System

Abstract

A system is provided.SOLUTION: A system comprising: means for automatically generating metadata using a generative AI and applying the metadata to data; means for automatically classifying the data using the generative AI; means for monitoring update frequency of the data and archiving the data based on a set condition; and means for allowing a user to edit metadata and classification rules through a web-based management interface.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's digital society, the amount of data held by companies is rapidly increasing. To centrally manage this data and utilize it efficiently, it is essential to organize, classify, and assign metadata to the data. However, performing these tasks manually requires a great deal of time and effort, and is prone to human error. This is particularly true when dealing with large amounts of data, which makes data management difficult and reduces the efficiency of data utilization. To address this issue, the challenge is to use generative AI to automate the organization, classification, and assignment of metadata to achieve efficient data management, while saving human resources and improving accuracy. [Means for solving the problem]

[0005] To address the above-mentioned problems, the present invention provides a system having the following features. The system includes a means for automatically generating metadata using a generation AI and assigning it to data, a means for automatically classifying data using the generation AI, a means for monitoring the update frequency of data and archiving the data based on set conditions, and a means for allowing users to edit metadata and classification rules through a web-based management interface. This system automates a series of processes, from collecting and importing data to generating metadata, classifying data, monitoring update frequency, and archiving. Furthermore, users can easily manage and edit data through the web-based interface, achieving efficient and accurate data management.

[0006] "Generative AI" refers to artificial intelligence techniques used to automatically perform tasks such as analyzing and generating data.

[0007] "Metadata" is information that accompanies the data itself, and is made up of tags and attributes that explain the content and characteristics of the data and make it easier to manage and search.

[0008] "Data classification" is the process of separating collected data into specific categories based on their content and format.

[0009] "Data update frequency" is an index that indicates how frequently data is updated or changed.

[0010] "Monitoring" is the process of continuously observing and tracking changes in certain parameters or conditions.

[0011] "Archiving" is a method for storing data for a long period of time by moving and storing infrequently used data in another storage device, thereby reducing the load on the main storage device.

[0012] A "web-based management interface" is a web application that users access via the Internet to manage and edit data.

[0013] "User" means a person or entity that uses the System to manage and edit data.

[0014] "Data collection" is the process of gathering data from different sources and bringing it into the system.

[0015] "Import" is the process of bringing data collected from outside into the system and making it available for use. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[0038] Data collection and import

[0039] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[0040] Automatic generation and assignment of metadata

[0041] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[0042] Creation date: Automatically taken from file meta information.

[0043] Administrator: Retrieves information from the user management system.

[0044] Data type: Automatically determined from file format and content.

[0045] Data description: Generated based on the results of AI content analysis.

[0046] Update frequency: Estimated based on past update history.

[0047] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[0048] Data classification and organization

[0049] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[0050] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[0051] Data Updates and Archiving

[0052] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[0053] Providing a management interface

[0054] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[0055] This system will enable companies to significantly reduce the amount of man-hours required for data management and enable them to organize, store, and utilize data with high accuracy, which is expected to dramatically improve the efficiency of data utilization and increase the competitiveness of companies.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[0059] Step 2:

[0060] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[0061] Step 3:

[0062] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[0063] Step 4:

[0064] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[0065] Step 5:

[0066] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[0067] Step 6:

[0068] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[0069] Step 7:

[0070] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[0071] Step 8:

[0072] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[0073] Step 9:

[0074] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[0075] Step 10:

[0076] The server continuously monitors the frequency of data updates, which is calculated based on past update history and access frequency.

[0077] Step 11:

[0078] The server determines which data to archive based on the archive conditions set. For example, data that has not been updated for six months will be archived.

[0079] Step 12:

[0080] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[0081] Step 13:

[0082] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[0083] Step 14:

[0084] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[0085] Step 15:

[0086] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] Conventional data management systems require separate tasks for data collection, metadata assignment, data classification, update frequency monitoring, archiving, and user management interfaces, resulting in significant man-hours and costs. Furthermore, because these tasks are all performed manually, there is a high risk of errors and data leaks, and management efficiency is low.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes means for accessing a data storage device and collecting data according to a schedule, means for analyzing the data content using a generation AI and automatically generating and assigning metadata to the data, means for learning past data and classification rules using the generation AI and automatically classifying the data, means for monitoring the frequency of data updates and archiving the data based on set conditions, and means for allowing users to edit the metadata and classification rules through a web-based management interface.This reduces the amount of human effort required for data management and enables data to be organized, stored, and utilized with high accuracy.

[0092] "Data storage device" refers to a hardware device used to store digital data in various formats, including cloud storage, data lakes, and local servers.

[0093] A "schedule" refers to a series of planned actions based on a specific period or time period, and is used in the present invention to control the timing of data collection.

[0094] "Metadata" refers to supplementary data that provides information about the content and nature of the data, such as the file creation date, the administrator, the type of data, a description of the data, and how often it is updated.

[0095] "Generative AI" refers to programs or models that use artificial intelligence techniques to analyze data and generate metadata, often using natural language processing techniques.

[0096] A "classification rule" is a set of criteria or rules for organizing data into specific categories, including historical data and predefined rules.

[0097] "Update frequency" refers to the metric that indicates how frequently data is changed or added, and is used to manage and archive data.

[0098] "Archiving" refers to the process of moving data that is no longer in use for long-term storage and managing it efficiently, primarily for the purpose of reducing storage load.

[0099] "Web-based Management Interface" means a user interface accessed by a user through an internet browser for managing data and metadata, including editing and search capabilities.

[0100] "User" refers to anyone who uses this system to manage and manipulate data, and generally includes data managers at companies.

[0101] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[0102] First, the server accesses a data storage device (such as cloud storage or a data lake) and collects data according to a specified schedule. For example, it retrieves data from cloud services such as Amazon S3 and Google® Cloud Storage. At the same time, it also retrieves basic data information (file name, size, and creation date and time) and imports it into local temporary storage. Specifically, it triggers a script every day at 2:00 AM to detect new CSV files from the Amazon S3 bucket and download them to local storage. It also records this basic information in a database.

[0103] Next, the server automatically generates metadata for the collected data using a generative AI model (e.g., GPT-3 (registered trademark)) and assigns it to the data. The data content is analyzed to generate information such as the creation date, administrator, data type, data description, and update frequency. Specifically, the server reads a CSV file stored in local storage, obtains the creation date from the file's metadata, and obtains and assigns administrator information from a separate management system. At the same time, the server uses the generative AI to generate a description of the file's contents and estimates the update frequency from past update history.

[0104] Next, the server uses generative AI to automatically classify the data. Here, the data is sorted into categories such as "sales data," "customer information data," and "product information data" based on predefined classification rules and past data. For example, if a user's purchase history data is imported, that data is classified as "sales data." Similarly, data containing customer contact information is classified as "customer information data."

[0105] Furthermore, the server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (e.g., six months), it determines that the data should be archived and moves it to archive storage (e.g., Amazon Glacier). This reduces the load on the primary storage and allows for efficient management of infrequently used data.

[0106] Finally, the terminal provides users with a web-based management interface. Through this interface, users can view and edit data and metadata as needed. For example, they can add new metadata items or modify existing classification rules. They can also view detailed information about specific data and search for data. The intuitive and user-friendly design of this management interface improves the efficiency of data management.

[0107] Examples of prompt statements

[0108] 1. "Collect and import a new sales data file from your Amazon S3 bucket."

[0109] 2. "Automatically generate metadata for customer information data and store it in the database."

[0110] 3. "Classify the collected data based on predefined rules and organize it into appropriate directories."

[0111] 4. "Check your update history and move any data that hasn't been updated for six months to archive storage."

[0112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0113] Step 1:

[0114] The server accesses the data storage device and collects data according to a schedule.

[0115] Specifically, the script is triggered at 2:00 AM every day. This script accesses cloud storage such as Amazon S3 and Google Cloud Storage and scans for new files. Detected files (e.g., CSV format data) are downloaded to local storage. Basic information such as the file name, size, and creation date and time is also obtained and recorded in a database.

[0116] Input: Cloud storage connection information and collection schedule

[0117] Output: A new data file saved in local storage with its basic information

[0118] Step 2:

[0119] The server automatically generates metadata for the collected data using a generative AI model and attaches it to the data.

[0120] Specifically, the system reads a CSV file stored in local storage. It then uses a generative AI model (e.g., GPT-3) to analyze the file contents and generate metadata. The generated metadata includes the creation date, administrator, data type, data description, update frequency, etc. This metadata is recorded in a database and attached to the original data file.

[0121] Input: Data file stored in local storage

[0122] Output: Generated metadata and the data file to which it is attached

[0123] Step 3:

[0124] The server uses generative AI to automatically classify the data.

[0125] Specifically, the system classifies data into categories such as "sales data," "customer information data," and "product information data" based on metadata information. The generative AI model performs this classification task by learning predefined classification rules and past data. The classified data is moved to the corresponding directory and the information is updated in the database.

[0126] Input: Generated metadata and data files

[0127] Output: Classified data file and updated database information

[0128] Step 4:

[0129] The server continuously monitors the update frequency of the data.

[0130] Specifically, it periodically checks the update history in the database and lists data that has not been updated for a certain period of time (for example, six months). The listed data is automatically moved to archive storage (for example, Amazon Glacier). This movement operation is also recorded in the database.

[0131] Input: Database update history and archive conditions

[0132] Output: Data moved to archive storage and updated database information

[0133] Step 5:

[0134] The terminal provides the user with a web-based management interface.

[0135] Specifically, users access the interface through a web browser and can view and optionally edit data and metadata. The interface is structured as a dashboard, displaying overviews and details for each data category, as well as options for editing metadata. Users can add new metadata items, modify existing classification rules, and search for specific data.

[0136] Input: Access information from web browser and user operations

[0137] Output: Data summary and edit results displayed on the dashboard

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0140] Modern logistics centers are required to efficiently manage massive amounts of data and optimize business operations. However, manually organizing and classifying data and continuously monitoring frequent data updates require a great deal of effort and are not efficient. Furthermore, real-time data management using smart devices and automated package sorting and movement using robots have yet to become widespread. Systems that can solve these issues are needed.

[0141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0142] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, means for displaying and managing data in real time using a smart device, and means for automatically sorting and moving data using a robot, thereby enabling more efficient data management in logistics centers.

[0143] "Generative AI" is an artificial intelligence technology that analyzes the content of data and automatically generates and classifies metadata.

[0144] "Metadata" refers to information that accompanies data, such as the creation date of the data, the administrator, the type of data, a description, and how often it is updated.

[0145] "Monitoring data update frequency" means continuously monitoring how frequently data is updated.

[0146] "Archiving" is the process of moving and storing data that has not been updated for a certain period of time to another storage.

[0147] "Web-based management interface" means a management screen accessible via the Internet that allows editing, viewing, and searching of data and metadata.

[0148] A "smart device" is a device with internet connectivity, such as a smartphone, smart glasses, or a head-mounted display.

[0149] "Automatic sorting by robots" is a process in which robots automatically sort and move packages to the appropriate locations based on the results of data analysis by AI.

[0150] The system that realizes this invention is composed of a server, a terminal, and a user operating in cooperation with each other. Each component and its role will be described below.

[0151] Server Roles

[0152] The server plays a central role and performs the following functions:

[0153] 1. Collecting and importing data

[0154] The server accesses the company's cloud storage or data lake, periodically collects data, and imports it into temporary local storage. For example, it scans at specific times to detect newly added data.

[0155] 2. Automatic generation and assignment of metadata

[0156] Generative AI is used to automatically generate metadata for the collected data, including the creation date, administrator, data type, data description, and update frequency. Specifically, natural language processing technology is used to analyze the data content and generate appropriate metadata.

[0157] 3. Data classification and organization

[0158] Generative AI is used to automatically classify data based on predefined rules and past learning results. For example, data may be classified into categories such as "sales data," "customer information data," and "product information data."

[0159] 4. Data Update and Archiving

[0160] The server monitors the frequency of data updates and archives data that has not been updated for a certain period of time (e.g., six months), thereby reducing the load on the main storage and efficiently managing data that is used infrequently.

[0161] Device Role

[0162] 1. Providing a web-based management interface

[0163] The terminal provides users with a web-based management interface through which they can view and edit data and metadata, as well as view detailed information about specific data and perform data searches.

[0164] 2. Management via smart devices

[0165] Data can be displayed and managed in real time through smart devices such as smartphones, smart glasses, head-mounted displays, etc. For example, an inventory management app can be used to check new inventory data in real time.

[0166] User Roles

[0167] 1. Viewing and editing data

[0168] Users can edit metadata and classification rules through a web-based management interface, allowing for customization of data management.

[0169] 2. Managing Robots

[0170] Users can use robots to automatically sort and move data. Automatic sorting is performed based on the analysis results of the generative AI.

[0171] Prompt Sentence Examples

[0172] New data has been imported. Product name: Apples, Size: 10kg, Stock date: October 10, 2023. Please generate metadata for this data. Also, please estimate how frequently it will be updated.

[0173] In this way, the present invention makes it possible to improve the efficiency of data management in logistics centers and optimize business operations, which is expected to contribute to improving the competitiveness of companies.

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server accesses the company's cloud storage or data lake and collects new data according to a specified schedule. It receives cloud storage access information and collection schedules as input, and obtains the newly collected data and its basic information (file name, size, creation date and time) as output. This data is stored in local temporary storage.

[0177] Step 2:

[0178] The server uses a generation AI on the collected data. Here, the generation AI analyzes the contents of the collected data and automatically generates metadata. The collected data files are passed as input, and metadata (creation date, administrator, data type, data description, update frequency) is generated as output. The metadata assigned to each piece of data is registered in the database.

[0179] Step 3:

[0180] The server uses generative AI to classify data based on predefined rules and past learning results. Data with metadata attached is passed as input, and classification results (e.g., sales data, customer information data, product information data) are obtained as output. The classified data is organized by category.

[0181] Step 4:

[0182] The server continuously monitors the frequency of data updates. The data update history and current date and time are passed as input, and the result of evaluating the update frequency is obtained as output. Based on this result, data that has not been updated for a certain period of time is moved to archive storage.

[0183] Step 5:

[0184] The terminal provides a web-based management interface to the user, which allows the user to view and edit metadata and classification rules. The input is the metadata and classification rules the user wants to edit, and the output is the updated metadata and classification rules.

[0185] Step 6:

[0186] Terminals use smart devices to display and manage data in real time. A specific data request is passed as input, and the data is displayed on the screen as output. For example, an inventory management app on a smartphone can be used to check new inventory data in real time.

[0187] Step 7:

[0188] Users use robots to automatically sort and move data. Metadata and classification results are passed as input, and the robot automatically sorts and moves the data to the appropriate location as output. For example, incoming parcels are automatically sorted and moved to the designated shelves.

