002] (Claim 1)

[2003] Means for collecting data from company-wide databases, file storage, mail servers, and project management tools,

[2004] A means of cleaning and standardizing the format of the collected data,

[2005] A method for tokenizing text data using natural language processing techniques and removing meaningless data,

[2006] A means for sending pre-processed data to an interactive artificial intelligence interface and receiving analysis results,

[2007] A means of analyzing the results, extracting useful information, and classifying it by category,

[2008] Methods for analyzing emotions from audio and text data,

[2009] A means of adjusting the priority of analysis results using emotional data,

[2010] A system that includes means of integrating analysis results and emotional data and providing them to humans.

[2011] (Claim 2)

[2012] The system according to claim 1, wherein the means for tokenizing text data using natural language processing techniques and removing meaningless data includes means for removing stop words.

[2013] (Claim 3)

[2014] The system according to claim 1, wherein the means for receiving analysis results from an interactive artificial intelligence interface is a means for receiving analysis results in JSON format.

[2015] (Claim 4)

[2016] Means for collecting data from sensors and equipment in industrial facilities,

[2017] A means for collecting worker voice data using a voice recognition device,

[2018] A means of sending pre-processed data to an interactive artificial intelligence interface and receiving analysis results regarding production efficiency, potential problems, and risk factors.

[2019] A method for analyzing emotions from voice data and adjusting the priority of the analysis results based on the emotional data,

[2020] The system according to claim 1, comprising means for integrating analysis results and emotional data and providing them to workers and managers in real time. [Explanation of symbols]

[2021] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting data from company-wide databases, file storage, mail servers, and project management tools, A means of cleaning and standardizing the format of the collected data, A method for tokenizing text data using natural language processing techniques and removing meaningless data, A means for sending pre-processed data to an interactive artificial intelligence interface and receiving analysis results, A means of analyzing the results, extracting useful information, and classifying it by category, A system that includes means of providing analysis results to humans.

2. The system according to claim 1, wherein the means for tokenizing text data using natural language processing techniques and removing meaningless data includes means for removing stop words.

3. The system according to claim 1, wherein the means for receiving analysis results from an interactive artificial intelligence interface is a means for receiving analysis results in JSON format.

Images