[0189] These steps will enable more efficient data management at logistics centers and optimize business operations.

[0190] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0191] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[0192] Data collection and import

[0193] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[0194] Automatic generation and assignment of metadata

[0195] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[0196] Creation date: Automatically taken from file meta information.

[0197] Administrator: Retrieves information from the user management system.

[0198] Data type: Automatically determined from file format and content.

[0199] Data description: Generated based on the results of AI content analysis.

[0200] Update frequency: Estimated based on past update history.

[0201] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[0202] Data classification and organization

[0203] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[0204] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[0205] Data Updates and Archiving

[0206] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[0207] Use of emotion engine

[0208] The system also incorporates an emotion engine that recognizes the user's emotional state in real time. When a user operates the management interface, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data can be used as follows:

[0209] The server dynamically changes the display content and operation method of the management interface based on the emotional data. For example, if the user is feeling stressed, it simplifies the operation procedure or displays a support message.

[0210] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[0211] Providing a management interface

[0212] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[0213] Furthermore, by reflecting the user's emotional state, more personalized operations are possible, improving the user experience.

[0214] This system allows companies to significantly reduce the amount of man-hours required for data management and allows them to organize, store, and utilize data with high accuracy. The introduction of the emotion engine also improves user efficiency, dramatically improving the overall efficiency of data utilization.

[0215] The processing flow will be explained below.

[0216] Step 1:

[0217] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[0218] Step 2:

[0219] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[0220] Step 3:

[0221] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[0222] Step 4:

[0223] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[0224] Step 5:

[0225] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[0226] Step 6:

[0227] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[0228] Step 7:

[0229] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[0230] Step 8:

[0231] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[0232] Step 9:

[0233] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[0234] Step 10:

[0235] The server continuously monitors how frequently the data is updated, for example by recording when the data was last updated and tracking how frequently it is updated.

[0236] Step 11:

[0237] The server determines which data to archive based on the set archive conditions. For example, data that has not been updated for six months is archived.

[0238] Step 12:

[0239] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[0240] Step 13:

[0241] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[0242] Step 14:

[0243] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[0244] Step 15:

[0245] The server uses an emotion engine to monitor the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time.

[0246] Step 16:

[0247] The server dynamically changes the display content and operation methods of the management interface based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the operation procedure can be simplified or a support message can be displayed.

[0248] Step 17:

[0249] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[0250] Step 18:

[0251] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[0252] Example 2

[0253] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0254] In recent years, the amount of data handled by companies and organizations has exploded, making data management extremely complex and burdensome. While improving the efficiency of data management is important, processes such as automatic metadata generation and data classification are often performed manually, resulting in time-consuming and costly issues. Furthermore, while improving user operational efficiency is also necessary, there has been little progress in interface design that takes into account the user's emotional state. The purpose of this invention is to solve these problems and improve the overall efficiency of data management.

[0255] The identification process 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 automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the update frequency of data and archiving the data based on set conditions, means for allowing a user to edit the metadata and classification rules through a web-based management interface, means for providing dynamic interface changes according to the user's operating status using an emotion engine that recognizes the user's emotions, and means for assigning the results of the emotion recognition to the data as metadata. This makes it possible to automate and efficiently manage data and improve the user's operating experience.

[0256] "Generative AI" refers to artificial intelligence systems used to analyze data content and generate metadata.

[0257] "Metadata" is additional information that describes the attributes and content of data, making it easier to manage and search for the data.

[0258] "Data classification" is the process of separating collected data into specific categories, making it easier to organize and manage.

[0259] "Update frequency" indicates the frequency of time intervals at which data is updated, and is an index for evaluating the recency of data.

[0260] "Archiving" is the process of moving data that has not been updated for a certain period of time to another storage device for long-term storage.

[0261] A "web-based management interface" is an interface for data management that a user can access through a web browser.

[0262] The "emotion engine" is a system that recognizes the user's emotional state in real time and analyzes that data.

[0263] "Dynamic interface change" is the process of changing the display and operation of the management interface in real time according to the user's emotional state.

[0264] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[0265] Data collection and import

[0266] First, the server starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded. The hardware used includes the company's cloud storage server and data lake system.

[0267] Examples:

[0268] The server scans the cloud storage for newly added files every day at 2:00 AM and imports them into local temporary storage.

[0269] At this time, the file name, size, and creation date and time are recorded at the same time.

[0270] Automatic generation and assignment of metadata

[0271] The server then analyzes the collected data using AI generation to automatically generate metadata, such as OpenAI's GPT model. This metadata includes the creation date, administrator, data type, data description, and update frequency.

[0272] Examples:

[0273] The server analyzes CSV files imported from the company's customer database and automatically assigns the creation date, administrator, data type, data description, and update frequency.

[0274] Data classification and organization

[0275] The server then uses generative AI to categorize the collected data, using predefined classification rules and the results of past data analysis.

[0276] Examples:

[0277] The server categorizes the user's purchase history data as "sales data" and the customer's contact information as "customer information data."

[0278] Data Updates and Archiving

[0279] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (for example, six months) is automatically moved to archive storage, reducing the load on the main storage.

[0280] Examples:

[0281] The server automatically moves unused customer information data to archive storage.

[0282] Use of emotion engine

[0283] The system also incorporates an emotion engine that recognizes the user's emotional state in real time as they operate the management interface. The emotion engine analyzes the user's facial expressions and tone of voice, and dynamically changes the content displayed and the operation method of the interface based on the results.

[0284] Examples:

[0285] If the emotion engine detects stress while the user is operating the data management interface, the server simplifies the operating procedure.

[0286] Providing a management interface

[0287] The terminal provides users with a web-based management interface that allows them to view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[0288] Examples:

[0289] Through the interface, users add new metadata items and modify existing classification rules.

[0290] Examples of prompt statements

[0291] Below are some example prompts to input to the generative AI model:

[0292] Write a program to automatically generate and assign the necessary metadata (creation date, administrator, data type, data description, update frequency) to a CSV file imported by a user from a company's customer database.

[0293] The above is a detailed description of the embodiment of the present invention, which enables the system to automate and streamline data management, improving the user's operational experience.

[0294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0295] Step 1:

[0296] The server accesses the company's cloud storage or data lake and scans the data according to a specified schedule (e.g., daily at 2:00 AM).

[0297] Input: Cloud storage and data lake access information and schedule information

[0298] Output: List of newly added files

[0299] Specific behavior: Retrieve a list of new files from cloud storage.

[0300] Step 2:

[0301] The server scans and detects newly added files and imports them into local temporary storage, recording basic information such as file name, size, and creation date and time.

[0302] Input: Newly added file list

[0303] Output: Files imported into local temporary storage and their basic information

[0304] Specific behavior: Downloads new files and records their filenames, sizes, and creation dates.

[0305] Step 3:

[0306] The server uses generative AI (e.g., OpenAI's GPT model) to analyze the contents of the collected data and automatically generate metadata (creation date, administrator, data type, data description, and update frequency).

[0307] Input: A file in local temporary storage

[0308] Output: Auto-generated metadata

[0309] Specific operation: Analyze the file contents using generative AI and generate the necessary metadata.

[0310] Step 4:

[0311] The server uses generative AI to classify the collected data into categories based on classification rules and the results of analysis of past data.

[0312] Input: Files in local temporary storage with auto-generated metadata

[0313] Output: Data categorized by category

[0314] Specific operation: Uses generative AI to analyze the content of the data and classify it into appropriate categories.

[0315] Step 5:

[0316] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (e.g., six months) is automatically moved to archive storage.

[0317] Input: Categorized data and its metadata

[0318] Output: Data moved to archive storage

[0319] Specific operation: Check the update date and time of the data and perform archiving based on the conditions.

[0320] Step 6:

[0321] The server uses an emotion engine to recognize the emotional state of the user while operating the management interface, and dynamically changes the display content and operation method of the interface based on the results.

[0322] Input: User's facial expressions and voice tone

[0323] Output: Dynamically changed management interface

[0324] Specific behavior: Adjust the interface based on the emotions recognized by the emotion engine.

[0325] Step 7:

[0326] The server generates the emotion recognition results as metadata and attaches it to the data.

[0327] Input: User's emotional state

[0328] Output: Metadata with emotional state

[0329] Specific operation: Emotional state is generated as metadata and added to the data.

[0330] Step 8:

[0331] The terminal provides a web-based management interface, allowing users to edit metadata and classification rules.

[0332] Input: User edit request

[0333] Output: Updated metadata and classification rules

[0334] Specific behavior: Updates metadata and classification rules based on user input.

[0335] In this way, the system efficiently and automatically performs data collection, analysis, classification, archiving, and dynamic interface changes based on the user's emotional state at each stage of data management.

[0336] (Application example 2)

[0337] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0338] In modern factories, the efficiency of production processes and data management are becoming increasingly important. In particular, manually processing large amounts of data, such as collecting, organizing, classifying, and archiving data, is a labor-intensive process, leading to reduced efficiency and data errors. Furthermore, uniform user interfaces that ignore the emotional state of workers increase operational complexity and stress, resulting in reduced productivity. To address these issues, automated data management systems and personalized interfaces that take the user's emotional state into account are needed.

[0339] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0340] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, and means for recognizing the user's emotional state using an emotion engine and dynamically changing the display content and operation method of the management interface based on the emotion data. This not only enables automatic and efficient management of large amounts of data, but also provides a highly operable interface that takes the worker's emotional state into consideration, thereby improving productivity.

[0341] "Generative AI" is an artificial intelligence technology that automatically generates data and generates metadata based on that data.

[0342] "Metadata" is data that indicates additional information such as the attributes and content of data, the creation date and time, and the administrator.

[0343] "Data classification" is the process of automatically separating collected data into categories or types based on their content.

[0344] "Archiving" is the process of automatically moving and storing data that has not been updated for a certain period of time to another storage device, thereby reducing the load on the primary storage device.

[0345] "Web-based management interface" means a user interface available on the web that allows for viewing and editing of data and metadata.

[0346] "Recognizing the user's emotional state" means using cameras and audio sensors to analyze the user's emotions in real time from their facial expressions and tone of voice.

[0347] An "emotion engine" is software that analyzes a user's emotions and adjusts the system's behavior based on those emotions.

[0348] "Dynamic change of the display content and operation method of the management interface" refers to the process of adjusting the interface content and operation procedure in real time based on the user's emotional data.

[0349] "Monitoring update frequency" is the process of continually monitoring how frequently data is updated.

[0350] The system of the present invention includes a metadata generation means using generative AI, a data classification means, an update frequency monitoring means, a web-based management interface, and an emotion recognition means using an emotion engine.

[0351] First, the server accesses the company's cloud storage or data lake and collects data according to a specified schedule. The collected data is analyzed using generative AI, and metadata is automatically generated. The metadata includes information such as the creation date, administrator, data type, data description, and update frequency. For example, a CSV file imported from a company's production data can be analyzed, and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" can be automatically assigned.

[0352] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "production data," "quality control data," and "equipment maintenance data."

[0353] Furthermore, the server continuously monitors the frequency of data updates and determines that data that has not been updated for a certain period of time (for example, six months) meets the conditions for archiving. Data that is subject to archiving is automatically moved to a separate storage device and managed as an archive.

[0354] The terminal also provides a user interface to the worker. When the worker operates the user interface, an emotion engine analyzes the worker's facial expressions and voice tone to obtain emotional data. Based on this emotional data, the server dynamically changes the display content and operation method of the management interface. For example, if a worker is feeling stressed, the server can simplify the operation procedure or display a support message. This emotional data is also generated as metadata, which can be used to improve the system over the long term.

[0355] Specifically, Tensorflow (registered trademark) and PyTorch are used for generative AI, while OpenCV and DeepFace are used for emotion recognition, with data collection, analysis, classification, archiving, emotion recognition, and interface optimization being carried out at each step. This not only enables automatic and efficient management of large amounts of data, but also makes it possible to provide a highly user-friendly interface that takes into account the emotional state of the worker, which is expected to improve productivity.

[0356] An example of a prompt is, "Please import new customer data from the customer database. Generate the following metadata for that data: - Creation date - Administrator - Data type - Data description - Update frequency." This is input into the generative AI model to generate the metadata.

[0357] These features enable companies to significantly reduce the effort required for data management and to organize, store, and utilize data with high accuracy.

[0358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0359] Step 1: Collect and import data

[0360] The server collects data from the company's cloud storage and data lake according to a specified schedule. Specifically, the server periodically scans the cloud storage to detect newly added files. Detected files are imported into local temporary storage and basic information such as file name, size, and creation date and time is recorded.

[0361] Input: Cloud storage and data lake connection information, schedule information

[0362] Output: Imported data, basic file information

[0363] Step 2: Automatically generate and assign metadata

[0364] The server automatically generates metadata for the imported data using a generation AI, which analyzes the data content and generates information such as the creation date, administrator, data type, data description, and update frequency, and assigns it to the data.

[0365] Input: Imported data, basic information of the file

[0366] Output: Data with metadata

[0367] Step 3: Classify the data

[0368] The server uses generative AI to categorize the metadata-annotated data into categories such as "production data," "quality control data," and "machine maintenance data" based on predefined classification rules and the results of learning from past data.

[0369] Input: Data with metadata, classification rules

[0370] Output: Classified data

[0371] Step 4: Monitoring and archiving data frequency

[0372] The server continuously monitors the frequency of data updates. Data that has not been updated for a set period of time (e.g., six months) is archived and automatically moved to another storage device.

[0373] Input: Classified data, update frequency monitoring rules

[0374] Output: Archived data

[0375] Step 5: Emotion Recognition and Interface Optimization

[0376] As the user operates the device's interface, the device uses cameras and audio sensors to recognize the user's emotions in real time. Based on the analyzed emotional data, the server dynamically changes the display content and operation methods of the management interface. For example, if the user is feeling stressed, the operating procedure will be simplified and a support message will be displayed.

[0377] Input: User's face image, voice data

[0378] Output: User emotion data, optimized interface display content

[0379] Step 6: Providing a management interface

[0380] The terminal provides users with a web-based management interface through which they can view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[0381] Input: User operation request

[0382] Output: Operation results, edited data

[0383] This will improve productivity by streamlining data management and optimizing the interface to suit individual emotions.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0385] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0390] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0392] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0394] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0395] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0396] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0399] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0400] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[0401] Data collection and import

[0402] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[0403] Automatic generation and assignment of metadata

[0404] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[0405] Creation date: Automatically taken from file meta information.

[0406] Administrator: Retrieves information from the user management system.

[0407] Data type: Automatically determined from file format and content.

[0408] Data description: Generated based on the results of AI content analysis.

[0409] Update frequency: Estimated based on past update history.

[0410] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[0411] Data classification and organization

[0412] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[0413] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[0414] Data Updates and Archiving

[0415] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[0416] Providing a management interface

[0417] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[0418] This system will enable companies to significantly reduce the amount of man-hours required for data management and enable them to organize, store, and utilize data with high accuracy, which is expected to dramatically improve the efficiency of data utilization and increase the competitiveness of companies.

[0419] The processing flow will be explained below.

[0420] Step 1:

[0421] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[0422] Step 2:

[0423] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[0424] Step 3:

[0425] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[0426] Step 4:

[0427] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[0428] Step 5:

[0429] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[0430] Step 6:

[0431] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[0432] Step 7:

[0433] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[0434] Step 8:

[0435] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[0436] Step 9:

[0437] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[0438] Step 10:

[0439] The server continuously monitors the frequency of data updates, which is calculated based on past update history and access frequency.

[0440] Step 11:

[0441] The server determines which data to archive based on the archive conditions set. For example, data that has not been updated for six months will be archived.

[0442] Step 12:

[0443] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[0444] Step 13:

[0445] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[0446] Step 14:

[0447] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[0448] Step 15:

[0449] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[0450] Example 1

[0451] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0452] Conventional data management systems require separate tasks for data collection, metadata assignment, data classification, update frequency monitoring, archiving, and user management interfaces, resulting in significant man-hours and costs. Furthermore, because these tasks are all performed manually, there is a high risk of errors and data leaks, and management efficiency is low.

[0453] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0454] In this invention, the server includes means for accessing a data storage device and collecting data according to a schedule, means for analyzing the data content using a generation AI and automatically generating and assigning metadata to the data, means for learning past data and classification rules using the generation AI and automatically classifying the data, means for monitoring the frequency of data updates and archiving the data based on set conditions, and means for allowing users to edit the metadata and classification rules through a web-based management interface.This reduces the amount of human effort required for data management and enables data to be organized, stored, and utilized with high accuracy.

[0455] "Data storage device" refers to a hardware device used to store digital data in various formats, including cloud storage, data lakes, and local servers.

[0456] A "schedule" refers to a series of planned actions based on a specific period or time period, and is used in the present invention to control the timing of data collection.

[0457] "Metadata" refers to supplementary data that provides information about the content and nature of the data, such as the file creation date, the administrator, the type of data, a description of the data, and how often it is updated.

[0458] "Generative AI" refers to programs or models that use artificial intelligence techniques to analyze data and generate metadata, often using natural language processing techniques.

[0459] A "classification rule" is a set of criteria or rules for organizing data into specific categories, including historical data and predefined rules.

[0460] "Update frequency" refers to the metric that indicates how frequently data is changed or added, and is used to manage and archive data.

[0461] "Archiving" refers to the process of moving data that is no longer in use for long-term storage and managing it efficiently, primarily for the purpose of reducing storage load.

[0462] "Web-based Management Interface" means a user interface accessed by a user through an internet browser for managing data and metadata, including editing and search capabilities.

[0463] "User" refers to anyone who uses this system to manage and manipulate data, and generally includes data managers at companies.

[0464] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[0465] First, the server accesses a data storage device (such as cloud storage or a data lake) and collects data according to a specified schedule. For example, it retrieves data from cloud services such as Amazon S3 or Google Cloud Storage. At the same time, it also retrieves basic data information (file name, size, creation date and time) and imports it into local temporary storage. Specifically, it triggers a script at 2:00 AM every day to detect new CSV files from the Amazon S3 bucket and download them to local storage. It also records this basic information in a database.

[0466] Next, the server uses a generative AI model (e.g., GPT-3) to automatically generate metadata for the collected data and assign it to the data. It analyzes the data content and generates information such as the creation date, administrator, data type, data description, and update frequency. Specifically, it reads the CSV file stored in local storage, obtains the creation date from the file's metadata, and assigns administrator information obtained from a separate management system. At the same time, it uses the generative AI to generate a description of the file content and estimates the update frequency from past update history.

[0467] Next, the server uses generative AI to automatically classify the data. Here, the data is sorted into categories such as "sales data," "customer information data," and "product information data" based on predefined classification rules and past data. For example, if a user's purchase history data is imported, that data is classified as "sales data." Similarly, data containing customer contact information is classified as "customer information data."

[0468] Furthermore, the server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (e.g., six months), it determines that the data should be archived and moves it to archive storage (e.g., Amazon Glacier). This reduces the load on the primary storage and allows for efficient management of infrequently used data.

[0469] Finally, the terminal provides users with a web-based management interface. Through this interface, users can view and edit data and metadata as needed. For example, they can add new metadata items or modify existing classification rules. They can also view detailed information about specific data and search for data. The intuitive and user-friendly design of this management interface improves the efficiency of data management.

[0470] Examples of prompt statements

[0471] 1. "Collect and import a new sales data file from your Amazon S3 bucket."

[0472] 2. "Automatically generate metadata for customer information data and store it in the database."

[0473] 3. "Classify the collected data based on predefined rules and organize it into appropriate directories."

[0474] 4. "Check your update history and move any data that hasn't been updated for six months to archive storage."

[0475] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0476] Step 1:

[0477] The server accesses the data storage device and collects data according to a schedule.

[0478] Specifically, the script is triggered at 2:00 AM every day. This script accesses cloud storage such as Amazon S3 and Google Cloud Storage and scans for new files. Detected files (e.g., CSV format data) are downloaded to local storage. Basic information such as the file name, size, and creation date and time is also obtained and recorded in a database.

[0479] Input: Cloud storage connection information and collection schedule

[0480] Output: A new data file saved in local storage with its basic information

[0481] Step 2:

[0482] The server automatically generates metadata for the collected data using a generative AI model and attaches it to the data.

[0483] Specifically, the system reads a CSV file stored in local storage. It then uses a generative AI model (e.g., GPT-3) to analyze the file contents and generate metadata. The generated metadata includes the creation date, administrator, data type, data description, update frequency, etc. This metadata is recorded in a database and attached to the original data file.

[0484] Input: Data file stored in local storage

[0485] Output: Generated metadata and the data file to which it is attached

[0486] Step 3:

[0487] The server uses generative AI to automatically classify the data.

[0488] Specifically, the system classifies data into categories such as "sales data," "customer information data," and "product information data" based on metadata information. The generative AI model performs this classification task by learning predefined classification rules and past data. The classified data is moved to the corresponding directory and the information is updated in the database.

[0489] Input: Generated metadata and data files

[0490] Output: Classified data file and updated database information

[0491] Step 4:

[0492] The server continuously monitors the update frequency of the data.

[0493] Specifically, it periodically checks the update history in the database and lists data that has not been updated for a certain period of time (for example, six months). The listed data is automatically moved to archive storage (for example, Amazon Glacier). This movement operation is also recorded in the database.

[0494] Input: Database update history and archive conditions

[0495] Output: Data moved to archive storage and updated database information

[0496] Step 5:

[0497] The terminal provides the user with a web-based management interface.

[0498] Specifically, users access the interface through a web browser and can view and optionally edit data and metadata. The interface is structured as a dashboard, displaying overviews and details for each data category, as well as options for editing metadata. Users can add new metadata items, modify existing classification rules, and search for specific data.

[0499] Input: Access information from web browser and user operations

[0500] Output: Data summary and edit results displayed on the dashboard

[0501] (Application example 1)

[0502] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0503] Modern logistics centers are required to efficiently manage massive amounts of data and optimize business operations. However, manually organizing and classifying data and continuously monitoring frequent data updates require a great deal of effort and are not efficient. Furthermore, real-time data management using smart devices and automated package sorting and movement using robots have yet to become widespread. Systems that can solve these issues are needed.

[0504] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0505] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, means for displaying and managing data in real time using a smart device, and means for automatically sorting and moving data using a robot, thereby enabling more efficient data management in logistics centers.

[0506] "Generative AI" is an artificial intelligence technology that analyzes the content of data and automatically generates and classifies metadata.

[0507] "Metadata" refers to information that accompanies data, such as the creation date of the data, the administrator, the type of data, a description, and how often it is updated.

[0508] "Monitoring data update frequency" means continuously monitoring how frequently data is updated.

[0509] "Archiving" is the process of moving and storing data that has not been updated for a certain period of time to another storage.

[0510] "Web-based management interface" means a management screen accessible via the Internet that allows editing, viewing, and searching of data and metadata.

[0511] A "smart device" is a device with internet connectivity, such as a smartphone, smart glasses, or a head-mounted display.

[0512] "Automatic sorting by robots" is a process in which robots automatically sort and move packages to the appropriate locations based on the results of data analysis by AI.

[0513] The system that realizes this invention is composed of a server, a terminal, and a user operating in cooperation with each other. Each component and its role will be described below.

[0514] Server Roles

[0515] The server plays a central role and performs the following functions:

[0516] 1. Collecting and importing data

[0517] The server accesses the company's cloud storage or data lake, periodically collects data, and imports it into temporary local storage. For example, it scans at specific times to detect newly added data.

[0518] 2. Automatic generation and assignment of metadata

[0519] Generative AI is used to automatically generate metadata for the collected data, including the creation date, administrator, data type, data description, and update frequency. Specifically, natural language processing technology is used to analyze the data content and generate appropriate metadata.

[0520] 3. Data classification and organization

[0521] Generative AI is used to automatically classify data based on predefined rules and past learning results. For example, data may be classified into categories such as "sales data," "customer information data," and "product information data."

[0522] 4. Data Update and Archiving

[0523] The server monitors the frequency of data updates and archives data that has not been updated for a certain period of time (e.g., six months), thereby reducing the load on the main storage and efficiently managing data that is used infrequently.

[0524] Device Role

[0525] 1. Providing a web-based management interface

[0526] The terminal provides users with a web-based management interface through which they can view and edit data and metadata, as well as view detailed information about specific data and perform data searches.

[0527] 2. Management via smart devices

[0528] Data can be displayed and managed in real time through smart devices such as smartphones, smart glasses, head-mounted displays, etc. For example, an inventory management app can be used to check new inventory data in real time.

[0529] User Roles

[0530] 1. Viewing and editing data

[0531] Users can edit metadata and classification rules through a web-based management interface, allowing for customization of data management.

[0532] 2. Managing Robots

[0533] Users can use robots to automatically sort and move data. Automatic sorting is performed based on the analysis results of the generative AI.

[0534] Prompt Sentence Examples

[0535] New data has been imported. Product name: Apples, Size: 10kg, Stock date: October 10, 2023. Please generate metadata for this data. Also, please estimate how frequently it will be updated.

[0536] In this way, the present invention makes it possible to improve the efficiency of data management in logistics centers and optimize business operations, which is expected to contribute to improving the competitiveness of companies.

[0537] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0538] Step 1:

[0539] The server accesses the company's cloud storage or data lake and collects new data according to a specified schedule. It receives cloud storage access information and collection schedules as input, and obtains the newly collected data and its basic information (file name, size, creation date and time) as output. This data is stored in local temporary storage.

[0540] Step 2:

[0541] The server uses a generation AI on the collected data. Here, the generation AI analyzes the contents of the collected data and automatically generates metadata. The collected data files are passed as input, and metadata (creation date, administrator, data type, data description, update frequency) is generated as output. The metadata assigned to each piece of data is registered in the database.

[0542] Step 3:

[0543] The server uses generative AI to classify data based on predefined rules and past learning results. Data with metadata attached is passed as input, and classification results (e.g., sales data, customer information data, product information data) are obtained as output. The classified data is organized by category.

[0544] Step 4:

[0545] The server continuously monitors the frequency of data updates. The data update history and current date and time are passed as input, and the result of evaluating the update frequency is obtained as output. Based on this result, data that has not been updated for a certain period of time is moved to archive storage.

[0546] Step 5:

[0547] The terminal provides a web-based management interface to the user, which allows the user to view and edit metadata and classification rules. The input is the metadata and classification rules the user wants to edit, and the output is the updated metadata and classification rules.

[0548] Step 6:

[0549] Terminals use smart devices to display and manage data in real time. A specific data request is passed as input, and the data is displayed on the screen as output. For example, an inventory management app on a smartphone can be used to check new inventory data in real time.

[0550] Step 7:

[0551] Users use robots to automatically sort and move data. Metadata and classification results are passed as input, and the robot automatically sorts and moves the data to the appropriate location as output. For example, incoming parcels are automatically sorted and moved to the designated shelves.

[0552] These steps will enable more efficient data management at logistics centers and optimize business operations.

[0553] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0554] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[0555] Data collection and import

[0556] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[0557] Automatic generation and assignment of metadata

[0558] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[0559] Creation date: Automatically taken from file meta information.

[0560] Administrator: Retrieves information from the user management system.

[0561] Data type: Automatically determined from file format and content.

[0562] Data description: Generated based on the results of AI content analysis.

[0563] Update frequency: Estimated based on past update history.

[0564] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[0565] Data classification and organization

[0566] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[0567] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[0568] Data Updates and Archiving

[0569] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[0570] Use of emotion engine

[0571] The system also incorporates an emotion engine that recognizes the user's emotional state in real time. When a user operates the management interface, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data can be used as follows:

[0572] The server dynamically changes the display content and operation method of the management interface based on the emotional data. For example, if the user is feeling stressed, it simplifies the operation procedure or displays a support message.

[0573] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[0574] Providing a management interface

[0575] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[0576] Furthermore, by reflecting the user's emotional state, more personalized operations are possible, improving the user experience.

[0577] This system allows companies to significantly reduce the amount of man-hours required for data management and allows them to organize, store, and utilize data with high accuracy. The introduction of the emotion engine also improves user efficiency, dramatically improving the overall efficiency of data utilization.

[0578] The processing flow will be explained below.

[0579] Step 1:

[0580] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[0581] Step 2:

[0582] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[0583] Step 3:

[0584] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[0585] Step 4:

[0586] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[0587] Step 5:

[0588] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[0589] Step 6:

[0590] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[0591] Step 7:

[0592] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[0593] Step 8:

[0594] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[0595] Step 9:

[0596] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[0597] Step 10:

[0598] The server continuously monitors how frequently the data is updated, for example by recording when the data was last updated and tracking how frequently it is updated.

[0599] Step 11:

[0600] The server determines which data to archive based on the set archive conditions. For example, data that has not been updated for six months is archived.

[0601] Step 12:

[0602] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[0603] Step 13:

[0604] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[0605] Step 14:

[0606] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[0607] Step 15:

[0608] The server uses an emotion engine to monitor the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time.

[0609] Step 16:

[0610] The server dynamically changes the display content and operation methods of the management interface based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the operation procedure can be simplified or a support message can be displayed.

[0611] Step 17:

[0612] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[0613] Step 18:

[0614] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[0615] Example 2

[0616] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0617] In recent years, the amount of data handled by companies and organizations has exploded, making data management extremely complex and burdensome. While improving the efficiency of data management is important, processes such as automatic metadata generation and data classification are often performed manually, resulting in time-consuming and costly issues. Furthermore, while improving user operational efficiency is also necessary, there has been little progress in interface design that takes into account the user's emotional state. The purpose of this invention is to solve these problems and improve the overall efficiency of data management.

[0618] The identification process 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 automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the update frequency of data and archiving the data based on set conditions, means for allowing a user to edit the metadata and classification rules through a web-based management interface, means for providing dynamic interface changes according to the user's operating status using an emotion engine that recognizes the user's emotions, and means for assigning the results of the emotion recognition to the data as metadata. This makes it possible to automate and efficiently manage data and improve the user's operating experience.

[0619] "Generative AI" refers to artificial intelligence systems used to analyze data content and generate metadata.

[0620] "Metadata" is additional information that describes the attributes and content of data, making it easier to manage and search for the data.

[0621] "Data classification" is the process of separating collected data into specific categories, making it easier to organize and manage.

[0622] "Update frequency" indicates the frequency of time intervals at which data is updated, and is an index for evaluating the recency of data.

[0623] "Archiving" is the process of moving data that has not been updated for a certain period of time to another storage device for long-term storage.

[0624] A "web-based management interface" is an interface for data management that a user can access through a web browser.

[0625] The "emotion engine" is a system that recognizes the user's emotional state in real time and analyzes that data.

[0626] "Dynamic interface change" is the process of changing the display and operation of the management interface in real time according to the user's emotional state.

[0627] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[0628] Data collection and import

[0629] First, the server starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded. The hardware used includes the company's cloud storage server and data lake system.

[0630] Examples:

[0631] The server scans the cloud storage for newly added files every day at 2:00 AM and imports them into local temporary storage.

[0632] At this time, the file name, size, and creation date and time are recorded at the same time.

[0633] Automatic generation and assignment of metadata

[0634] The server then analyzes the collected data using AI technology, such as OpenAI's GPT model, to automatically generate metadata, including the creation date, administrator, data type, data description, and update frequency.

[0635] Examples:

[0636] The server analyzes CSV files imported from the company's customer database and automatically assigns the creation date, administrator, data type, data description, and update frequency.

[0637] Data classification and organization

[0638] The server then uses generative AI to categorize the collected data, using predefined classification rules and the results of past data analysis.

[0639] Examples:

[0640] The server categorizes the user's purchase history data as "sales data" and the customer's contact information as "customer information data."

[0641] Data Updates and Archiving

[0642] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (for example, six months) is automatically moved to archive storage, reducing the load on the main storage.

[0643] Examples:

[0644] The server automatically moves unused customer information data to archive storage.

[0645] Use of emotion engine

[0646] The system also incorporates an emotion engine that recognizes the user's emotional state in real time as they operate the management interface. The emotion engine analyzes the user's facial expressions and tone of voice, and dynamically changes the content displayed and the operation method of the interface based on the results.

[0647] Examples:

[0648] If the emotion engine detects stress while the user is operating the data management interface, the server simplifies the operating procedure.

[0649] Providing a management interface

[0650] The terminal provides users with a web-based management interface that allows them to view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[0651] Examples:

[0652] Through the interface, users add new metadata items and modify existing classification rules.

[0653] Examples of prompt statements

[0654] Below are some example prompts to input to the generative AI model:

[0655] Write a program to automatically generate and assign the necessary metadata (creation date, administrator, data type, data description, update frequency) to a CSV file imported by a user from a company's customer database.

[0656] The above is a detailed description of the embodiment of the present invention, which enables the system to automate and streamline data management, improving the user's operational experience.

[0657] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0658] Step 1:

[0659] The server accesses the company's cloud storage or data lake and scans the data according to a specified schedule (e.g., daily at 2:00 AM).

[0660] Input: Cloud storage and data lake access information and schedule information

[0661] Output: List of newly added files

[0662] Specific behavior: Retrieve a list of new files from cloud storage.

[0663] Step 2:

[0664] The server scans and detects newly added files and imports them into local temporary storage, recording basic information such as file name, size, and creation date and time.

[0665] Input: Newly added file list

[0666] Output: Files imported into local temporary storage and their basic information

[0667] Specific behavior: Downloads new files and records their filenames, sizes, and creation dates.

[0668] Step 3:

[0669] The server uses generative AI (e.g., OpenAI's GPT model) to analyze the contents of the collected data and automatically generate metadata (creation date, administrator, data type, data description, and update frequency).

[0670] Input: A file in local temporary storage

[0671] Output: Auto-generated metadata

[0672] Specific operation: Analyze the file contents using generative AI and generate the necessary metadata.

[0673] Step 4:

[0674] The server uses generative AI to classify the collected data into categories based on classification rules and the results of analysis of past data.

[0675] Input: Files in local temporary storage with auto-generated metadata

[0676] Output: Data categorized by category

[0677] Specific operation: Uses generative AI to analyze the content of the data and classify it into appropriate categories.

[0678] Step 5:

[0679] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (e.g., six months) is automatically moved to archive storage.

[0680] Input: Categorized data and its metadata

[0681] Output: Data moved to archive storage

[0682] Specific operation: Check the update date and time of the data and perform archiving based on the conditions.

[0683] Step 6:

[0684] The server uses an emotion engine to recognize the emotional state of the user while operating the management interface, and dynamically changes the display content and operation method of the interface based on the results.

[0685] Input: User's facial expressions and voice tone

[0686] Output: Dynamically changed management interface

[0687] Specific behavior: Adjust the interface based on the emotions recognized by the emotion engine.

[0688] Step 7:

[0689] The server generates the emotion recognition results as metadata and attaches it to the data.

[0690] Input: User's emotional state

[0691] Output: Metadata with emotional state

[0692] Specific operation: Emotional state is generated as metadata and added to the data.

[0693] Step 8:

[0694] The terminal provides a web-based management interface, allowing users to edit metadata and classification rules.

[0695] Input: User edit request

[0696] Output: Updated metadata and classification rules

[0697] Specific behavior: Updates metadata and classification rules based on user input.

[0698] In this way, the system efficiently and automatically performs data collection, analysis, classification, archiving, and dynamic interface changes based on the user's emotional state at each stage of data management.

[0699] (Application example 2)

[0700] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0701] In modern factories, the efficiency of production processes and data management are becoming increasingly important. In particular, manually processing large amounts of data, such as collecting, organizing, classifying, and archiving data, is a labor-intensive process, leading to reduced efficiency and data errors. Furthermore, uniform user interfaces that ignore the emotional state of workers increase operational complexity and stress, resulting in reduced productivity. To address these issues, automated data management systems and personalized interfaces that take the user's emotional state into account are needed.

[0702] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0703] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, and means for recognizing the user's emotional state using an emotion engine and dynamically changing the display content and operation method of the management interface based on the emotion data. This not only enables automatic and efficient management of large amounts of data, but also provides a highly operable interface that takes the worker's emotional state into consideration, thereby improving productivity.

[0704] "Generative AI" is an artificial intelligence technology that automatically generates data and generates metadata based on that data.

[0705] "Metadata" is data that indicates additional information such as the attributes and content of data, the creation date and time, and the administrator.

[0706] "Data classification" is the process of automatically separating collected data into categories or types based on their content.

[0707] "Archiving" is the process of automatically moving and storing data that has not been updated for a certain period of time to another storage device, thereby reducing the load on the primary storage device.

[0708] "Web-based management interface" means a user interface available on the web that allows for viewing and editing of data and metadata.

[0709] "Recognizing the user's emotional state" means using cameras and audio sensors to analyze the user's emotions in real time from their facial expressions and tone of voice.

[0710] An "emotion engine" is software that analyzes a user's emotions and adjusts the system's behavior based on those emotions.

[0711] "Dynamic change of the display content and operation method of the management interface" refers to the process of adjusting the interface content and operation procedure in real time based on the user's emotional data.

[0712] "Monitoring update frequency" is the process of continually monitoring how frequently data is updated.

[0713] The system of the present invention includes a metadata generation means using generative AI, a data classification means, an update frequency monitoring means, a web-based management interface, and an emotion recognition means using an emotion engine.

[0714] First, the server accesses the company's cloud storage or data lake and collects data according to a specified schedule. The collected data is analyzed using generative AI, and metadata is automatically generated. The metadata includes information such as the creation date, administrator, data type, data description, and update frequency. For example, a CSV file imported from a company's production data can be analyzed, and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" can be automatically assigned.

[0715] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "production data," "quality control data," and "equipment maintenance data."

[0716] Furthermore, the server continuously monitors the frequency of data updates and determines that data that has not been updated for a certain period of time (for example, six months) meets the conditions for archiving. Data that is subject to archiving is automatically moved to a separate storage device and managed as an archive.

[0717] The terminal also provides a user interface to the worker. When the worker operates the user interface, an emotion engine analyzes the worker's facial expressions and voice tone to obtain emotional data. Based on this emotional data, the server dynamically changes the display content and operation method of the management interface. For example, if a worker is feeling stressed, the server can simplify the operation procedure or display a support message. This emotional data is also generated as metadata, which can be used to improve the system over the long term.

[0718] Specifically, TensorFlow and PyTorch are used for generative AI, while OpenCV and DeepFace are used for emotion recognition, with data collection, analysis, classification, archiving, emotion recognition, and interface optimization being carried out at each step. This not only enables automatic and efficient management of large amounts of data, but also makes it possible to provide a highly user-friendly interface that takes into account the emotional state of the worker, which is expected to improve productivity.

[0719] An example of a prompt is, "Please import new customer data from the customer database. Generate the following metadata for that data: - Creation date - Administrator - Data type - Data description - Update frequency." This is input into the generative AI model to generate the metadata.

[0720] These features enable companies to significantly reduce the effort required for data management and to organize, store, and utilize data with high accuracy.

[0721] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0722] Step 1: Collect and import data

[0723] The server collects data from the company's cloud storage and data lake according to a specified schedule. Specifically, the server periodically scans the cloud storage to detect newly added files. Detected files are imported into local temporary storage and basic information such as file name, size, and creation date and time is recorded.

[0724] Input: Cloud storage and data lake connection information, schedule information

[0725] Output: Imported data, basic file information

[0726] Step 2: Automatically generate and assign metadata

[0727] The server automatically generates metadata for the imported data using a generation AI, which analyzes the data content and generates information such as the creation date, administrator, data type, data description, and update frequency, and assigns it to the data.

[0728] Input: Imported data, basic information of the file

[0729] Output: Data with metadata

[0730] Step 3: Classify the data

[0731] The server uses generative AI to categorize the metadata-annotated data into categories such as "production data," "quality control data," and "machine maintenance data" based on predefined classification rules and the results of learning from past data.

[0732] Input: Data with metadata, classification rules

[0733] Output: Classified data

[0734] Step 4: Monitoring and archiving data frequency

[0735] The server continuously monitors the frequency of data updates. Data that has not been updated for a set period of time (e.g., six months) is archived and automatically moved to another storage device.

[0736] Input: Classified data, update frequency monitoring rules

[0737] Output: Archived data

[0738] Step 5: Emotion Recognition and Interface Optimization

[0739] As the user operates the device's interface, the device uses cameras and audio sensors to recognize the user's emotions in real time. Based on the analyzed emotional data, the server dynamically changes the display content and operation methods of the management interface. For example, if the user is feeling stressed, the operating procedure will be simplified and a support message will be displayed.

[0740] Input: User's face image, voice data

[0741] Output: User emotion data, optimized interface display content

[0742] Step 6: Providing a management interface

[0743] The terminal provides users with a web-based management interface through which they can view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[0744] Input: User operation request

[0745] Output: Operation results, edited data

[0746] This will improve productivity by streamlining data management and optimizing the interface to suit individual emotions.

[0747] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0748] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0749] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0750] [Third embodiment]

[0751] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0752] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0753] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0754] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0755] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0756] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0757] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0758] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0759] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0760] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0761] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0762] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0763] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[0764] Data collection and import

[0765] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[0766] Automatic generation and assignment of metadata

[0767] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[0768] Creation date: Automatically taken from file meta information.

[0769] Administrator: Retrieves information from the user management system.

[0770] Data type: Automatically determined from file format and content.

[0771] Data description: Generated based on the results of AI content analysis.

[0772] Update frequency: Estimated based on past update history.

[0773] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[0774] Data classification and organization

[0775] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[0776] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[0777] Data Updates and Archiving

[0778] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[0779] Providing a management interface

[0780] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[0781] This system will enable companies to significantly reduce the amount of man-hours required for data management and enable them to organize, store, and utilize data with high accuracy, which is expected to dramatically improve the efficiency of data utilization and increase the competitiveness of companies.

[0782] The processing flow will be explained below.

[0783] Step 1:

[0784] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[0785] Step 2:

[0786] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[0787] Step 3:

[0788] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[0789] Step 4:

[0790] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[0791] Step 5:

[0792] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[0793] Step 6:

[0794] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[0795] Step 7:

[0796] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[0797] Step 8:

[0798] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[0799] Step 9:

[0800] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[0801] Step 10:

[0802] The server continuously monitors the frequency of data updates, which is calculated based on past update history and access frequency.

[0803] Step 11:

[0804] The server determines which data to archive based on the archive conditions set. For example, data that has not been updated for six months will be archived.

[0805] Step 12:

[0806] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[0807] Step 13:

[0808] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[0809] Step 14:

[0810] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[0811] Step 15:

[0812] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[0813] Example 1

[0814] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0815] Conventional data management systems require separate tasks for data collection, metadata assignment, data classification, update frequency monitoring, archiving, and user management interfaces, resulting in significant man-hours and costs. Furthermore, because these tasks are all performed manually, there is a high risk of errors and data leaks, and management efficiency is low.

[0816] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0817] In this invention, the server includes means for accessing a data storage device and collecting data according to a schedule, means for analyzing the data content using a generation AI and automatically generating and assigning metadata to the data, means for learning past data and classification rules using the generation AI and automatically classifying the data, means for monitoring the frequency of data updates and archiving the data based on set conditions, and means for allowing users to edit the metadata and classification rules through a web-based management interface.This reduces the amount of human effort required for data management and enables data to be organized, stored, and utilized with high accuracy.

[0818] "Data storage device" refers to a hardware device used to store digital data in various formats, including cloud storage, data lakes, and local servers.

[0819] A "schedule" refers to a series of planned actions based on a specific period or time period, and is used in the present invention to control the timing of data collection.

[0820] "Metadata" refers to supplementary data that provides information about the content and nature of the data, such as the file creation date, the administrator, the type of data, a description of the data, and how often it is updated.

[0821] "Generative AI" refers to programs or models that use artificial intelligence techniques to analyze data and generate metadata, often using natural language processing techniques.

[0822] A "classification rule" is a set of criteria or rules for organizing data into specific categories, including historical data and predefined rules.

[0823] "Update frequency" refers to the metric that indicates how frequently data is changed or added, and is used to manage and archive data.

[0824] "Archiving" refers to the process of moving data that is no longer in use for long-term storage and managing it efficiently, primarily for the purpose of reducing storage load.

[0825] "Web-based Management Interface" means a user interface accessed by a user through an internet browser for managing data and metadata, including editing and search capabilities.

[0826] "User" refers to anyone who uses this system to manage and manipulate data, and generally includes data managers at companies.

[0827] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[0828] First, the server accesses a data storage device (such as cloud storage or a data lake) and collects data according to a specified schedule. For example, it retrieves data from cloud services such as Amazon S3 or Google Cloud Storage. At the same time, it also retrieves basic data information (file name, size, creation date and time) and imports it into local temporary storage. Specifically, it triggers a script at 2:00 AM every day to detect new CSV files from the Amazon S3 bucket and download them to local storage. It also records this basic information in a database.

[0829] Next, the server uses a generative AI model (e.g., GPT-3) to automatically generate metadata for the collected data and assign it to the data. It analyzes the data content and generates information such as the creation date, administrator, data type, data description, and update frequency. Specifically, it reads the CSV file stored in local storage, obtains the creation date from the file's metadata, and assigns administrator information obtained from a separate management system. At the same time, it uses the generative AI to generate a description of the file content and estimates the update frequency from past update history.

[0830] Next, the server uses generative AI to automatically classify the data. Here, the data is sorted into categories such as "sales data," "customer information data," and "product information data" based on predefined classification rules and past data. For example, if a user's purchase history data is imported, that data is classified as "sales data." Similarly, data containing customer contact information is classified as "customer information data."

[0831] Furthermore, the server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (e.g., six months), it determines that the data should be archived and moves it to archive storage (e.g., Amazon Glacier). This reduces the load on the primary storage and allows for efficient management of infrequently used data.

[0832] Finally, the terminal provides users with a web-based management interface. Through this interface, users can view and edit data and metadata as needed. For example, they can add new metadata items or modify existing classification rules. They can also view detailed information about specific data and search for data. The intuitive and user-friendly design of this management interface improves the efficiency of data management.

[0833] Examples of prompt statements

[0834] 1. "Collect and import a new sales data file from your Amazon S3 bucket."

[0835] 2. "Automatically generate metadata for customer information data and store it in the database."

[0836] 3. "Classify the collected data based on predefined rules and organize it into appropriate directories."

[0837] 4. "Check your update history and move any data that hasn't been updated for six months to archive storage."

[0838] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0839] Step 1:

[0840] The server accesses the data storage device and collects data according to a schedule.

[0841] Specifically, the script is triggered at 2:00 AM every day. This script accesses cloud storage such as Amazon S3 and Google Cloud Storage and scans for new files. Detected files (e.g., CSV format data) are downloaded to local storage. Basic information such as the file name, size, and creation date and time is also obtained and recorded in a database.

[0842] Input: Cloud storage connection information and collection schedule

[0843] Output: A new data file saved in local storage with its basic information

[0844] Step 2:

[0845] The server automatically generates metadata for the collected data using a generative AI model and attaches it to the data.

[0846] Specifically, the system reads a CSV file stored in local storage. It then uses a generative AI model (e.g., GPT-3) to analyze the file contents and generate metadata. The generated metadata includes the creation date, administrator, data type, data description, update frequency, etc. This metadata is recorded in a database and attached to the original data file.

[0847] Input: Data file stored in local storage

[0848] Output: Generated metadata and the data file to which it is attached

[0849] Step 3:

[0850] The server uses generative AI to automatically classify the data.

[0851] Specifically, the system classifies data into categories such as "sales data," "customer information data," and "product information data" based on metadata information. The generative AI model performs this classification task by learning predefined classification rules and past data. The classified data is moved to the corresponding directory and the information is updated in the database.

[0852] Input: Generated metadata and data files

[0853] Output: Classified data file and updated database information

[0854] Step 4:

[0855] The server continuously monitors the update frequency of the data.

[0856] Specifically, it periodically checks the update history in the database and lists data that has not been updated for a certain period of time (for example, six months). The listed data is automatically moved to archive storage (for example, Amazon Glacier). This movement operation is also recorded in the database.

[0857] Input: Database update history and archive conditions

[0858] Output: Data moved to archive storage and updated database information

[0859] Step 5:

[0860] The terminal provides the user with a web-based management interface.

[0861] Specifically, users access the interface through a web browser and can view and optionally edit data and metadata. The interface is structured as a dashboard, displaying overviews and details for each data category, as well as options for editing metadata. Users can add new metadata items, modify existing classification rules, and search for specific data.

[0862] Input: Access information from web browser and user operations

[0863] Output: Data summary and edit results displayed on the dashboard

[0864] (Application example 1)

[0865] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0866] Modern logistics centers are required to efficiently manage massive amounts of data and optimize business operations. However, manually organizing and classifying data and continuously monitoring frequent data updates require a great deal of effort and are not efficient. Furthermore, real-time data management using smart devices and automated package sorting and movement using robots have yet to become widespread. Systems that can solve these issues are needed.

[0867] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0868] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, means for displaying and managing data in real time using a smart device, and means for automatically sorting and moving data using a robot, thereby enabling more efficient data management in logistics centers.

[0869] "Generative AI" is an artificial intelligence technology that analyzes the content of data and automatically generates and classifies metadata.

[0870] "Metadata" refers to information that accompanies data, such as the creation date of the data, the administrator, the type of data, a description, and how often it is updated.

[0871] "Monitoring data update frequency" means continuously monitoring how frequently data is updated.

[0872] "Archiving" is the process of moving and storing data that has not been updated for a certain period of time to another storage.

[0873] "Web-based management interface" means a management screen accessible via the Internet that allows editing, viewing, and searching of data and metadata.

[0874] A "smart device" is a device with internet connectivity, such as a smartphone, smart glasses, or a head-mounted display.

[0875] "Automatic sorting by robots" is a process in which robots automatically sort and move packages to the appropriate locations based on the results of data analysis by AI.

[0876] The system that realizes this invention is composed of a server, a terminal, and a user operating in cooperation with each other. Each component and its role will be described below.

[0877] Server Roles

[0878] The server plays a central role and performs the following functions:

[0879] 1. Collecting and importing data

[0880] The server accesses the company's cloud storage or data lake, periodically collects data, and imports it into temporary local storage. For example, it scans at specific times to detect newly added data.

[0881] 2. Automatic generation and assignment of metadata

[0882] Generative AI is used to automatically generate metadata for the collected data, including the creation date, administrator, data type, data description, and update frequency. Specifically, natural language processing technology is used to analyze the data content and generate appropriate metadata.

[0883] 3. Data classification and organization

[0884] Generative AI is used to automatically classify data based on predefined rules and past learning results. For example, data may be classified into categories such as "sales data," "customer information data," and "product information data."

[0885] 4. Data Update and Archiving

[0886] The server monitors the frequency of data updates and archives data that has not been updated for a certain period of time (e.g., six months), thereby reducing the load on the main storage and efficiently managing data that is used infrequently.

[0887] Device Role

[0888] 1. Providing a web-based management interface

[0889] The terminal provides users with a web-based management interface through which they can view and edit data and metadata, as well as view detailed information about specific data and perform data searches.

[0890] 2. Management via smart devices

[0891] Data can be displayed and managed in real time through smart devices such as smartphones, smart glasses, head-mounted displays, etc. For example, an inventory management app can be used to check new inventory data in real time.

[0892] User Roles

[0893] 1. Viewing and editing data

[0894] Users can edit metadata and classification rules through a web-based management interface, allowing for customization of data management.

[0895] 2. Managing Robots

[0896] Users can use robots to automatically sort and move data. Automatic sorting is performed based on the analysis results of the generative AI.

[0897] Prompt Sentence Examples

[0898] New data has been imported. Product name: Apples, Size: 10kg, Stock date: October 10, 2023. Please generate metadata for this data. Also, please estimate how frequently it will be updated.

[0899] In this way, the present invention makes it possible to improve the efficiency of data management in logistics centers and optimize business operations, which is expected to contribute to improving the competitiveness of companies.

[0900] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0901] Step 1:

[0902] The server accesses the company's cloud storage or data lake and collects new data according to a specified schedule. It receives cloud storage access information and collection schedules as input, and obtains the newly collected data and its basic information (file name, size, creation date and time) as output. This data is stored in local temporary storage.

[0903] Step 2:

[0904] The server uses a generation AI on the collected data. Here, the generation AI analyzes the contents of the collected data and automatically generates metadata. The collected data files are passed as input, and metadata (creation date, administrator, data type, data description, update frequency) is generated as output. The metadata assigned to each piece of data is registered in the database.

[0905] Step 3:

[0906] The server uses generative AI to classify data based on predefined rules and past learning results. Data with metadata attached is passed as input, and classification results (e.g., sales data, customer information data, product information data) are obtained as output. The classified data is organized by category.

[0907] Step 4:

[0908] The server continuously monitors the frequency of data updates. The data update history and current date and time are passed as input, and the result of evaluating the update frequency is obtained as output. Based on this result, data that has not been updated for a certain period of time is moved to archive storage.

[0909] Step 5:

[0910] The terminal provides a web-based management interface to the user, which allows the user to view and edit metadata and classification rules. The input is the metadata and classification rules the user wants to edit, and the output is the updated metadata and classification rules.

[0911] Step 6:

[0912] Terminals use smart devices to display and manage data in real time. A specific data request is passed as input, and the data is displayed on the screen as output. For example, an inventory management app on a smartphone can be used to check new inventory data in real time.

[0913] Step 7:

[0914] Users use robots to automatically sort and move data. Metadata and classification results are passed as input, and the robot automatically sorts and moves the data to the appropriate location as output. For example, incoming parcels are automatically sorted and moved to the designated shelves.

[0915] These steps will enable more efficient data management at logistics centers and optimize business operations.

[0916] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0917] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[0918] Data collection and import

[0919] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[0920] Automatic generation and assignment of metadata

[0921] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[0922] Creation date: Automatically taken from file meta information.

[0923] Administrator: Retrieves information from the user management system.

[0924] Data type: Automatically determined from file format and content.

[0925] Data description: Generated based on the results of AI content analysis.

[0926] Update frequency: Estimated based on past update history.

[0927] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[0928] Data classification and organization

[0929] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[0930] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[0931] Data Updates and Archiving

[0932] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[0933] Use of emotion engine

[0934] The system also incorporates an emotion engine that recognizes the user's emotional state in real time. When a user operates the management interface, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data can be used as follows:

[0935] The server dynamically changes the display content and operation method of the management interface based on the emotional data. For example, if the user is feeling stressed, it simplifies the operation procedure or displays a support message.

[0936] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[0937] Providing a management interface

[0938] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[0939] Furthermore, by reflecting the user's emotional state, more personalized operations are possible, improving the user experience.

[0940] This system allows companies to significantly reduce the amount of man-hours required for data management and allows them to organize, store, and utilize data with high accuracy. The introduction of the emotion engine also improves user efficiency, dramatically improving the overall efficiency of data utilization.

[0941] The processing flow will be explained below.

[0942] Step 1:

[0943] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[0944] Step 2:

[0945] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[0946] Step 3:

[0947] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[0948] Step 4:

[0949] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[0950] Step 5:

[0951] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[0952] Step 6:

[0953] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[0954] Step 7:

[0955] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[0956] Step 8:

[0957] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[0958] Step 9:

[0959] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[0960] Step 10:

[0961] The server continuously monitors how frequently the data is updated, for example by recording when the data was last updated and tracking how frequently it is updated.

[0962] Step 11:

[0963] The server determines which data to archive based on the set archive conditions. For example, data that has not been updated for six months is archived.

[0964] Step 12:

[0965] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[0966] Step 13:

[0967] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[0968] Step 14:

[0969] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[0970] Step 15:

[0971] The server uses an emotion engine to monitor the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time.

[0972] Step 16:

[0973] The server dynamically changes the display content and operation methods of the management interface based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the operation procedure can be simplified or a support message can be displayed.

[0974] Step 17:

[0975] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[0976] Step 18:

[0977] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[0978] Example 2

[0979] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0980] In recent years, the amount of data handled by companies and organizations has exploded, making data management extremely complex and burdensome. While improving the efficiency of data management is important, processes such as automatic metadata generation and data classification are often performed manually, resulting in time-consuming and costly issues. Furthermore, while improving user operational efficiency is also necessary, there has been little progress in interface design that takes into account the user's emotional state. The purpose of this invention is to solve these problems and improve the overall efficiency of data management.

[0981] The identification process 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 automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the update frequency of data and archiving the data based on set conditions, means for allowing a user to edit the metadata and classification rules through a web-based management interface, means for providing dynamic interface changes according to the user's operating status using an emotion engine that recognizes the user's emotions, and means for assigning the results of the emotion recognition to the data as metadata. This makes it possible to automate and efficiently manage data and improve the user's operating experience.

[0982] "Generative AI" refers to artificial intelligence systems used to analyze data content and generate metadata.

[0983] "Metadata" is additional information that describes the attributes and content of data, making it easier to manage and search for the data.

[0984] "Data classification" is the process of separating collected data into specific categories, making it easier to organize and manage.

[0985] "Update frequency" indicates the frequency of time intervals at which data is updated, and is an index for evaluating the recency of data.

[0986] "Archiving" is the process of moving data that has not been updated for a certain period of time to another storage device for long-term storage.

[0987] A "web-based management interface" is an interface for data management that a user can access through a web browser.

[0988] The "emotion engine" is a system that recognizes the user's emotional state in real time and analyzes that data.

[0989] "Dynamic interface change" is the process of changing the display and operation of the management interface in real time according to the user's emotional state.

[0990] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[0991] Data collection and import

[0992] First, the server starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded. The hardware used includes the company's cloud storage server and data lake system.

[0993] Examples:

[0994] The server scans the cloud storage for newly added files every day at 2:00 AM and imports them into local temporary storage.

[0995] At this time, the file name, size, and creation date and time are recorded at the same time.

[0996] Automatic generation and assignment of metadata

[0997] The server then analyzes the collected data using AI technology, such as OpenAI's GPT model, to automatically generate metadata, including the creation date, administrator, data type, data description, and update frequency.

[0998] Examples:

[0999] The server analyzes CSV files imported from the company's customer database and automatically assigns the creation date, administrator, data type, data description, and update frequency.

[1000] Data classification and organization

[1001] The server then uses generative AI to categorize the collected data, using predefined classification rules and the results of past data analysis.

[1002] Examples:

[1003] The server categorizes the user's purchase history data as "sales data" and the customer's contact information as "customer information data."

[1004] Data Updates and Archiving

[1005] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (for example, six months) is automatically moved to archive storage, reducing the load on the main storage.

[1006] Examples:

[1007] The server automatically moves unused customer information data to archive storage.

[1008] Use of emotion engine

[1009] The system also incorporates an emotion engine that recognizes the user's emotional state in real time as they operate the management interface. The emotion engine analyzes the user's facial expressions and tone of voice, and dynamically changes the content displayed and the operation method of the interface based on the results.

[1010] Examples:

[1011] If the emotion engine detects stress while the user is operating the data management interface, the server simplifies the operating procedure.

[1012] Providing a management interface

[1013] The terminal provides users with a web-based management interface that allows them to view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[1014] Examples:

[1015] Through the interface, users add new metadata items and modify existing classification rules.

[1016] Examples of prompt statements

[1017] Below are some example prompts to input to the generative AI model:

[1018] Write a program to automatically generate and assign the necessary metadata (creation date, administrator, data type, data description, update frequency) to a CSV file imported by a user from a company's customer database.

[1019] The above is a detailed description of the embodiment of the present invention, which enables the system to automate and streamline data management, improving the user's operational experience.

[1020] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1021] Step 1:

[1022] The server accesses the company's cloud storage or data lake and scans the data according to a specified schedule (e.g., daily at 2:00 AM).

[1023] Input: Cloud storage and data lake access information and schedule information

[1024] Output: List of newly added files

[1025] Specific behavior: Retrieve a list of new files from cloud storage.

[1026] Step 2:

[1027] The server scans and detects newly added files and imports them into local temporary storage, recording basic information such as file name, size, and creation date and time.

[1028] Input: Newly added file list

[1029] Output: Files imported into local temporary storage and their basic information

[1030] Specific behavior: Downloads new files and records their filenames, sizes, and creation dates.

[1031] Step 3:

[1032] The server uses generative AI (e.g., OpenAI's GPT model) to analyze the contents of the collected data and automatically generate metadata (creation date, administrator, data type, data description, and update frequency).

[1033] Input: A file in local temporary storage

[1034] Output: Auto-generated metadata

[1035] Specific operation: Analyze the file contents using generative AI and generate the necessary metadata.

[1036] Step 4:

[1037] The server uses generative AI to classify the collected data into categories based on classification rules and the results of analysis of past data.

[1038] Input: Files in local temporary storage with auto-generated metadata

[1039] Output: Data categorized by category

[1040] Specific operation: Uses generative AI to analyze the content of the data and classify it into appropriate categories.

[1041] Step 5:

[1042] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (e.g., six months) is automatically moved to archive storage.

[1043] Input: Categorized data and its metadata

[1044] Output: Data moved to archive storage

[1045] Specific operation: Check the update date and time of the data and perform archiving based on the conditions.

[1046] Step 6:

[1047] The server uses an emotion engine to recognize the emotional state of the user while operating the management interface, and dynamically changes the display content and operation method of the interface based on the results.

[1048] Input: User's facial expressions and voice tone

[1049] Output: Dynamically changed management interface

[1050] Specific behavior: Adjust the interface based on the emotions recognized by the emotion engine.

[1051] Step 7:

[1052] The server generates the emotion recognition results as metadata and attaches it to the data.

[1053] Input: User's emotional state

[1054] Output: Metadata with emotional state

[1055] Specific operation: Emotional state is generated as metadata and added to the data.

[1056] Step 8:

[1057] The terminal provides a web-based management interface, allowing users to edit metadata and classification rules.

[1058] Input: User edit request

[1059] Output: Updated metadata and classification rules

[1060] Specific behavior: Updates metadata and classification rules based on user input.

[1061] In this way, the system efficiently and automatically performs data collection, analysis, classification, archiving, and dynamic interface changes based on the user's emotional state at each stage of data management.

[1062] (Application example 2)

[1063] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1064] In modern factories, the efficiency of production processes and data management are becoming increasingly important. In particular, manually processing large amounts of data, such as collecting, organizing, classifying, and archiving data, is a labor-intensive process, leading to reduced efficiency and data errors. Furthermore, uniform user interfaces that ignore the emotional state of workers increase operational complexity and stress, resulting in reduced productivity. To address these issues, automated data management systems and personalized interfaces that take the user's emotional state into account are needed.

[1065] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1066] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, and means for recognizing the user's emotional state using an emotion engine and dynamically changing the display content and operation method of the management interface based on the emotion data. This not only enables automatic and efficient management of large amounts of data, but also provides a highly operable interface that takes the worker's emotional state into consideration, thereby improving productivity.

[1067] "Generative AI" is an artificial intelligence technology that automatically generates data and generates metadata based on that data.

[1068] "Metadata" is data that indicates additional information such as the attributes and content of data, the creation date and time, and the administrator.

[1069] "Data classification" is the process of automatically separating collected data into categories or types based on their content.

[1070] "Archiving" is the process of automatically moving and storing data that has not been updated for a certain period of time to another storage device, thereby reducing the load on the primary storage device.

[1071] "Web-based management interface" means a user interface available on the web that allows for viewing and editing of data and metadata.

[1072] "Recognizing the user's emotional state" means using cameras and audio sensors to analyze the user's emotions in real time from their facial expressions and tone of voice.

[1073] An "emotion engine" is software that analyzes a user's emotions and adjusts the system's behavior based on those emotions.

[1074] "Dynamic change of the display content and operation method of the management interface" refers to the process of adjusting the interface content and operation procedure in real time based on the user's emotional data.

[1075] "Monitoring update frequency" is the process of continually monitoring how frequently data is updated.

[1076] The system of the present invention includes a metadata generation means using generative AI, a data classification means, an update frequency monitoring means, a web-based management interface, and an emotion recognition means using an emotion engine.

[1077] First, the server accesses the company's cloud storage or data lake and collects data according to a specified schedule. The collected data is analyzed using generative AI, and metadata is automatically generated. The metadata includes information such as the creation date, administrator, data type, data description, and update frequency. For example, a CSV file imported from a company's production data can be analyzed, and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" can be automatically assigned.

[1078] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "production data," "quality control data," and "equipment maintenance data."

[1079] Furthermore, the server continuously monitors the frequency of data updates and determines that data that has not been updated for a certain period of time (for example, six months) meets the conditions for archiving. Data that is subject to archiving is automatically moved to a separate storage device and managed as an archive.

[1080] The terminal also provides a user interface to the worker. When the worker operates the user interface, an emotion engine analyzes the worker's facial expressions and voice tone to obtain emotional data. Based on this emotional data, the server dynamically changes the display content and operation method of the management interface. For example, if a worker is feeling stressed, the server can simplify the operation procedure or display a support message. This emotional data is also generated as metadata, which can be used to improve the system over the long term.

[1081] Specifically, TensorFlow and PyTorch are used for generative AI, while OpenCV and DeepFace are used for emotion recognition, with data collection, analysis, classification, archiving, emotion recognition, and interface optimization being carried out at each step. This not only enables automatic and efficient management of large amounts of data, but also makes it possible to provide a highly user-friendly interface that takes into account the emotional state of the worker, which is expected to improve productivity.

[1082] An example of a prompt is, "Please import new customer data from the customer database. Generate the following metadata for that data: - Creation date - Administrator - Data type - Data description - Update frequency." This is input into the generative AI model to generate the metadata.

[1083] These features enable companies to significantly reduce the effort required for data management and to organize, store, and utilize data with high accuracy.

[1084] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1085] Step 1: Collect and import data

[1086] The server collects data from the company's cloud storage and data lake according to a specified schedule. Specifically, the server periodically scans the cloud storage to detect newly added files. Detected files are imported into local temporary storage and basic information such as file name, size, and creation date and time is recorded.

[1087] Input: Cloud storage and data lake connection information, schedule information

[1088] Output: Imported data, basic file information

[1089] Step 2: Automatically generate and assign metadata

[1090] The server automatically generates metadata for the imported data using a generation AI, which analyzes the data content and generates information such as the creation date, administrator, data type, data description, and update frequency, and assigns it to the data.

[1091] Input: Imported data, basic information of the file

[1092] Output: Data with metadata

[1093] Step 3: Classify the data

[1094] The server uses generative AI to categorize the metadata-annotated data into categories such as "production data," "quality control data," and "machine maintenance data" based on predefined classification rules and the results of learning from past data.

[1095] Input: Data with metadata, classification rules

[1096] Output: Classified data

[1097] Step 4: Monitoring and archiving data frequency

[1098] The server continuously monitors the frequency of data updates. Data that has not been updated for a set period of time (e.g., six months) is archived and automatically moved to another storage device.

[1099] Input: Classified data, update frequency monitoring rules

[1100] Output: Archived data

[1101] Step 5: Emotion Recognition and Interface Optimization

[1102] As the user operates the device's interface, the device uses cameras and audio sensors to recognize the user's emotions in real time. Based on the analyzed emotional data, the server dynamically changes the display content and operation methods of the management interface. For example, if the user is feeling stressed, the operating procedure will be simplified and a support message will be displayed.

[1103] Input: User's face image, voice data

[1104] Output: User emotion data, optimized interface display content

[1105] Step 6: Providing a management interface

[1106] The terminal provides users with a web-based management interface through which they can view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[1107] Input: User operation request

[1108] Output: Operation results, edited data

[1109] This will improve productivity by streamlining data management and optimizing the interface to suit individual emotions.

[1110] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1112] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1113] [Fourth embodiment]

[1114] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1115] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1117] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1118] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1119] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1121] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1122] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1123] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1125] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1126] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1127] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[1128] Data collection and import

[1129] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[1130] Automatic generation and assignment of metadata

[1131] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[1132] Creation date: Automatically taken from file meta information.

[1133] Administrator: Retrieves information from the user management system.

[1134] Data type: Automatically determined from file format and content.

[1135] Data description: Generated based on the results of AI content analysis.

[1136] Update frequency: Estimated based on past update history.

[1137] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[1138] Data classification and organization

[1139] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[1140] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[1141] Data Updates and Archiving

[1142] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[1143] Providing a management interface

[1144] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[1145] This system will enable companies to significantly reduce the amount of man-hours required for data management and enable them to organize, store, and utilize data with high accuracy, which is expected to dramatically improve the efficiency of data utilization and increase the competitiveness of companies.

[1146] The processing flow will be explained below.

[1147] Step 1:

[1148] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[1149] Step 2:

[1150] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[1151] Step 3:

[1152] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[1153] Step 4:

[1154] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[1155] Step 5:

[1156] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[1157] Step 6:

[1158] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[1159] Step 7:

[1160] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[1161] Step 8:

[1162] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[1163] Step 9:

[1164] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[1165] Step 10:

[1166] The server continuously monitors the frequency of data updates, which is calculated based on past update history and access frequency.

[1167] Step 11:

[1168] The server determines which data to archive based on the archive conditions set. For example, data that has not been updated for six months will be archived.

[1169] Step 12:

[1170] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[1171] Step 13:

[1172] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[1173] Step 14:

[1174] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[1175] Step 15:

[1176] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[1177] Example 1

[1178] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1179] Conventional data management systems require separate tasks for data collection, metadata assignment, data classification, update frequency monitoring, archiving, and user management interfaces, resulting in significant man-hours and costs. Furthermore, because these tasks are all performed manually, there is a high risk of errors and data leaks, and management efficiency is low.

[1180] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1181] In this invention, the server includes means for accessing a data storage device and collecting data according to a schedule, means for analyzing the data content using a generation AI and automatically generating and assigning metadata to the data, means for learning past data and classification rules using the generation AI and automatically classifying the data, means for monitoring the frequency of data updates and archiving the data based on set conditions, and means for allowing users to edit the metadata and classification rules through a web-based management interface.This reduces the amount of human effort required for data management and enables data to be organized, stored, and utilized with high accuracy.

[1182] "Data storage device" refers to a hardware device used to store digital data in various formats, including cloud storage, data lakes, and local servers.

[1183] A "schedule" refers to a series of planned actions based on a specific period or time period, and is used in the present invention to control the timing of data collection.

[1184] "Metadata" refers to supplementary data that provides information about the content and nature of the data, such as the file creation date, the administrator, the type of data, a description of the data, and how often it is updated.

[1185] "Generative AI" refers to programs or models that use artificial intelligence techniques to analyze data and generate metadata, often using natural language processing techniques.

[1186] A "classification rule" is a set of criteria or rules for organizing data into specific categories, including historical data and predefined rules.

[1187] "Update frequency" refers to the metric that indicates how frequently data is changed or added, and is used to manage and archive data.

[1188] "Archiving" refers to the process of moving data that is no longer in use for long-term storage and managing it efficiently, primarily for the purpose of reducing storage load.

[1189] "Web-based Management Interface" means a user interface accessed by a user through an internet browser for managing data and metadata, including editing and search capabilities.

[1190] "User" refers to anyone who uses this system to manage and manipulate data, and generally includes data managers at companies.

[1191] This invention is a system that utilizes generative AI to automate data organization, metadata assignment, data classification, update frequency monitoring, and archiving. This system operates as follows.

[1192] First, the server accesses a data storage device (such as cloud storage or a data lake) and collects data according to a specified schedule. For example, it retrieves data from cloud services such as Amazon S3 or Google Cloud Storage. At the same time, it also retrieves basic data information (file name, size, creation date and time) and imports it into local temporary storage. Specifically, it triggers a script at 2:00 AM every day to detect new CSV files from the Amazon S3 bucket and download them to local storage. It also records this basic information in a database.

[1193] Next, the server uses a generative AI model (e.g., GPT-3) to automatically generate metadata for the collected data and assign it to the data. It analyzes the data content and generates information such as the creation date, administrator, data type, data description, and update frequency. Specifically, it reads the CSV file stored in local storage, obtains the creation date from the file's metadata, and assigns administrator information obtained from a separate management system. At the same time, it uses the generative AI to generate a description of the file content and estimates the update frequency from past update history.

[1194] Next, the server uses generative AI to automatically classify the data. Here, the data is sorted into categories such as "sales data," "customer information data," and "product information data" based on predefined classification rules and past data. For example, if a user's purchase history data is imported, that data is classified as "sales data." Similarly, data containing customer contact information is classified as "customer information data."

[1195] Furthermore, the server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (e.g., six months), it determines that the data should be archived and moves it to archive storage (e.g., Amazon Glacier). This reduces the load on the primary storage and allows for efficient management of infrequently used data.

[1196] Finally, the terminal provides users with a web-based management interface. Through this interface, users can view and edit data and metadata as needed. For example, they can add new metadata items or modify existing classification rules. They can also view detailed information about specific data and search for data. The intuitive and user-friendly design of this management interface improves the efficiency of data management.

[1197] Examples of prompt statements

[1198] 1. "Collect and import a new sales data file from your Amazon S3 bucket."

[1199] 2. "Automatically generate metadata for customer information data and store it in the database."

[1200] 3. "Classify the collected data based on predefined rules and organize it into appropriate directories."

[1201] 4. "Check your update history and move any data that hasn't been updated for six months to archive storage."

[1202] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1203] Step 1:

[1204] The server accesses the data storage device and collects data according to a schedule.

[1205] Specifically, the script is triggered at 2:00 AM every day. This script accesses cloud storage such as Amazon S3 and Google Cloud Storage and scans for new files. Detected files (e.g., CSV format data) are downloaded to local storage. Basic information such as the file name, size, and creation date and time is also obtained and recorded in a database.

[1206] Input: Cloud storage connection information and collection schedule

[1207] Output: A new data file saved in local storage with its basic information

[1208] Step 2:

[1209] The server automatically generates metadata for the collected data using a generative AI model and attaches it to the data.

[1210] Specifically, the system reads a CSV file stored in local storage. It then uses a generative AI model (e.g., GPT-3) to analyze the file contents and generate metadata. The generated metadata includes the creation date, administrator, data type, data description, update frequency, etc. This metadata is recorded in a database and attached to the original data file.

[1211] Input: Data file stored in local storage

[1212] Output: Generated metadata and the data file to which it is attached

[1213] Step 3:

[1214] The server uses generative AI to automatically classify the data.

[1215] Specifically, the system classifies data into categories such as "sales data," "customer information data," and "product information data" based on metadata information. The generative AI model performs this classification task by learning predefined classification rules and past data. The classified data is moved to the corresponding directory and the information is updated in the database.

[1216] Input: Generated metadata and data files

[1217] Output: Classified data file and updated database information

[1218] Step 4:

[1219] The server continuously monitors the update frequency of the data.

[1220] Specifically, it periodically checks the update history in the database and lists data that has not been updated for a certain period of time (for example, six months). The listed data is automatically moved to archive storage (for example, Amazon Glacier). This movement operation is also recorded in the database.

[1221] Input: Database update history and archive conditions

[1222] Output: Data moved to archive storage and updated database information

[1223] Step 5:

[1224] The terminal provides the user with a web-based management interface.

[1225] Specifically, users access the interface through a web browser and can view and optionally edit data and metadata. The interface is structured as a dashboard, displaying overviews and details for each data category, as well as options for editing metadata. Users can add new metadata items, modify existing classification rules, and search for specific data.

[1226] Input: Access information from web browser and user operations

[1227] Output: Data summary and edit results displayed on the dashboard

[1228] (Application example 1)

[1229] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1230] Modern logistics centers are required to efficiently manage massive amounts of data and optimize business operations. However, manually organizing and classifying data and continuously monitoring frequent data updates require a great deal of effort and are not efficient. Furthermore, real-time data management using smart devices and automated package sorting and movement using robots have yet to become widespread. Systems that can solve these issues are needed.

[1231] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1232] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, means for displaying and managing data in real time using a smart device, and means for automatically sorting and moving data using a robot, thereby enabling more efficient data management in logistics centers.

[1233] "Generative AI" is an artificial intelligence technology that analyzes the content of data and automatically generates and classifies metadata.

[1234] "Metadata" refers to information that accompanies data, such as the creation date of the data, the administrator, the type of data, a description, and how often it is updated.

[1235] "Monitoring data update frequency" means continuously monitoring how frequently data is updated.

[1236] "Archiving" is the process of moving and storing data that has not been updated for a certain period of time to another storage.

[1237] "Web-based management interface" means a management screen accessible via the Internet that allows editing, viewing, and searching of data and metadata.

[1238] A "smart device" is a device with internet connectivity, such as a smartphone, smart glasses, or a head-mounted display.

[1239] "Automatic sorting by robots" is a process in which robots automatically sort and move packages to the appropriate locations based on the results of data analysis by AI.

[1240] The system that realizes this invention is composed of a server, a terminal, and a user operating in cooperation with each other. Each component and its role will be described below.

[1241] Server Roles

[1242] The server plays a central role and performs the following functions:

[1243] 1. Collecting and importing data

[1244] The server accesses the company's cloud storage or data lake, periodically collects data, and imports it into temporary local storage. For example, it scans at specific times to detect newly added data.

[1245] 2. Automatic generation and assignment of metadata

[1246] Generative AI is used to automatically generate metadata for the collected data, including the creation date, administrator, data type, data description, and update frequency. Specifically, natural language processing technology is used to analyze the data content and generate appropriate metadata.

[1247] 3. Data classification and organization

[1248] Generative AI is used to automatically classify data based on predefined rules and past learning results. For example, data may be classified into categories such as "sales data," "customer information data," and "product information data."

[1249] 4. Data Update and Archiving

[1250] The server monitors the frequency of data updates and archives data that has not been updated for a certain period of time (e.g., six months), thereby reducing the load on the main storage and efficiently managing data that is used infrequently.

[1251] Device Role

[1252] 1. Providing a web-based management interface

[1253] The terminal provides users with a web-based management interface through which they can view and edit data and metadata, as well as view detailed information about specific data and perform data searches.

[1254] 2. Management via smart devices

[1255] Data can be displayed and managed in real time through smart devices such as smartphones, smart glasses, head-mounted displays, etc. For example, an inventory management app can be used to check new inventory data in real time.

[1256] User Roles

[1257] 1. Viewing and editing data

[1258] Users can edit metadata and classification rules through a web-based management interface, allowing for customization of data management.

[1259] 2. Managing Robots

[1260] Users can use robots to automatically sort and move data. Automatic sorting is performed based on the analysis results of the generative AI.

[1261] Prompt Sentence Examples

[1262] New data has been imported. Product name: Apples, Size: 10kg, Stock date: October 10, 2023. Please generate metadata for this data. Also, please estimate how frequently it will be updated.

[1263] In this way, the present invention makes it possible to improve the efficiency of data management in logistics centers and optimize business operations, which is expected to contribute to improving the competitiveness of companies.

[1264] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1265] Step 1:

[1266] The server accesses the company's cloud storage or data lake and collects new data according to a specified schedule. It receives cloud storage access information and collection schedules as input, and obtains the newly collected data and its basic information (file name, size, creation date and time) as output. This data is stored in local temporary storage.

[1267] Step 2:

[1268] The server uses a generation AI on the collected data. Here, the generation AI analyzes the contents of the collected data and automatically generates metadata. The collected data files are passed as input, and metadata (creation date, administrator, data type, data description, update frequency) is generated as output. The metadata assigned to each piece of data is registered in the database.

[1269] Step 3:

[1270] The server uses generative AI to classify data based on predefined rules and past learning results. Data with metadata attached is passed as input, and classification results (e.g., sales data, customer information data, product information data) are obtained as output. The classified data is organized by category.

[1271] Step 4:

[1272] The server continuously monitors the frequency of data updates. The data update history and current date and time are passed as input, and the result of evaluating the update frequency is obtained as output. Based on this result, data that has not been updated for a certain period of time is moved to archive storage.

[1273] Step 5:

[1274] The terminal provides a web-based management interface to the user, which allows the user to view and edit metadata and classification rules. The input is the metadata and classification rules the user wants to edit, and the output is the updated metadata and classification rules.

[1275] Step 6:

[1276] Terminals use smart devices to display and manage data in real time. A specific data request is passed as input, and the data is displayed on the screen as output. For example, an inventory management app on a smartphone can be used to check new inventory data in real time.

[1277] Step 7:

[1278] Users use robots to automatically sort and move data. Metadata and classification results are passed as input, and the robot automatically sorts and moves the data to the appropriate location as output. For example, incoming parcels are automatically sorted and moved to the designated shelves.

[1279] These steps will enable more efficient data management at logistics centers and optimize business operations.

[1280] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1281] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[1282] Data collection and import

[1283] The system starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded.

[1284] Automatic generation and assignment of metadata

[1285] Next, the server automatically assigns metadata to the collected data. The server uses AI to analyze the data and generate the following metadata:

[1286] Creation date: Automatically taken from file meta information.

[1287] Administrator: Retrieves information from the user management system.

[1288] Data type: Automatically determined from file format and content.

[1289] Data description: Generated based on the results of AI content analysis.

[1290] Update frequency: Estimated based on past update history.

[1291] For example, when a CSV file is imported from a company's customer database, its contents are analyzed and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" are automatically added.

[1292] Data classification and organization

[1293] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "sales data," "customer information data," and "product information data."

[1294] Specifically, when a user's purchase history data is imported, it is classified as "sales data." Also, data containing customer contact information is classified as "customer information data."

[1295] Data Updates and Archiving

[1296] The server continuously monitors the frequency of data updates. If data has not been updated for a certain period of time (for example, six months), it is determined to meet the conditions for archiving. Data that has been archived is automatically moved to a separate storage device and managed as an archive. This reduces the load on the main storage device and allows for efficient management of infrequently used data.

[1297] Use of emotion engine

[1298] The system also incorporates an emotion engine that recognizes the user's emotional state in real time. When a user operates the management interface, the emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data. This emotional data can be used as follows:

[1299] The server dynamically changes the display content and operation method of the management interface based on the emotional data. For example, if the user is feeling stressed, it simplifies the operation procedure or displays a support message.

[1300] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[1301] Providing a management interface

[1302] The terminal provides users with a web-based management interface. Through this interface, users can view data and metadata and edit them as needed. For example, they can add new metadata items or change existing classification rules. They can also view detailed information about specific data and search for data. The management interface is designed to be intuitive and easy to use, improving the efficiency of data management.

[1303] Furthermore, by reflecting the user's emotional state, more personalized operations are possible, improving the user experience.

[1304] This system allows companies to significantly reduce the amount of man-hours required for data management and allows them to organize, store, and utilize data with high accuracy. The introduction of the emotion engine also improves user efficiency, dramatically improving the overall efficiency of data utilization.

[1305] The processing flow will be explained below.

[1306] Step 1:

[1307] The server sets the schedule for data collection. Specifically, it determines the timing for periodic data collection, for example, setting it to collect data at 2:00 AM every day.

[1308] Step 2:

[1309] The server accesses the specified storage (e.g., cloud storage, data lake) and scans for new data. It identifies the file formats to be collected (e.g., CSV, JSON, image files).

[1310] Step 3:

[1311] The server imports the collected data into local temporary storage, while simultaneously recording basic information about the data (file name, size, creation date and time).

[1312] Step 4:

[1313] The server uses generated AI to analyze the imported data, specifically by reading the data content and analyzing column names and data formats.

[1314] Step 5:

[1315] The server generates metadata based on the analysis results, including the creation date, administrator, data type, data description, and update frequency.

[1316] Step 6:

[1317] The server then tags the imported data with the generated metadata, making it easier to search and manage the data.

[1318] Step 7:

[1319] The server loads predefined classification rules, which contain classification criteria based on data content and format.

[1320] Step 8:

[1321] The server uses generative AI to automatically classify the imported data, for example, into categories such as "customer information data" and "product data."

[1322] Step 9:

[1323] The server stores the classification results in a database and moves the classified data to corresponding directories or storage buckets.

[1324] Step 10:

[1325] The server continuously monitors how frequently the data is updated, for example by recording when the data was last updated and tracking how frequently it is updated.

[1326] Step 11:

[1327] The server determines which data to archive based on the set archive conditions. For example, data that has not been updated for six months is archived.

[1328] Step 12:

[1329] The server moves the data to be archived to another storage location and marks it as archived, which removes the infrequently used data from the primary storage location.

[1330] Step 13:

[1331] The device provides the user with a web-based management interface through which the user can view and edit data and metadata.

[1332] Step 14:

[1333] The user uses the administration interface to edit the metadata and classification rules, for example, to add new metadata items or revise existing classification rules.

[1334] Step 15:

[1335] The server uses an emotion engine to monitor the user's emotional state. Specifically, it analyzes the user's facial expressions and tone of voice to recognize the user's emotional state in real time.

[1336] Step 16:

[1337] The server dynamically changes the display content and operation methods of the management interface based on the emotional data obtained from the emotion engine. For example, if the user is feeling stressed, the operation procedure can be simplified or a support message can be displayed.

[1338] Step 17:

[1339] The server generates emotional states as metadata and attaches them to the data, allowing the system to record data usage and user reactions for long-term improvements.

[1340] Step 18:

[1341] The server saves the changes made by the user and immediately applies them to the system for the next data collection, classification, and archiving.

[1342] Example 2

[1343] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1344] In recent years, the amount of data handled by companies and organizations has exploded, making data management extremely complex and burdensome. While improving the efficiency of data management is important, processes such as automatic metadata generation and data classification are often performed manually, resulting in time-consuming and costly issues. Furthermore, while improving user operational efficiency is also necessary, there has been little progress in interface design that takes into account the user's emotional state. The purpose of this invention is to solve these problems and improve the overall efficiency of data management.

[1345] The identification process 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 automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the update frequency of data and archiving the data based on set conditions, means for allowing a user to edit the metadata and classification rules through a web-based management interface, means for providing dynamic interface changes according to the user's operating status using an emotion engine that recognizes the user's emotions, and means for assigning the results of the emotion recognition to the data as metadata. This makes it possible to automate and efficiently manage data and improve the user's operating experience.

[1346] "Generative AI" refers to artificial intelligence systems used to analyze data content and generate metadata.

[1347] "Metadata" is additional information that describes the attributes and content of data, making it easier to manage and search for the data.

[1348] "Data classification" is the process of separating collected data into specific categories, making it easier to organize and manage.

[1349] "Update frequency" indicates the frequency of time intervals at which data is updated, and is an index for evaluating the recency of data.

[1350] "Archiving" is the process of moving data that has not been updated for a certain period of time to another storage device for long-term storage.

[1351] A "web-based management interface" is an interface for data management that a user can access through a web browser.

[1352] The "emotion engine" is a system that recognizes the user's emotional state in real time and analyzes that data.

[1353] "Dynamic interface change" is the process of changing the display and operation of the management interface in real time according to the user's emotional state.

[1354] This invention is a system that combines generative AI and an emotion engine to automate data management and improve user operation efficiency. This system provides comprehensive data management through data organization, automatic metadata assignment, data classification, update frequency monitoring, archiving, and user emotion recognition.

[1355] Data collection and import

[1356] First, the server starts by collecting and importing data. The server accesses the company's cloud storage or data lake and collects data according to a specified schedule. For example, it scans the data at a specific time each day, detects newly added files, and imports them into local temporary storage. At the same time, basic information about the data (file name, size, creation date and time) is also recorded. The hardware used includes the company's cloud storage server and data lake system.

[1357] Examples:

[1358] The server scans the cloud storage for newly added files every day at 2:00 AM and imports them into local temporary storage.

[1359] At this time, the file name, size, and creation date and time are recorded at the same time.

[1360] Automatic generation and assignment of metadata

[1361] The server then analyzes the collected data using AI technology, such as OpenAI's GPT model, to automatically generate metadata, including the creation date, administrator, data type, data description, and update frequency.

[1362] Examples:

[1363] The server analyzes CSV files imported from the company's customer database and automatically assigns the creation date, administrator, data type, data description, and update frequency.

[1364] Data classification and organization

[1365] The server then uses generative AI to categorize the collected data, using predefined classification rules and the results of past data analysis.

[1366] Examples:

[1367] The server categorizes the user's purchase history data as "sales data" and the customer's contact information as "customer information data."

[1368] Data Updates and Archiving

[1369] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (for example, six months) is automatically moved to archive storage, reducing the load on the main storage.

[1370] Examples:

[1371] The server automatically moves unused customer information data to archive storage.

[1372] Use of emotion engine

[1373] The system also incorporates an emotion engine that recognizes the user's emotional state in real time as they operate the management interface. The emotion engine analyzes the user's facial expressions and tone of voice, and dynamically changes the content displayed and the operation method of the interface based on the results.

[1374] Examples:

[1375] If the emotion engine detects stress while the user is operating the data management interface, the server simplifies the operating procedure.

[1376] Providing a management interface

[1377] The terminal provides users with a web-based management interface that allows them to view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[1378] Examples:

[1379] Through the interface, users add new metadata items and modify existing classification rules.

[1380] Examples of prompt statements

[1381] Below are some example prompts to input to the generative AI model:

[1382] Write a program to automatically generate and assign the necessary metadata (creation date, administrator, data type, data description, update frequency) to a CSV file imported by a user from a company's customer database.

[1383] The above is a detailed description of the embodiment of the present invention, which enables the system to automate and streamline data management, improving the user's operational experience.

[1384] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1385] Step 1:

[1386] The server accesses the company's cloud storage or data lake and scans the data according to a specified schedule (e.g., daily at 2:00 AM).

[1387] Input: Cloud storage and data lake access information and schedule information

[1388] Output: List of newly added files

[1389] Specific behavior: Retrieve a list of new files from cloud storage.

[1390] Step 2:

[1391] The server scans and detects newly added files and imports them into local temporary storage, recording basic information such as file name, size, and creation date and time.

[1392] Input: Newly added file list

[1393] Output: Files imported into local temporary storage and their basic information

[1394] Specific behavior: Downloads new files and records their filenames, sizes, and creation dates.

[1395] Step 3:

[1396] The server uses generative AI (e.g., OpenAI's GPT model) to analyze the contents of the collected data and automatically generate metadata (creation date, administrator, data type, data description, and update frequency).

[1397] Input: A file in local temporary storage

[1398] Output: Auto-generated metadata

[1399] Specific operation: Analyze the file contents using generative AI and generate the necessary metadata.

[1400] Step 4:

[1401] The server uses generative AI to classify the collected data into categories based on classification rules and the results of analysis of past data.

[1402] Input: Files in local temporary storage with auto-generated metadata

[1403] Output: Data categorized by category

[1404] Specific operation: Uses generative AI to analyze the content of the data and classify it into appropriate categories.

[1405] Step 5:

[1406] The server continuously monitors the frequency of data updates. Data that has not been updated for a certain period of time (e.g., six months) is automatically moved to archive storage.

[1407] Input: Categorized data and its metadata

[1408] Output: Data moved to archive storage

[1409] Specific operation: Check the update date and time of the data and perform archiving based on the conditions.

[1410] Step 6:

[1411] The server uses an emotion engine to recognize the emotional state of the user while operating the management interface, and dynamically changes the display content and operation method of the interface based on the results.

[1412] Input: User's facial expressions and voice tone

[1413] Output: Dynamically changed management interface

[1414] Specific behavior: Adjust the interface based on the emotions recognized by the emotion engine.

[1415] Step 7:

[1416] The server generates the emotion recognition results as metadata and attaches it to the data.

[1417] Input: User's emotional state

[1418] Output: Metadata with emotional state

[1419] Specific operation: Emotional state is generated as metadata and added to the data.

[1420] Step 8:

[1421] The terminal provides a web-based management interface, allowing users to edit metadata and classification rules.

[1422] Input: User edit request

[1423] Output: Updated metadata and classification rules

[1424] Specific behavior: Updates metadata and classification rules based on user input.

[1425] In this way, the system efficiently and automatically performs data collection, analysis, classification, archiving, and dynamic interface changes based on the user's emotional state at each stage of data management.

[1426] (Application example 2)

[1427] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1428] In modern factories, the efficiency of production processes and data management are becoming increasingly important. In particular, manually processing large amounts of data, such as collecting, organizing, classifying, and archiving data, is a labor-intensive process, leading to reduced efficiency and data errors. Furthermore, uniform user interfaces that ignore the emotional state of workers increase operational complexity and stress, resulting in reduced productivity. To address these issues, automated data management systems and personalized interfaces that take the user's emotional state into account are needed.

[1429] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1430] In this invention, the server includes means for automatically generating metadata using a generation AI and assigning it to data, means for automatically classifying data using the generation AI, means for monitoring the frequency of data updates and archiving the data based on set conditions, means for allowing users to edit the metadata and classification rules through a web-based management interface, and means for recognizing the user's emotional state using an emotion engine and dynamically changing the display content and operation method of the management interface based on the emotion data. This not only enables automatic and efficient management of large amounts of data, but also provides a highly operable interface that takes the worker's emotional state into consideration, thereby improving productivity.

[1431] "Generative AI" is an artificial intelligence technology that automatically generates data and generates metadata based on that data.

[1432] "Metadata" is data that indicates additional information such as the attributes and content of data, the creation date and time, and the administrator.

[1433] "Data classification" is the process of automatically separating collected data into categories or types based on their content.

[1434] "Archiving" is the process of automatically moving and storing data that has not been updated for a certain period of time to another storage device, thereby reducing the load on the primary storage device.

[1435] "Web-based management interface" means a user interface available on the web that allows for viewing and editing of data and metadata.

[1436] "Recognizing the user's emotional state" means using cameras and audio sensors to analyze the user's emotions in real time from their facial expressions and tone of voice.

[1437] An "emotion engine" is software that analyzes a user's emotions and adjusts the system's behavior based on those emotions.

[1438] "Dynamic change of the display content and operation method of the management interface" refers to the process of adjusting the interface content and operation procedure in real time based on the user's emotional data.

[1439] "Monitoring update frequency" is the process of continually monitoring how frequently data is updated.

[1440] The system of the present invention includes a metadata generation means using generative AI, a data classification means, an update frequency monitoring means, a web-based management interface, and an emotion recognition means using an emotion engine.

[1441] First, the server accesses the company's cloud storage or data lake and collects data according to a specified schedule. The collected data is analyzed using generative AI, and metadata is automatically generated. The metadata includes information such as the creation date, administrator, data type, data description, and update frequency. For example, a CSV file imported from a company's production data can be analyzed, and metadata such as "creation date," "administrator," "data type," "data description," and "update frequency" can be automatically assigned.

[1442] Next, the server uses generative AI to classify the data. Based on predefined classification rules and the results of learning from past data, the collected data is divided into categories. For example, it is automatically classified into categories such as "production data," "quality control data," and "equipment maintenance data."

[1443] Furthermore, the server continuously monitors the frequency of data updates and determines that data that has not been updated for a certain period of time (for example, six months) meets the conditions for archiving. Data that is subject to archiving is automatically moved to a separate storage device and managed as an archive.

[1444] The terminal also provides a user interface to the worker. When the worker operates the user interface, an emotion engine analyzes the worker's facial expressions and voice tone to obtain emotional data. Based on this emotional data, the server dynamically changes the display content and operation method of the management interface. For example, if a worker is feeling stressed, the server can simplify the operation procedure or display a support message. This emotional data is also generated as metadata, which can be used to improve the system over the long term.

[1445] Specifically, TensorFlow and PyTorch are used for generative AI, while OpenCV and DeepFace are used for emotion recognition, with data collection, analysis, classification, archiving, emotion recognition, and interface optimization being carried out at each step. This not only enables automatic and efficient management of large amounts of data, but also makes it possible to provide a highly user-friendly interface that takes into account the emotional state of the worker, which is expected to improve productivity.

[1446] An example of a prompt is, "Please import new customer data from the customer database. Generate the following metadata for that data: - Creation date - Administrator - Data type - Data description - Update frequency." This is input into the generative AI model to generate the metadata.

[1447] These features enable companies to significantly reduce the effort required for data management and to organize, store, and utilize data with high accuracy.

[1448] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1449] Step 1: Collect and import data

[1450] The server collects data from the company's cloud storage and data lake according to a specified schedule. Specifically, the server periodically scans the cloud storage to detect newly added files. Detected files are imported into local temporary storage and basic information such as file name, size, and creation date and time is recorded.

[1451] Input: Cloud storage and data lake connection information, schedule information

[1452] Output: Imported data, basic file information

[1453] Step 2: Automatically generate and assign metadata

[1454] The server automatically generates metadata for the imported data using a generation AI, which analyzes the data content and generates information such as the creation date, administrator, data type, data description, and update frequency, and assigns it to the data.

[1455] Input: Imported data, basic information of the file

[1456] Output: Data with metadata

[1457] Step 3: Classify the data

[1458] The server uses generative AI to categorize the metadata-annotated data into categories such as "production data," "quality control data," and "machine maintenance data" based on predefined classification rules and the results of learning from past data.

[1459] Input: Data with metadata, classification rules

[1460] Output: Classified data

[1461] Step 4: Monitoring and archiving data frequency

[1462] The server continuously monitors the frequency of data updates. Data that has not been updated for a set period of time (e.g., six months) is archived and automatically moved to another storage device.

[1463] Input: Classified data, update frequency monitoring rules

[1464] Output: Archived data

[1465] Step 5: Emotion Recognition and Interface Optimization

[1466] As the user operates the device's interface, the device uses cameras and audio sensors to recognize the user's emotions in real time. Based on the analyzed emotional data, the server dynamically changes the display content and operation methods of the management interface. For example, if the user is feeling stressed, the operating procedure will be simplified and a support message will be displayed.

[1467] Input: User's face image, voice data

[1468] Output: User emotion data, optimized interface display content

[1469] Step 6: Providing a management interface

[1470] The terminal provides users with a web-based management interface through which they can view and optionally edit data and metadata, as well as view detailed information about specific data and perform data searches.

[1471] Input: User operation request

[1472] Output: Operation results, edited data

[1473] This will improve productivity by streamlining data management and optimizing the interface to suit individual emotions.

[1474] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1475] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1476] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1477] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1478] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1479] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1480] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1481] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1482] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1483] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1484] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1485] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1486] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1487] 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.

[1488] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1489] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1490] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1491] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1492] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1493] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1494] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1495] The following is further disclosed regarding the above embodiment.

[1496] (Claim 1)

[1497] A means to automatically generate metadata using generative AI and assign it to data;

[1498] A means of automatically classifying data using generative AI;

[1499] A means to monitor the frequency of data updates and archive the data based on set conditions;

[1500] a means for allowing users to edit metadata and classification rules through a web-based administrative interface;

[1501] A system including:

[1502] (Claim 2)

[1503] 10. The system of claim 1, further comprising means for automatically collecting and importing data.

[1504] (Claim 3)

[1505] 10. The system of claim 1, wherein the generation AI uses natural language processing techniques to analyze the content of the data and generate the metadata.

[1506] "Example 1"

[1507] (Claim 1)

[1508] means for accessing a data storage device and collecting data according to a schedule;

[1509] A means of analyzing data content using generative AI, automatically generating metadata, and attaching it to the data;

[1510] A means to automatically classify data by learning past data and classification rules using generative AI,

[1511] A means to monitor the frequency of data updates and archive the data based on set conditions;

[1512] a means for users to edit metadata and classification rules through a web-based administrative interface;

[1513] A system including:

[1514] (Claim 2)

[1515] 10. The system of claim 1, further comprising means for automatically collecting and importing data.

[1516] (Claim 3)

[1517] 10. The system of claim 1, wherein the generation AI uses natural language processing techniques to analyze the content of the data and generate the metadata.

[1518] "Application Example 1"

[1519] (Claim 1)

[1520] A means to automatically generate metadata using generative AI and assign it to data;

[1521] A means of automatically classifying data using generative AI;

[1522] A means to monitor the frequency of data updates and archive the data based on set conditions;

[1523] a means for allowing users to edit metadata and classification rules through a web-based administrative interface;

[1524] a means for displaying and managing data in real time using a smart device;

[1525] means for robotically and automatically sorting and transferring data;

[1526] A system including:

[1527] (Claim 2)

[1528] 10. The system of claim 1, further comprising means for automatically collecting and importing data.

[1529] (Claim 3)

[1530] 10. The system of claim 1, wherein the generative AI uses natural language processing techniques to analyze the content of the data and generate the metadata.

[1531] "Example 2: Combining Emotion Engines"

[1532] (Claim 1)

[1533] A means to automatically generate metadata using generative AI and assign it to data;

[1534] A means of automatically classifying data using generative AI;

[1535] A means to monitor the frequency of data updates and archive the data based on set conditions;

[1536] a means for allowing users to edit metadata and classification rules through a web-based administrative interface;

[1537] a means for providing a dynamic interface change according to the user's operating situation using an emotion engine that recognizes the user's emotion;

[1538] a means for attaching the emotion recognition results to the data as metadata;

[1539] A system including:

[1540] (Claim 2)

[1541] 10. The system of claim 1, further comprising means for automatically collecting and importing data.

[1542] (Claim 3)

[1543] 10. The system of claim 1, wherein the generation AI uses natural language processing techniques to analyze the content of the data and generate the metadata.

[1544] "Application example 2 when combining emotion engines"

[1545] (Claim 1)

[1546] A means to automatically generate metadata using generative AI and assign it to data;

[1547] A means of automatically classifying data using generative AI;

[1548] A means to monitor the frequency of data updates and archive the data based on set conditions;

[1549] a means for allowing users to edit metadata and classification rules through a web-based administrative interface;

[1550] a means for recognizing the emotional state of a user using an emotion engine and dynamically changing the display content and operation method of the management interface based on the emotional data;

[1551] A system including:

[1552] (Claim 2)

[1553] 10. The system of claim 1, further comprising means for automatically collecting and importing data.

[1554] (Claim 3)

[1555] 10. The system of claim 1, wherein the generation AI uses natural language processing techniques to analyze the content of the data and generate the metadata. [Explanation of symbols]

[1556] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to automatically generate metadata using generative AI and assign it to data; A means of automatically classifying data using generative AI; A means to monitor the frequency of data updates and archive the data based on set conditions; a means for allowing users to edit metadata and classification rules through a web-based administrative interface; A system including:

2. The system of claim 1 further comprising means for automatically collecting and importing data.

3. The system of claim 1 , wherein the generation AI uses natural language processing techniques to analyze the content of the data and generate the metadata.

Images